From f68dfe97b1ccf9d68d155730a5b28a0ba8e37bf5 Mon Sep 17 00:00:00 2001
From: Martin Stamenov <stamenov.martin@gmail.com>
Date: Wed, 6 Dec 2017 21:34:37 +0100
Subject: [PATCH 01/23] Add function get_new_author_topics() to infer topics
 distribution for new unseen author.

---
 gensim/models/atmodel.py | 93 ++++++++++++++++++++++++++++++++++++++++
 1 file changed, 93 insertions(+)

diff --git a/gensim/models/atmodel.py b/gensim/models/atmodel.py
index 9c691b8c25..2671772be8 100755
--- a/gensim/models/atmodel.py
+++ b/gensim/models/atmodel.py
@@ -34,6 +34,7 @@
 # and do_estep methods.
 
 import logging
+import traceback
 import numpy as np  # for arrays, array broadcasting etc.
 from copy import deepcopy
 from shutil import copyfile
@@ -882,6 +883,98 @@ def get_document_topics(self, word_id, minimum_probability=None):
 
         raise NotImplementedError('Method "get_document_topics" is not valid for the author-topic model. Use the "get_author_topics" method.')
 
+    def get_new_author_topics(self, corpus, minimum_probability=None):
+        """
+        Infers a topic distribution for a new author over the passed corpus of docs,
+        assuming that all documents are from this single new author.
+
+        Args:
+            corpus (list): Bag-of-words representation of the documents to get topics for.
+            minimum_probability (float): Ignore topics with probability below this value
+                (None by default). If set to None, a value of 1e-8 is used to prevent 0s.
+        Returns:
+            topic distribution for the given list of documents `corpus` in bow format,
+            as a list of `(topic_id, topic_probability)` 2-tuples.
+        """
+
+        #use the training hyperparameters from the model initialization
+        passes = self.passes
+
+        #TODO: how should this function look like for get_new_author_topics?
+        def rho():
+            return pow(self.offset + 1 + 1, -self.decay)
+
+        #wrap in fuction to avoid code duplication
+        def rollback_new_author_chages():
+            self.state.gamma = self.state.gamma[0:-1]
+            for doc in corpus:
+                self.corpus.remove(doc)
+
+            del self.author2doc[new_author_name]
+            a_id = self.author2id[new_author_name]
+            del self.id2author[a_id]
+            del self.author2id[new_author_name]
+
+            for new_doc_id in corpus_doc_idx:
+                del self.doc2author[new_doc_id]
+
+            self.total_docs -= len_input_corpus
+            self.num_authors -= num_new_authors
+
+        try:
+            len_input_corpus = len(corpus)
+        except TypeError:
+            logger.warning("input corpus stream has no len(); counting documents")
+            len_input_corpus = sum(1 for _ in corpus)
+        if len_input_corpus == 0:
+            logger.warning("AuthorTopicModel.get_new_author_topics() called with an empty corpus")
+            return
+        if not len_input_corpus < self.chunksize:
+            logger.warning("AuthorTopicModel.get_new_author_topics() called with to many documents. Use update().")
+            return
+
+        new_author_name = "placeholder_name"
+
+        # Add new documents in corpus to self.corpus.
+        self.extend_corpus(corpus)
+
+        corpus_doc_idx = list(range(self.total_docs, len_input_corpus+self.total_docs))
+        #increment number of total docs
+        self.total_docs += len_input_corpus
+
+        # Add the new placeholder author to author2id/id2author dictionaries.
+        num_new_authors = 1
+        author_id = 0
+        self.author2id[new_author_name] = author_id + self.num_authors
+        self.id2author[author_id + self.num_authors] = new_author_name
+
+        # Increment the number of total authors seen.
+        self.num_authors += num_new_authors
+
+        #add new author in author2doc and doc into doc2author
+        self.author2doc[new_author_name] = corpus_doc_idx
+        for new_doc_id in corpus_doc_idx:
+            self.doc2author[new_doc_id] = [new_author_name]
+
+        gamma_new = self.random_state.gamma(100., 1. / 100., (num_new_authors, self.num_topics))
+        self.state.gamma = np.vstack([self.state.gamma, gamma_new])
+
+        # should not record the sstats, as we are goint to delete the new author after calculated
+        try:
+            gammat, _ = self.inference(
+                corpus, self.author2doc, self.doc2author, rho(),
+                collect_sstats=False, chunk_doc_idx=corpus_doc_idx
+            )
+        except Exception as e:
+            #something went wrong! Rollback temporary changes in object and log
+            rollback_new_author_chages()
+            logging.error(traceback.format_exc())
+            return
+
+        new_author_topics = self.get_author_topics(new_author_name, minimum_probability)
+        rollback_new_author_chages()
+        return new_author_topics
+
     def get_author_topics(self, author_name, minimum_probability=None):
         """
         Return topic distribution the given author, as a list of

From 2843d1bcdbdb5978bfb38a78cde8b63fe6a4fd2c Mon Sep 17 00:00:00 2001
From: Martin Stamenov <stamenov.martin@gmail.com>
Date: Thu, 7 Dec 2017 11:23:45 +0100
Subject: [PATCH 02/23] Fixes for pep8 compliance. Concrete exception handling.

---
 gensim/models/atmodel.py | 22 +++++++++++-----------
 1 file changed, 11 insertions(+), 11 deletions(-)

diff --git a/gensim/models/atmodel.py b/gensim/models/atmodel.py
index 2671772be8..661c1b13b5 100755
--- a/gensim/models/atmodel.py
+++ b/gensim/models/atmodel.py
@@ -34,7 +34,6 @@
 # and do_estep methods.
 
 import logging
-import traceback
 import numpy as np  # for arrays, array broadcasting etc.
 from copy import deepcopy
 from shutil import copyfile
@@ -884,7 +883,8 @@ def get_document_topics(self, word_id, minimum_probability=None):
         raise NotImplementedError('Method "get_document_topics" is not valid for the author-topic model. Use the "get_author_topics" method.')
 
     def get_new_author_topics(self, corpus, minimum_probability=None):
-        """
+        """Inference topics for new author.
+
         Infers a topic distribution for a new author over the passed corpus of docs,
         assuming that all documents are from this single new author.
 
@@ -897,14 +897,14 @@ def get_new_author_topics(self, corpus, minimum_probability=None):
             as a list of `(topic_id, topic_probability)` 2-tuples.
         """
 
-        #use the training hyperparameters from the model initialization
+        # Use the training hyperparameters from the model initialization.
         passes = self.passes
 
-        #TODO: how should this function look like for get_new_author_topics?
+        # TODO: how should this function look like for get_new_author_topics?
         def rho():
             return pow(self.offset + 1 + 1, -self.decay)
 
-        #wrap in fuction to avoid code duplication
+        # Wrap in fuction to avoid code duplication.
         def rollback_new_author_chages():
             self.state.gamma = self.state.gamma[0:-1]
             for doc in corpus:
@@ -939,7 +939,7 @@ def rollback_new_author_chages():
         self.extend_corpus(corpus)
 
         corpus_doc_idx = list(range(self.total_docs, len_input_corpus+self.total_docs))
-        #increment number of total docs
+        # Increment number of total docs.
         self.total_docs += len_input_corpus
 
         # Add the new placeholder author to author2id/id2author dictionaries.
@@ -951,7 +951,7 @@ def rollback_new_author_chages():
         # Increment the number of total authors seen.
         self.num_authors += num_new_authors
 
-        #add new author in author2doc and doc into doc2author
+        # Add new author in author2doc and doc into doc2author.
         self.author2doc[new_author_name] = corpus_doc_idx
         for new_doc_id in corpus_doc_idx:
             self.doc2author[new_doc_id] = [new_author_name]
@@ -959,16 +959,16 @@ def rollback_new_author_chages():
         gamma_new = self.random_state.gamma(100., 1. / 100., (num_new_authors, self.num_topics))
         self.state.gamma = np.vstack([self.state.gamma, gamma_new])
 
-        # should not record the sstats, as we are goint to delete the new author after calculated
+        # Should not record the sstats, as we are goint to delete the new author after calculated.
         try:
             gammat, _ = self.inference(
                 corpus, self.author2doc, self.doc2author, rho(),
                 collect_sstats=False, chunk_doc_idx=corpus_doc_idx
             )
-        except Exception as e:
-            #something went wrong! Rollback temporary changes in object and log
+        except ValueError as e:
+            # Something went wrong! Rollback temporary changes in object and log
             rollback_new_author_chages()
-            logging.error(traceback.format_exc())
+            logging.exception(e)
             return
 
         new_author_topics = self.get_author_topics(new_author_name, minimum_probability)

From 92ef7595cca357babb7132e7011b2e8db83e1808 Mon Sep 17 00:00:00 2001
From: Martin Stamenov <stamenov.martin@gmail.com>
Date: Thu, 7 Dec 2017 11:32:10 +0100
Subject: [PATCH 03/23] small docstring fix

---
 gensim/models/atmodel.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/gensim/models/atmodel.py b/gensim/models/atmodel.py
index 661c1b13b5..35410d6819 100755
--- a/gensim/models/atmodel.py
+++ b/gensim/models/atmodel.py
@@ -883,7 +883,7 @@ def get_document_topics(self, word_id, minimum_probability=None):
         raise NotImplementedError('Method "get_document_topics" is not valid for the author-topic model. Use the "get_author_topics" method.')
 
     def get_new_author_topics(self, corpus, minimum_probability=None):
-        """Inference topics for new author.
+        """Infers topics for new author.
 
         Infers a topic distribution for a new author over the passed corpus of docs,
         assuming that all documents are from this single new author.

From ee51f7198348ab9227214b3bc404a1fe0a59b1c9 Mon Sep 17 00:00:00 2001
From: Martin Stamenov <stamenov.martin@gmail.com>
Date: Thu, 28 Dec 2017 12:49:32 +0200
Subject: [PATCH 04/23] dont extend self.corpus

---
 gensim/models/atmodel.py | 12 +-----------
 1 file changed, 1 insertion(+), 11 deletions(-)

diff --git a/gensim/models/atmodel.py b/gensim/models/atmodel.py
index 35410d6819..df569a6191 100755
--- a/gensim/models/atmodel.py
+++ b/gensim/models/atmodel.py
@@ -907,8 +907,6 @@ def rho():
         # Wrap in fuction to avoid code duplication.
         def rollback_new_author_chages():
             self.state.gamma = self.state.gamma[0:-1]
-            for doc in corpus:
-                self.corpus.remove(doc)
 
             del self.author2doc[new_author_name]
             a_id = self.author2id[new_author_name]
@@ -918,7 +916,6 @@ def rollback_new_author_chages():
             for new_doc_id in corpus_doc_idx:
                 del self.doc2author[new_doc_id]
 
-            self.total_docs -= len_input_corpus
             self.num_authors -= num_new_authors
 
         try:
@@ -935,12 +932,8 @@ def rollback_new_author_chages():
 
         new_author_name = "placeholder_name"
 
-        # Add new documents in corpus to self.corpus.
-        self.extend_corpus(corpus)
 
-        corpus_doc_idx = list(range(self.total_docs, len_input_corpus+self.total_docs))
-        # Increment number of total docs.
-        self.total_docs += len_input_corpus
+        corpus_doc_idx = list(range(0, len_input_corpus))
 
         # Add the new placeholder author to author2id/id2author dictionaries.
         num_new_authors = 1
@@ -948,9 +941,6 @@ def rollback_new_author_chages():
         self.author2id[new_author_name] = author_id + self.num_authors
         self.id2author[author_id + self.num_authors] = new_author_name
 
-        # Increment the number of total authors seen.
-        self.num_authors += num_new_authors
-
         # Add new author in author2doc and doc into doc2author.
         self.author2doc[new_author_name] = corpus_doc_idx
         for new_doc_id in corpus_doc_idx:

From 2de1b348f27c6e8a7133913f2fed29998892d8fd Mon Sep 17 00:00:00 2001
From: Martin Stamenov <stamenov.martin@gmail.com>
Date: Tue, 2 Jan 2018 12:00:55 +0200
Subject: [PATCH 05/23] pep8 fixes

---
 gensim/models/atmodel.py | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/gensim/models/atmodel.py b/gensim/models/atmodel.py
index df569a6191..ff6d2ce543 100755
--- a/gensim/models/atmodel.py
+++ b/gensim/models/atmodel.py
@@ -897,9 +897,6 @@ def get_new_author_topics(self, corpus, minimum_probability=None):
             as a list of `(topic_id, topic_probability)` 2-tuples.
         """
 
-        # Use the training hyperparameters from the model initialization.
-        passes = self.passes
-
         # TODO: how should this function look like for get_new_author_topics?
         def rho():
             return pow(self.offset + 1 + 1, -self.decay)
@@ -931,8 +928,6 @@ def rollback_new_author_chages():
             return
 
         new_author_name = "placeholder_name"
-
-
         corpus_doc_idx = list(range(0, len_input_corpus))
 
         # Add the new placeholder author to author2id/id2author dictionaries.

From cbe904909c41a008b137adf4e8e082eab4903b64 Mon Sep 17 00:00:00 2001
From: Martin Stamenov <stamenov.martin@gmail.com>
Date: Sat, 10 Feb 2018 15:57:13 +0100
Subject: [PATCH 06/23] remove chunksize limitation and small fix

---
 gensim/models/atmodel.py | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/gensim/models/atmodel.py b/gensim/models/atmodel.py
index ff6d2ce543..8f6ea6562f 100755
--- a/gensim/models/atmodel.py
+++ b/gensim/models/atmodel.py
@@ -921,12 +921,8 @@ def rollback_new_author_chages():
             logger.warning("input corpus stream has no len(); counting documents")
             len_input_corpus = sum(1 for _ in corpus)
         if len_input_corpus == 0:
-            logger.warning("AuthorTopicModel.get_new_author_topics() called with an empty corpus")
-            return
-        if not len_input_corpus < self.chunksize:
-            logger.warning("AuthorTopicModel.get_new_author_topics() called with to many documents. Use update().")
-            return
-
+            raise ValueError("AuthorTopicModel.get_new_author_topics() called with an empty corpus")
+            
         new_author_name = "placeholder_name"
         corpus_doc_idx = list(range(0, len_input_corpus))
 

From a94c0b1a892d012c6bf3429713839e87a4b2d781 Mon Sep 17 00:00:00 2001
From: Martin Stamenov <stamenov.martin@gmail.com>
Date: Sat, 10 Feb 2018 17:43:34 +0100
Subject: [PATCH 07/23] pep8 fix

---
 gensim/models/atmodel.py | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/gensim/models/atmodel.py b/gensim/models/atmodel.py
index 8f6ea6562f..217d073bde 100755
--- a/gensim/models/atmodel.py
+++ b/gensim/models/atmodel.py
@@ -922,7 +922,7 @@ def rollback_new_author_chages():
             len_input_corpus = sum(1 for _ in corpus)
         if len_input_corpus == 0:
             raise ValueError("AuthorTopicModel.get_new_author_topics() called with an empty corpus")
-            
+
         new_author_name = "placeholder_name"
         corpus_doc_idx = list(range(0, len_input_corpus))
 
@@ -964,9 +964,8 @@ def get_author_topics(self, author_name, minimum_probability=None):
 
         Obtaining topic probabilities of each word, as in LDA (via `per_word_topics`),
         is not supported.
-
         """
-
+        
         author_id = self.author2id[author_name]
 
         if minimum_probability is None:

From 783a5857bf9141e6c53cff836267b820521687e8 Mon Sep 17 00:00:00 2001
From: Martin Stamenov <stamenov.martin@gmail.com>
Date: Sun, 11 Feb 2018 21:04:18 +0100
Subject: [PATCH 08/23] try pep8 fix

---
 gensim/models/atmodel.py | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/gensim/models/atmodel.py b/gensim/models/atmodel.py
index 217d073bde..bf91142b1c 100755
--- a/gensim/models/atmodel.py
+++ b/gensim/models/atmodel.py
@@ -958,14 +958,15 @@ def rollback_new_author_chages():
 
     def get_author_topics(self, author_name, minimum_probability=None):
         """
-        Return topic distribution the given author, as a list of
+        Return topic distribution the given author.
+
+        Input as as a list of
         (topic_id, topic_probability) 2-tuples.
         Ignore topics with very low probability (below `minimum_probability`).
-
         Obtaining topic probabilities of each word, as in LDA (via `per_word_topics`),
         is not supported.
         """
-        
+
         author_id = self.author2id[author_name]
 
         if minimum_probability is None:

From a85563b750be1edbe95e03a89e527949e1cc278a Mon Sep 17 00:00:00 2001
From: ivan <menshikh.iv@gmail.com>
Date: Mon, 12 Feb 2018 16:49:57 +0500
Subject: [PATCH 09/23] convert docstring to numpy-style

---
 gensim/models/atmodel.py | 19 ++++++++++++-------
 1 file changed, 12 insertions(+), 7 deletions(-)

diff --git a/gensim/models/atmodel.py b/gensim/models/atmodel.py
index 57e0e8792b..ea45f24c2c 100755
--- a/gensim/models/atmodel.py
+++ b/gensim/models/atmodel.py
@@ -925,13 +925,18 @@ def get_new_author_topics(self, corpus, minimum_probability=None):
         Infers a topic distribution for a new author over the passed corpus of docs,
         assuming that all documents are from this single new author.
 
-        Args:
-            corpus (list): Bag-of-words representation of the documents to get topics for.
-            minimum_probability (float): Ignore topics with probability below this value
-                (None by default). If set to None, a value of 1e-8 is used to prevent 0s.
-        Returns:
-            topic distribution for the given list of documents `corpus` in bow format,
-            as a list of `(topic_id, topic_probability)` 2-tuples.
+        Parameters
+        ----------
+        corpus : iterable of iterable of (int, int)
+            Corpus in BoW format.
+        minimum_probability : float, optional
+            Ignore topics with probability below this value, if None - 1e-8 is used.
+
+        Returns
+        -------
+        list of (int, float)
+            Topic distribution for the given `corpus`.
+    
         """
 
         # TODO: how should this function look like for get_new_author_topics?

From 5eb84ff9c9bf190df18e524a5f00b68a797cf472 Mon Sep 17 00:00:00 2001
From: ivan <menshikh.iv@gmail.com>
Date: Mon, 12 Feb 2018 16:51:58 +0500
Subject: [PATCH 10/23] fix PEP8

---
 gensim/models/atmodel.py | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/gensim/models/atmodel.py b/gensim/models/atmodel.py
index ea45f24c2c..94c376df9e 100755
--- a/gensim/models/atmodel.py
+++ b/gensim/models/atmodel.py
@@ -936,9 +936,8 @@ def get_new_author_topics(self, corpus, minimum_probability=None):
         -------
         list of (int, float)
             Topic distribution for the given `corpus`.
-    
-        """
 
+        """
         # TODO: how should this function look like for get_new_author_topics?
         def rho():
             return pow(self.offset + 1 + 1, -self.decay)

From 7df70654a23257b499b380bd9279aeb721785dea Mon Sep 17 00:00:00 2001
From: Martin Stamenov <stamenov.martin@gmail.com>
Date: Thu, 22 Feb 2018 19:06:33 +0100
Subject: [PATCH 11/23] fix major bug

---
 gensim/models/atmodel.py | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/gensim/models/atmodel.py b/gensim/models/atmodel.py
index 94c376df9e..a8f0752cff 100755
--- a/gensim/models/atmodel.py
+++ b/gensim/models/atmodel.py
@@ -954,8 +954,6 @@ def rollback_new_author_chages():
             for new_doc_id in corpus_doc_idx:
                 del self.doc2author[new_doc_id]
 
-            self.num_authors -= num_new_authors
-
         try:
             len_input_corpus = len(corpus)
         except TypeError:
@@ -965,7 +963,7 @@ def rollback_new_author_chages():
             raise ValueError("AuthorTopicModel.get_new_author_topics() called with an empty corpus")
 
         new_author_name = "placeholder_name"
-        corpus_doc_idx = list(range(0, len_input_corpus))
+        corpus_doc_idx = list(range(self.total_docs, self.total_docs+len_input_corpus))
 
         # Add the new placeholder author to author2id/id2author dictionaries.
         num_new_authors = 1

From f818bf253e2d57eafffcb2c4667cbfe9960779f2 Mon Sep 17 00:00:00 2001
From: Martin Stamenov <stamenov.martin@gmail.com>
Date: Thu, 22 Feb 2018 19:53:14 +0100
Subject: [PATCH 12/23] fix pep8

---
 gensim/models/atmodel.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/gensim/models/atmodel.py b/gensim/models/atmodel.py
index a8f0752cff..be69477697 100755
--- a/gensim/models/atmodel.py
+++ b/gensim/models/atmodel.py
@@ -963,7 +963,7 @@ def rollback_new_author_chages():
             raise ValueError("AuthorTopicModel.get_new_author_topics() called with an empty corpus")
 
         new_author_name = "placeholder_name"
-        corpus_doc_idx = list(range(self.total_docs, self.total_docs+len_input_corpus))
+        corpus_doc_idx = list(range(self.total_docs, self.total_docs + len_input_corpus))
 
         # Add the new placeholder author to author2id/id2author dictionaries.
         num_new_authors = 1

From 8c5765fa5f475f8f82acea86f6e3b97a9c247d06 Mon Sep 17 00:00:00 2001
From: Martin Stamenov <stamenov.martin@gmail.com>
Date: Fri, 23 Feb 2018 13:04:27 +0100
Subject: [PATCH 13/23] fix merge

---
 gensim/models/atmodel.py | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/gensim/models/atmodel.py b/gensim/models/atmodel.py
index be69477697..fb4a475e19 100755
--- a/gensim/models/atmodel.py
+++ b/gensim/models/atmodel.py
@@ -940,7 +940,11 @@ def get_new_author_topics(self, corpus, minimum_probability=None):
         """
         # TODO: how should this function look like for get_new_author_topics?
         def rho():
+<<<<<<< Updated upstream
             return pow(self.offset + 1 + 1, -self.decay)
+=======
+            return pow(self.offset + 1, -self.decay)
+>>>>>>> Stashed changes
 
         # Wrap in fuction to avoid code duplication.
         def rollback_new_author_chages():

From 5ad9a0b7b42e31ed0c08bfa113d8758939f8063c Mon Sep 17 00:00:00 2001
From: Martin Stamenov <stamenov.martin@gmail.com>
Date: Fri, 23 Feb 2018 13:26:18 +0100
Subject: [PATCH 14/23] add tests for get_new_author_topics

---
 gensim/test/test_atmodel.py | 25 +++++++++++++++++++++++++
 1 file changed, 25 insertions(+)

diff --git a/gensim/test/test_atmodel.py b/gensim/test/test_atmodel.py
index cd1293e6fa..89b5a0f438 100644
--- a/gensim/test/test_atmodel.py
+++ b/gensim/test/test_atmodel.py
@@ -450,6 +450,31 @@ def testTermTopics(self):
             self.assertTrue(isinstance(topic_no, int))
             self.assertTrue(isinstance(probability, float))
 
+    def testNewAuthorTopics(self):
+        model = self.class_(
+            corpus, author2doc=author2doc, id2word=dictionary, num_topics=2,
+            passes=100, random_state=np.random.seed(0)
+        )
+        #temp save model state vars before get_new_author_topics is called
+        state_gamma_len = len(model.state.gamma)
+        author2doc_len = len(model.author2doc)
+        author2id_len = len(model.author2id)
+        id2author_len = len(model.id2author)
+        doc2author_len = len(model.doc2author)
+
+        new_author_topics = model.get_new_author_topics(corpus=corpus[0:2])
+
+        for k, v in new_author_topics:
+            self.assertTrue(isinstance(k, int))
+            self.assertTrue(isinstance(v, float))
+
+        #assure rollback was successful and the model state is as before
+        self.assertEqual(state_gamma_len, len(model.state.gamma))
+        self.assertEqual(author2doc_len, len(model.author2doc))
+        self.assertEqual(author2id_len, len(model.author2id))
+        self.assertEqual(id2author_len, len(model.id2author))
+        self.assertEqual(doc2author_len, len(model.doc2author))
+
     def testPasses(self):
         # long message includes the original error message with a custom one
         self.longMessage = True

From 8e4899ce69d93e2a62342b8721d00201b405ee15 Mon Sep 17 00:00:00 2001
From: Martin Stamenov <stamenov.martin@gmail.com>
Date: Fri, 23 Feb 2018 13:28:53 +0100
Subject: [PATCH 15/23] fix stash changes

---
 gensim/models/atmodel.py | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/gensim/models/atmodel.py b/gensim/models/atmodel.py
index fb4a475e19..be69477697 100755
--- a/gensim/models/atmodel.py
+++ b/gensim/models/atmodel.py
@@ -940,11 +940,7 @@ def get_new_author_topics(self, corpus, minimum_probability=None):
         """
         # TODO: how should this function look like for get_new_author_topics?
         def rho():
-<<<<<<< Updated upstream
             return pow(self.offset + 1 + 1, -self.decay)
-=======
-            return pow(self.offset + 1, -self.decay)
->>>>>>> Stashed changes
 
         # Wrap in fuction to avoid code duplication.
         def rollback_new_author_chages():

From 10ba9c84b195d19258ab33348df6caba4fffb6f4 Mon Sep 17 00:00:00 2001
From: Martin Stamenov <stamenov.martin@gmail.com>
Date: Fri, 23 Feb 2018 13:57:53 +0100
Subject: [PATCH 16/23] fix test pep8

---
 gensim/test/test_atmodel.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/gensim/test/test_atmodel.py b/gensim/test/test_atmodel.py
index 89b5a0f438..f3844fa603 100644
--- a/gensim/test/test_atmodel.py
+++ b/gensim/test/test_atmodel.py
@@ -455,7 +455,7 @@ def testNewAuthorTopics(self):
             corpus, author2doc=author2doc, id2word=dictionary, num_topics=2,
             passes=100, random_state=np.random.seed(0)
         )
-        #temp save model state vars before get_new_author_topics is called
+        # temp save model state vars before get_new_author_topics is called
         state_gamma_len = len(model.state.gamma)
         author2doc_len = len(model.author2doc)
         author2id_len = len(model.author2id)
@@ -468,7 +468,7 @@ def testNewAuthorTopics(self):
             self.assertTrue(isinstance(k, int))
             self.assertTrue(isinstance(v, float))
 
-        #assure rollback was successful and the model state is as before
+        # assure rollback was successful and the model state is as before
         self.assertEqual(state_gamma_len, len(model.state.gamma))
         self.assertEqual(author2doc_len, len(model.author2doc))
         self.assertEqual(author2id_len, len(model.author2id))

From 0a3eedb267fb766d323349932d593298419ce9af Mon Sep 17 00:00:00 2001
From: Martin Stamenov <stamenov.martin@gmail.com>
Date: Mon, 26 Feb 2018 23:53:19 +0100
Subject: [PATCH 17/23] fix exception catching and rollback

---
 gensim/models/atmodel.py | 10 ++--------
 1 file changed, 2 insertions(+), 8 deletions(-)

diff --git a/gensim/models/atmodel.py b/gensim/models/atmodel.py
index be69477697..f5c8b3a353 100755
--- a/gensim/models/atmodel.py
+++ b/gensim/models/atmodel.py
@@ -938,7 +938,6 @@ def get_new_author_topics(self, corpus, minimum_probability=None):
             Topic distribution for the given `corpus`.
 
         """
-        # TODO: how should this function look like for get_new_author_topics?
         def rho():
             return pow(self.offset + 1 + 1, -self.decay)
 
@@ -985,14 +984,9 @@ def rollback_new_author_chages():
                 corpus, self.author2doc, self.doc2author, rho(),
                 collect_sstats=False, chunk_doc_idx=corpus_doc_idx
             )
-        except ValueError as e:
-            # Something went wrong! Rollback temporary changes in object and log
+            new_author_topics = self.get_author_topics(new_author_name, minimum_probability)
+        finally:
             rollback_new_author_chages()
-            logging.exception(e)
-            return
-
-        new_author_topics = self.get_author_topics(new_author_name, minimum_probability)
-        rollback_new_author_chages()
         return new_author_topics
 
     def get_author_topics(self, author_name, minimum_probability=None):

From f5875969390ce5ff4c9f95fa61a30a0bea106549 Mon Sep 17 00:00:00 2001
From: Martin Stamenov <stamenov.martin@gmail.com>
Date: Mon, 26 Feb 2018 23:55:35 +0100
Subject: [PATCH 18/23] add test for topic similarity

---
 gensim/test/test_atmodel.py | 17 ++++++++++++++++-
 1 file changed, 16 insertions(+), 1 deletion(-)

diff --git a/gensim/test/test_atmodel.py b/gensim/test/test_atmodel.py
index f3844fa603..48f08cdc9f 100644
--- a/gensim/test/test_atmodel.py
+++ b/gensim/test/test_atmodel.py
@@ -26,7 +26,7 @@
 from gensim.test import basetmtests
 from gensim.test.utils import (datapath,
     get_tmpfile, common_texts, common_dictionary as dictionary, common_corpus as corpus)
-
+from gensim.matutils import jensen_shannon
 # TODO:
 # Test that computing the bound on new unseen documents works as expected (this is somewhat different
 # in the author-topic model than in LDA).
@@ -451,10 +451,15 @@ def testTermTopics(self):
             self.assertTrue(isinstance(probability, float))
 
     def testNewAuthorTopics(self):
+
         model = self.class_(
             corpus, author2doc=author2doc, id2word=dictionary, num_topics=2,
             passes=100, random_state=np.random.seed(0)
         )
+        author2doc_newauthor = {}
+        author2doc_newauthor["test"] = [0,1]
+        model.update(corpus=corpus[0:2], author2doc=author2doc_newauthor)
+
         # temp save model state vars before get_new_author_topics is called
         state_gamma_len = len(model.state.gamma)
         author2doc_len = len(model.author2doc)
@@ -464,10 +469,19 @@ def testNewAuthorTopics(self):
 
         new_author_topics = model.get_new_author_topics(corpus=corpus[0:2])
 
+        # sanity check
         for k, v in new_author_topics:
             self.assertTrue(isinstance(k, int))
             self.assertTrue(isinstance(v, float))
 
+        # make sure topics are similar enough
+        similarity = 1 / (1 + jensen_shannon(model["test"], new_author_topics))
+        self.assertTrue(similarity >= 0.9)
+
+        # produce an error to test if rollback occurs
+        with self.assertRaises(TypeError):
+            new_author_topics_error = model.get_new_author_topics(corpus=corpus[0])
+
         # assure rollback was successful and the model state is as before
         self.assertEqual(state_gamma_len, len(model.state.gamma))
         self.assertEqual(author2doc_len, len(model.author2doc))
@@ -475,6 +489,7 @@ def testNewAuthorTopics(self):
         self.assertEqual(id2author_len, len(model.id2author))
         self.assertEqual(doc2author_len, len(model.doc2author))
 
+
     def testPasses(self):
         # long message includes the original error message with a custom one
         self.longMessage = True

From 1bc929c46f46d9d3faaebf0e1d21553ace5d4ae9 Mon Sep 17 00:00:00 2001
From: Martin Stamenov <stamenov.martin@gmail.com>
Date: Tue, 27 Feb 2018 10:20:40 +0100
Subject: [PATCH 19/23] fix pep8

---
 gensim/test/test_atmodel.py | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/gensim/test/test_atmodel.py b/gensim/test/test_atmodel.py
index 48f08cdc9f..00d4d2aafa 100644
--- a/gensim/test/test_atmodel.py
+++ b/gensim/test/test_atmodel.py
@@ -457,7 +457,7 @@ def testNewAuthorTopics(self):
             passes=100, random_state=np.random.seed(0)
         )
         author2doc_newauthor = {}
-        author2doc_newauthor["test"] = [0,1]
+        author2doc_newauthor["test"] = [0, 1]
         model.update(corpus=corpus[0:2], author2doc=author2doc_newauthor)
 
         # temp save model state vars before get_new_author_topics is called
@@ -480,7 +480,7 @@ def testNewAuthorTopics(self):
 
         # produce an error to test if rollback occurs
         with self.assertRaises(TypeError):
-            new_author_topics_error = model.get_new_author_topics(corpus=corpus[0])
+            model.get_new_author_topics(corpus=corpus[0])
 
         # assure rollback was successful and the model state is as before
         self.assertEqual(state_gamma_len, len(model.state.gamma))
@@ -489,7 +489,6 @@ def testNewAuthorTopics(self):
         self.assertEqual(id2author_len, len(model.id2author))
         self.assertEqual(doc2author_len, len(model.doc2author))
 
-
     def testPasses(self):
         # long message includes the original error message with a custom one
         self.longMessage = True

From 6085b901d097bc52ffbfb010f43049875d8e13df Mon Sep 17 00:00:00 2001
From: Martin Stamenov <stamenov.martin@gmail.com>
Date: Wed, 21 Mar 2018 17:43:22 +0100
Subject: [PATCH 20/23] some last cosmetic changes

---
 gensim/models/atmodel.py | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/gensim/models/atmodel.py b/gensim/models/atmodel.py
index f5c8b3a353..7cc4170c4d 100755
--- a/gensim/models/atmodel.py
+++ b/gensim/models/atmodel.py
@@ -941,7 +941,6 @@ def get_new_author_topics(self, corpus, minimum_probability=None):
         def rho():
             return pow(self.offset + 1 + 1, -self.decay)
 
-        # Wrap in fuction to avoid code duplication.
         def rollback_new_author_chages():
             self.state.gamma = self.state.gamma[0:-1]
 
@@ -962,11 +961,14 @@ def rollback_new_author_chages():
             raise ValueError("AuthorTopicModel.get_new_author_topics() called with an empty corpus")
 
         new_author_name = "placeholder_name"
+        # indexes representing the documents in the input corpus
         corpus_doc_idx = list(range(self.total_docs, self.total_docs + len_input_corpus))
 
         # Add the new placeholder author to author2id/id2author dictionaries.
         num_new_authors = 1
-        author_id = 0
+        author_id = self.num_authors
+        if new_author_name in self.author2id:
+            raise ValueError("self.author2id already has 'placeholder_name' author")
         self.author2id[new_author_name] = author_id + self.num_authors
         self.id2author[author_id + self.num_authors] = new_author_name
 

From 34f5222e0b6fb5fb85bae655a30ef8a700c167ff Mon Sep 17 00:00:00 2001
From: Martin Stamenov <stamenov.martin@gmail.com>
Date: Wed, 21 Mar 2018 18:18:53 +0100
Subject: [PATCH 21/23] author id fix

---
 gensim/models/atmodel.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/gensim/models/atmodel.py b/gensim/models/atmodel.py
index 7cc4170c4d..017bf6efd0 100755
--- a/gensim/models/atmodel.py
+++ b/gensim/models/atmodel.py
@@ -969,8 +969,8 @@ def rollback_new_author_chages():
         author_id = self.num_authors
         if new_author_name in self.author2id:
             raise ValueError("self.author2id already has 'placeholder_name' author")
-        self.author2id[new_author_name] = author_id + self.num_authors
-        self.id2author[author_id + self.num_authors] = new_author_name
+        self.author2id[new_author_name] = author_id
+        self.id2author[author_id] = new_author_name
 
         # Add new author in author2doc and doc into doc2author.
         self.author2doc[new_author_name] = corpus_doc_idx

From 6d7141d0650534977210b9957e8b2d1294022997 Mon Sep 17 00:00:00 2001
From: Martin Stamenov <stamenov.martin@gmail.com>
Date: Sun, 25 Mar 2018 18:40:47 +0200
Subject: [PATCH 22/23] add tutorial for authorship prediction

---
 .../atmodel_prediction_tutorial.ipynb         | 530 ++++++++++++++++++
 1 file changed, 530 insertions(+)
 create mode 100644 docs/notebooks/atmodel_prediction_tutorial.ipynb

diff --git a/docs/notebooks/atmodel_prediction_tutorial.ipynb b/docs/notebooks/atmodel_prediction_tutorial.ipynb
new file mode 100644
index 0000000000..9a7e3bff33
--- /dev/null
+++ b/docs/notebooks/atmodel_prediction_tutorial.ipynb
@@ -0,0 +1,530 @@
+<!DOCTYPE HTML>
+<html>
+
+<head>
+    <meta charset="utf-8">
+
+    <title>Jupyter Notebook</title>
+    <link rel="shortcut icon" type="image/x-icon" href="/static/base/images/favicon.ico?v=97c6417ed01bdc0ae3ef32ae4894fd03">
+    <meta http-equiv="X-UA-Compatible" content="IE=edge" />
+    <link rel="stylesheet" href="/static/components/jquery-ui/themes/smoothness/jquery-ui.min.css?v=9b2c8d3489227115310662a343fce11c" type="text/css" />
+    <link rel="stylesheet" href="/static/components/jquery-typeahead/dist/jquery.typeahead.min.css?v=7afb461de36accb1aa133a1710f5bc56" type="text/css" />
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    
+    
+
+
+<script type="text/javascript" src="/static/components/MathJax/MathJax.js?config=TeX-AMS-MML_HTMLorMML-full,Safe&delayStartupUntil=configured" charset="utf-8"></script>
+
+<script type="text/javascript">
+// MathJax disabled, set as null to distingish from *missing* MathJax,
+// where it will be undefined, and should prompt a dialog later.
+window.mathjax_url = "/static/components/MathJax/MathJax.js";
+</script>
+
+<link rel="stylesheet" href="/static/components/bootstrap-tour/build/css/bootstrap-tour.min.css?v=d0b3c2fce6056a2ddd5a4513762a94c4" type="text/css" />
+<link rel="stylesheet" href="/static/components/codemirror/lib/codemirror.css?v=f25e9a9159e54b423b5a8dc4b1ab5c6e">
+
+
+    <link rel="stylesheet" href="/static/style/style.min.css?v=29c09309dd70e7fe93378815e5f022ae" type="text/css"/>
+    
+
+<link rel="stylesheet" href="/static/notebook/css/override.css?v=e6f18013b8771987812e992b38ec3318" type="text/css" />
+<link rel="stylesheet" href=""  id='kernel-css'                             type="text/css" />
+
+
+    <link rel="stylesheet" href="/custom/custom.css" type="text/css" />
+    <script src="/static/components/es6-promise/promise.min.js?v=f004a16cb856e0ff11781d01ec5ca8fe" type="text/javascript" charset="utf-8"></script>
+    <script src="/static/components/preact/index.js?v=5b98fce8b86ce059de89f9e728e16957" type="text/javascript"></script>
+    <script src="/static/components/proptypes/index.js?v=c40890eb04df9811fcc4d47e53a29604" type="text/javascript"></script>
+    <script src="/static/components/preact-compat/index.js?v=d376eb109a00b9b2e8c0d30782eb6df7" type="text/javascript"></script>
+    <script src="/static/components/requirejs/require.js?v=6da8be361b9ee26c5e721e76c6d4afce" type="text/javascript" charset="utf-8"></script>
+    <script>
+      require.config({
+          
+          urlArgs: "v=20180311121747",
+          
+          baseUrl: '/static/',
+          paths: {
+            'auth/js/main': 'auth/js/main.min',
+            custom : '/custom',
+            nbextensions : '/nbextensions',
+            kernelspecs : '/kernelspecs',
+            underscore : 'components/underscore/underscore-min',
+            backbone : 'components/backbone/backbone-min',
+            jquery: 'components/jquery/jquery.min',
+            bootstrap: 'components/bootstrap/js/bootstrap.min',
+            bootstraptour: 'components/bootstrap-tour/build/js/bootstrap-tour.min',
+            'jquery-ui': 'components/jquery-ui/ui/minified/jquery-ui.min',
+            moment: 'components/moment/moment',
+            codemirror: 'components/codemirror',
+            termjs: 'components/xterm.js/dist/xterm',
+            typeahead: 'components/jquery-typeahead/dist/jquery.typeahead.min',
+          },
+          map: { // for backward compatibility
+              "*": {
+                  "jqueryui": "jquery-ui",
+              }
+          },
+          shim: {
+            typeahead: {
+              deps: ["jquery"],
+              exports: "typeahead"
+            },
+            underscore: {
+              exports: '_'
+            },
+            backbone: {
+              deps: ["underscore", "jquery"],
+              exports: "Backbone"
+            },
+            bootstrap: {
+              deps: ["jquery"],
+              exports: "bootstrap"
+            },
+            bootstraptour: {
+              deps: ["bootstrap"],
+              exports: "Tour"
+            },
+            "jquery-ui": {
+              deps: ["jquery"],
+              exports: "$"
+            }
+          },
+          waitSeconds: 30,
+      });
+
+      require.config({
+          map: {
+              '*':{
+                'contents': 'services/contents',
+              }
+          }
+      });
+
+      // error-catching custom.js shim.
+      define("custom", function (require, exports, module) {
+          try {
+              var custom = require('custom/custom');
+              console.debug('loaded custom.js');
+              return custom;
+          } catch (e) {
+              console.error("error loading custom.js", e);
+              return {};
+          }
+      })
+    </script>
+
+    
+    
+
+</head>
+
+<body class="notebook_app "
+ 
+
+
+  
+    data-jupyter-api-token="9c0c3761a459e9bfb3fdf5923bcfee31a85104b3d664476c"
+  
+ 
+data-base-url="/"
+data-ws-url=""
+data-notebook-name="atmodel_prediction_tutorial.ipynb"
+data-notebook-path="atmodel_prediction_tutorial.ipynb"
+
+dir="ltr">
+
+<noscript>
+    <div id='noscript'>
+      Jupyter Notebook requires JavaScript.<br>
+      Please enable it to proceed.
+  </div>
+</noscript>
+
+<div id="header">
+  <div id="header-container" class="container">
+  <div id="ipython_notebook" class="nav navbar-brand pull-left"><a href="/tree" title='dashboard'><img src='/static/base/images/logo.png?v=641991992878ee24c6f3826e81054a0f' alt='Jupyter Notebook'/></a></div>
+
+  
+  
+  
+
+    <span id="login_widget">
+      
+        <button id="logout" class="btn btn-sm navbar-btn">Logout</button>
+      
+    </span>
+
+  
+
+  
+
+  
+
+
+<span id="save_widget" class="pull-left save_widget">
+    <span id="notebook_name" class="filename"></span>
+    <span class="checkpoint_status"></span>
+    <span class="autosave_status"></span>
+</span>
+
+<span id="kernel_logo_widget">
+  
+  <img class="current_kernel_logo" src="data:image/gif;base64,R0lGODlhAQABAIAAAAAAAP///yH5BAEAAAAALAAAAAABAAEAAAIBRAA7"/>
+  
+</span>
+
+
+  </div>
+  <div class="header-bar"></div>
+
+  
+<div id="menubar-container" class="container">
+<div id="menubar">
+    <div id="menus" class="navbar navbar-default" role="navigation">
+        <div class="container-fluid">
+            <button type="button" class="btn btn-default navbar-btn navbar-toggle" data-toggle="collapse" data-target=".navbar-collapse">
+              <i class="fa fa-bars"></i>
+              <span class="navbar-text">Menu</span>
+            </button>
+            <p id="kernel_indicator" class="navbar-text indicator_area">
+              <span class="kernel_indicator_name">Kernel</span>
+              <i id="kernel_indicator_icon"></i>
+            </p>
+            <i id="readonly-indicator" class="navbar-text" title='This notebook is read-only'>
+                <span class="fa-stack">
+                    <i class="fa fa-save fa-stack-1x"></i>
+                    <i class="fa fa-ban fa-stack-2x text-danger"></i>
+                </span>
+            </i>
+            <i id="modal_indicator" class="navbar-text"></i>
+            <span id="notification_area"></span>
+            <div class="navbar-collapse collapse">
+              <ul class="nav navbar-nav">
+                <li class="dropdown"><a href="#" class="dropdown-toggle" data-toggle="dropdown">File</a>
+                    <ul id="file_menu" class="dropdown-menu">
+                        <li id="new_notebook" class="dropdown-submenu">
+                            <a href="#">New Notebook</a>
+                            <ul class="dropdown-menu" id="menu-new-notebook-submenu"></ul>
+                        </li>
+                        <li id="open_notebook"
+                            title="Opens a new window with the Dashboard view">
+                            <a href="#">Open...</a></li>
+                        <!-- <hr/> -->
+                        <li class="divider"></li>
+                        <li id="copy_notebook"
+                            title="Open a copy of this notebook's contents and start a new kernel">
+                            <a href="#">Make a Copy...</a></li>
+                        <li id="rename_notebook"><a href="#">Rename...</a></li>
+                        <li id="save_checkpoint"><a href="#">Save and Checkpoint</a></li>
+                        <!-- <hr/> -->
+                        <li class="divider"></li>
+                        <li id="restore_checkpoint" class="dropdown-submenu"><a href="#">Revert to Checkpoint</a>
+                          <ul class="dropdown-menu">
+                            <li><a href="#"></a></li>
+                            <li><a href="#"></a></li>
+                            <li><a href="#"></a></li>
+                            <li><a href="#"></a></li>
+                            <li><a href="#"></a></li>
+                          </ul>
+                        </li>
+                        <li class="divider"></li>
+                        <li id="print_preview"><a href="#">Print Preview</a></li>
+                        <li class="dropdown-submenu"><a href="#">Download as</a>
+                            <ul id="download_menu" class="dropdown-menu">
+                                <li id="download_ipynb"><a href="#">Notebook (.ipynb)</a></li>
+                                <li id="download_script"><a href="#">Script</a></li>
+                                <li id="download_html"><a href="#">HTML (.html)</a></li>
+                                <li id="download_markdown"><a href="#">Markdown (.md)</a></li>
+                                <li id="download_rst"><a href="#">reST (.rst)</a></li>
+                                <li id="download_latex"><a href="#">LaTeX (.tex)</a></li>
+                                <li id="download_pdf"><a href="#">PDF via LaTeX (.pdf)</a></li>
+                            </ul>
+                        </li>
+                        <li class="dropdown-submenu hidden"><a href="#">Deploy as</a>
+                            <ul id="deploy_menu" class="dropdown-menu"></ul>
+                        </li>
+                        <li class="divider"></li>
+                        <li id="trust_notebook"
+                            title="Trust the output of this notebook">
+                            <a href="#" >Trust Notebook</a></li>
+                        <li class="divider"></li>
+                        <li id="kill_and_exit"
+                            title="Shutdown this notebook's kernel, and close this window">
+                            <a href="#" >Close and Halt</a></li>
+                    </ul>
+                </li>
+                <li class="dropdown"><a href="#" class="dropdown-toggle" data-toggle="dropdown">Edit</a>
+                    <ul id="edit_menu" class="dropdown-menu">
+                        <li id="cut_cell"><a href="#">Cut Cells</a></li>
+                        <li id="copy_cell"><a href="#">Copy Cells</a></li>
+                        <li id="paste_cell_above" class="disabled"><a href="#">Paste Cells Above</a></li>
+                        <li id="paste_cell_below" class="disabled"><a href="#">Paste Cells Below</a></li>
+                        <li id="paste_cell_replace" class="disabled"><a href="#">Paste Cells &amp; Replace</a></li>
+                        <li id="delete_cell"><a href="#">Delete Cells</a></li>
+                        <li id="undelete_cell" class="disabled"><a href="#">Undo Delete Cells</a></li>
+                        <li class="divider"></li>
+                        <li id="split_cell"><a href="#">Split Cell</a></li>
+                        <li id="merge_cell_above"><a href="#">Merge Cell Above</a></li>
+                        <li id="merge_cell_below"><a href="#">Merge Cell Below</a></li>
+                        <li class="divider"></li>
+                        <li id="move_cell_up"><a href="#">Move Cell Up</a></li>
+                        <li id="move_cell_down"><a href="#">Move Cell Down</a></li>
+                        <li class="divider"></li>
+                        <li id="edit_nb_metadata"><a href="#">Edit Notebook Metadata</a></li>
+                        <li class="divider"></li>
+                        <li id="find_and_replace"><a href="#"> Find and Replace </a></li>
+                        <li class="divider"></li>
+                        <li id="cut_cell_attachments"><a href="#">Cut Cell Attachments</a></li>
+                        <li id="copy_cell_attachments"><a href="#">Copy Cell Attachments</a></li>
+                        <li id="paste_cell_attachments" class="disabled"><a href="#">Paste Cell Attachments</a></li>
+                        <li class="divider"></li>
+                        <li id="insert_image" class="disabled"><a href="#"> Insert Image </a></li>
+                    </ul>
+                </li>
+                <li class="dropdown"><a href="#" class="dropdown-toggle" data-toggle="dropdown">View</a>
+                    <ul id="view_menu" class="dropdown-menu">
+                        <li id="toggle_header"
+                            title="Show/Hide the logo and notebook title (above menu bar)">
+                            <a href="#">Toggle Header</a>
+                        </li>
+                        <li id="toggle_toolbar"
+                            title="Show/Hide the action icons (below menu bar)">
+                            <a href="#">Toggle Toolbar</a>
+                        </li>
+                        <li id="toggle_line_numbers"
+                            title="Show/Hide line numbers in cells">
+                            <a href="#">Toggle Line Numbers</a>
+                        </li>
+                        <li id="menu-cell-toolbar" class="dropdown-submenu">
+                            <a href="#">Cell Toolbar</a>
+                            <ul class="dropdown-menu" id="menu-cell-toolbar-submenu"></ul>
+                        </li>
+                    </ul>
+                </li>
+                <li class="dropdown"><a href="#" class="dropdown-toggle" data-toggle="dropdown">Insert</a>
+                    <ul id="insert_menu" class="dropdown-menu">
+                        <li id="insert_cell_above"
+                            title="Insert an empty Code cell above the currently active cell">
+                            <a href="#">Insert Cell Above</a></li>
+                        <li id="insert_cell_below"
+                            title="Insert an empty Code cell below the currently active cell">
+                            <a href="#">Insert Cell Below</a></li>
+                    </ul>
+                </li>
+                <li class="dropdown"><a href="#" class="dropdown-toggle" data-toggle="dropdown">Cell</a>
+                    <ul id="cell_menu" class="dropdown-menu">
+                        <li id="run_cell" title="Run this cell, and move cursor to the next one">
+                            <a href="#">Run Cells</a></li>
+                        <li id="run_cell_select_below" title="Run this cell, select below">
+                            <a href="#">Run Cells and Select Below</a></li>
+                        <li id="run_cell_insert_below" title="Run this cell, insert below">
+                            <a href="#">Run Cells and Insert Below</a></li>
+                        <li id="run_all_cells" title="Run all cells in the notebook">
+                            <a href="#">Run All</a></li>
+                        <li id="run_all_cells_above" title="Run all cells above (but not including) this cell">
+                            <a href="#">Run All Above</a></li>
+                        <li id="run_all_cells_below" title="Run this cell and all cells below it">
+                            <a href="#">Run All Below</a></li>
+                        <li class="divider"></li>
+                        <li id="change_cell_type" class="dropdown-submenu"
+                            title="All cells in the notebook have a cell type. By default, new cells are created as 'Code' cells">
+                            <a href="#">Cell Type</a>
+                            <ul class="dropdown-menu">
+                              <li id="to_code"
+                                  title="Contents will be sent to the kernel for execution, and output will display in the footer of cell">
+                                  <a href="#">Code</a></li>
+                              <li id="to_markdown"
+                                  title="Contents will be rendered as HTML and serve as explanatory text">
+                                  <a href="#">Markdown</a></li>
+                              <li id="to_raw"
+                                  title="Contents will pass through nbconvert unmodified">
+                                  <a href="#">Raw NBConvert</a></li>
+                            </ul>
+                        </li>
+                        <li class="divider"></li>
+                        <li id="current_outputs" class="dropdown-submenu"><a href="#">Current Outputs</a>
+                            <ul class="dropdown-menu">
+                                <li id="toggle_current_output"
+                                    title="Hide/Show the output of the current cell">
+                                    <a href="#">Toggle</a>
+                                </li>
+                                <li id="toggle_current_output_scroll"
+                                    title="Scroll the output of the current cell">
+                                    <a href="#">Toggle Scrolling</a>
+                                </li>
+                                <li id="clear_current_output"
+                                    title="Clear the output of the current cell">
+                                    <a href="#">Clear</a>
+                                </li>
+                            </ul>
+                        </li>
+                        <li id="all_outputs" class="dropdown-submenu"><a href="#">All Output</a>
+                            <ul class="dropdown-menu">
+                                <li id="toggle_all_output"
+                                    title="Hide/Show the output of all cells">
+                                    <a href="#">Toggle</a>
+                                </li>
+                                <li id="toggle_all_output_scroll"
+                                    title="Scroll the output of all cells">
+                                    <a href="#">Toggle Scrolling</a>
+                                </li>
+                                <li id="clear_all_output"
+                                    title="Clear the output of all cells">
+                                    <a href="#">Clear</a>
+                                </li>
+                            </ul>
+                        </li>
+                    </ul>
+                </li>
+                <li class="dropdown"><a href="#" class="dropdown-toggle" data-toggle="dropdown">Kernel</a>
+                    <ul id="kernel_menu" class="dropdown-menu">
+                        <li id="int_kernel"
+                            title="Send KeyboardInterrupt (CTRL-C) to the Kernel">
+                            <a href="#">Interrupt</a>
+                        </li>
+                        <li id="restart_kernel"
+                            title="Restart the Kernel">
+                            <a href="#">Restart</a>
+                        </li>
+                        <li id="restart_clear_output"
+                            title="Restart the Kernel and clear all output">
+                            <a href="#">Restart &amp; Clear Output</a>
+                        </li>
+                        <li id="restart_run_all"
+                            title="Restart the Kernel and re-run the notebook">
+                            <a href="#">Restart &amp; Run All</a>
+                        </li>
+                        <li id="reconnect_kernel"
+                            title="Reconnect to the Kernel">
+                            <a href="#">Reconnect</a>
+                        </li>
+                        <li id="shutdown_kernel"
+                            title="Shutdown the Kernel">
+                            <a href="#">Shutdown</a>
+                        </li>
+                        <li class="divider"></li>
+                        <li id="menu-change-kernel" class="dropdown-submenu">
+                            <a href="#">Change kernel</a>
+                            <ul class="dropdown-menu" id="menu-change-kernel-submenu"></ul>
+                        </li>
+                    </ul>
+                </li>
+                <li class="dropdown"><a href="#" class="dropdown-toggle" data-toggle="dropdown">Help</a>
+                    <ul  id="help_menu" class="dropdown-menu">
+                        
+                        <li id="notebook_tour" title="A quick tour of the notebook user interface"><a href="#">User Interface Tour</a></li>
+                        <li id="keyboard_shortcuts" title="Opens a dialog which shows all keyboard shortcuts"><a href="#">Keyboard Shortcuts</a></li>
+                        <li id="edit_keyboard_shortcuts" title="Opens a dialog allowing you to edit Keyboard shortcuts"><a href="#">Edit Keyboard Shortcuts</a></li>
+                        <li class="divider"></li>
+                        
+
+                        
+                            
+                                <li><a rel="noreferrer" href="http://nbviewer.ipython.org/github/ipython/ipython/blob/3.x/examples/Notebook/Index.ipynb" target="_blank" title="Opens in a new window">
+                                
+                                    <i class="fa fa-external-link menu-icon pull-right"></i>
+                                
+
+                                Notebook Help
+                                </a></li>
+                            
+                                <li><a rel="noreferrer" href="https://help.github.com/articles/markdown-basics/" target="_blank" title="Opens in a new window">
+                                
+                                    <i class="fa fa-external-link menu-icon pull-right"></i>
+                                
+
+                                Markdown
+                                </a></li>
+                            
+                            
+                        
+                        <li class="divider"></li>
+                        <li title="About Jupyter Notebook"><a id="notebook_about" href="#">About</a></li>
+                        
+                    </ul>
+                </li>
+              </ul>
+            </div>
+        </div>
+    </div>
+</div>
+
+<div id="maintoolbar" class="navbar">
+  <div class="toolbar-inner navbar-inner navbar-nobg">
+    <div id="maintoolbar-container" class="container"></div>
+  </div>
+</div>
+</div>
+
+<div class="lower-header-bar"></div>
+
+</div>
+
+<div id="site">
+
+
+<div id="ipython-main-app">
+    <div id="notebook_panel">
+        <div id="notebook"></div>
+        <div id='tooltip' class='ipython_tooltip' style='display:none'></div>
+    </div>
+</div>
+
+
+
+</div>
+
+
+
+<div id="pager">
+    <div id="pager-contents">
+        <div id="pager-container" class="container"></div>
+    </div>
+    <div id='pager-button-area'></div>
+</div>
+
+
+
+
+
+
+<script type="text/javascript">
+    sys_info = {"notebook_path": "/Users/martin/virtualenvs/bachelor/lib/python3.5/site-packages/notebook", "os_name": "posix", "platform": "Darwin-17.4.0-x86_64-i386-64bit", "commit_source": "", "commit_hash": "", "sys_executable": "/Users/martin/virtualenvs/bachelor/bin/python3.5", "sys_version": "3.5.0 (default, Sep 23 2015, 04:42:00) \n[GCC 4.2.1 Compatible Apple LLVM 7.0.0 (clang-700.0.72)]", "default_encoding": "UTF-8", "notebook_version": "5.0.0", "sys_platform": "darwin"};
+</script>
+
+<script src="/static/components/text-encoding/lib/encoding.js?v=d5bb0fc9ffeff7d98a69bb83daa51052" charset="utf-8"></script>
+
+<script src="/static/notebook/js/main.min.js?v=6a166b31c5a20f809e44ec2d50e40412" type="text/javascript" charset="utf-8"></script>
+
+
+
+<script type='text/javascript'>
+  function _remove_token_from_url() {
+    if (window.location.search.length <= 1) {
+      return;
+    }
+    var search_parameters = window.location.search.slice(1).split('&');
+    for (var i = 0; i < search_parameters.length; i++) {
+      if (search_parameters[i].split('=')[0] === 'token') {
+        // remote token from search parameters
+        search_parameters.splice(i, 1);
+        var new_search = '';
+        if (search_parameters.length) {
+          new_search = '?' + search_parameters.join('&');
+        }
+        var new_url = window.location.origin + 
+                      window.location.pathname + 
+                      new_search + 
+                      window.location.hash;
+        window.history.replaceState({}, "", new_url);
+        return;
+      }
+    }
+  }
+  _remove_token_from_url();
+</script>
+</body>
+
+</html>
\ No newline at end of file

From c5258455ad678f48c6cecf13f36cd33327a4310a Mon Sep 17 00:00:00 2001
From: Martin Stamenov <stamenov.martin@gmail.com>
Date: Mon, 26 Mar 2018 12:35:49 +0200
Subject: [PATCH 23/23] add ipynb

---
 .../atmodel_prediction_tutorial.ipynb         | 2368 +++++++++++++----
 1 file changed, 1841 insertions(+), 527 deletions(-)

diff --git a/docs/notebooks/atmodel_prediction_tutorial.ipynb b/docs/notebooks/atmodel_prediction_tutorial.ipynb
index 9a7e3bff33..bb70d1056b 100644
--- a/docs/notebooks/atmodel_prediction_tutorial.ipynb
+++ b/docs/notebooks/atmodel_prediction_tutorial.ipynb
@@ -1,530 +1,1844 @@
-<!DOCTYPE HTML>
-<html>
-
-<head>
-    <meta charset="utf-8">
-
-    <title>Jupyter Notebook</title>
-    <link rel="shortcut icon" type="image/x-icon" href="/static/base/images/favicon.ico?v=97c6417ed01bdc0ae3ef32ae4894fd03">
-    <meta http-equiv="X-UA-Compatible" content="IE=edge" />
-    <link rel="stylesheet" href="/static/components/jquery-ui/themes/smoothness/jquery-ui.min.css?v=9b2c8d3489227115310662a343fce11c" type="text/css" />
-    <link rel="stylesheet" href="/static/components/jquery-typeahead/dist/jquery.typeahead.min.css?v=7afb461de36accb1aa133a1710f5bc56" type="text/css" />
-    <meta name="viewport" content="width=device-width, initial-scale=1.0">
-    
-    
-
-
-<script type="text/javascript" src="/static/components/MathJax/MathJax.js?config=TeX-AMS-MML_HTMLorMML-full,Safe&delayStartupUntil=configured" charset="utf-8"></script>
-
-<script type="text/javascript">
-// MathJax disabled, set as null to distingish from *missing* MathJax,
-// where it will be undefined, and should prompt a dialog later.
-window.mathjax_url = "/static/components/MathJax/MathJax.js";
-</script>
-
-<link rel="stylesheet" href="/static/components/bootstrap-tour/build/css/bootstrap-tour.min.css?v=d0b3c2fce6056a2ddd5a4513762a94c4" type="text/css" />
-<link rel="stylesheet" href="/static/components/codemirror/lib/codemirror.css?v=f25e9a9159e54b423b5a8dc4b1ab5c6e">
-
-
-    <link rel="stylesheet" href="/static/style/style.min.css?v=29c09309dd70e7fe93378815e5f022ae" type="text/css"/>
-    
-
-<link rel="stylesheet" href="/static/notebook/css/override.css?v=e6f18013b8771987812e992b38ec3318" type="text/css" />
-<link rel="stylesheet" href=""  id='kernel-css'                             type="text/css" />
-
-
-    <link rel="stylesheet" href="/custom/custom.css" type="text/css" />
-    <script src="/static/components/es6-promise/promise.min.js?v=f004a16cb856e0ff11781d01ec5ca8fe" type="text/javascript" charset="utf-8"></script>
-    <script src="/static/components/preact/index.js?v=5b98fce8b86ce059de89f9e728e16957" type="text/javascript"></script>
-    <script src="/static/components/proptypes/index.js?v=c40890eb04df9811fcc4d47e53a29604" type="text/javascript"></script>
-    <script src="/static/components/preact-compat/index.js?v=d376eb109a00b9b2e8c0d30782eb6df7" type="text/javascript"></script>
-    <script src="/static/components/requirejs/require.js?v=6da8be361b9ee26c5e721e76c6d4afce" type="text/javascript" charset="utf-8"></script>
-    <script>
-      require.config({
-          
-          urlArgs: "v=20180311121747",
-          
-          baseUrl: '/static/',
-          paths: {
-            'auth/js/main': 'auth/js/main.min',
-            custom : '/custom',
-            nbextensions : '/nbextensions',
-            kernelspecs : '/kernelspecs',
-            underscore : 'components/underscore/underscore-min',
-            backbone : 'components/backbone/backbone-min',
-            jquery: 'components/jquery/jquery.min',
-            bootstrap: 'components/bootstrap/js/bootstrap.min',
-            bootstraptour: 'components/bootstrap-tour/build/js/bootstrap-tour.min',
-            'jquery-ui': 'components/jquery-ui/ui/minified/jquery-ui.min',
-            moment: 'components/moment/moment',
-            codemirror: 'components/codemirror',
-            termjs: 'components/xterm.js/dist/xterm',
-            typeahead: 'components/jquery-typeahead/dist/jquery.typeahead.min',
-          },
-          map: { // for backward compatibility
-              "*": {
-                  "jqueryui": "jquery-ui",
-              }
-          },
-          shim: {
-            typeahead: {
-              deps: ["jquery"],
-              exports: "typeahead"
-            },
-            underscore: {
-              exports: '_'
-            },
-            backbone: {
-              deps: ["underscore", "jquery"],
-              exports: "Backbone"
-            },
-            bootstrap: {
-              deps: ["jquery"],
-              exports: "bootstrap"
-            },
-            bootstraptour: {
-              deps: ["bootstrap"],
-              exports: "Tour"
-            },
-            "jquery-ui": {
-              deps: ["jquery"],
-              exports: "$"
-            }
-          },
-          waitSeconds: 30,
-      });
-
-      require.config({
-          map: {
-              '*':{
-                'contents': 'services/contents',
-              }
-          }
-      });
-
-      // error-catching custom.js shim.
-      define("custom", function (require, exports, module) {
-          try {
-              var custom = require('custom/custom');
-              console.debug('loaded custom.js');
-              return custom;
-          } catch (e) {
-              console.error("error loading custom.js", e);
-              return {};
-          }
-      })
-    </script>
-
-    
-    
-
-</head>
-
-<body class="notebook_app "
- 
-
-
-  
-    data-jupyter-api-token="9c0c3761a459e9bfb3fdf5923bcfee31a85104b3d664476c"
-  
- 
-data-base-url="/"
-data-ws-url=""
-data-notebook-name="atmodel_prediction_tutorial.ipynb"
-data-notebook-path="atmodel_prediction_tutorial.ipynb"
-
-dir="ltr">
-
-<noscript>
-    <div id='noscript'>
-      Jupyter Notebook requires JavaScript.<br>
-      Please enable it to proceed.
-  </div>
-</noscript>
-
-<div id="header">
-  <div id="header-container" class="container">
-  <div id="ipython_notebook" class="nav navbar-brand pull-left"><a href="/tree" title='dashboard'><img src='/static/base/images/logo.png?v=641991992878ee24c6f3826e81054a0f' alt='Jupyter Notebook'/></a></div>
-
-  
-  
-  
-
-    <span id="login_widget">
-      
-        <button id="logout" class="btn btn-sm navbar-btn">Logout</button>
-      
-    </span>
-
-  
-
-  
-
-  
-
-
-<span id="save_widget" class="pull-left save_widget">
-    <span id="notebook_name" class="filename"></span>
-    <span class="checkpoint_status"></span>
-    <span class="autosave_status"></span>
-</span>
-
-<span id="kernel_logo_widget">
-  
-  <img class="current_kernel_logo" src="data:image/gif;base64,R0lGODlhAQABAIAAAAAAAP///yH5BAEAAAAALAAAAAABAAEAAAIBRAA7"/>
-  
-</span>
-
-
-  </div>
-  <div class="header-bar"></div>
-
-  
-<div id="menubar-container" class="container">
-<div id="menubar">
-    <div id="menus" class="navbar navbar-default" role="navigation">
-        <div class="container-fluid">
-            <button type="button" class="btn btn-default navbar-btn navbar-toggle" data-toggle="collapse" data-target=".navbar-collapse">
-              <i class="fa fa-bars"></i>
-              <span class="navbar-text">Menu</span>
-            </button>
-            <p id="kernel_indicator" class="navbar-text indicator_area">
-              <span class="kernel_indicator_name">Kernel</span>
-              <i id="kernel_indicator_icon"></i>
-            </p>
-            <i id="readonly-indicator" class="navbar-text" title='This notebook is read-only'>
-                <span class="fa-stack">
-                    <i class="fa fa-save fa-stack-1x"></i>
-                    <i class="fa fa-ban fa-stack-2x text-danger"></i>
-                </span>
-            </i>
-            <i id="modal_indicator" class="navbar-text"></i>
-            <span id="notification_area"></span>
-            <div class="navbar-collapse collapse">
-              <ul class="nav navbar-nav">
-                <li class="dropdown"><a href="#" class="dropdown-toggle" data-toggle="dropdown">File</a>
-                    <ul id="file_menu" class="dropdown-menu">
-                        <li id="new_notebook" class="dropdown-submenu">
-                            <a href="#">New Notebook</a>
-                            <ul class="dropdown-menu" id="menu-new-notebook-submenu"></ul>
-                        </li>
-                        <li id="open_notebook"
-                            title="Opens a new window with the Dashboard view">
-                            <a href="#">Open...</a></li>
-                        <!-- <hr/> -->
-                        <li class="divider"></li>
-                        <li id="copy_notebook"
-                            title="Open a copy of this notebook's contents and start a new kernel">
-                            <a href="#">Make a Copy...</a></li>
-                        <li id="rename_notebook"><a href="#">Rename...</a></li>
-                        <li id="save_checkpoint"><a href="#">Save and Checkpoint</a></li>
-                        <!-- <hr/> -->
-                        <li class="divider"></li>
-                        <li id="restore_checkpoint" class="dropdown-submenu"><a href="#">Revert to Checkpoint</a>
-                          <ul class="dropdown-menu">
-                            <li><a href="#"></a></li>
-                            <li><a href="#"></a></li>
-                            <li><a href="#"></a></li>
-                            <li><a href="#"></a></li>
-                            <li><a href="#"></a></li>
-                          </ul>
-                        </li>
-                        <li class="divider"></li>
-                        <li id="print_preview"><a href="#">Print Preview</a></li>
-                        <li class="dropdown-submenu"><a href="#">Download as</a>
-                            <ul id="download_menu" class="dropdown-menu">
-                                <li id="download_ipynb"><a href="#">Notebook (.ipynb)</a></li>
-                                <li id="download_script"><a href="#">Script</a></li>
-                                <li id="download_html"><a href="#">HTML (.html)</a></li>
-                                <li id="download_markdown"><a href="#">Markdown (.md)</a></li>
-                                <li id="download_rst"><a href="#">reST (.rst)</a></li>
-                                <li id="download_latex"><a href="#">LaTeX (.tex)</a></li>
-                                <li id="download_pdf"><a href="#">PDF via LaTeX (.pdf)</a></li>
-                            </ul>
-                        </li>
-                        <li class="dropdown-submenu hidden"><a href="#">Deploy as</a>
-                            <ul id="deploy_menu" class="dropdown-menu"></ul>
-                        </li>
-                        <li class="divider"></li>
-                        <li id="trust_notebook"
-                            title="Trust the output of this notebook">
-                            <a href="#" >Trust Notebook</a></li>
-                        <li class="divider"></li>
-                        <li id="kill_and_exit"
-                            title="Shutdown this notebook's kernel, and close this window">
-                            <a href="#" >Close and Halt</a></li>
-                    </ul>
-                </li>
-                <li class="dropdown"><a href="#" class="dropdown-toggle" data-toggle="dropdown">Edit</a>
-                    <ul id="edit_menu" class="dropdown-menu">
-                        <li id="cut_cell"><a href="#">Cut Cells</a></li>
-                        <li id="copy_cell"><a href="#">Copy Cells</a></li>
-                        <li id="paste_cell_above" class="disabled"><a href="#">Paste Cells Above</a></li>
-                        <li id="paste_cell_below" class="disabled"><a href="#">Paste Cells Below</a></li>
-                        <li id="paste_cell_replace" class="disabled"><a href="#">Paste Cells &amp; Replace</a></li>
-                        <li id="delete_cell"><a href="#">Delete Cells</a></li>
-                        <li id="undelete_cell" class="disabled"><a href="#">Undo Delete Cells</a></li>
-                        <li class="divider"></li>
-                        <li id="split_cell"><a href="#">Split Cell</a></li>
-                        <li id="merge_cell_above"><a href="#">Merge Cell Above</a></li>
-                        <li id="merge_cell_below"><a href="#">Merge Cell Below</a></li>
-                        <li class="divider"></li>
-                        <li id="move_cell_up"><a href="#">Move Cell Up</a></li>
-                        <li id="move_cell_down"><a href="#">Move Cell Down</a></li>
-                        <li class="divider"></li>
-                        <li id="edit_nb_metadata"><a href="#">Edit Notebook Metadata</a></li>
-                        <li class="divider"></li>
-                        <li id="find_and_replace"><a href="#"> Find and Replace </a></li>
-                        <li class="divider"></li>
-                        <li id="cut_cell_attachments"><a href="#">Cut Cell Attachments</a></li>
-                        <li id="copy_cell_attachments"><a href="#">Copy Cell Attachments</a></li>
-                        <li id="paste_cell_attachments" class="disabled"><a href="#">Paste Cell Attachments</a></li>
-                        <li class="divider"></li>
-                        <li id="insert_image" class="disabled"><a href="#"> Insert Image </a></li>
-                    </ul>
-                </li>
-                <li class="dropdown"><a href="#" class="dropdown-toggle" data-toggle="dropdown">View</a>
-                    <ul id="view_menu" class="dropdown-menu">
-                        <li id="toggle_header"
-                            title="Show/Hide the logo and notebook title (above menu bar)">
-                            <a href="#">Toggle Header</a>
-                        </li>
-                        <li id="toggle_toolbar"
-                            title="Show/Hide the action icons (below menu bar)">
-                            <a href="#">Toggle Toolbar</a>
-                        </li>
-                        <li id="toggle_line_numbers"
-                            title="Show/Hide line numbers in cells">
-                            <a href="#">Toggle Line Numbers</a>
-                        </li>
-                        <li id="menu-cell-toolbar" class="dropdown-submenu">
-                            <a href="#">Cell Toolbar</a>
-                            <ul class="dropdown-menu" id="menu-cell-toolbar-submenu"></ul>
-                        </li>
-                    </ul>
-                </li>
-                <li class="dropdown"><a href="#" class="dropdown-toggle" data-toggle="dropdown">Insert</a>
-                    <ul id="insert_menu" class="dropdown-menu">
-                        <li id="insert_cell_above"
-                            title="Insert an empty Code cell above the currently active cell">
-                            <a href="#">Insert Cell Above</a></li>
-                        <li id="insert_cell_below"
-                            title="Insert an empty Code cell below the currently active cell">
-                            <a href="#">Insert Cell Below</a></li>
-                    </ul>
-                </li>
-                <li class="dropdown"><a href="#" class="dropdown-toggle" data-toggle="dropdown">Cell</a>
-                    <ul id="cell_menu" class="dropdown-menu">
-                        <li id="run_cell" title="Run this cell, and move cursor to the next one">
-                            <a href="#">Run Cells</a></li>
-                        <li id="run_cell_select_below" title="Run this cell, select below">
-                            <a href="#">Run Cells and Select Below</a></li>
-                        <li id="run_cell_insert_below" title="Run this cell, insert below">
-                            <a href="#">Run Cells and Insert Below</a></li>
-                        <li id="run_all_cells" title="Run all cells in the notebook">
-                            <a href="#">Run All</a></li>
-                        <li id="run_all_cells_above" title="Run all cells above (but not including) this cell">
-                            <a href="#">Run All Above</a></li>
-                        <li id="run_all_cells_below" title="Run this cell and all cells below it">
-                            <a href="#">Run All Below</a></li>
-                        <li class="divider"></li>
-                        <li id="change_cell_type" class="dropdown-submenu"
-                            title="All cells in the notebook have a cell type. By default, new cells are created as 'Code' cells">
-                            <a href="#">Cell Type</a>
-                            <ul class="dropdown-menu">
-                              <li id="to_code"
-                                  title="Contents will be sent to the kernel for execution, and output will display in the footer of cell">
-                                  <a href="#">Code</a></li>
-                              <li id="to_markdown"
-                                  title="Contents will be rendered as HTML and serve as explanatory text">
-                                  <a href="#">Markdown</a></li>
-                              <li id="to_raw"
-                                  title="Contents will pass through nbconvert unmodified">
-                                  <a href="#">Raw NBConvert</a></li>
-                            </ul>
-                        </li>
-                        <li class="divider"></li>
-                        <li id="current_outputs" class="dropdown-submenu"><a href="#">Current Outputs</a>
-                            <ul class="dropdown-menu">
-                                <li id="toggle_current_output"
-                                    title="Hide/Show the output of the current cell">
-                                    <a href="#">Toggle</a>
-                                </li>
-                                <li id="toggle_current_output_scroll"
-                                    title="Scroll the output of the current cell">
-                                    <a href="#">Toggle Scrolling</a>
-                                </li>
-                                <li id="clear_current_output"
-                                    title="Clear the output of the current cell">
-                                    <a href="#">Clear</a>
-                                </li>
-                            </ul>
-                        </li>
-                        <li id="all_outputs" class="dropdown-submenu"><a href="#">All Output</a>
-                            <ul class="dropdown-menu">
-                                <li id="toggle_all_output"
-                                    title="Hide/Show the output of all cells">
-                                    <a href="#">Toggle</a>
-                                </li>
-                                <li id="toggle_all_output_scroll"
-                                    title="Scroll the output of all cells">
-                                    <a href="#">Toggle Scrolling</a>
-                                </li>
-                                <li id="clear_all_output"
-                                    title="Clear the output of all cells">
-                                    <a href="#">Clear</a>
-                                </li>
-                            </ul>
-                        </li>
-                    </ul>
-                </li>
-                <li class="dropdown"><a href="#" class="dropdown-toggle" data-toggle="dropdown">Kernel</a>
-                    <ul id="kernel_menu" class="dropdown-menu">
-                        <li id="int_kernel"
-                            title="Send KeyboardInterrupt (CTRL-C) to the Kernel">
-                            <a href="#">Interrupt</a>
-                        </li>
-                        <li id="restart_kernel"
-                            title="Restart the Kernel">
-                            <a href="#">Restart</a>
-                        </li>
-                        <li id="restart_clear_output"
-                            title="Restart the Kernel and clear all output">
-                            <a href="#">Restart &amp; Clear Output</a>
-                        </li>
-                        <li id="restart_run_all"
-                            title="Restart the Kernel and re-run the notebook">
-                            <a href="#">Restart &amp; Run All</a>
-                        </li>
-                        <li id="reconnect_kernel"
-                            title="Reconnect to the Kernel">
-                            <a href="#">Reconnect</a>
-                        </li>
-                        <li id="shutdown_kernel"
-                            title="Shutdown the Kernel">
-                            <a href="#">Shutdown</a>
-                        </li>
-                        <li class="divider"></li>
-                        <li id="menu-change-kernel" class="dropdown-submenu">
-                            <a href="#">Change kernel</a>
-                            <ul class="dropdown-menu" id="menu-change-kernel-submenu"></ul>
-                        </li>
-                    </ul>
-                </li>
-                <li class="dropdown"><a href="#" class="dropdown-toggle" data-toggle="dropdown">Help</a>
-                    <ul  id="help_menu" class="dropdown-menu">
-                        
-                        <li id="notebook_tour" title="A quick tour of the notebook user interface"><a href="#">User Interface Tour</a></li>
-                        <li id="keyboard_shortcuts" title="Opens a dialog which shows all keyboard shortcuts"><a href="#">Keyboard Shortcuts</a></li>
-                        <li id="edit_keyboard_shortcuts" title="Opens a dialog allowing you to edit Keyboard shortcuts"><a href="#">Edit Keyboard Shortcuts</a></li>
-                        <li class="divider"></li>
-                        
-
-                        
-                            
-                                <li><a rel="noreferrer" href="http://nbviewer.ipython.org/github/ipython/ipython/blob/3.x/examples/Notebook/Index.ipynb" target="_blank" title="Opens in a new window">
-                                
-                                    <i class="fa fa-external-link menu-icon pull-right"></i>
-                                
-
-                                Notebook Help
-                                </a></li>
-                            
-                                <li><a rel="noreferrer" href="https://help.github.com/articles/markdown-basics/" target="_blank" title="Opens in a new window">
-                                
-                                    <i class="fa fa-external-link menu-icon pull-right"></i>
-                                
-
-                                Markdown
-                                </a></li>
-                            
-                            
-                        
-                        <li class="divider"></li>
-                        <li title="About Jupyter Notebook"><a id="notebook_about" href="#">About</a></li>
-                        
-                    </ul>
-                </li>
-              </ul>
-            </div>
-        </div>
-    </div>
-</div>
-
-<div id="maintoolbar" class="navbar">
-  <div class="toolbar-inner navbar-inner navbar-nobg">
-    <div id="maintoolbar-container" class="container"></div>
-  </div>
-</div>
-</div>
-
-<div class="lower-header-bar"></div>
-
-</div>
-
-<div id="site">
-
-
-<div id="ipython-main-app">
-    <div id="notebook_panel">
-        <div id="notebook"></div>
-        <div id='tooltip' class='ipython_tooltip' style='display:none'></div>
-    </div>
-</div>
-
-
-
-</div>
-
-
-
-<div id="pager">
-    <div id="pager-contents">
-        <div id="pager-container" class="container"></div>
-    </div>
-    <div id='pager-button-area'></div>
-</div>
-
-
-
-
-
-
-<script type="text/javascript">
-    sys_info = {"notebook_path": "/Users/martin/virtualenvs/bachelor/lib/python3.5/site-packages/notebook", "os_name": "posix", "platform": "Darwin-17.4.0-x86_64-i386-64bit", "commit_source": "", "commit_hash": "", "sys_executable": "/Users/martin/virtualenvs/bachelor/bin/python3.5", "sys_version": "3.5.0 (default, Sep 23 2015, 04:42:00) \n[GCC 4.2.1 Compatible Apple LLVM 7.0.0 (clang-700.0.72)]", "default_encoding": "UTF-8", "notebook_version": "5.0.0", "sys_platform": "darwin"};
-</script>
-
-<script src="/static/components/text-encoding/lib/encoding.js?v=d5bb0fc9ffeff7d98a69bb83daa51052" charset="utf-8"></script>
-
-<script src="/static/notebook/js/main.min.js?v=6a166b31c5a20f809e44ec2d50e40412" type="text/javascript" charset="utf-8"></script>
-
-
-
-<script type='text/javascript'>
-  function _remove_token_from_url() {
-    if (window.location.search.length <= 1) {
-      return;
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Authorship prediction with the author-topic model"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "In this tutorial, you will learn how to use the author-topic model in Gensim for authorship prediction, based on the topic distributions and mesuring their similarity.\n",
+    "We will train the author-topic model on a Reuters dataset, which contains 50 authors, each with 50 documents for trianing and another 50 documents for testing: https://archive.ics.uci.edu/ml/datasets/Reuter_50_50 ."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "If you wish to learn more about the Author-topic model and LDA and how to train them, you should check out these tutorials beforehand. A lot of the preprocessing and configuration here has been done using their example:\n",
+    "* [LDA training tips](https://nbviewer.jupyter.org/github/rare-technologies/gensim/blob/develop/docs/notebooks/lda_training_tips.ipynb)\n",
+    "* [Training the author-topic model](https://nbviewer.jupyter.org/github/rare-technologies/gensim/blob/develop/docs/notebooks/atmodel_tutorial.ipynb)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "> **NOTE:**\n",
+    ">\n",
+    "> To run this tutorial on your own, install Jupyter, Gensim, SpaCy, Scikit-Learn, Bokeh and Pandas, e.g. using pip:\n",
+    ">\n",
+    "> `pip install jupyter gensim spacy sklearn bokeh pandas`\n",
+    ">\n",
+    "> Note that you need to download some data for SpaCy using `python -m spacy.en.download`.\n",
+    ">\n",
+    "> Download the notebook at https://github.com/RaRe-Technologies/gensim/tree/develop/docs/notebooks/atmodel_prediction_tutorial.ipynb.\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Predicting the author of a document is a difficult task, where current approaches usually turn to neural networks. These base a lot of their predictions on learing stylistic and syntactic preferences of the authors and also other features which help rather identify the author. \n",
+    "\n",
+    "In our case, we first model the domain knowledge of a certain author, based on what the author writes about. We do this by calculating the topic distributions for each author using the author-topic model.\n",
+    "After that, we perform the [new author inference](https://github.com/RaRe-Technologies/gensim/pull/1766) on the held-out subset. This again calculates a topic distribution for this new unknown author. \n",
+    "In order to perform the prediction, we find out of all known authors, the most similar one to the new unknown. Mathematically speaking, we find the author, whose topic distribution is the closest to the topic distribution of the new author, by a certrain distrance function or metric. \n",
+    "Here we explore the [Hellinger distance](https://en.wikipedia.org/wiki/Hellinger_distance) for the measuring the distance between two discrete multinomial topic distributions."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "We start off by downloading the dataset. You can do it manually using the aforementioned link, or run the following code cell."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "--2018-03-25 17:24:26--  https://archive.ics.uci.edu/ml/machine-learning-databases/00217/C50.zip\n",
+      "Resolving archive.ics.uci.edu... 128.195.10.249\n",
+      "Connecting to archive.ics.uci.edu|128.195.10.249|:443... connected.\n",
+      "HTTP request sent, awaiting response... 200 OK\n",
+      "Length: 8194031 (7.8M) [application/zip]\n",
+      "Saving to: 'STDOUT'\n",
+      "\n",
+      "-                   100%[===================>]   7.81M  2.30MB/s    in 3.4s    \n",
+      "\n",
+      "2018-03-25 17:24:31 (2.30 MB/s) - written to stdout [8194031/8194031]\n",
+      "\n"
+     ]
     }
-    var search_parameters = window.location.search.slice(1).split('&');
-    for (var i = 0; i < search_parameters.length; i++) {
-      if (search_parameters[i].split('=')[0] === 'token') {
-        // remote token from search parameters
-        search_parameters.splice(i, 1);
-        var new_search = '';
-        if (search_parameters.length) {
-          new_search = '?' + search_parameters.join('&');
-        }
-        var new_url = window.location.origin + 
-                      window.location.pathname + 
-                      new_search + 
-                      window.location.hash;
-        window.history.replaceState({}, "", new_url);
-        return;
-      }
+   ],
+   "source": [
+    "!wget -O - \"https://archive.ics.uci.edu/ml/machine-learning-databases/00217/C50.zip\" > /tmp/C50.zip"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "import logging\n",
+    "logging.basicConfig(format='%(asctime)s %(levelname)s:%(message)s', level=logging.DEBUG, datefmt='%I:%M:%S')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "import zipfile\n",
+    "\n",
+    "filename = '/tmp/C50.zip'\n",
+    "\n",
+    "zip_ref = zipfile.ZipFile(filename, 'r')\n",
+    "zip_ref.extractall(\"/tmp/\")\n",
+    "zip_ref.close()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "We wrap all the preprocessing steps, that you can find more about in the [author-topic notebook](https://nbviewer.jupyter.org/github/rare-technologies/gensim/blob/develop/docs/notebooks/atmodel_tutorial.ipynb) , in one fucntion so that we are able to iterate over different preprocessing parameters."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "import os, re, io\n",
+    "def preprocess_docs(data_dir):\n",
+    "    doc_ids = []\n",
+    "    author2doc = {}\n",
+    "    docs = []\n",
+    "    \n",
+    "    folders = os.listdir(data_dir)  # List of filenames.\n",
+    "    for authorname in folders:\n",
+    "        files = file = os.listdir(data_dir + '/' + authorname)\n",
+    "        for filen in files:\n",
+    "            (idx1, idx2) = re.search('[0-9]+', filen).span()  # Matches the indexes of the start end end of the ID.\n",
+    "            if not author2doc.get(authorname):\n",
+    "                # This is a new author.\n",
+    "                author2doc[authorname] = []\n",
+    "            doc_id = str(int(filen[idx1:idx2]))\n",
+    "            doc_ids.append(doc_id)\n",
+    "            author2doc[authorname].extend([doc_id])\n",
+    "\n",
+    "            # Read document text.\n",
+    "            # Note: ignoring characters that cause encoding errors.\n",
+    "            with io.open(data_dir + '/' + authorname + '/' + filen, errors='ignore', encoding='utf-8') as fid:\n",
+    "                txt = fid.read()\n",
+    "\n",
+    "            # Replace any whitespace (newline, tabs, etc.) by a single space.\n",
+    "            txt = re.sub('\\s', ' ', txt)\n",
+    "            docs.append(txt)\n",
+    "            \n",
+    "    doc_id_dict = dict(zip(doc_ids, range(len(doc_ids))))\n",
+    "    # Replace dataset IDs by integer IDs.\n",
+    "    for a, a_doc_ids in author2doc.items():\n",
+    "        for i, doc_id in enumerate(a_doc_ids):\n",
+    "            author2doc[a][i] = doc_id_dict[doc_id]\n",
+    "    import spacy\n",
+    "    nlp = spacy.load('en')\n",
+    "    \n",
+    "    %%time\n",
+    "    processed_docs = []\n",
+    "    for doc in nlp.pipe(docs, n_threads=4, batch_size=100):\n",
+    "        # Process document using Spacy NLP pipeline.\n",
+    "\n",
+    "        ents = doc.ents  # Named entities.\n",
+    "\n",
+    "        # Keep only words (no numbers, no punctuation).\n",
+    "        # Lemmatize tokens, remove punctuation and remove stopwords.\n",
+    "        doc = [token.lemma_ for token in doc if token.is_alpha and not token.is_stop]\n",
+    "\n",
+    "        # Remove common words from a stopword list.\n",
+    "        #doc = [token for token in doc if token not in STOPWORDS]\n",
+    "\n",
+    "        # Add named entities, but only if they are a compound of more than word.\n",
+    "        doc.extend([str(entity) for entity in ents if len(entity) > 1])\n",
+    "        processed_docs.append(doc)\n",
+    "    docs = processed_docs\n",
+    "    del processed_docs\n",
+    "    \n",
+    "    # Compute bigrams.\n",
+    "\n",
+    "    from gensim.models import Phrases\n",
+    "\n",
+    "    # Add bigrams and trigrams to docs (only ones that appear 20 times or more).\n",
+    "    bigram = Phrases(docs, min_count=20)\n",
+    "    for idx in range(len(docs)):\n",
+    "        for token in bigram[docs[idx]]:\n",
+    "            if '_' in token:\n",
+    "                # Token is a bigram, add to document.\n",
+    "                docs[idx].append(token)\n",
+    "    return docs, author2doc"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "We create the corpus of the train and test data using two separate functions, since each corpus is tied to a certain dictionary which maps the words to their ids. Also in order to create the test corpus, we use the dictionary from the train data, since the trained model has have the same id2word reference as the new test data. Otherwise token with id 1 from the test data wont't mean the same as the trained upon token with id 1 in the model."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "def create_corpus_dictionary(docs, max_freq=0.5, min_wordcount=20):\n",
+    "    # Create a dictionary representation of the documents, and filter out frequent and rare words.\n",
+    "    from gensim.corpora import Dictionary\n",
+    "    dictionary = Dictionary(docs)\n",
+    "\n",
+    "    # Remove rare and common tokens.\n",
+    "    # Filter out words that occur too frequently or too rarely.\n",
+    "    max_freq = max_freq\n",
+    "    min_wordcount = min_wordcount\n",
+    "    dictionary.filter_extremes(no_below=min_wordcount, no_above=max_freq)\n",
+    "\n",
+    "    _ = dictionary[0]  # This sort of \"initializes\" dictionary.id2token.\n",
+    "\n",
+    "    # Vectorize data.\n",
+    "    # Bag-of-words representation of the documents.\n",
+    "    corpus = [dictionary.doc2bow(doc) for doc in docs]\n",
+    "\n",
+    "    return corpus, dictionary\n",
+    "\n",
+    "def create_test_corpus(train_dictionary, docs):\n",
+    "    # Create test corpus using the dictionary from the train data.\n",
+    "    return [train_dictionary.doc2bow(doc) for doc in docs]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "For our first training, we specify that we want the parameters max_freq and min_wordcoun to be 50 and 20, as proposed by the original notebook tutorial. We will find out if this configuration is good enough for us."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {
+    "scrolled": false
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "05:24:36 DEBUG:Registered VCS backend: git\n",
+      "05:24:36 DEBUG:Registered VCS backend: hg\n",
+      "05:24:36 DEBUG:Registered VCS backend: svn\n",
+      "05:24:36 DEBUG:Registered VCS backend: bzr\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "CPU times: user 3 µs, sys: 0 ns, total: 3 µs\n",
+      "Wall time: 7.15 µs\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "05:26:17 INFO:'pattern' package not found; tag filters are not available for English\n",
+      "05:26:17 INFO:collecting all words and their counts\n",
+      "05:26:17 INFO:PROGRESS: at sentence #0, processed 0 words and 0 word types\n",
+      "05:26:19 INFO:collected 437598 word types from a corpus of 746622 words (unigram + bigrams) and 2500 sentences\n",
+      "05:26:19 INFO:using 437598 counts as vocab in Phrases<0 vocab, min_count=20, threshold=10.0, max_vocab_size=40000000>\n",
+      "/Users/martin/Projects/bachelor/gensim/gensim/models/phrases.py:490: UserWarning: For a faster implementation, use the gensim.models.phrases.Phraser class\n",
+      "  warnings.warn(\"For a faster implementation, use the gensim.models.phrases.Phraser class\")\n",
+      "05:26:24 INFO:adding document #0 to Dictionary(0 unique tokens: [])\n",
+      "05:26:25 INFO:built Dictionary(46905 unique tokens: ['$83.4 million', 'boarder', '$2.72 billion', 'checking', 'suzuki']...) from 2500 documents (total 786032 corpus positions)\n",
+      "05:26:25 INFO:discarding 42991 tokens: [('$1.4 billion', 11), ('$15', 3), ('$17.25', 1), ('$380 million', 2), ('12.5 cents', 7), ('Big B', 3), ('Big B Inc.', 2), (\"Big B's\", 3), ('Big B. I', 1), ('Dwayne Hoven', 1)]...\n",
+      "05:26:25 INFO:keeping 3914 tokens which were in no less than 20 and no more than 1250 (=50.0%) documents\n",
+      "05:26:25 DEBUG:rebuilding dictionary, shrinking gaps\n",
+      "05:26:25 INFO:resulting dictionary: Dictionary(3914 unique tokens: ['chris_patten', 'online', 'loss', 'hub', 'sound']...)\n"
+     ]
     }
+   ],
+   "source": [
+    "traindata_dir = \"/tmp/C50train\"\n",
+    "train_docs, train_author2doc = preprocess_docs(traindata_dir)\n",
+    "train_corpus_50_20, train_dictionary_50_20 = create_corpus_dictionary(train_docs, 0.5, 20)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Number of unique tokens: 3914\n"
+     ]
+    }
+   ],
+   "source": [
+    "print('Number of unique tokens: %d' % len(train_dictionary_50_20))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {
+    "scrolled": false
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "CPU times: user 3 µs, sys: 1e+03 ns, total: 4 µs\n",
+      "Wall time: 15 µs\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "05:28:06 INFO:collecting all words and their counts\n",
+      "05:28:06 INFO:PROGRESS: at sentence #0, processed 0 words and 0 word types\n",
+      "05:28:08 INFO:collected 448895 word types from a corpus of 758070 words (unigram + bigrams) and 2500 sentences\n",
+      "05:28:08 INFO:using 448895 counts as vocab in Phrases<0 vocab, min_count=20, threshold=10.0, max_vocab_size=40000000>\n",
+      "/Users/martin/Projects/bachelor/gensim/gensim/models/phrases.py:490: UserWarning: For a faster implementation, use the gensim.models.phrases.Phraser class\n",
+      "  warnings.warn(\"For a faster implementation, use the gensim.models.phrases.Phraser class\")\n"
+     ]
+    }
+   ],
+   "source": [
+    "testdata_dir = \"/tmp/C50test\"\n",
+    "test_docs, test_author2doc = preprocess_docs(testdata_dir)\n",
+    "test_corpus_50_20 = create_test_corpus(train_dictionary_50_20, test_docs)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "We wrap the model training also in a function, in order to, again, be able to iterate over different parametrizations."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "def train_model(corpus, author2doc, dictionary, num_topics=20, eval_every=0, iterations=50, passes=20):\n",
+    "    from gensim.models import AuthorTopicModel\n",
+    "    \n",
+    "    model = AuthorTopicModel(corpus=corpus, num_topics=num_topics, id2word=dictionary.id2token, \\\n",
+    "                    author2doc=author2doc, chunksize=2500, passes=passes, \\\n",
+    "                    eval_every=eval_every, iterations=iterations, random_state=1)\n",
+    "    top_topics = model.top_topics(corpus)\n",
+    "    tc = sum([t[1] for t in top_topics]) \n",
+    "    print(tc / num_topics)\n",
+    "    return model"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "# NOTE: Author of the logic of this function is the Olavur Mortensen, from his notebook tutorial.\n",
+    "\n",
+    "def predict_author(new_doc, atmodel, top_n=10, smallest_author=1):\n",
+    "    from gensim import matutils\n",
+    "    import pandas as pd\n",
+    "\n",
+    "    def similarity(vec1, vec2):\n",
+    "        '''Get similarity between two vectors'''\n",
+    "        dist = matutils.hellinger(matutils.sparse2full(vec1, atmodel.num_topics), \\\n",
+    "                                  matutils.sparse2full(vec2, atmodel.num_topics))\n",
+    "        sim = 1.0 / (1.0 + dist)\n",
+    "        return sim\n",
+    "\n",
+    "    def get_sims(vec):\n",
+    "        '''Get similarity of vector to all authors.'''\n",
+    "        sims = [similarity(vec, vec2) for vec2 in author_vecs]\n",
+    "        return sims\n",
+    "\n",
+    "    author_vecs = [atmodel.get_author_topics(author) for author in atmodel.id2author.values()]\n",
+    "    new_doc_topics = atmodel.get_new_author_topics(new_doc)\n",
+    "    # Get similarities.\n",
+    "    sims = get_sims(new_doc_topics)\n",
+    "\n",
+    "    # Arrange author names, similarities, and author sizes in a list of tuples.\n",
+    "    table = []\n",
+    "    for elem in enumerate(sims):\n",
+    "        author_name = atmodel.id2author[elem[0]]\n",
+    "        sim = elem[1]\n",
+    "        author_size = len(atmodel.author2doc[author_name])\n",
+    "        if author_size >= smallest_author:\n",
+    "            table.append((author_name, sim, author_size))\n",
+    "\n",
+    "    # Make dataframe and retrieve top authors.\n",
+    "    df = pd.DataFrame(table, columns=['Author', 'Score', 'Size'])\n",
+    "    df = df.sort_values('Score', ascending=False)[:top_n]\n",
+    "\n",
+    "    return df\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "We define a custom function, which measures the prediction accuracy, following the [precision at k](https://en.wikipedia.org/wiki/Information_retrieval#Precision_at_K) principle. We parametrize the accuracy by a parameter k, k=1 meaning we need an exact match in order to be accurate, k=5 meaning our prediction has be in the top 5 results, ordered by similarity."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "def prediction_accuracy(test_author2doc, test_corpus, model, k=5):\n",
+    "\n",
+    "    print(\"Precision@k: top_n={}\".format(k))\n",
+    "    matches=0\n",
+    "    tries = 0\n",
+    "    for author in test_author2doc:\n",
+    "        author_id = model.author2id[author]\n",
+    "        for doc_id in test_author2doc[author]:\n",
+    "            predicted_authors = predict_author(test_corpus[doc_id:doc_id+1], atmodel=model, top_n=k)\n",
+    "            tries = tries+1\n",
+    "            if author_id in predicted_authors[\"Author\"]:\n",
+    "                matches=matches+1\n",
+    "\n",
+    "    accuracy = matches/tries\n",
+    "    print(\"Prediction accuracy: {}\".format(accuracy))\n",
+    "    return accuracy, k"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "def plot_accuracy(scores1, label1, scores2=None, label2=None):\n",
+    "    \n",
+    "    import matplotlib.pyplot as plt\n",
+    "    s = [score*100 for score in scores1.values()]\n",
+    "    t = list(scores1.keys())\n",
+    "\n",
+    "    plt.plot(t, s, \"b-\", label=label1)\n",
+    "    plt.plot(t, s, \"r^\", label=label1+\" data points\")\n",
+    "    \n",
+    "    if scores2 is not None:\n",
+    "        s2 = [score*100 for score in scores2.values()]\n",
+    "        plt.plot(t, s2, label=label2)\n",
+    "        plt.plot(t, s2, \"o\", label=label2+\" data points\")\n",
+    "        \n",
+    "    plt.legend(loc=\"lower right\")\n",
+    "\n",
+    "    plt.xlabel('parameter k')\n",
+    "    plt.ylabel('prediction accuracy')\n",
+    "    plt.title('Precision at k')\n",
+    "    plt.xticks(t)\n",
+    "    plt.grid(True)\n",
+    "    plt.yticks([30,40,50,60,70,80,90,100])\n",
+    "    plt.axis([0, 11, 30, 100])\n",
+    "    plt.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "We calculate the accuracy for a range of values for k=[1,2,3,4,5,6,8,10] and plot how exactly the prediction accuracy naturally rises with higher k."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "05:28:14 INFO:Vocabulary consists of 3914 words.\n",
+      "05:28:14 INFO:using symmetric alpha at 0.05\n",
+      "05:28:14 INFO:using symmetric eta at 0.05\n",
+      "05:28:14 INFO:running online author-topic training, 20 topics, 50 authors, 20 passes over the supplied corpus of 2500 documents, updating model once every 2500 documents, evaluating perplexity every 0 documents, iterating 50x with a convergence threshold of 0.001000\n",
+      "05:28:14 INFO:PROGRESS: pass 0, at document #2500/2500\n",
+      "05:28:14 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "05:28:22 DEBUG:3/2500 documents converged within 50 iterations\n",
+      "05:28:22 DEBUG:updating topics\n",
+      "05:28:22 INFO:topic #11 (0.050): 0.028*\"gm\" + 0.013*\"plant\" + 0.012*\"strike\" + 0.009*\"worker\" + 0.009*\"uaw\" + 0.007*\"automaker\" + 0.007*\"share\" + 0.007*\"union\" + 0.006*\"truck\" + 0.006*\"analyst\"\n",
+      "05:28:22 INFO:topic #17 (0.050): 0.018*\"apple\" + 0.008*\"computer\" + 0.008*\"software\" + 0.008*\"share\" + 0.008*\"analyst\" + 0.007*\"quarter\" + 0.006*\"microsoft\" + 0.006*\"service\" + 0.006*\"base\" + 0.005*\"plan\"\n",
+      "05:28:22 INFO:topic #15 (0.050): 0.009*\"analyst\" + 0.008*\"computer\" + 0.008*\"stock\" + 0.007*\"billion\" + 0.007*\"quarter\" + 0.007*\"share\" + 0.006*\"industry\" + 0.005*\"software\" + 0.005*\"oil\" + 0.005*\"sale\"\n",
+      "05:28:22 INFO:topic #9 (0.050): 0.009*\"analyst\" + 0.006*\"share\" + 0.006*\"china\" + 0.006*\"gold\" + 0.006*\"chinese\" + 0.005*\"price\" + 0.005*\"government\" + 0.005*\"stock\" + 0.004*\"base\" + 0.004*\"drug\"\n",
+      "05:28:22 INFO:topic #14 (0.050): 0.010*\"pound\" + 0.009*\"share\" + 0.008*\"profit\" + 0.007*\"billion\" + 0.007*\"analyst\" + 0.007*\"group\" + 0.007*\"bank\" + 0.006*\"business\" + 0.005*\"million_pound\" + 0.005*\"price\"\n",
+      "05:28:22 INFO:topic diff=2.864277, rho=1.000000\n",
+      "05:28:22 INFO:PROGRESS: pass 1, at document #2500/2500\n",
+      "05:28:22 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "05:28:25 DEBUG:2491/2500 documents converged within 50 iterations\n",
+      "05:28:25 DEBUG:updating topics\n",
+      "05:28:25 INFO:topic #0 (0.050): 0.011*\"bank\" + 0.009*\"analyst\" + 0.005*\"share\" + 0.005*\"billion\" + 0.005*\"government\" + 0.004*\"news\" + 0.004*\"business\" + 0.004*\"rule\" + 0.004*\"profit\" + 0.004*\"group\"\n",
+      "05:28:25 INFO:topic #14 (0.050): 0.011*\"pound\" + 0.010*\"share\" + 0.009*\"profit\" + 0.008*\"group\" + 0.008*\"analyst\" + 0.008*\"billion\" + 0.007*\"bank\" + 0.006*\"business\" + 0.006*\"million_pound\" + 0.005*\"penny\"\n",
+      "05:28:25 INFO:topic #15 (0.050): 0.010*\"analyst\" + 0.009*\"stock\" + 0.008*\"share\" + 0.008*\"billion\" + 0.007*\"quarter\" + 0.007*\"computer\" + 0.006*\"oil\" + 0.006*\"bank\" + 0.005*\"industry\" + 0.005*\"high\"\n",
+      "05:28:25 INFO:topic #1 (0.050): 0.014*\"bank\" + 0.010*\"china\" + 0.009*\"hong_kong\" + 0.009*\"kong\" + 0.008*\"hong\" + 0.008*\"billion\" + 0.007*\"Hong Kong\" + 0.006*\"analyst\" + 0.006*\"stock\" + 0.006*\"fund\"\n",
+      "05:28:25 INFO:topic #7 (0.050): 0.007*\"analyst\" + 0.007*\"sale\" + 0.007*\"share\" + 0.006*\"group\" + 0.005*\"business\" + 0.005*\"price\" + 0.004*\"profit\" + 0.004*\"industry\" + 0.004*\"pound\" + 0.004*\"billion\"\n",
+      "05:28:25 INFO:topic diff=1.147566, rho=0.577350\n",
+      "05:28:25 INFO:PROGRESS: pass 2, at document #2500/2500\n",
+      "05:28:25 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "05:28:27 DEBUG:2498/2500 documents converged within 50 iterations\n",
+      "05:28:27 DEBUG:updating topics\n",
+      "05:28:27 INFO:topic #9 (0.050): 0.011*\"drug\" + 0.009*\"colombia\" + 0.007*\"analyst\" + 0.006*\"government\" + 0.006*\"sale\" + 0.005*\"share\" + 0.005*\"base\" + 0.004*\"price\" + 0.004*\"stock\" + 0.004*\"united\"\n",
+      "05:28:27 INFO:topic #15 (0.050): 0.010*\"stock\" + 0.009*\"analyst\" + 0.008*\"share\" + 0.008*\"billion\" + 0.007*\"bank\" + 0.007*\"oil\" + 0.006*\"quarter\" + 0.006*\"canada\" + 0.006*\"toronto\" + 0.005*\"high\"\n",
+      "05:28:27 INFO:topic #8 (0.050): 0.026*\"bre\" + 0.024*\"gold\" + 0.024*\"bre_x\" + 0.024*\"x\" + 0.018*\"Bre-X\" + 0.015*\"barrick\" + 0.011*\"analyst\" + 0.010*\"busang\" + 0.010*\"indonesian\" + 0.008*\"government\"\n",
+      "05:28:27 INFO:topic #19 (0.050): 0.019*\"hong\" + 0.018*\"kong\" + 0.018*\"hong_kong\" + 0.014*\"china\" + 0.012*\"Hong Kong\" + 0.006*\"chinese\" + 0.005*\"price\" + 0.005*\"british\" + 0.005*\"tell\" + 0.004*\"tung\"\n",
+      "05:28:27 INFO:topic #10 (0.050): 0.009*\"billion\" + 0.008*\"bank\" + 0.005*\"loan\" + 0.005*\"tonne\" + 0.005*\"yen\" + 0.005*\"price\" + 0.005*\"exporter\" + 0.004*\"real_estate\" + 0.004*\"analyst\" + 0.004*\"real\"\n",
+      "05:28:27 INFO:topic diff=1.010061, rho=0.500000\n",
+      "05:28:27 INFO:PROGRESS: pass 3, at document #2500/2500\n",
+      "05:28:27 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "05:28:29 DEBUG:2500/2500 documents converged within 50 iterations\n",
+      "05:28:29 DEBUG:updating topics\n",
+      "05:28:29 INFO:topic #13 (0.050): 0.017*\"china\" + 0.014*\"wang\" + 0.012*\"beijing\" + 0.011*\"taiwan\" + 0.009*\"court\" + 0.009*\"party\" + 0.008*\"chinese\" + 0.008*\"government\" + 0.007*\"official\" + 0.007*\"communist\"\n",
+      "05:28:29 INFO:topic #19 (0.050): 0.022*\"hong\" + 0.021*\"kong\" + 0.021*\"hong_kong\" + 0.015*\"china\" + 0.014*\"Hong Kong\" + 0.006*\"chinese\" + 0.005*\"airbus\" + 0.005*\"tung\" + 0.005*\"british\" + 0.005*\"Hong Kong's\"\n",
+      "05:28:29 INFO:topic #12 (0.050): 0.012*\"czech\" + 0.007*\"bank\" + 0.007*\"crown\" + 0.006*\"government\" + 0.006*\"klaus\" + 0.005*\"billion\" + 0.005*\"price\" + 0.005*\"party\" + 0.005*\"prague\" + 0.005*\"foreign\"\n",
+      "05:28:29 INFO:topic #17 (0.050): 0.041*\"apple\" + 0.026*\"computer\" + 0.022*\"software\" + 0.020*\"quarter\" + 0.013*\"microsoft\" + 0.013*\"analyst\" + 0.010*\"share\" + 0.009*\"sale\" + 0.009*\"macintosh\" + 0.008*\"pc\"\n",
+      "05:28:29 INFO:topic #6 (0.050): 0.020*\"share\" + 0.017*\"analyst\" + 0.010*\"bank\" + 0.010*\"shanghai\" + 0.009*\"stock\" + 0.007*\"sale\" + 0.007*\"b\" + 0.006*\"quarter\" + 0.006*\"base\" + 0.005*\"business\"\n",
+      "05:28:29 INFO:topic diff=0.877566, rho=0.447214\n",
+      "05:28:29 INFO:PROGRESS: pass 4, at document #2500/2500\n",
+      "05:28:29 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "05:28:31 DEBUG:2500/2500 documents converged within 50 iterations\n",
+      "05:28:31 DEBUG:updating topics\n",
+      "05:28:31 INFO:topic #14 (0.050): 0.012*\"pound\" + 0.010*\"profit\" + 0.010*\"share\" + 0.009*\"group\" + 0.008*\"analyst\" + 0.008*\"billion\" + 0.007*\"business\" + 0.007*\"bank\" + 0.006*\"million_pound\" + 0.005*\"british\"\n",
+      "05:28:31 INFO:topic #9 (0.050): 0.014*\"drug\" + 0.011*\"colombia\" + 0.006*\"government\" + 0.005*\"analyst\" + 0.005*\"sale\" + 0.005*\"united\" + 0.005*\"colombian\" + 0.004*\"guerrilla\" + 0.004*\"base\" + 0.004*\"force\"\n",
+      "05:28:31 INFO:topic #13 (0.050): 0.018*\"china\" + 0.015*\"wang\" + 0.013*\"beijing\" + 0.012*\"taiwan\" + 0.009*\"court\" + 0.009*\"party\" + 0.009*\"chinese\" + 0.008*\"government\" + 0.007*\"communist\" + 0.007*\"official\"\n",
+      "05:28:31 INFO:topic #2 (0.050): 0.010*\"share\" + 0.009*\"analyst\" + 0.008*\"service\" + 0.007*\"billion\" + 0.007*\"deal\" + 0.006*\"offer\" + 0.006*\"stock\" + 0.006*\"corp\" + 0.006*\"industry\" + 0.005*\"business\"\n",
+      "05:28:31 INFO:topic #15 (0.050): 0.010*\"stock\" + 0.009*\"analyst\" + 0.008*\"billion\" + 0.008*\"share\" + 0.008*\"bank\" + 0.007*\"oil\" + 0.007*\"canada\" + 0.007*\"toronto\" + 0.006*\"russia\" + 0.005*\"high\"\n",
+      "05:28:31 INFO:topic diff=0.761073, rho=0.408248\n",
+      "05:28:31 INFO:PROGRESS: pass 5, at document #2500/2500\n",
+      "05:28:31 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "05:28:33 DEBUG:2500/2500 documents converged within 50 iterations\n",
+      "05:28:33 DEBUG:updating topics\n",
+      "05:28:33 INFO:topic #15 (0.050): 0.010*\"stock\" + 0.009*\"analyst\" + 0.009*\"bank\" + 0.008*\"billion\" + 0.008*\"share\" + 0.007*\"oil\" + 0.007*\"canada\" + 0.007*\"toronto\" + 0.006*\"russia\" + 0.006*\"tonne\"\n",
+      "05:28:33 INFO:topic #2 (0.050): 0.011*\"share\" + 0.009*\"analyst\" + 0.008*\"service\" + 0.007*\"billion\" + 0.007*\"deal\" + 0.006*\"offer\" + 0.006*\"stock\" + 0.006*\"corp\" + 0.006*\"industry\" + 0.005*\"business\"\n",
+      "05:28:33 INFO:topic #13 (0.050): 0.018*\"china\" + 0.015*\"wang\" + 0.013*\"beijing\" + 0.012*\"taiwan\" + 0.009*\"court\" + 0.009*\"chinese\" + 0.009*\"party\" + 0.008*\"government\" + 0.007*\"communist\" + 0.007*\"official\"\n",
+      "05:28:33 INFO:topic #8 (0.050): 0.027*\"gold\" + 0.026*\"bre\" + 0.026*\"bre_x\" + 0.026*\"x\" + 0.019*\"Bre-X\" + 0.015*\"barrick\" + 0.012*\"analyst\" + 0.011*\"busang\" + 0.010*\"indonesian\" + 0.009*\"government\"\n",
+      "05:28:33 INFO:topic #1 (0.050): 0.017*\"bank\" + 0.010*\"fund\" + 0.010*\"china\" + 0.009*\"billion\" + 0.008*\"hong_kong\" + 0.008*\"kong\" + 0.008*\"hong\" + 0.007*\"financial\" + 0.007*\"japan\" + 0.006*\"Hong Kong\"\n",
+      "05:28:33 INFO:topic diff=0.658823, rho=0.377964\n",
+      "05:28:33 INFO:PROGRESS: pass 6, at document #2500/2500\n",
+      "05:28:33 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "05:28:35 DEBUG:2500/2500 documents converged within 50 iterations\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "05:28:35 DEBUG:updating topics\n",
+      "05:28:35 INFO:topic #17 (0.050): 0.038*\"apple\" + 0.027*\"computer\" + 0.022*\"software\" + 0.021*\"quarter\" + 0.014*\"analyst\" + 0.013*\"microsoft\" + 0.010*\"sale\" + 0.010*\"share\" + 0.008*\"pc\" + 0.008*\"macintosh\"\n",
+      "05:28:35 INFO:topic #9 (0.050): 0.015*\"drug\" + 0.012*\"colombia\" + 0.006*\"government\" + 0.005*\"united\" + 0.005*\"sale\" + 0.005*\"colombian\" + 0.005*\"guerrilla\" + 0.005*\"analyst\" + 0.004*\"force\" + 0.004*\"week\"\n",
+      "05:28:35 INFO:topic #15 (0.050): 0.010*\"stock\" + 0.009*\"bank\" + 0.009*\"analyst\" + 0.008*\"billion\" + 0.008*\"share\" + 0.007*\"oil\" + 0.007*\"canada\" + 0.007*\"toronto\" + 0.006*\"russia\" + 0.006*\"tonne\"\n",
+      "05:28:35 INFO:topic #13 (0.050): 0.018*\"china\" + 0.015*\"wang\" + 0.014*\"beijing\" + 0.012*\"taiwan\" + 0.009*\"court\" + 0.009*\"chinese\" + 0.009*\"party\" + 0.008*\"government\" + 0.007*\"communist\" + 0.007*\"official\"\n",
+      "05:28:35 INFO:topic #16 (0.050): 0.016*\"franc\" + 0.015*\"french\" + 0.015*\"air\" + 0.014*\"france\" + 0.011*\"thomson\" + 0.010*\"billion\" + 0.009*\"group\" + 0.007*\"government\" + 0.007*\"plan\" + 0.007*\"bid\"\n",
+      "05:28:35 INFO:topic diff=0.568497, rho=0.353553\n",
+      "05:28:35 INFO:PROGRESS: pass 7, at document #2500/2500\n",
+      "05:28:35 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "05:28:36 DEBUG:2500/2500 documents converged within 50 iterations\n",
+      "05:28:36 DEBUG:updating topics\n",
+      "05:28:37 INFO:topic #17 (0.050): 0.037*\"apple\" + 0.027*\"computer\" + 0.022*\"software\" + 0.021*\"quarter\" + 0.014*\"analyst\" + 0.013*\"microsoft\" + 0.010*\"sale\" + 0.010*\"share\" + 0.008*\"pc\" + 0.008*\"macintosh\"\n",
+      "05:28:37 INFO:topic #2 (0.050): 0.011*\"share\" + 0.010*\"analyst\" + 0.007*\"service\" + 0.007*\"billion\" + 0.007*\"deal\" + 0.006*\"offer\" + 0.006*\"stock\" + 0.006*\"corp\" + 0.006*\"industry\" + 0.005*\"business\"\n",
+      "05:28:37 INFO:topic #3 (0.050): 0.027*\"bt\" + 0.017*\"telecom\" + 0.015*\"mci\" + 0.013*\"pound\" + 0.011*\"billion\" + 0.011*\"analyst\" + 0.011*\"deal\" + 0.010*\"british\" + 0.010*\"share\" + 0.010*\"group\"\n",
+      "05:28:37 INFO:topic #13 (0.050): 0.018*\"china\" + 0.016*\"wang\" + 0.014*\"beijing\" + 0.012*\"taiwan\" + 0.009*\"court\" + 0.009*\"chinese\" + 0.009*\"party\" + 0.008*\"government\" + 0.007*\"communist\" + 0.007*\"official\"\n",
+      "05:28:37 INFO:topic #4 (0.050): 0.018*\"china\" + 0.011*\"official\" + 0.009*\"state\" + 0.008*\"beijing\" + 0.008*\"tibet\" + 0.007*\"chinese\" + 0.007*\"government\" + 0.007*\"wang\" + 0.006*\"people\" + 0.005*\"dissident\"\n",
+      "05:28:37 INFO:topic diff=0.488932, rho=0.333333\n",
+      "05:28:37 INFO:PROGRESS: pass 8, at document #2500/2500\n",
+      "05:28:37 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "05:28:38 DEBUG:2500/2500 documents converged within 50 iterations\n",
+      "05:28:38 DEBUG:updating topics\n",
+      "05:28:38 INFO:topic #17 (0.050): 0.037*\"apple\" + 0.027*\"computer\" + 0.022*\"software\" + 0.021*\"quarter\" + 0.014*\"analyst\" + 0.013*\"microsoft\" + 0.010*\"sale\" + 0.010*\"share\" + 0.008*\"pc\" + 0.008*\"macintosh\"\n",
+      "05:28:38 INFO:topic #5 (0.050): 0.032*\"china\" + 0.016*\"chinese\" + 0.013*\"beijing\" + 0.012*\"official\" + 0.009*\"tonne\" + 0.007*\"hong\" + 0.007*\"hong_kong\" + 0.007*\"kong\" + 0.007*\"trade\" + 0.006*\"state\"\n",
+      "05:28:38 INFO:topic #13 (0.050): 0.018*\"china\" + 0.016*\"wang\" + 0.014*\"beijing\" + 0.012*\"taiwan\" + 0.009*\"chinese\" + 0.009*\"court\" + 0.009*\"party\" + 0.008*\"government\" + 0.007*\"communist\" + 0.007*\"official\"\n",
+      "05:28:38 INFO:topic #14 (0.050): 0.012*\"pound\" + 0.011*\"profit\" + 0.010*\"share\" + 0.009*\"analyst\" + 0.009*\"group\" + 0.008*\"billion\" + 0.007*\"bank\" + 0.007*\"business\" + 0.006*\"million_pound\" + 0.005*\"british\"\n",
+      "05:28:38 INFO:topic #6 (0.050): 0.019*\"share\" + 0.016*\"analyst\" + 0.012*\"shanghai\" + 0.011*\"bank\" + 0.009*\"stock\" + 0.007*\"b\" + 0.007*\"sale\" + 0.006*\"exchange\" + 0.006*\"base\" + 0.006*\"quarter\"\n",
+      "05:28:38 INFO:topic diff=0.419457, rho=0.316228\n",
+      "05:28:38 INFO:PROGRESS: pass 9, at document #2500/2500\n",
+      "05:28:38 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "05:28:40 DEBUG:2500/2500 documents converged within 50 iterations\n",
+      "05:28:40 DEBUG:updating topics\n",
+      "05:28:40 INFO:topic #3 (0.050): 0.027*\"bt\" + 0.017*\"telecom\" + 0.015*\"mci\" + 0.013*\"pound\" + 0.011*\"billion\" + 0.011*\"analyst\" + 0.011*\"deal\" + 0.010*\"british\" + 0.010*\"share\" + 0.010*\"group\"\n",
+      "05:28:40 INFO:topic #1 (0.050): 0.018*\"bank\" + 0.011*\"fund\" + 0.009*\"billion\" + 0.008*\"china\" + 0.008*\"financial\" + 0.007*\"japan\" + 0.007*\"kong\" + 0.007*\"hong_kong\" + 0.007*\"hong\" + 0.006*\"analyst\"\n",
+      "05:28:40 INFO:topic #15 (0.050): 0.010*\"bank\" + 0.009*\"stock\" + 0.008*\"analyst\" + 0.008*\"billion\" + 0.008*\"share\" + 0.008*\"oil\" + 0.007*\"canada\" + 0.007*\"toronto\" + 0.006*\"tonne\" + 0.006*\"russia\"\n",
+      "05:28:40 INFO:topic #19 (0.050): 0.029*\"hong\" + 0.028*\"kong\" + 0.028*\"hong_kong\" + 0.019*\"Hong Kong\" + 0.019*\"china\" + 0.008*\"chinese\" + 0.007*\"tung\" + 0.007*\"Hong Kong's\" + 0.006*\"beijing\" + 0.006*\"airbus\"\n",
+      "05:28:40 INFO:topic #8 (0.050): 0.028*\"gold\" + 0.026*\"bre\" + 0.026*\"bre_x\" + 0.026*\"x\" + 0.019*\"Bre-X\" + 0.015*\"barrick\" + 0.012*\"analyst\" + 0.011*\"busang\" + 0.010*\"indonesian\" + 0.009*\"government\"\n",
+      "05:28:40 INFO:topic diff=0.359320, rho=0.301511\n",
+      "05:28:40 INFO:PROGRESS: pass 10, at document #2500/2500\n",
+      "05:28:40 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "05:28:41 DEBUG:2500/2500 documents converged within 50 iterations\n",
+      "05:28:41 DEBUG:updating topics\n",
+      "05:28:41 INFO:topic #6 (0.050): 0.019*\"share\" + 0.016*\"analyst\" + 0.013*\"shanghai\" + 0.011*\"bank\" + 0.009*\"stock\" + 0.008*\"b\" + 0.007*\"sale\" + 0.007*\"exchange\" + 0.006*\"china\" + 0.006*\"base\"\n",
+      "05:28:41 INFO:topic #11 (0.050): 0.042*\"gm\" + 0.028*\"plant\" + 0.016*\"uaw\" + 0.016*\"strike\" + 0.015*\"worker\" + 0.011*\"automaker\" + 0.010*\"local\" + 0.010*\"truck\" + 0.009*\"part\" + 0.008*\"ford\"\n",
+      "05:28:41 INFO:topic #2 (0.050): 0.011*\"share\" + 0.010*\"analyst\" + 0.007*\"service\" + 0.007*\"billion\" + 0.007*\"deal\" + 0.006*\"offer\" + 0.006*\"stock\" + 0.006*\"corp\" + 0.006*\"industry\" + 0.005*\"business\"\n",
+      "05:28:41 INFO:topic #1 (0.050): 0.019*\"bank\" + 0.011*\"fund\" + 0.009*\"billion\" + 0.008*\"financial\" + 0.008*\"china\" + 0.008*\"japan\" + 0.007*\"kong\" + 0.007*\"hong_kong\" + 0.007*\"hong\" + 0.006*\"analyst\"\n",
+      "05:28:41 INFO:topic #12 (0.050): 0.014*\"czech\" + 0.008*\"crown\" + 0.008*\"bank\" + 0.007*\"klaus\" + 0.007*\"government\" + 0.006*\"billion\" + 0.006*\"prague\" + 0.005*\"price\" + 0.005*\"foreign\" + 0.005*\"party\"\n",
+      "05:28:41 INFO:topic diff=0.307661, rho=0.288675\n",
+      "05:28:41 INFO:PROGRESS: pass 11, at document #2500/2500\n",
+      "05:28:41 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "05:28:43 DEBUG:2500/2500 documents converged within 50 iterations\n",
+      "05:28:43 DEBUG:updating topics\n",
+      "05:28:43 INFO:topic #15 (0.050): 0.011*\"bank\" + 0.009*\"stock\" + 0.008*\"billion\" + 0.008*\"analyst\" + 0.008*\"share\" + 0.008*\"oil\" + 0.007*\"canada\" + 0.007*\"toronto\" + 0.006*\"russia\" + 0.006*\"tonne\"\n",
+      "05:28:43 INFO:topic #2 (0.050): 0.011*\"share\" + 0.010*\"analyst\" + 0.007*\"service\" + 0.007*\"billion\" + 0.007*\"deal\" + 0.006*\"offer\" + 0.006*\"stock\" + 0.006*\"corp\" + 0.006*\"industry\" + 0.005*\"business\"\n",
+      "05:28:43 INFO:topic #5 (0.050): 0.032*\"china\" + 0.016*\"chinese\" + 0.013*\"beijing\" + 0.012*\"official\" + 0.009*\"tonne\" + 0.007*\"hong\" + 0.007*\"hong_kong\" + 0.007*\"kong\" + 0.007*\"trade\" + 0.006*\"state\"\n",
+      "05:28:43 INFO:topic #7 (0.050): 0.009*\"sale\" + 0.009*\"analyst\" + 0.007*\"share\" + 0.007*\"group\" + 0.006*\"profit\" + 0.006*\"business\" + 0.005*\"pound\" + 0.005*\"price\" + 0.005*\"billion\" + 0.005*\"executive\"\n",
+      "05:28:43 INFO:topic #19 (0.050): 0.029*\"hong\" + 0.029*\"kong\" + 0.029*\"hong_kong\" + 0.019*\"Hong Kong\" + 0.019*\"china\" + 0.008*\"chinese\" + 0.008*\"tung\" + 0.007*\"Hong Kong's\" + 0.006*\"beijing\" + 0.006*\"airbus\"\n",
+      "05:28:43 INFO:topic diff=0.263525, rho=0.277350\n",
+      "05:28:43 INFO:PROGRESS: pass 12, at document #2500/2500\n",
+      "05:28:43 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "05:28:44 DEBUG:2500/2500 documents converged within 50 iterations\n",
+      "05:28:44 DEBUG:updating topics\n",
+      "05:28:45 INFO:topic #11 (0.050): 0.042*\"gm\" + 0.028*\"plant\" + 0.016*\"uaw\" + 0.016*\"strike\" + 0.015*\"worker\" + 0.011*\"automaker\" + 0.010*\"local\" + 0.010*\"truck\" + 0.009*\"part\" + 0.008*\"ford\"\n",
+      "05:28:45 INFO:topic #13 (0.050): 0.018*\"china\" + 0.016*\"wang\" + 0.014*\"beijing\" + 0.012*\"taiwan\" + 0.009*\"chinese\" + 0.009*\"court\" + 0.008*\"party\" + 0.008*\"government\" + 0.007*\"official\" + 0.007*\"communist\"\n",
+      "05:28:45 INFO:topic #4 (0.050): 0.021*\"china\" + 0.012*\"official\" + 0.010*\"beijing\" + 0.009*\"chinese\" + 0.009*\"wang\" + 0.008*\"tibet\" + 0.007*\"state\" + 0.007*\"government\" + 0.006*\"people\" + 0.006*\"dissident\"\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "05:28:45 INFO:topic #16 (0.050): 0.020*\"franc\" + 0.018*\"french\" + 0.017*\"air\" + 0.017*\"france\" + 0.014*\"thomson\" + 0.012*\"billion\" + 0.010*\"group\" + 0.008*\"billion_franc\" + 0.008*\"telecom\" + 0.007*\"plan\"\n",
+      "05:28:45 INFO:topic #18 (0.050): 0.014*\"analyst\" + 0.011*\"computer\" + 0.010*\"quarter\" + 0.010*\"internet\" + 0.008*\"share\" + 0.008*\"business\" + 0.008*\"service\" + 0.008*\"stock\" + 0.007*\"industry\" + 0.007*\"software\"\n",
+      "05:28:45 INFO:topic diff=0.226015, rho=0.267261\n",
+      "05:28:45 INFO:PROGRESS: pass 13, at document #2500/2500\n",
+      "05:28:45 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "05:28:46 DEBUG:2500/2500 documents converged within 50 iterations\n",
+      "05:28:46 DEBUG:updating topics\n",
+      "05:28:46 INFO:topic #4 (0.050): 0.021*\"china\" + 0.012*\"official\" + 0.010*\"beijing\" + 0.009*\"wang\" + 0.009*\"chinese\" + 0.008*\"tibet\" + 0.007*\"state\" + 0.007*\"government\" + 0.006*\"people\" + 0.006*\"dissident\"\n",
+      "05:28:46 INFO:topic #3 (0.050): 0.027*\"bt\" + 0.017*\"telecom\" + 0.015*\"mci\" + 0.013*\"pound\" + 0.011*\"billion\" + 0.011*\"analyst\" + 0.011*\"deal\" + 0.010*\"british\" + 0.010*\"share\" + 0.010*\"group\"\n",
+      "05:28:46 INFO:topic #12 (0.050): 0.015*\"czech\" + 0.009*\"crown\" + 0.008*\"bank\" + 0.007*\"klaus\" + 0.007*\"government\" + 0.006*\"prague\" + 0.006*\"billion\" + 0.005*\"foreign\" + 0.005*\"party\" + 0.005*\"price\"\n",
+      "05:28:46 INFO:topic #19 (0.050): 0.030*\"hong\" + 0.030*\"kong\" + 0.030*\"hong_kong\" + 0.020*\"Hong Kong\" + 0.020*\"china\" + 0.008*\"chinese\" + 0.008*\"tung\" + 0.007*\"Hong Kong's\" + 0.007*\"beijing\" + 0.006*\"airbus\"\n",
+      "05:28:46 INFO:topic #5 (0.050): 0.032*\"china\" + 0.016*\"chinese\" + 0.013*\"beijing\" + 0.012*\"official\" + 0.010*\"tonne\" + 0.007*\"hong\" + 0.007*\"kong\" + 0.007*\"hong_kong\" + 0.007*\"trade\" + 0.006*\"state\"\n",
+      "05:28:46 INFO:topic diff=0.194260, rho=0.258199\n",
+      "05:28:46 INFO:PROGRESS: pass 14, at document #2500/2500\n",
+      "05:28:46 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "05:28:48 DEBUG:2500/2500 documents converged within 50 iterations\n",
+      "05:28:48 DEBUG:updating topics\n",
+      "05:28:48 INFO:topic #5 (0.050): 0.033*\"china\" + 0.016*\"chinese\" + 0.013*\"beijing\" + 0.012*\"official\" + 0.010*\"tonne\" + 0.008*\"hong\" + 0.007*\"kong\" + 0.007*\"hong_kong\" + 0.007*\"trade\" + 0.007*\"state\"\n",
+      "05:28:48 INFO:topic #13 (0.050): 0.018*\"china\" + 0.016*\"wang\" + 0.014*\"beijing\" + 0.012*\"taiwan\" + 0.009*\"chinese\" + 0.009*\"court\" + 0.008*\"party\" + 0.008*\"government\" + 0.007*\"official\" + 0.007*\"communist\"\n",
+      "05:28:48 INFO:topic #2 (0.050): 0.011*\"share\" + 0.010*\"analyst\" + 0.007*\"service\" + 0.007*\"billion\" + 0.007*\"deal\" + 0.006*\"offer\" + 0.006*\"stock\" + 0.006*\"corp\" + 0.006*\"industry\" + 0.006*\"business\"\n",
+      "05:28:48 INFO:topic #0 (0.050): 0.011*\"bank\" + 0.009*\"internet\" + 0.009*\"fcc\" + 0.008*\"service\" + 0.008*\"phone\" + 0.007*\"rule\" + 0.006*\"local\" + 0.006*\"tv\" + 0.006*\"court\" + 0.006*\"law\"\n",
+      "05:28:48 INFO:topic #16 (0.050): 0.020*\"franc\" + 0.019*\"french\" + 0.018*\"air\" + 0.017*\"france\" + 0.014*\"thomson\" + 0.013*\"billion\" + 0.010*\"group\" + 0.008*\"billion_franc\" + 0.008*\"telecom\" + 0.007*\"plan\"\n",
+      "05:28:48 INFO:topic diff=0.167433, rho=0.250000\n",
+      "05:28:48 INFO:PROGRESS: pass 15, at document #2500/2500\n",
+      "05:28:48 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "05:28:49 DEBUG:2500/2500 documents converged within 50 iterations\n",
+      "05:28:49 DEBUG:updating topics\n",
+      "05:28:49 INFO:topic #3 (0.050): 0.027*\"bt\" + 0.017*\"telecom\" + 0.015*\"mci\" + 0.013*\"pound\" + 0.011*\"analyst\" + 0.011*\"billion\" + 0.011*\"deal\" + 0.010*\"british\" + 0.010*\"share\" + 0.010*\"group\"\n",
+      "05:28:49 INFO:topic #10 (0.050): 0.001*\"billion\" + 0.000*\"bank\" + 0.000*\"loan\" + 0.000*\"tonne\" + 0.000*\"yen\" + 0.000*\"price\" + 0.000*\"exporter\" + 0.000*\"real_estate\" + 0.000*\"analyst\" + 0.000*\"real\"\n",
+      "05:28:49 INFO:topic #5 (0.050): 0.033*\"china\" + 0.017*\"chinese\" + 0.013*\"beijing\" + 0.012*\"official\" + 0.010*\"tonne\" + 0.008*\"hong\" + 0.008*\"kong\" + 0.007*\"hong_kong\" + 0.007*\"trade\" + 0.007*\"state\"\n",
+      "05:28:49 INFO:topic #4 (0.050): 0.021*\"china\" + 0.012*\"official\" + 0.011*\"beijing\" + 0.009*\"wang\" + 0.009*\"chinese\" + 0.008*\"tibet\" + 0.007*\"state\" + 0.007*\"government\" + 0.006*\"people\" + 0.006*\"dissident\"\n",
+      "05:28:49 INFO:topic #0 (0.050): 0.010*\"bank\" + 0.009*\"internet\" + 0.009*\"fcc\" + 0.008*\"service\" + 0.008*\"phone\" + 0.007*\"rule\" + 0.007*\"local\" + 0.007*\"tv\" + 0.006*\"court\" + 0.006*\"law\"\n",
+      "05:28:49 INFO:topic diff=0.144777, rho=0.242536\n",
+      "05:28:49 INFO:PROGRESS: pass 16, at document #2500/2500\n",
+      "05:28:49 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "05:28:51 DEBUG:2500/2500 documents converged within 50 iterations\n",
+      "05:28:51 DEBUG:updating topics\n",
+      "05:28:51 INFO:topic #2 (0.050): 0.011*\"share\" + 0.010*\"analyst\" + 0.007*\"service\" + 0.007*\"billion\" + 0.007*\"deal\" + 0.006*\"offer\" + 0.006*\"stock\" + 0.006*\"corp\" + 0.006*\"industry\" + 0.006*\"business\"\n",
+      "05:28:51 INFO:topic #9 (0.050): 0.016*\"drug\" + 0.013*\"colombia\" + 0.006*\"government\" + 0.006*\"united\" + 0.005*\"colombian\" + 0.005*\"guerrilla\" + 0.005*\"force\" + 0.004*\"oil\" + 0.004*\"country\" + 0.004*\"police\"\n",
+      "05:28:51 INFO:topic #7 (0.050): 0.009*\"sale\" + 0.008*\"analyst\" + 0.007*\"share\" + 0.007*\"group\" + 0.007*\"profit\" + 0.006*\"business\" + 0.005*\"pound\" + 0.005*\"price\" + 0.005*\"billion\" + 0.005*\"executive\"\n",
+      "05:28:51 INFO:topic #4 (0.050): 0.021*\"china\" + 0.012*\"official\" + 0.011*\"beijing\" + 0.009*\"wang\" + 0.009*\"chinese\" + 0.008*\"tibet\" + 0.007*\"state\" + 0.007*\"government\" + 0.006*\"people\" + 0.006*\"dissident\"\n",
+      "05:28:51 INFO:topic #13 (0.050): 0.018*\"china\" + 0.016*\"wang\" + 0.014*\"beijing\" + 0.012*\"taiwan\" + 0.009*\"chinese\" + 0.009*\"court\" + 0.008*\"party\" + 0.008*\"government\" + 0.007*\"official\" + 0.007*\"communist\"\n",
+      "05:28:51 INFO:topic diff=0.125646, rho=0.235702\n",
+      "05:28:51 INFO:PROGRESS: pass 17, at document #2500/2500\n",
+      "05:28:51 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "05:28:52 DEBUG:2500/2500 documents converged within 50 iterations\n",
+      "05:28:52 DEBUG:updating topics\n",
+      "05:28:52 INFO:topic #6 (0.050): 0.019*\"share\" + 0.016*\"analyst\" + 0.013*\"shanghai\" + 0.012*\"bank\" + 0.009*\"stock\" + 0.008*\"china\" + 0.007*\"b\" + 0.007*\"sale\" + 0.007*\"exchange\" + 0.006*\"base\"\n",
+      "05:28:52 INFO:topic #14 (0.050): 0.011*\"pound\" + 0.011*\"profit\" + 0.010*\"share\" + 0.009*\"analyst\" + 0.009*\"group\" + 0.008*\"billion\" + 0.007*\"bank\" + 0.007*\"business\" + 0.006*\"million_pound\" + 0.005*\"british\"\n",
+      "05:28:52 INFO:topic #17 (0.050): 0.036*\"apple\" + 0.026*\"computer\" + 0.021*\"software\" + 0.021*\"quarter\" + 0.014*\"analyst\" + 0.013*\"microsoft\" + 0.010*\"sale\" + 0.010*\"share\" + 0.008*\"pc\" + 0.008*\"technology\"\n",
+      "05:28:52 INFO:topic #7 (0.050): 0.009*\"sale\" + 0.008*\"analyst\" + 0.007*\"share\" + 0.007*\"group\" + 0.007*\"profit\" + 0.006*\"business\" + 0.005*\"pound\" + 0.005*\"price\" + 0.005*\"billion\" + 0.005*\"executive\"\n",
+      "05:28:52 INFO:topic #8 (0.050): 0.028*\"gold\" + 0.026*\"bre\" + 0.026*\"bre_x\" + 0.026*\"x\" + 0.019*\"Bre-X\" + 0.016*\"barrick\" + 0.012*\"analyst\" + 0.011*\"busang\" + 0.010*\"indonesian\" + 0.009*\"government\"\n",
+      "05:28:52 INFO:topic diff=0.109484, rho=0.229416\n",
+      "05:28:52 INFO:PROGRESS: pass 18, at document #2500/2500\n",
+      "05:28:52 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "05:28:54 DEBUG:2500/2500 documents converged within 50 iterations\n",
+      "05:28:54 DEBUG:updating topics\n",
+      "05:28:54 INFO:topic #2 (0.050): 0.011*\"share\" + 0.010*\"analyst\" + 0.007*\"service\" + 0.007*\"billion\" + 0.007*\"deal\" + 0.006*\"offer\" + 0.006*\"stock\" + 0.006*\"corp\" + 0.006*\"industry\" + 0.006*\"business\"\n",
+      "05:28:54 INFO:topic #15 (0.050): 0.012*\"bank\" + 0.009*\"stock\" + 0.008*\"billion\" + 0.008*\"analyst\" + 0.008*\"oil\" + 0.007*\"canada\" + 0.007*\"share\" + 0.007*\"toronto\" + 0.007*\"russia\" + 0.006*\"tonne\"\n",
+      "05:28:54 INFO:topic #0 (0.050): 0.010*\"bank\" + 0.009*\"internet\" + 0.009*\"fcc\" + 0.009*\"service\" + 0.008*\"phone\" + 0.007*\"rule\" + 0.007*\"local\" + 0.007*\"tv\" + 0.007*\"court\" + 0.006*\"law\"\n",
+      "05:28:54 INFO:topic #7 (0.050): 0.009*\"sale\" + 0.008*\"analyst\" + 0.007*\"share\" + 0.007*\"group\" + 0.007*\"profit\" + 0.006*\"business\" + 0.005*\"pound\" + 0.005*\"price\" + 0.005*\"billion\" + 0.005*\"executive\"\n",
+      "05:28:54 INFO:topic #18 (0.050): 0.014*\"analyst\" + 0.011*\"computer\" + 0.010*\"quarter\" + 0.010*\"internet\" + 0.008*\"share\" + 0.008*\"business\" + 0.008*\"stock\" + 0.008*\"service\" + 0.007*\"industry\" + 0.007*\"software\"\n",
+      "05:28:54 INFO:topic diff=0.095805, rho=0.223607\n",
+      "05:28:54 INFO:PROGRESS: pass 19, at document #2500/2500\n",
+      "05:28:54 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "05:28:55 DEBUG:2500/2500 documents converged within 50 iterations\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "05:28:55 DEBUG:updating topics\n",
+      "05:28:55 INFO:topic #7 (0.050): 0.009*\"sale\" + 0.008*\"analyst\" + 0.007*\"share\" + 0.007*\"group\" + 0.007*\"profit\" + 0.006*\"business\" + 0.005*\"pound\" + 0.005*\"price\" + 0.005*\"billion\" + 0.005*\"executive\"\n",
+      "05:28:55 INFO:topic #4 (0.050): 0.022*\"china\" + 0.012*\"official\" + 0.011*\"beijing\" + 0.010*\"wang\" + 0.009*\"chinese\" + 0.008*\"tibet\" + 0.007*\"state\" + 0.007*\"government\" + 0.007*\"people\" + 0.006*\"dissident\"\n",
+      "05:28:55 INFO:topic #19 (0.050): 0.032*\"hong\" + 0.031*\"kong\" + 0.031*\"hong_kong\" + 0.021*\"Hong Kong\" + 0.021*\"china\" + 0.009*\"chinese\" + 0.008*\"tung\" + 0.008*\"Hong Kong's\" + 0.007*\"beijing\" + 0.007*\"airbus\"\n",
+      "05:28:55 INFO:topic #3 (0.050): 0.027*\"bt\" + 0.018*\"telecom\" + 0.015*\"mci\" + 0.013*\"pound\" + 0.011*\"deal\" + 0.011*\"analyst\" + 0.011*\"billion\" + 0.011*\"british\" + 0.010*\"share\" + 0.010*\"group\"\n",
+      "05:28:55 INFO:topic #8 (0.050): 0.028*\"gold\" + 0.026*\"bre\" + 0.026*\"bre_x\" + 0.026*\"x\" + 0.019*\"Bre-X\" + 0.016*\"barrick\" + 0.012*\"analyst\" + 0.011*\"busang\" + 0.010*\"indonesian\" + 0.009*\"government\"\n",
+      "05:28:55 INFO:topic diff=0.084200, rho=0.218218\n",
+      "05:28:55 DEBUG:Setting topics to those of the model: AuthorTopicModel(num_terms=3914, num_topics=20, num_authors=50, decay=0.5, chunksize=2500)\n",
+      "05:28:55 INFO:CorpusAccumulator accumulated stats from 1000 documents\n",
+      "05:28:55 INFO:CorpusAccumulator accumulated stats from 2000 documents\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "-1.50354141347\n"
+     ]
+    }
+   ],
+   "source": [
+    "atmodel_standard = train_model(train_corpus_50_20, train_author2doc, train_dictionary_50_20)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "We run our first training and observe that the **passes** and **iterations** parameters are set high enough, so that the model converges.\n",
+    "\n",
+    "07:47:24 INFO:PROGRESS: pass 15, at document #2500/2500\n",
+    "\n",
+    "07:47:24 DEBUG:performing inference on a chunk of 2500 documents \n",
+    "\n",
+    "07:47:27 DEBUG:2500/2500 documents converged within 50 iterations \n",
+    "\n",
+    "Tells us that the model indeed conveges well."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Precision@k: top_n=1\n",
+      "Prediction accuracy: 0.3548\n",
+      "Precision@k: top_n=2\n",
+      "Prediction accuracy: 0.5228\n",
+      "Precision@k: top_n=3\n",
+      "Prediction accuracy: 0.6456\n",
+      "Precision@k: top_n=4\n",
+      "Prediction accuracy: 0.7208\n",
+      "Precision@k: top_n=5\n",
+      "Prediction accuracy: 0.7748\n",
+      "Precision@k: top_n=6\n",
+      "Prediction accuracy: 0.8188\n",
+      "Precision@k: top_n=8\n",
+      "Prediction accuracy: 0.8576\n",
+      "Precision@k: top_n=10\n",
+      "Prediction accuracy: 0.8936\n"
+     ]
+    },
+    {
+     "data": {
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYgAAAEWCAYAAAB8LwAVAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDIuMS4yLCBo\ndHRwOi8vbWF0cGxvdGxpYi5vcmcvNQv5yAAAIABJREFUeJzt3Xl8VOX1x/HPYTMoCIIaQVBoRUU0\nBIJWtCoB7U+RChV/LlVEq+JeLLUuv1ZBo1baKipaV0RcQakWi1sLDbYogiwiyF4VRUOBCAgIBpLz\n++PehCFMkknIzM3yfb9e85q5N3fmOTfGOTz3uc95zN0REREprUHUAYiISM2kBCEiInEpQYiISFxK\nECIiEpcShIiIxKUEISIicSlBiFTAzD4xs14VHHOImW02s4YpCithZva5mZ0adRxS+yhBSK0VfvFt\nDb+Y/2tmz5hZs+pux927uPu0Co75wt2buXthdbdfHjMbYWbPp7JNqT+UIKS2+6m7NwO6Az2A35U+\nwAL6WxepJP1PI3WCu38FvAUcDWBm08zsbjN7D/gO+IGZtTCzMWaWZ2ZfmdldsZeEzOwKM1tsZpvM\nbJGZdQ/3l1yiMbPjzGy2mX0b9lruD/d3MDM3s0bhdlsze93MvjGzFWZ2RUw7I8zsZTN7NmzrEzPr\nUda5mdmDZvZl2OYcMzsp3H868H/AeWEvan5Fvycz62xmn5nZBZX9HUv9owQhdYKZtQf6AvNidg8C\nhgDNgZXAM8AO4DCgG/AT4PLw/f8LjAAuBvYFzgLy4zT1IPCgu+8L/BB4uYyQxgOrgLbAOcA9ZtY7\n5udnhce0BF4HHi7n9D4EMoFWwIvAK2aW5u5vA/cAE8LLW13L+QzChPcOcL27v1TesSKgBCG131/N\nbAMwHXiX4Auz2DPu/om77yD4cu0L3ODuW9x9DTAKOD889nLgD+7+oQdWuPvKOO1tBw4zs/3dfbO7\nf1D6gDBZnQjc7O7b3P0j4CmC5FNsuru/GY5ZPAeU+eXu7s+7e76773D3+4C9gCMS+eXEOIkgEV3s\n7pMr+V6pp5QgpLYb4O4t3f1Qd7/G3bfG/OzLmNeHAo2BPDPbECaVx4EDw5+3B/6TQHuXAYcDS8zs\nQzPrF+eYtsA37r4pZt9K4OCY7dUxr78D0oovT5VmZjeGl742hnG3APZPINZYVwHvVzTYLhJLCULq\nsthSxV8C3wP7hwmlpbvv6+5dYn7+wwo/0H25u19AkFhGAhPNbJ9Sh30NtDKz5jH7DgG+quwJhOMN\nNwHnAvu5e0tgI2DFISX4UVcBh5jZqMrGIPWXEoTUC+6eB/wduM/M9jWzBmb2QzM7JTzkKeBGM8sK\n73o6zMwOLf05ZnaRmR3g7kXAhnB3Uam2vgTeB35vZmlmlkHQ86jK7ajNCcZN1gKNzOx2gjGSYv8F\nOiRwl9Ym4HTgZDO7twpxSD2kBCH1ycVAE2ARsB6YCLQBcPdXgLsJBoE3AX8lGLco7XTgEzPbTDBg\nfX6py1rFLgA6EPQmXgOGu/uUKsT8DvA2sIzgMtU2dr109kr4nG9mc8v7IHffAJwGnGFmOVWIReoZ\n04JBIiISj3oQIiISV9IShJk9bWZrzGxhzL5WZvYPM1sePu8X7jczeyicUPRx8QQlERGJTjJ7EM8Q\nXK+NdQsw1d07AVPDbYAzgE7hYwjwaBLjEhGRBCQtQbj7v4BvSu3uD4wLX48DBsTsfzacoPQB0NLM\n2iQrNhERqVjciTlJlB7ebgjBRKH08PXB7HpnxqpwXx6lmNkQgl4GTZs2zWrfvn3yoi1HUVERDRqk\nfginvrUbZdv18ZyjVN/OOcrzXbZs2Tp3P6DCA909aQ+C2/wWxmxvKPXz9eHzZODHMfunAj0q+vys\nrCyPSm5urtqt423Xx3OOUn075yjPF5jtCXyHpzp9/bf40lH4vCbc/xVBqYNi7ajCrFMREak+qU4Q\nrwODw9eDgUkx+y8O72Y6HtjoOy9FiYhIBJI2BmFmLwG9gP3NbBUwHLgXeNnMLiOYFXpuePibBJU2\nVxAULrs0WXGJiEhikpYgPChoFk+fOMc6cG2yYhERkcqrP7cMiIhIpShBiIhIXEoQIiISlxKEiIjE\npQQhIiJxKUGIiEhcShAiIhKXEoSIiMSlBCEiInEpQYiISFxKECIiEpcShIiIxKUEISIicSlBiIhI\nXEoQIiISlxKEiIjEpQQhIiJxKUGIiEhcShAiIhKXEoSIiMSlBCEiInEpQYiISFyRJAgzG2pmC83s\nEzO7IdzXysz+YWbLw+f9oohNREQCKU8QZnY0cAVwHNAV6GdmhwG3AFPdvRMwNdwWEZGIRNGD6AzM\ndPfv3H0H8C5wNtAfGBceMw4YEEFsIiLJl5dH5tChsHp11JGUy9w9tQ2adQYmAT2BrQS9hdnAIHdv\nGR5jwPri7VLvHwIMAUhPT88aP358qkLfxebNm2nWrJnarcNt18dzjlJ9OudOo0bR9m9/4+uzzmL5\nDTekvP3s7Ow57t6jwgPdPeUP4DJgDvAv4FHgAWBDqWPWV/Q5WVlZHpXc3Fy1W8fbro/nHKX6cs7f\nf/61F+6V5g5e1LSpe15eymMAZnsC39WRDFK7+xh3z3L3k4H1wDLgv2bWBiB8XhNFbCIi1WXtWpgy\nBe67Dy6+GLp2hac75lDwfREAvqMQcnIijrJsjaJo1MwOdPc1ZnYIwfjD8UBHYDBwb/g8KYrYREQq\na8cOWLYM5s/f9ZGXt/OYtm2h1xF5XNZwLI13FADQYHsBjB0Lt90GBx0UUfRliyRBAH8xs9bAduBa\nd99gZvcCL5vZZcBK4NyIYhMRKdOGDfDxx7smgoULYdu24OeNG0PnznDqqZCZGfQaMjLggAOAa3Lg\nvaJdP7Aw7EU88kjKz6UikSQIdz8pzr58oE8E4YiI7KaoCD79dPdewcqVO4/Zf/8gAVxzTfDctWuQ\nHJo0KeNDZ8yAgoJd9xUUwPvvJ+089kRUPQgRkRpj82ZYsGDXRLBgQbAfoEEDOOII6NkTrrpqZzJo\n0wbMKtHQvHklL6dNm0avXr2q9TyqmxKEiNQb7vDFF7v3Cv7zn+BnAC1aBF/+l166MxF06QJNm0Yb\nexSUIESkTtq6FT75ZNdE8PHHwRhCscMOCxJA8R1GXbvCIYdUsldQhylBiEit5h7cLVS6V7B0aTCO\nALDPPnDMMXDeeUESyMwMtuvJvLwqU4IQkVqjoAAWL949Gaxbt/OYQw4JksDAgTt7BT/8YTCOIJWj\nBCEi0SuuTfTOOyXzAdau3T0RLF4M27cHb9lrLzj6aDjrrJ2JICMD9lMd6GqjBCEikSoshI3Dcmi5\nYAEz+uZwZ/oju00ya9MmSABnnLEzGRx+ODTSN1hS6dcrIimzYwcsWQJz5gSPuXMhb24eC7eOpQFO\n13lj+b7zbZx66kEliaBr13CSmaScEoSIJMX27bBoUZAEihPC/PnB3UUAe+8dDBY/88McmiwugkJo\n2qSQf2bXzFnF9ZEShIjssYKC4JbS2J7B/Pnw/ffBz5s1g27d4MoroXt3yMoKJp41XJMHPxgLhcHs\nYiuo2bWJ6hslCBGplO+/D2YZFyeCOXOC7eIKEvvuGySBa68NEkFWFnTqVMZdRDk5O+9FLVaDaxPV\nN0oQIlKmrVt3JoPix8KFwVgCQMuWQTIYOjRIBN27V/KW0lpWm6i+UYIQEQC++y64LBTbM/jkk+Af\n9ACtWgVJ4MYbd14m6thxD2cd17LaRPWNEoRIPbR5M3z00a4DyIsX77zac8ABQQLo12/nZSKVoKh/\nlCBE6rhNm4J/qMf2DJYs2VmcLj09SABnn73zMlG7dkoGogQhUqds3BgkgdiewfLlO5NB27ZBEjjv\nvJ2Xidq2jTZmqbmUIERqqfXrd00Ec+fCihU7f96+fZAALrpoZ89Ad45KZShBiNQ0ceoS5efveolo\nzhz47LOdb+nQIUgAl14aJINu3eDAA6MJX+oOJQiRGmbbb3PYd8ECZvfP4Z6DH2Hu3F2XufzBD6BH\nj52Tzrp3h9ato4tX6i4lCJEaYu5cGHNXHn96LahLdNSssazueBs9ex5UMumsWzdVK5XUUYIQiVBR\nEbz5Jtx3H0ybBk82zqFxw511id4/QzOKJTpaQkMkAlu3whNPwFFHwU9/GqyJ/OjteVzWcCyNStcl\nWr064milvookQZjZr8zsEzNbaGYvmVmamXU0s5lmtsLMJphZkyhiE0mmNWtg+PBg0tmVVwZF7F58\nMUgQV63NwcqqSyQSgZQnCDM7GPgl0MPdjwYaAucDI4FR7n4YsB64LNWxiSTL4sVwxRVBYrjzTujZ\nM7ik9OGHcMEF0LgxqkskNU6FCcLMjklCu42ApmbWCNgbyAN6AxPDn48DBiShXZGUcYd//hPOPDO4\nlPT883DJJcEs5tdfh1NOKTVbed684E3uTMvNLXkdW69IJJXMi6dYlnWA2b+BvYBngBfcfeMeN2o2\nFLgb2Ar8HRgKfBD2HjCz9sBbYQ+j9HuHAEMA0tPTs8aPH7+n4VTJ5s2badasmdqtw21Xtd0dO4zc\n3AN55ZV2LF/enJYtCxgw4Cv69/+ali23J7Xt2qy+nXOU55udnT3H3XtUeKC7V/gAOgG/B1YALwKn\nJfK+Mj5rP+CfwAFAY+CvwEXAiphj2gMLK/qsrKwsj0pubq7areNtV7bd9evdR450P/jg4J/+nTu7\nP/mk+9atyW+7Lqhv5xzl+QKzPYHv64Ruc3X35Wb2O2A28BDQzcwM+D93f7USiQvgVOAzd18LYGav\nAicCLc2skbvvANoBX1Xyc0Ui8dln8OCDMGZMUCW1d+/gDqXTT6/EuggiNVAiYxAZZjYKWEwwTvBT\nd+8cvh5VhTa/AI43s73DJNMHWATkAueExwwGJlXhs0VSZuZMOPdcOOywYKrCgAHBZLepU6FvXyUH\nqf0S6UGMBp4i6C1sLd7p7l+HvYpKcfeZZjYRmAvsAOYBTwBvAOPN7K5w35jKfrZIshUWBgPM990H\n770HLVoEC+hcf31QIlukLkkkQZwJbHX3QgAzawCkuft37v5cVRp19+HA8FK7PwWOq8rniVS7UgXz\ntmyBZ56BUaOCOQsdOsADD8AvfgHNm0cdrEhyJNIJngI0jdneO9wnUnfl5NBiwQK23JLDb38blM6+\n7jrYf394+eVgjYWhQ5UcpG5LpAeR5u6bizfcfbOZ7Z3EmESilZdH0dNjaeCOjRvL09xGr58dxK9/\nDSecoJXWpP5IpAexxcy6F2+YWRbB/AWROmfNGvjXaTkUfB+UvGjcoJDFF+bw6qtw4olKDlK/JJIg\nbgBeMbN/m9l0YAJwXXLDEkmt776De+6BE3+Qx7GfjCWNoORF46ICWr6qgnlSP1V4icndPzSzI4Ej\nwl1L3T2x6aAiNVxhITz3HPzud/DVV/Bmhxz2KiiC7aUOylHZbal/Er1T+wjgKKA7cIGZXZy8kERS\n4+9/37lMZ9u28O67cEbLGTTYroJ5IpDYRLnhBHMhRgPZwB+As5Icl0jSfPwx/M//BI9Nm+Cll+CD\nD+Dkk1HBPJEYifQgziGY7bza3S8FugItkhqVSBKsWhX0FjIzgzLb990XlOE+/3zNehaJJ5HbXLe6\ne5GZ7TCzfYE1BMX0RGqFb7+FkSODSW6FhTBsGPz2t1rbWaQiiSSI2WbWEngSmANsBmYkNSqRarB9\ne1A07447YO3aYGGeu++Gjh2jjkykdig3QYTF9H7v7huAx8zsbWBfd/84JdGJVIE7TJoEN98My5YF\nC/P88Y9w7LFRRyZSu5R75TWsG/5mzPbnSg5Sk82cGQw2/+xnwbjC669Dbq6Sg0hVJDI0N9fM9L+X\n1GiffgrnnQfHHx/USXrsMViwAH76U81+FqmqRMYgfgRcaGYrgS2AEXQuMpIamUgC8vPhrruCOWyN\nG8Ntt8FvfqMieiLVIZEE8T9Jj0KkkrZtg9Gjg0HnTZuC21fvvDOY8CYi1SORBOFJj0IkQUVFwcS2\n3/4WVq6EM86AP/wBjj466shE6p5EEsQbBEnCgDSgI7AU6JLEuEQCMQv35C4+iN/8BubMCSa7jRkD\nffpEHaBI3ZVIsb5jYrfD0t/XJC0ikVjhwj1vHJ9Dv5WP0L49PPssXHihZj+LJFul/xdz97kEA9ci\nSbX10zwKnhiLudN75VhG/3Y1S5fCoEFKDiKpUGEPwsyGxWw2IKjo+nXSIhIBVqyAOT/KoX9hsHBP\nWpNCrlufA01VclskVRL5d1jzmMdeBGMS/ZMZlNRvr70GfbvlcdY3OxfusYICGKuFe0RSKZExiDtS\nEYjI9u1w661BldVXDsgh7Xst3CMSpUTWg/hHWKyveHs/M3unqg2a2RFm9lHM41szu8HMWoVtLQ+f\nVWuzHvn6a+jdO0gO114LZ7eZgWnhHpFIJXKJ6YCwWB8A7r4eOLCqDbr7UnfPdPdMIAv4DngNuAWY\n6u6dgKnhttQD//wndOsWrMnzwgvw8MPQYL4W7hGJWiIJotDMDineMLNDqb7Jc32A/7j7SoJxjXHh\n/nHAgGpqQ2qooiK45x447TRo3RpmzYKf/zzqqESkWCIT5X4LTDezdwkmy50EDKmm9s8HXgpfp7t7\nXvh6NZBeTW1IDfTNN3DxxfDGG8GKbk8+Cc2aRR2ViMSyoKJ3BQeZ7Q8cH25+4O7r9rhhsyYEt8t2\ncff/mtkGd48d61jv7ruNQ5jZEMIElZ6enjV+/Pg9DaVKNm/eTLMIvtHqQrtLlzZn+PAu5Oc34Zpr\nVjBgwNflVlytC+dcm9qOSn075yjPNzs7e46796jwQHcv9wH8DGgRs90SGFDR+xL43P7A32O2lwJt\nwtdtgKUVfUZWVpZHJTc3V+1WUlGR+6OPujdp4n7IIe4zZ6au7aqIqt2o245KfTvnKM8XmO0JfE8n\nMgYx3N03xiSUDcDwSiSrslzAzstLAK8Dg8PXg4FJ1dCG1BBbtgQzoK++OqifNHcuHHdc1FGJSHkS\nSRDxjklk7KJMZrYPcBrwaszue4HTzGw5cGq4LXXAkiVBMnjxxWAaw+TJwaC0iNRsiXzRzzaz+4Hi\n2UnXAnP2pFF33wK0LrUvn+CuJqlDJkyAyy+HtDT4+9/h1FOjjkhEEpVID+J6oACYED6+J0gSImUq\nKIBf/jK4QykjI5i+oOQgUrskUmpjC5q0JpXwxRdw7rkwcyb86lcwcmSwHKiI1C6JVHM9ALiJYIGg\ntOL97t47iXFJLfXOO8FaDQUF8MorcM45UUckIlWVyCWmF4AlBCvJ3QF8DnyYxJikFioshBEjgiVA\n27aF2bOVHERqu0QSRGt3HwNsd/d33f0XgHoPUmLtWujbF+64I7iV9YMP4PDDo45KRPZUIncxFRdc\nzjOzMwlmP7dKXkhSm8yYEYw3rF0LTzwR3LFU3qxoEak9EkkQd5lZC+DXwGhgX+BXSY1Kajx3GD0a\nfv1raN8+qMLdvXvUUYlIdUrkLqbJ4cuNQHZyw5HaYNOmoKfw8stw1lnwzDOwn1bvEKlztPS7VCwv\nj8yhQ2H1ahYuhGOPhYkTg9tXX3tNyUGkrtqjkhlST+Tk0GLBApZelMOPZjxC8+bBIj+nnBJ1YCKS\nTOpBSPny8vCxYzF32k8dy08yVjNvnpKDSH2QyES5vYCBQIfY4939zuSFJTWF35nDjoIiGgNNGhby\nl8wcGrR5pML3iUjtl0gPYhLB2g07gC0xD6nr8vIoHDOWxkUFADQqLKDBuLGwenXEgYlIKiQyBtHO\n3U9PeiRS43x9dQ6tthft+kdSWBjU7H5EvQiRui6RHsT7ZnZM0iORGmXVKsifPIM0Cnb9QUFBMOlB\nROq8RBLEj4E5ZrbUzD42swVm9nGyA5PobNsGAwfCCU3nsXiRgzvTcnOD2XHuQe1uEanzErnEdEbS\no5Aawx2uvRZmzYJXX4XOnaOOSESiUmEPwt1XAi2Bn4aPluE+qYMefxyefhp+9zv42c+ijkZEolRh\ngjCzoQQlvw8MH8+b2fXJDkxS7733glXg+vYNSneLSP2WyCWmy4AfhSvLYWYjgRkEhfukjvj662D9\nhkMPhRdegIYNo45IRKKWSIIwoDBmuzDcJ3XE998Hg9KbNsGUKdCyZdQRiUhNkEiCGAvMNLPXwu0B\nwJjkhSSp9stfBov8TJwIXbpEHY2I1BSJDFLfD1wKfBM+LnX3B/akUTNraWYTzWyJmS02s55m1srM\n/mFmy8Nn1QhNgSeeCB633hr0IkREipWZIMxs3/C5FcE61M+Hj5Xhvj3xIPC2ux8JdAUWA7cAU929\nEzA13JYkmjEDrrsOTj89mBwtIhKrvEtMLwL9gDmAx+y3cPsHVWkwXJ3uZOASAHcvAArMrD/QKzxs\nHDANuLkqbUjF8vKCHkP79vDiixqUFpHdlZkg3L1f+NyxmtvsCKwFxppZV4IENBRId/e88JjVQHo1\ntyuhgoLgjqVvv4V33tGCPyISn7l7+QeYTXX3PhXtS7hBsx7AB8CJ7j7TzB4EvgWud/eWMcetd/fd\nvrrMbAgwBCA9PT1r/PjxVQljj23evJlmzZrVynZHjerE668fzPDhn9Cr19qUtVtVtfl3XRvbjkp9\nO+cozzc7O3uOu/eo8EB3j/sA0oBWwHxgv/B1K4J1IZaU9b6KHsBBwOcx2ycBbwBLgTbhvjbA0oo+\nKysry6OSm5tbK9t96qmgoNLNN6e23T1RW3/XtbXtqNS3c47yfIHZnsD3dXl3MV1JcPnnyPC5+DEJ\neLhS6WrXhLQa+NLMjgh39QEWAa8Dg8N9g8N2pBrNnAnXXAM/+QncfXfU0YhITVfeGMSDwINmdr27\nV/es6euBF8ysCfApwW20DYCXzewyYCVwbjW3Wa+tXh0MSh98MLz0kgalRaRiiUyUKzKzlu6+ASCc\nn3CBu/+5qo26+0dAvOtfVRrXkPIVFMD//i+sXx/c2tpqT29SFpF6IZH1IK4oTg4A7r4euCJ5IUl1\nGzYMpk+HMWMgIyPqaESktkgkQTQ0s5LaS2bWEGiSvJCkOo0dG6wOeuONcP75UUcjIrVJIpeY3gYm\nmNnj4faV4T6p4T78EK6+Gk49FX7/+6ijEZHaJpEEcTNBUrg63P4H8FTSIpJqsWYNnH02tGkD48dD\no0T+S4uIxKjwa8Pdi4BHw4fUAtu3B4PS+fnw/vvQunXUEYlIbVRmgjCzl939XDNbwK61mABwdw13\n1lA33gj/+lew8E9mZtTRiEhtVV4PYmj43C8VgUj1ePZZeOih4M6ln/886mhEpDYrb6JcXvi8MnXh\nyJ6YMweuvBJ694aRI6OORkRqu/IuMW0izqWlYu6+b1IikipZuzYYlD7wQA1Ki0j1KK8H0RzAzHKA\nPOA5grUgLiQopic1xI4dcO65wZ1L770HBxwQdUQiUhck8u/Ms9y9a8z2o2Y2H7g9STFJJd10E0yb\nFow/dO8edTQiUlckMpN6i5ldaGYNzayBmV0IbEl2YJKYF16AUaNg6FAYNCjqaESkLkkkQfycoLLq\nf8PH/4b7JGLz5sHll8Mpp8Af/xh1NCJS1yQyUe5zoH/yQ5HKWLcOfvazYLzh5ZehceOoIxKRuqbC\nHoSZHW5mU81sYbidYWa/S35oUpYdO4LCe6tXw6uvBncuiYhUt0QuMT0J3ApsB3D3jwHVBY3QrbfC\n1Knw2GPQo+JVZUVEqiSRu5j2dvdZMRW/AXYkKR4pT14ehw7+Dc998Teuu+4gLrkk6oBEpC5LpAex\nzsx+SDhpzszOIZgXISm2bmgOh3wxl0fb5HD//VFHIyJ1XSIJ4lrgceBIM/sKuAG4KqlRyW4KVubR\nbOJYGlLEgPVjaZy/OuqQRKSOKzdBmFkDoIe7nwocABzp7j9WfabU++SCHPAiAKyoEHJyIo5IROq6\nchNEuBbETeHrLe6+KSVRyS7WzM/jyBljSaMg2FFQEKwlulq9CBFJnkQuMU0xsxvNrL2ZtSp+JD0y\nKbHwvByMol13FqoXISLJlchdTOeFz9fG7HPgB9UfjpQ2axbst3TGzt5DsYKCYLk4EZEkSWQmdcfq\nbtTMPgc2AYXADnfvEfZKJgAdgM+Bc919fXW3XZsUFcEvfwkrD5rHsmXQvDlMmzaNXr16RR2aiNQD\nicykTjOzYWb2qpn9xcxuMLO0amg7290z3b14qtctwFR37wRMDbfrteefh5kzg8V/mjePOhoRqW8S\nGYN4FugCjAYeDl8/l4RY+gPjwtfjgAFJaKPW2LQJbr4ZfvQjuOiiqKMRkfrI3MtcNC44wGyRux9V\n0b5KNWr2GbCeYCzjcXd/wsw2uHvL8OcGrC/eLvXeIcAQgPT09Kzx48dXNYw9snnzZpo1a5a0z3/8\n8R8wfvwhPProHI48cufNY8lutyxRtRtl2/XxnKNU3845yvPNzs6eE3P1pmzuXu4DeB44Pmb7R8Cz\nFb2vgs88OHw+EJgPnAxsKHXM+oo+Jysry6OSm5ubtM9etsy9cWP3Sy9NbbvliardKNuuj+ccpfp2\nzlGeLzDbE/iuTuQupizgfTP7Itw+BFhqZguC/OIZieetkqT0Vfi8xsxeA44D/mtmbdw9z8zaAGsq\n+7l1xa9+BWlpcM89UUciIvVZIgni9Ops0Mz2ARq4+6bw9U+AO4HXgcHAveHzpOpst7Z46y14441g\nAaCDDoo6GhGpzxK5zbW6y2qkA6+F1WEbAS+6+9tm9iHwspldBqwkWMWuXikogBtugMMPD25vFRGJ\nUiI9iGrl7p8CXePszwf6pDqemuShh2DZMnjzTWjSJOpoRKS+S+Q2V0mB1avhzjvhzDPhjDOijkZE\nRAmixvi//4Nt22DUqKgjEREJKEHUALNmBcVZf/Ur6NQp6mhERAJKEBErrrd00EHwu99FHY2IyE4p\nH6SWXRXXW3rmGdVbEpGaRT2ICMXWWxo0KOpoRER2pR5EhO66K7h7adIkaKBULSI1jL6WIrJ8eXDH\n0iWXwHHHRR2NiMjulCAiUlxv6fe/jzoSEZH4dIkpAqq3JCK1gXoQKaZ6SyJSW6gHkWKjRwf1lt54\nQ/WWRKRmUw8ihVavhjvuCOot9e0bdTQiIuVTgkgh1VsSkdpECSJFiust3XCD6i2JSO2gBJECqrck\nIrWRBqlTILbe0r77Rh2NiEiXl59wAAATGElEQVRi1INIsuJ6S8cdp3pLIlK7qAeRZKq3JNVp+/bt\nrFq1im3btkUdSrVr0aIFixcvjjqMlEnF+aalpdGuXTsaN25cpfcrQSSR6i1JdVu1ahXNmzenQ4cO\nmFnU4VSrTZs20bwe1bxP9vm6O/n5+axatYqOHTtW6TP0b9okGjZM9Zakem3bto3WrVvXueQg1c/M\naN269R71NtWDSJK33oLJk+EPf1C9JaleSg6SqD39W4msB2FmDc1snplNDrc7mtlMM1thZhPMrNYW\nooittzR0aNTRiIhUTZSXmIYCsSM0I4FR7n4YsB64LJKoqkFxvaVRo1RvSeqWL7/8kuzsbI466ii6\ndOnCgw8+WPKzb775htNOO41OnTpx2mmnsX79+t3e/9FHH/Hmm29Wuf2vv/6ac845p8rvl8qJJEGY\nWTvgTOCpcNuA3sDE8JBxwIAoYttTxfWW+vZVvSWpexo1asR9993HokWL+OCDD3jkkUdYtGgRAPfe\ney99+vRh+fLl9OnTh3vvvXe39+9pgmjbti0TJ06s+ECpFubuqW/UbCLwe6A5cCNwCfBB2HvAzNoD\nb7n70XHeOwQYApCenp41fvz4VIW9i82bN9OsWbPd9o8ceQRTpqTz9NMf0r791pS1m2xRtRtl2zXx\nnFu0aMFhhx0GwM0378WCBdX7b7xjjili5MjvEz7+/PPPZ8iQIfTu3Zvu3bvz5ptvctBBB7F69Wr6\n9u3L3LlzS44tKCggMzOTrVu30rZtW4YNG0Z2djbXXnstn3/+OU2bNuWhhx7i6KOP5p577uGzzz7j\n008/JT8/nxtuuIFLLrmElStXcu655zJz5kwKCwu5/fbbmTJlCg0aNGDw4MFcddVVDB8+nDfffJNG\njRrRu3dv7r777mr9HVWXwsJCGjZsmPR2VqxYwcaNG3fZl52dPcfde1T03pQPUptZP2CNu88xs16V\nfb+7PwE8AdCjRw/v1avSH1Etpk2bRum2Z82Ct9+G3/wGBg36UcraTYWo2o2y7Zp4zosXLy65NbJJ\nE6ju75cmTaB588Sui37++ecsWLCA7Oxsmjdvztq1a+kUFhpr1qwZa9eu3e02zpycHGbPns3DDz8M\nwPXXX8+xxx7L5MmTmTx5MldffTUfffQRe+21F4sXL+aDDz5gy5YtdOvWjYEDB9KsWTMaNGhA8+bN\nefTRR/n666/5+OOPadSoEd988w0FBQW88cYbLFmyBDNjw4YNNfbW2VTd1puWlka3bt2q9N4o7mI6\nETjLzPoCacC+wINASzNr5O47gHbAVxHEVmXF9ZbS01VvSVLjgQeia3vz5s0MHDiQBx54gH3j1I8x\ns4TuoJk+fTp/+ctfADjllFPIz8/n22+/BaB///40bdqUpk2bkp2dzaxZs8jMzCx575QpU7jqqqto\n1Cj4GmvVqhU7duwgLS2Nyy67jH79+tGvX7/qON16K+VjEO5+q7u3c/cOwPnAP939QiAXKB59GgxM\nSnVse6K43tK996rektRt27dvZ+DAgVx44YWcffbZJfvT09PJy8sDIC8vjwMPPHCP2imdYBJJOI0a\nNWLWrFmcc845TJ48mdNPP32PYqjvatJEuZuBYWa2AmgNjIk4noTF1lu6+OKooxFJHnfnsssuo3Pn\nzgwbNmyXn5111lmMGzcOgHHjxtG/f//d3t+8eXM2bdpUsn3SSSfxwgsvAPDvf/+b/fffv6RHMmnS\nJLZt20Z+fj7Tpk3j2GOP3eWzTjvtNB5//HF27NgBBHdRbd68mY0bN9K3b19GjRrF/Pnzq+/k66FI\nJ8q5+zRgWvj6U6BWFqQorrf017+q3pLUbe+99x7PPfccxxxzTMnlnnvuuYe+fftyyy23cO655zJm\nzBgOPfRQXn755d3en52dzb333ktmZia33norI0aM4Be/+AUZGRnstddeJQkGICMjg+zsbNatW8dt\nt91G27Zt+fzzz0t+fvnll7Ns2TIyMjJo3LgxV1xxBQMHDqR///5s27YNd+f+++9P+u+kLtNM6j1U\nXG9p8GD4UXLGpUVqjB//+MeUdedj69atmTp1arnvb9WqFR9++OEu+/76178Cuw/aZmRk8Oyzz+5y\nbIcOHVi4cCEQXE66//77d0sCs2bNSuxkpEL69+4eUr0lEamr1IPYA7H1ltq0iToakbpjxIgRUYcg\nqAdRZdu3W8n60qq3JCJ1kXoQVfTaawezbFnQg1C9JRGpi9SDqII18/O44PFfcGGf1Zx5ZtTRiIgk\nhxJEFSw8L4cTit7j4fScqEMREUkaJYhKmvdmHj2XjqUhRbR8bWwwAUKkJsvLg1NOqZa/1bpY7rtD\nhw6sW7eu3GPuueeeam0znscee2y323pL29PfX2UpQVRSpwk5NGpQFGwUFkKOehFSw+XkwPTp1fK3\nWl/LfaciQVx11VVcXEEpBiWImiwvj2Yvj6VxUUGwXVAAY9WLkBosLy/4Gy0qqpa/1TZt2tC9e3cg\nKJvRuXNnvvoqqKs5adIkBg8eDMDgwYNLJsAVKygo4Pbbb2fChAlkZmYyYcIEvvnmGwYMGEBGRga9\ne/fm448/BoLbXAcNGkTPnj3p1KkTTz75JBBUkD366GAVgMLCQm688UaOPvpoMjIyGD16NAC33HIL\nRx11FBkZGdx44427nUN+fj4/+clP6NKlC5dffvkuE/8GDBhAVlYWXbp04Yknnij5vK1bt5KZmcmF\nF15Y5nGldejQgZtuuoljjjmG4447jhUrVpScQ+/evenZsyd9+vThiy++KDnnP/3pTwD06tWLm2++\nmeOOO47DDz+cf//733F/f++++y6ZmZlkZmbSrVu3XcqYVAt3r7WPrKwsT6mrr3Zv0sQddj6aNHG/\n5pqUhZCbm5uytmpCu1G2XRPPedGiRZX7oNi/2Wr+W/3ss8+8ffv2vnHjRnd3b9GiRcnPioqKdtku\nNnbsWL/22mtLtq+77jofMWKEu7v/7W9/865du7q7+/Dhwz0jI8O/++47X7t2rbdr186/+uor/+yz\nz7xLly7u7v7nP//ZBw4c6Nu3b3d39/z8fF+3bp0ffvjhXlRU5O7u69ev3y2G66+/3u+44w53d588\nebIDvnbt2pLPcHf/7rvvvEuXLr5u3Tp3d99nn312+Yyyjot16KGH+l133eXu7uPGjfMzzzzT3d37\n9evnzzzzjH/77bc+ZswY79+/f8k5//GPf3R391NOOcWHDRvm7u5vvPGG9+nTJ+7vr1+/fj59+nR3\nd9+0aVPJ7yJWvL8ZYLYn8B2rHkRlzJgR9BpiFRTA++9HE49IeYp7DwXV3+OtznLfgwYNAsou973/\n/vuXlPuONWXKFK688spdyn23aNGipNz3q6++yt57771bm//617+46KKLADjzzDPZb7/9Sn720EMP\n0bVrV44//ni+/PJLli9fHjfuRI+74IILSp5nzJgBwIwZM/j5z38OwKBBg5g+fXrc9xZXys3Kytql\nBlWsE088kWHDhvHQQw+xYcOGkt9FdVGCqIx580r6DtNyc3f2I+bNizoykd3l5ASXlmJVw7hZXS33\nPW3aNKZMmcKMGTOYP38+3bp1Y9u2bVU+rnTMicQfa6+99gKgYcOGJRVrS7vlllt46qmn2Lp1Kyee\neCJLliypVBsVUYIQqauS0OP1OlDu++STT+bFF18E4K233iq522rjxo3st99+7L333ixZsoQPPvig\n5D2NGzdm+/btFR5X2oQJE0qee/bsCcAJJ5xA8VLJL7zwAieddFKZ7y+t9O/vP//5D8cccww333wz\nxx57bLUnCM2kFqmrktCzrQvlvocPH84FF1xAly5dOOGEEzjkkEMAOP3003nsscfo3LkzRxxxBMcf\nf3zJe4YMGUJGRgbdu3fn6aefLvO40tavX19ybi+99BIAo0eP5tJLL2XkyJGkp6czduzYhH//pX9/\n06dPJzc3lwYNGtClSxfOOOOMhD8rIYkMVNTUR8oHqWPUt4HTmjhgW1fbLa/tSg9S1yLffvttyevY\nAdva6tBDDy0Z/I4n9nyTSYPUIiJS7XSJSURqnLpQ7rusO49qE/UgRGoZL2NFN5HS9vRvRQlCpBZJ\nS0sjPz9fSUIq5O7k5+eTlpZW5c/QJSaRWqRdu3asWrWKtWvXRh1Ktdu2bdsefZnVNqk437S0NNq1\na1fl9ytBiNQijRs3pmPHjlGHkRTTpk2jW7duUYeRMrXhfFN+icnM0sxslpnNN7NPzOyOcH9HM5tp\nZivMbIKZaZ02EZEIRTEG8T3Q2927ApnA6WZ2PDASGOXuhwHrgcsiiE1EREIpTxDhPI3N4Wbj8OFA\nb6C40Ps4YECqYxMRkZ0iGYMws4bAHOAw4BHgP8AGdy+uSLUKOLiM9w4BhoSbm81saZLDLcv+QPnL\nUKnd2t52fTznKNW3c47yfA9N5KBIEoS7FwKZZtYSeA04shLvfQKIv0JHCpnZbHfvoXbrbtv18Zyj\nVN/OuTacb6TzINx9A5AL9ARamllxwmoHfBVZYCIiEsldTAeEPQfMrClwGrCYIFEUr0Y+GJiU6thE\nRGSnKC4xtQHGheMQDYCX3X2ymS0CxpvZXcA8YEwEsVVGVJe56lu7UbZdH885SvXtnGv8+Zqm7IuI\nSDyqxSQiInEpQYiISFxKEJVgZk+b2RozWxhB2+3NLNfMFoUlSoamqN24pVFSxcwamtk8M5uc4nY/\nN7MFZvaRmc1OYbstzWyimS0xs8Vm1jNVbUfFzH4V/m0tNLOXzKzOVeyL991hZq3M7B9mtjx83i/K\nGONRgqicZ4DTI2p7B/Brdz8KOB641syOSkG7ZZVGSZWhBHe5RSHb3TNTfK/6g8Db7n4k0JXozj0l\nzOxg4JdAD3c/GmgInB9tVEnxDLt/d9wCTHX3TsDUcLtGUYKoBHf/F/BNRG3nufvc8PUmgi+OuLPN\nq7ndskqjJJ2ZtQPOBJ5KRXtRM7MWwMmEd/C5e0E4V6iuawQ0DedB7Q18HXE81a6M747+BGWFoIaW\nF1KCqIXMrAPQDZiZovYamtlHwBrgH+6eknaBB4CbgKIUtRfLgb+b2ZywvEsqdATWAmPDy2pPmdk+\nKWo7Eu7+FfAn4AsgD9jo7n+PNqqUSXf3vPD1aiA9ymDiUYKoZcysGfAX4AZ3/zYVbbp7obtnEsxw\nP87Mjk52m2bWD1jj7nOS3VYZfuzu3YEzCC7nnZyCNhsB3YFH3b0bsIUaeNmhOoXX3fsTJMe2wD5m\ndlG0UaWeB/MNatycAyWIWsTMGhMkhxfc/dVUtx9TGiUV4zAnAmeZ2efAeKC3mT2fgnaBkn/Z4u5r\nCOqFHZeCZlcBq2J6aBMJEkZddirwmbuvdfftwKvACRHHlCr/NbM2AOHzmojj2Y0SRC1hZkZwbXqx\nu9+fwnbjlUZZkux23f1Wd2/n7h0IBi3/6e4p+Zelme1jZs2LXwM/AZJ+55q7rwa+NLMjwl19gEXJ\nbjdiXwDHm9ne4d94H+r4wHyM1wnKCkENLS+kBFEJZvYSMAM4wsxWmVkqFzU6ERhE8C/pj8JH3xS0\n2wbINbOPgQ8JxiBSestpBNKB6WY2H5gFvOHub6eo7euBF8LfdyZwT4rajUTYW5oIzAUWEHwn1fgS\nFJVVxnfHvcBpZracoCd1b5QxxqNSGyIiEpd6ECIiEpcShIiIxKUEISIicSlBiIhIXEoQIiISlxKE\nSETM7BIza7uHnzHCzG6srphEYilBiJQjLCCXLJcQlJdIWJLjEdmFEoTUaWbWIVxb4YVwfYWJZrZ3\n+LPbzezDcB2CJ8KZvJjZNDN7IFwHYqiZ/dTMZoYF9KaYWXp43AgzG2dm/zazlWZ2tpn9IVxH4u2w\nNApmlmVm74aF/94xszZmdg7Qg2BS3Edm1jTecfHiKedcrzCzt8IZ7yJ7TAlC6oMjgD+7e2fgW+Ca\ncP/D7n5suA5BU6BfzHuauHsPd78PmA4cHxbQG09QYbbYD4HewFnA80Cuux8DbAXODJPEaOAcd88C\nngbudveJwGzgwrAQ4o54x5URz27M7Low/gHuvrUqvySR0tRdlfrgS3d/L3z9PMECNX8Css3sJoI1\nCFoBnwB/C4+bEPP+dsCE8F/0TYDPYn72lrtvN7MFBIvdFJfkWAB0IEhORwP/CDsoDQnKWpdW0XET\n4ryn2MXAlwTJYXs5x4lUihKE1Ael68l4uKzlnwlWMvvSzEYAsUtdbol5PRq4391fN7NewIiYn30P\n4O5FZrbdd9auKSL4/8uAT9y9oqVDKzpuSxn7IUhGxeXYPyvnOJFK0SUmqQ8OsZ1rO/+c4JJRcTJY\nF66xcU45728BfBW+HlzOcfEsBQ4obt/MGptZl/Bnm4DmCRxXkXnAlcDre3pXlEgsJQipD5YSLPqz\nGNiPYEGeDcCTBGW83yGoVFuWEcArZjYHWFeZht29gCD5jAyrw37EzvUOngEeC1fra1jOcYm0Mx24\nEXjDzPavTIwiZVE1V6nTLFiedXI4EC0ilaAehIiIxKUehIiIxKUehIiIxKUEISIicSlBiIhIXEoQ\nIiISlxKEiIjE9f9n/fUpJVjPoQAAAABJRU5ErkJggg==\n",
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x1190ddb70>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "accuracy_scores_20topic={}\n",
+    "for i in [1,2,3,4,5,6,8,10]:\n",
+    "    accuracy, k = prediction_accuracy(test_author2doc, test_corpus_50_20, atmodel_standard, k=i)\n",
+    "    accuracy_scores_20topic[k] = accuracy\n",
+    "    \n",
+    "plot_accuracy(scores1=accuracy_scores_20topic, label1=\"20 topics\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "This is a rather poor accuracy performace. We increase the number of topic to 100."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "05:31:51 INFO:Vocabulary consists of 3914 words.\n",
+      "05:31:51 INFO:using symmetric alpha at 0.01\n",
+      "05:31:51 INFO:using symmetric eta at 0.01\n",
+      "05:31:53 INFO:running online author-topic training, 100 topics, 50 authors, 10 passes over the supplied corpus of 2500 documents, updating model once every 2500 documents, evaluating perplexity every 0 documents, iterating 50x with a convergence threshold of 0.001000\n",
+      "05:31:53 INFO:PROGRESS: pass 0, at document #2500/2500\n",
+      "05:31:53 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "05:32:05 DEBUG:5/2500 documents converged within 50 iterations\n",
+      "05:32:05 DEBUG:updating topics\n",
+      "05:32:05 INFO:topic #18 (0.010): 0.007*\"analyst\" + 0.007*\"business\" + 0.005*\"billion\" + 0.005*\"stock\" + 0.005*\"boeing\" + 0.004*\"quarter\" + 0.004*\"industry\" + 0.004*\"share\" + 0.004*\"shareholder\" + 0.004*\"sale\"\n",
+      "05:32:05 INFO:topic #71 (0.010): 0.015*\"fcc\" + 0.015*\"phone\" + 0.011*\"local\" + 0.011*\"carrier\" + 0.010*\"service\" + 0.009*\"rule\" + 0.008*\"court\" + 0.008*\"distance\" + 0.008*\"long\" + 0.007*\"tv\"\n",
+      "05:32:05 INFO:topic #79 (0.010): 0.011*\"china\" + 0.010*\"beijing\" + 0.007*\"official\" + 0.006*\"chinese\" + 0.006*\"lama\" + 0.006*\"tibet\" + 0.006*\"share\" + 0.005*\"analyst\" + 0.005*\"region\" + 0.005*\"billion\"\n",
+      "05:32:05 INFO:topic #93 (0.010): 0.015*\"ibm\" + 0.011*\"analyst\" + 0.011*\"computer\" + 0.010*\"pc\" + 0.009*\"sale\" + 0.009*\"quarter\" + 0.008*\"industry\" + 0.008*\"price\" + 0.007*\"consumer\" + 0.007*\"service\"\n",
+      "05:32:05 INFO:topic #99 (0.010): 0.008*\"world\" + 0.008*\"czech\" + 0.007*\"analyst\" + 0.006*\"stock\" + 0.006*\"win\" + 0.005*\"billion\" + 0.005*\"team\" + 0.005*\"game\" + 0.005*\"bank\" + 0.005*\"second\"\n",
+      "05:32:05 INFO:topic diff=25.070898, rho=1.000000\n",
+      "05:32:05 INFO:PROGRESS: pass 1, at document #2500/2500\n",
+      "05:32:05 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "05:32:12 DEBUG:2492/2500 documents converged within 50 iterations\n",
+      "05:32:12 DEBUG:updating topics\n",
+      "05:32:12 INFO:topic #70 (0.010): 0.019*\"shanghai\" + 0.018*\"share\" + 0.017*\"china\" + 0.011*\"stock\" + 0.011*\"beijing\" + 0.010*\"b\" + 0.010*\"foreign\" + 0.010*\"exchange\" + 0.009*\"analyst\" + 0.008*\"investor\"\n",
+      "05:32:12 INFO:topic #2 (0.010): 0.020*\"mci\" + 0.012*\"long\" + 0.012*\"service\" + 0.010*\"distance\" + 0.010*\"analyst\" + 0.010*\"sprint\" + 0.010*\"billion\" + 0.010*\"corp\" + 0.008*\"local\" + 0.008*\"deal\"\n",
+      "05:32:12 INFO:topic #57 (0.010): 0.024*\"china\" + 0.013*\"beijing\" + 0.011*\"chinese\" + 0.010*\"wang\" + 0.010*\"hong_kong\" + 0.009*\"hong\" + 0.008*\"kong\" + 0.008*\"official\" + 0.007*\"Hong Kong\" + 0.006*\"people\"\n",
+      "05:32:12 INFO:topic #45 (0.010): 0.021*\"time\" + 0.016*\"executive\" + 0.013*\"cable\" + 0.011*\"rise\" + 0.011*\"sale\" + 0.010*\"billion\" + 0.009*\"quarter\" + 0.008*\"share\" + 0.008*\"group\" + 0.007*\"analyst\"\n",
+      "05:32:12 INFO:topic #18 (0.010): 0.007*\"analyst\" + 0.006*\"business\" + 0.005*\"billion\" + 0.004*\"stock\" + 0.004*\"boeing\" + 0.004*\"quarter\" + 0.004*\"industry\" + 0.004*\"share\" + 0.004*\"shareholder\" + 0.003*\"sale\"\n",
+      "05:32:12 INFO:topic diff=7.998665, rho=0.577350\n",
+      "05:32:12 INFO:PROGRESS: pass 2, at document #2500/2500\n",
+      "05:32:12 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "05:32:19 DEBUG:2500/2500 documents converged within 50 iterations\n",
+      "05:32:19 DEBUG:updating topics\n",
+      "05:32:19 INFO:topic #70 (0.010): 0.021*\"share\" + 0.021*\"shanghai\" + 0.019*\"china\" + 0.012*\"b\" + 0.011*\"foreign\" + 0.011*\"stock\" + 0.011*\"bank\" + 0.011*\"analyst\" + 0.010*\"beijing\" + 0.010*\"exchange\"\n",
+      "05:32:19 INFO:topic #71 (0.010): 0.020*\"fcc\" + 0.015*\"phone\" + 0.013*\"carrier\" + 0.013*\"tv\" + 0.012*\"local\" + 0.010*\"service\" + 0.010*\"rule\" + 0.010*\"long\" + 0.009*\"distance\" + 0.008*\"long_distance\"\n",
+      "05:32:19 INFO:topic #22 (0.010): 0.033*\"bank\" + 0.010*\"rate\" + 0.010*\"cut\" + 0.009*\"analyst\" + 0.008*\"day\" + 0.008*\"merger\" + 0.007*\"profit\" + 0.007*\"australia\" + 0.007*\"financial\" + 0.006*\"ltd\"\n",
+      "05:32:19 INFO:topic #18 (0.010): 0.006*\"analyst\" + 0.005*\"business\" + 0.004*\"billion\" + 0.004*\"stock\" + 0.004*\"boeing\" + 0.003*\"quarter\" + 0.003*\"industry\" + 0.003*\"share\" + 0.003*\"shareholder\" + 0.003*\"sale\"\n",
+      "05:32:19 INFO:topic #5 (0.010): 0.018*\"china\" + 0.009*\"beijing\" + 0.008*\"tonne\" + 0.007*\"chinese\" + 0.006*\"official\" + 0.005*\"trade\" + 0.005*\"price\" + 0.005*\"chen\" + 0.005*\"trader\" + 0.004*\"million_tonne\"\n",
+      "05:32:19 INFO:topic diff=7.090922, rho=0.500000\n",
+      "05:32:19 INFO:PROGRESS: pass 3, at document #2500/2500\n",
+      "05:32:19 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "05:32:25 DEBUG:2500/2500 documents converged within 50 iterations\n",
+      "05:32:25 DEBUG:updating topics\n",
+      "05:32:26 INFO:topic #9 (0.010): 0.004*\"analyst\" + 0.003*\"government\" + 0.002*\"share\" + 0.002*\"china\" + 0.002*\"cost\" + 0.002*\"sale\" + 0.002*\"right\" + 0.002*\"stock\" + 0.002*\"big\" + 0.002*\"end\"\n",
+      "05:32:26 INFO:topic #20 (0.010): 0.016*\"gold\" + 0.016*\"bre\" + 0.015*\"x\" + 0.015*\"bre_x\" + 0.010*\"barrick\" + 0.009*\"Bre-X\" + 0.008*\"gm\" + 0.008*\"price\" + 0.008*\"analyst\" + 0.008*\"plant\"\n",
+      "05:32:26 INFO:topic #4 (0.010): 0.015*\"franc\" + 0.015*\"thomson\" + 0.014*\"french\" + 0.009*\"group\" + 0.009*\"share\" + 0.008*\"france\" + 0.008*\"government\" + 0.008*\"plan\" + 0.008*\"lagardere\" + 0.007*\"billion\"\n",
+      "05:32:26 INFO:topic #87 (0.010): 0.017*\"analyst\" + 0.011*\"sale\" + 0.010*\"share\" + 0.009*\"business\" + 0.008*\"quarter\" + 0.008*\"price\" + 0.007*\"add\" + 0.007*\"chemical\" + 0.006*\"stock\" + 0.006*\"earning\"\n",
+      "05:32:26 INFO:topic #62 (0.010): 0.022*\"profit\" + 0.014*\"pound\" + 0.011*\"sale\" + 0.011*\"rise\" + 0.010*\"analyst\" + 0.010*\"stg\" + 0.010*\"group\" + 0.009*\"business\" + 0.009*\"half\" + 0.009*\"million_stg\"\n",
+      "05:32:26 INFO:topic diff=6.178695, rho=0.447214\n",
+      "05:32:26 INFO:PROGRESS: pass 4, at document #2500/2500\n",
+      "05:32:26 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "05:32:31 DEBUG:2500/2500 documents converged within 50 iterations\n",
+      "05:32:31 DEBUG:updating topics\n",
+      "05:32:32 INFO:topic #47 (0.010): 0.012*\"gold\" + 0.008*\"oil\" + 0.008*\"share\" + 0.007*\"stock\" + 0.006*\"analyst\" + 0.006*\"government\" + 0.006*\"price\" + 0.006*\"colombia\" + 0.005*\"rise\" + 0.005*\"issue\"\n",
+      "05:32:32 INFO:topic #86 (0.010): 0.014*\"cargo\" + 0.010*\"service\" + 0.010*\"kong\" + 0.009*\"hong\" + 0.009*\"air\" + 0.009*\"airline\" + 0.008*\"hong_kong\" + 0.007*\"Hong Kong\" + 0.007*\"route\" + 0.006*\"rate\"\n",
+      "05:32:32 INFO:topic #25 (0.010): 0.010*\"boeing\" + 0.009*\"share\" + 0.009*\"analyst\" + 0.007*\"billion\" + 0.006*\"service\" + 0.006*\"mci\" + 0.006*\"business\" + 0.005*\"stock\" + 0.005*\"jet\" + 0.005*\"growth\"\n",
+      "05:32:32 INFO:topic #74 (0.010): 0.043*\"china\" + 0.020*\"chinese\" + 0.014*\"official\" + 0.014*\"beijing\" + 0.010*\"trade\" + 0.009*\"state\" + 0.007*\"states\" + 0.006*\"united\" + 0.006*\"united_states\" + 0.006*\"import\"\n",
+      "05:32:32 INFO:topic #53 (0.010): 0.032*\"fund\" + 0.012*\"investment\" + 0.011*\"hong_kong\" + 0.011*\"hong\" + 0.010*\"stock\" + 0.010*\"management\" + 0.010*\"week\" + 0.009*\"manager\" + 0.009*\"billion\" + 0.009*\"kong\"\n",
+      "05:32:32 INFO:topic diff=5.327576, rho=0.408248\n",
+      "05:32:32 INFO:PROGRESS: pass 5, at document #2500/2500\n",
+      "05:32:32 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "05:32:36 DEBUG:2500/2500 documents converged within 50 iterations\n",
+      "05:32:36 DEBUG:updating topics\n",
+      "05:32:37 INFO:topic #60 (0.010): 0.002*\"financial\" + 0.002*\"official\" + 0.002*\"stock\" + 0.002*\"policy\" + 0.002*\"group\" + 0.002*\"share\" + 0.002*\"china\" + 0.001*\"chinese\" + 0.001*\"beijing\" + 0.001*\"bank\"\n",
+      "05:32:37 INFO:topic #77 (0.010): 0.006*\"computer\" + 0.005*\"internet\" + 0.005*\"quarter\" + 0.005*\"analyst\" + 0.004*\"business\" + 0.004*\"share\" + 0.004*\"service\" + 0.003*\"profit\" + 0.003*\"industry\" + 0.003*\"system\"\n",
+      "05:32:37 INFO:topic #43 (0.010): 0.003*\"bre_x\" + 0.003*\"bre\" + 0.002*\"analyst\" + 0.002*\"gold\" + 0.002*\"barrick\" + 0.002*\"government\" + 0.002*\"Bre-X\" + 0.002*\"x\" + 0.002*\"share\" + 0.002*\"stock\"\n",
+      "05:32:37 INFO:topic #10 (0.010): 0.002*\"billion\" + 0.001*\"investment\" + 0.001*\"tonne\" + 0.001*\"quarter\" + 0.001*\"venture\" + 0.001*\"industry\" + 0.001*\"price\" + 0.001*\"cocoa\" + 0.001*\"coast\" + 0.001*\"month\"\n",
+      "05:32:37 INFO:topic #99 (0.010): 0.005*\"world\" + 0.005*\"czech\" + 0.004*\"analyst\" + 0.004*\"stock\" + 0.004*\"win\" + 0.003*\"billion\" + 0.003*\"team\" + 0.003*\"game\" + 0.003*\"bank\" + 0.003*\"second\"\n",
+      "05:32:37 INFO:topic diff=4.560862, rho=0.377964\n",
+      "05:32:37 INFO:PROGRESS: pass 6, at document #2500/2500\n",
+      "05:32:37 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "05:32:41 DEBUG:2500/2500 documents converged within 50 iterations\n",
+      "05:32:41 DEBUG:updating topics\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "05:32:41 INFO:topic #38 (0.010): 0.015*\"analyst\" + 0.014*\"australian\" + 0.013*\"ltd\" + 0.012*\"share\" + 0.011*\"australia\" + 0.011*\"profit\" + 0.010*\"sydney\" + 0.009*\"group\" + 0.009*\"news\" + 0.008*\"corp\"\n",
+      "05:32:41 INFO:topic #46 (0.010): 0.004*\"hong\" + 0.004*\"kong\" + 0.003*\"china\" + 0.002*\"Hong Kong\" + 0.002*\"official\" + 0.002*\"hong_kong\" + 0.002*\"chinese\" + 0.002*\"united\" + 0.002*\"singapore\" + 0.001*\"month\"\n",
+      "05:32:41 INFO:topic #97 (0.010): 0.021*\"internet\" + 0.017*\"bank\" + 0.008*\"law\" + 0.008*\"court\" + 0.008*\"congress\" + 0.007*\"service\" + 0.007*\"credit\" + 0.007*\"allow\" + 0.007*\"bill\" + 0.006*\"policy\"\n",
+      "05:32:41 INFO:topic #75 (0.010): 0.028*\"bank\" + 0.016*\"japan\" + 0.015*\"billion\" + 0.014*\"yen\" + 0.014*\"financial\" + 0.012*\"loan\" + 0.011*\"japanese\" + 0.010*\"problem\" + 0.010*\"analyst\" + 0.009*\"firm\"\n",
+      "05:32:41 INFO:topic #11 (0.010): 0.063*\"gm\" + 0.032*\"plant\" + 0.024*\"strike\" + 0.021*\"automaker\" + 0.021*\"worker\" + 0.017*\"uaw\" + 0.013*\"truck\" + 0.013*\"local\" + 0.013*\"union\" + 0.012*\"chrysler\"\n",
+      "05:32:41 INFO:topic diff=3.882969, rho=0.353553\n",
+      "05:32:41 INFO:PROGRESS: pass 7, at document #2500/2500\n",
+      "05:32:41 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "05:32:46 DEBUG:2500/2500 documents converged within 50 iterations\n",
+      "05:32:46 DEBUG:updating topics\n",
+      "05:32:46 INFO:topic #82 (0.010): 0.003*\"quarter\" + 0.003*\"executive\" + 0.003*\"internet\" + 0.003*\"high\" + 0.003*\"share\" + 0.002*\"loss\" + 0.002*\"technology\" + 0.002*\"high_tech\" + 0.002*\"stock\" + 0.002*\"software\"\n",
+      "05:32:46 INFO:topic #38 (0.010): 0.015*\"analyst\" + 0.014*\"australian\" + 0.013*\"ltd\" + 0.012*\"share\" + 0.011*\"australia\" + 0.011*\"profit\" + 0.010*\"sydney\" + 0.009*\"group\" + 0.009*\"news\" + 0.008*\"corp\"\n",
+      "05:32:46 INFO:topic #9 (0.010): 0.001*\"analyst\" + 0.001*\"government\" + 0.001*\"share\" + 0.001*\"china\" + 0.001*\"cost\" + 0.001*\"sale\" + 0.001*\"right\" + 0.001*\"stock\" + 0.001*\"big\" + 0.001*\"end\"\n",
+      "05:32:46 INFO:topic #13 (0.010): 0.001*\"china\" + 0.001*\"share\" + 0.001*\"official\" + 0.001*\"analyst\" + 0.001*\"group\" + 0.001*\"sale\" + 0.001*\"beijing\" + 0.001*\"party\" + 0.001*\"month\" + 0.001*\"billion\"\n",
+      "05:32:46 INFO:topic #76 (0.010): 0.024*\"cocoa\" + 0.019*\"exporter\" + 0.019*\"tonne\" + 0.012*\"ivory\" + 0.012*\"coast\" + 0.012*\"ivory_coast\" + 0.011*\"crop\" + 0.011*\"price\" + 0.010*\"buyer\" + 0.009*\"export\"\n",
+      "05:32:46 INFO:topic diff=3.291750, rho=0.333333\n",
+      "05:32:46 INFO:PROGRESS: pass 8, at document #2500/2500\n",
+      "05:32:46 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "05:32:50 DEBUG:2500/2500 documents converged within 50 iterations\n",
+      "05:32:50 DEBUG:updating topics\n",
+      "05:32:50 INFO:topic #18 (0.010): 0.001*\"analyst\" + 0.001*\"business\" + 0.001*\"billion\" + 0.001*\"stock\" + 0.001*\"boeing\" + 0.001*\"quarter\" + 0.001*\"industry\" + 0.001*\"share\" + 0.001*\"shareholder\" + 0.001*\"sale\"\n",
+      "05:32:50 INFO:topic #61 (0.010): 0.014*\"analyst\" + 0.014*\"microsoft\" + 0.010*\"share\" + 0.009*\"software\" + 0.009*\"quarter\" + 0.009*\"boeing\" + 0.009*\"office\" + 0.008*\"computer\" + 0.008*\"worker\" + 0.008*\"fiscal\"\n",
+      "05:32:50 INFO:topic #2 (0.010): 0.019*\"mci\" + 0.013*\"analyst\" + 0.011*\"long\" + 0.011*\"share\" + 0.011*\"service\" + 0.010*\"distance\" + 0.010*\"long_distance\" + 0.010*\"billion\" + 0.010*\"corp\" + 0.008*\"local\"\n",
+      "05:32:50 INFO:topic #98 (0.010): 0.031*\"tonne\" + 0.030*\"china\" + 0.019*\"trader\" + 0.018*\"chinese\" + 0.018*\"price\" + 0.016*\"hong_kong\" + 0.016*\"hong\" + 0.016*\"kong\" + 0.013*\"source\" + 0.013*\"import\"\n",
+      "05:32:50 INFO:topic #71 (0.010): 0.019*\"fcc\" + 0.014*\"tv\" + 0.014*\"phone\" + 0.013*\"carrier\" + 0.011*\"local\" + 0.010*\"service\" + 0.010*\"long\" + 0.009*\"rule\" + 0.009*\"distance\" + 0.009*\"long_distance\"\n",
+      "05:32:50 INFO:topic diff=2.781235, rho=0.316228\n",
+      "05:32:50 INFO:PROGRESS: pass 9, at document #2500/2500\n",
+      "05:32:50 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "05:32:54 DEBUG:2500/2500 documents converged within 50 iterations\n",
+      "05:32:54 DEBUG:updating topics\n",
+      "05:32:55 INFO:topic #99 (0.010): 0.002*\"world\" + 0.002*\"czech\" + 0.002*\"analyst\" + 0.002*\"stock\" + 0.002*\"win\" + 0.001*\"billion\" + 0.001*\"team\" + 0.001*\"game\" + 0.001*\"bank\" + 0.001*\"second\"\n",
+      "05:32:55 INFO:topic #26 (0.010): 0.003*\"business\" + 0.002*\"analyst\" + 0.002*\"gm\" + 0.001*\"share\" + 0.001*\"internet\" + 0.001*\"billion\" + 0.001*\"stock\" + 0.001*\"access\" + 0.001*\"chemical\" + 0.001*\"service\"\n",
+      "05:32:55 INFO:topic #80 (0.010): 0.012*\"analyst\" + 0.012*\"computer\" + 0.009*\"stock\" + 0.009*\"internet\" + 0.008*\"quarter\" + 0.008*\"technology\" + 0.008*\"service\" + 0.007*\"software\" + 0.007*\"share\" + 0.007*\"business\"\n",
+      "05:32:55 INFO:topic #67 (0.010): 0.045*\"gm\" + 0.033*\"plant\" + 0.021*\"uaw\" + 0.017*\"strike\" + 0.017*\"worker\" + 0.012*\"part\" + 0.011*\"local\" + 0.010*\"truck\" + 0.010*\"automaker\" + 0.010*\"contract\"\n",
+      "05:32:55 INFO:topic #97 (0.010): 0.021*\"internet\" + 0.017*\"bank\" + 0.008*\"law\" + 0.008*\"court\" + 0.008*\"congress\" + 0.007*\"service\" + 0.007*\"credit\" + 0.007*\"allow\" + 0.007*\"bill\" + 0.006*\"policy\"\n",
+      "05:32:55 INFO:topic diff=2.344407, rho=0.301511\n",
+      "05:32:55 DEBUG:Setting topics to those of the model: AuthorTopicModel(num_terms=3914, num_topics=100, num_authors=50, decay=0.5, chunksize=2500)\n",
+      "05:32:55 INFO:CorpusAccumulator accumulated stats from 1000 documents\n",
+      "05:32:55 INFO:CorpusAccumulator accumulated stats from 2000 documents\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "-1.89056657258\n"
+     ]
+    }
+   ],
+   "source": [
+    "atmodel_100topics = train_model(train_corpus_50_20, train_author2doc, train_dictionary_50_20, num_topics=100, eval_every=0, iterations=50, passes=10)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {
+    "scrolled": false
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Precision@k: top_n=1\n",
+      "Prediction accuracy: 0.5808\n",
+      "Precision@k: top_n=2\n",
+      "Prediction accuracy: 0.7472\n",
+      "Precision@k: top_n=3\n",
+      "Prediction accuracy: 0.8252\n",
+      "Precision@k: top_n=4\n",
+      "Prediction accuracy: 0.8732\n",
+      "Precision@k: top_n=5\n",
+      "Prediction accuracy: 0.8956\n",
+      "Precision@k: top_n=6\n",
+      "Prediction accuracy: 0.9072\n",
+      "Precision@k: top_n=8\n",
+      "Prediction accuracy: 0.9276\n",
+      "Precision@k: top_n=10\n",
+      "Prediction accuracy: 0.9412\n"
+     ]
+    },
+    {
+     "data": {
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYgAAAEWCAYAAAB8LwAVAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nSUVORK5CYII=\n",
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x15f425eb8>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "accuracy_scores_100topic={}\n",
+    "for i in [1,2,3,4,5,6,8,10]:\n",
+    "    accuracy, k = prediction_accuracy(test_author2doc, test_corpus_50_20, atmodel_100topics, k=i)\n",
+    "    accuracy_scores_100topic[k] = accuracy\n",
+    "    \n",
+    "plot_accuracy(scores1=accuracy_scores_20topic, label1=\"20 topics\", scores2=accuracy_scores_100topic, label2=\"100 topics\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "The 100-topic model is much more accurate than the 20-topic model. We continue to increase the topic until convergence."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "05:36:37 INFO:Vocabulary consists of 3914 words.\n",
+      "05:36:37 INFO:using symmetric alpha at 0.006666666666666667\n",
+      "05:36:37 INFO:using symmetric eta at 0.006666666666666667\n",
+      "05:36:40 INFO:running online author-topic training, 150 topics, 50 authors, 15 passes over the supplied corpus of 2500 documents, updating model once every 2500 documents, evaluating perplexity every 0 documents, iterating 50x with a convergence threshold of 0.001000\n",
+      "05:36:40 INFO:PROGRESS: pass 0, at document #2500/2500\n",
+      "05:36:40 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "05:36:55 DEBUG:15/2500 documents converged within 50 iterations\n",
+      "05:36:55 DEBUG:updating topics\n",
+      "05:36:56 INFO:topic #51 (0.007): 0.015*\"profit\" + 0.012*\"price\" + 0.012*\"group\" + 0.012*\"analyst\" + 0.009*\"share\" + 0.009*\"steel\" + 0.008*\"tell\" + 0.008*\"australian\" + 0.007*\"month\" + 0.007*\"forecast\"\n",
+      "05:36:56 INFO:topic #86 (0.007): 0.011*\"china\" + 0.008*\"kong\" + 0.007*\"hong\" + 0.007*\"cargo\" + 0.006*\"hong_kong\" + 0.006*\"service\" + 0.006*\"Hong Kong\" + 0.005*\"profit\" + 0.005*\"analyst\" + 0.005*\"month\"\n",
+      "05:36:56 INFO:topic #125 (0.007): 0.009*\"analyst\" + 0.007*\"share\" + 0.007*\"bank\" + 0.005*\"problem\" + 0.004*\"billion\" + 0.004*\"sale\" + 0.004*\"loan\" + 0.004*\"plant\" + 0.004*\"gm\" + 0.004*\"corp\"\n",
+      "05:36:56 INFO:topic #4 (0.007): 0.020*\"franc\" + 0.018*\"thomson\" + 0.016*\"french\" + 0.011*\"group\" + 0.011*\"share\" + 0.010*\"government\" + 0.009*\"plan\" + 0.009*\"france\" + 0.009*\"lagardere\" + 0.009*\"billion\"\n",
+      "05:36:56 INFO:topic #114 (0.007): 0.006*\"analyst\" + 0.006*\"sale\" + 0.005*\"chairman\" + 0.005*\"business\" + 0.004*\"social\" + 0.004*\"party\" + 0.004*\"month\" + 0.004*\"industry\" + 0.003*\"share\" + 0.003*\"government\"\n",
+      "05:36:56 INFO:topic diff=43.566047, rho=1.000000\n",
+      "05:36:56 INFO:PROGRESS: pass 1, at document #2500/2500\n",
+      "05:36:56 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "05:37:04 DEBUG:2493/2500 documents converged within 50 iterations\n",
+      "05:37:04 DEBUG:updating topics\n",
+      "05:37:04 INFO:topic #72 (0.007): 0.024*\"gold\" + 0.024*\"bre_x\" + 0.023*\"x\" + 0.023*\"bre\" + 0.020*\"Bre-X\" + 0.013*\"barrick\" + 0.010*\"government\" + 0.010*\"indonesian\" + 0.010*\"busang\" + 0.010*\"analyst\"\n",
+      "05:37:04 INFO:topic #133 (0.007): 0.013*\"group\" + 0.012*\"pound\" + 0.011*\"share\" + 0.009*\"billion\" + 0.006*\"bt\" + 0.006*\"business\" + 0.006*\"analyst\" + 0.005*\"british\" + 0.005*\"profit\" + 0.005*\"britain\"\n",
+      "05:37:04 INFO:topic #19 (0.007): 0.007*\"billion\" + 0.006*\"group\" + 0.006*\"airbus\" + 0.005*\"state\" + 0.005*\"profit\" + 0.005*\"industry\" + 0.005*\"tobacco\" + 0.005*\"tell\" + 0.004*\"price\" + 0.004*\"cost\"\n",
+      "05:37:04 INFO:topic #90 (0.007): 0.029*\"bank\" + 0.017*\"canadian\" + 0.016*\"billion\" + 0.014*\"canada\" + 0.010*\"toronto\" + 0.009*\"analyst\" + 0.008*\"stock\" + 0.008*\"fund\" + 0.008*\"share\" + 0.007*\"high\"\n",
+      "05:37:04 INFO:topic #91 (0.007): 0.008*\"analyst\" + 0.007*\"bre\" + 0.005*\"bre_x\" + 0.005*\"x\" + 0.005*\"gm\" + 0.005*\"billion\" + 0.005*\"Bre-X\" + 0.005*\"stock\" + 0.004*\"sale\" + 0.004*\"share\"\n",
+      "05:37:04 INFO:topic diff=12.489199, rho=0.577350\n",
+      "05:37:04 INFO:PROGRESS: pass 2, at document #2500/2500\n",
+      "05:37:04 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "05:37:12 DEBUG:2497/2500 documents converged within 50 iterations\n",
+      "05:37:12 DEBUG:updating topics\n",
+      "05:37:12 INFO:topic #58 (0.007): 0.011*\"shanghai\" + 0.010*\"china\" + 0.005*\"bank\" + 0.005*\"chinese\" + 0.004*\"city\" + 0.004*\"stock\" + 0.004*\"chen\" + 0.003*\"beijing\" + 0.003*\"analyst\" + 0.003*\"modern\"\n",
+      "05:37:12 INFO:topic #26 (0.007): 0.010*\"business\" + 0.005*\"analyst\" + 0.005*\"share\" + 0.004*\"billion\" + 0.004*\"stock\" + 0.004*\"continue\" + 0.003*\"states\" + 0.003*\"chemical\" + 0.003*\"united\" + 0.003*\"internet\"\n",
+      "05:37:12 INFO:topic #61 (0.007): 0.027*\"boeing\" + 0.014*\"analyst\" + 0.013*\"billion\" + 0.012*\"microsoft\" + 0.012*\"jet\" + 0.010*\"airbus\" + 0.009*\"share\" + 0.009*\"order\" + 0.008*\"mcdonnell\" + 0.007*\"revenue\"\n",
+      "05:37:12 INFO:topic #149 (0.007): 0.018*\"china\" + 0.010*\"official\" + 0.010*\"chinese\" + 0.008*\"beijing\" + 0.006*\"trade\" + 0.006*\"world\" + 0.005*\"foreign\" + 0.005*\"united_states\" + 0.005*\"drug\" + 0.005*\"metre\"\n",
+      "05:37:12 INFO:topic #74 (0.007): 0.044*\"china\" + 0.022*\"chinese\" + 0.012*\"official\" + 0.012*\"tonne\" + 0.011*\"beijing\" + 0.008*\"trade\" + 0.008*\"import\" + 0.008*\"trader\" + 0.007*\"price\" + 0.007*\"state\"\n",
+      "05:37:12 INFO:topic diff=10.945011, rho=0.500000\n",
+      "05:37:12 INFO:PROGRESS: pass 3, at document #2500/2500\n",
+      "05:37:12 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "05:37:19 DEBUG:2499/2500 documents converged within 50 iterations\n",
+      "05:37:19 DEBUG:updating topics\n",
+      "05:37:19 INFO:topic #125 (0.007): 0.004*\"analyst\" + 0.003*\"share\" + 0.003*\"bank\" + 0.002*\"problem\" + 0.002*\"billion\" + 0.002*\"sale\" + 0.002*\"loan\" + 0.002*\"plant\" + 0.002*\"gm\" + 0.002*\"corp\"\n",
+      "05:37:19 INFO:topic #95 (0.007): 0.038*\"bank\" + 0.018*\"billion\" + 0.016*\"society\" + 0.010*\"analyst\" + 0.009*\"debt\" + 0.009*\"eurotunnel\" + 0.008*\"banking\" + 0.008*\"pound\" + 0.008*\"member\" + 0.007*\"convert\"\n",
+      "05:37:19 INFO:topic #19 (0.007): 0.007*\"billion\" + 0.006*\"state\" + 0.005*\"group\" + 0.005*\"airbus\" + 0.005*\"loss\" + 0.005*\"cost\" + 0.005*\"profit\" + 0.005*\"industry\" + 0.005*\"sale\" + 0.004*\"executive\"\n",
+      "05:37:19 INFO:topic #115 (0.007): 0.003*\"share\" + 0.002*\"stock\" + 0.002*\"billion\" + 0.002*\"analyst\" + 0.002*\"china\" + 0.002*\"industry\" + 0.001*\"month\" + 0.001*\"rise\" + 0.001*\"big\" + 0.001*\"deal\"\n",
+      "05:37:20 INFO:topic #29 (0.007): 0.018*\"czech\" + 0.008*\"klaus\" + 0.007*\"government\" + 0.007*\"crown\" + 0.007*\"party\" + 0.007*\"bank\" + 0.007*\"prague\" + 0.005*\"country\" + 0.005*\"foreign\" + 0.005*\"election\"\n",
+      "05:37:20 INFO:topic diff=9.415271, rho=0.447214\n",
+      "05:37:20 INFO:PROGRESS: pass 4, at document #2500/2500\n",
+      "05:37:20 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "05:37:26 DEBUG:2499/2500 documents converged within 50 iterations\n",
+      "05:37:26 DEBUG:updating topics\n",
+      "05:37:27 INFO:topic #31 (0.007): 0.010*\"franc\" + 0.009*\"french\" + 0.008*\"china\" + 0.008*\"billion\" + 0.006*\"shanghai\" + 0.006*\"analyst\" + 0.006*\"share\" + 0.005*\"government\" + 0.005*\"plan\" + 0.005*\"exchange\"\n",
+      "05:37:27 INFO:topic #76 (0.007): 0.007*\"china\" + 0.006*\"hong_kong\" + 0.006*\"price\" + 0.005*\"kong\" + 0.005*\"hong\" + 0.004*\"tonne\" + 0.004*\"world\" + 0.004*\"analyst\" + 0.003*\"chinese\" + 0.003*\"Hong Kong\"\n",
+      "05:37:27 INFO:topic #36 (0.007): 0.024*\"bid\" + 0.021*\"penny\" + 0.020*\"analyst\" + 0.017*\"share\" + 0.015*\"electric\" + 0.013*\"electricity\" + 0.012*\"offer\" + 0.012*\"price\" + 0.011*\"northern\" + 0.010*\"water\"\n",
+      "05:37:27 INFO:topic #144 (0.007): 0.008*\"computer\" + 0.007*\"software\" + 0.006*\"technology\" + 0.006*\"internet\" + 0.005*\"web\" + 0.004*\"site\" + 0.004*\"people\" + 0.004*\"quarter\" + 0.004*\"industry\" + 0.004*\"base\"\n",
+      "05:37:27 INFO:topic #96 (0.007): 0.013*\"tv\" + 0.011*\"industry\" + 0.010*\"group\" + 0.010*\"system\" + 0.008*\"television\" + 0.008*\"plan\" + 0.008*\"service\" + 0.007*\"rating\" + 0.006*\"american\" + 0.006*\"long\"\n",
+      "05:37:27 INFO:topic diff=8.020445, rho=0.408248\n",
+      "05:37:27 INFO:PROGRESS: pass 5, at document #2500/2500\n",
+      "05:37:27 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "05:37:33 DEBUG:2500/2500 documents converged within 50 iterations\n",
+      "05:37:33 DEBUG:updating topics\n",
+      "05:37:33 INFO:topic #128 (0.007): 0.019*\"ford\" + 0.017*\"gm\" + 0.015*\"sale\" + 0.015*\"plant\" + 0.011*\"car\" + 0.011*\"vehicle\" + 0.008*\"chrysler\" + 0.008*\"worker\" + 0.008*\"automaker\" + 0.007*\"truck\"\n",
+      "05:37:33 INFO:topic #82 (0.007): 0.006*\"china\" + 0.004*\"tonne\" + 0.004*\"chinese\" + 0.003*\"trader\" + 0.003*\"copper\" + 0.002*\"price\" + 0.002*\"source\" + 0.002*\"kong\" + 0.002*\"shanghai\" + 0.002*\"metal\"\n",
+      "05:37:33 INFO:topic #96 (0.007): 0.013*\"tv\" + 0.011*\"industry\" + 0.010*\"group\" + 0.010*\"system\" + 0.008*\"plan\" + 0.008*\"television\" + 0.008*\"service\" + 0.007*\"rating\" + 0.007*\"american\" + 0.006*\"long\"\n",
+      "05:37:33 INFO:topic #41 (0.007): 0.016*\"australian\" + 0.014*\"bank\" + 0.013*\"profit\" + 0.013*\"share\" + 0.013*\"news\" + 0.013*\"sydney\" + 0.013*\"australia\" + 0.011*\"ltd\" + 0.011*\"analyst\" + 0.011*\"corp\"\n",
+      "05:37:33 INFO:topic #79 (0.007): 0.006*\"china\" + 0.006*\"beijing\" + 0.004*\"official\" + 0.004*\"lama\" + 0.004*\"tibet\" + 0.004*\"chinese\" + 0.003*\"region\" + 0.003*\"dalai_lama\" + 0.003*\"share\" + 0.003*\"analyst\"\n",
+      "05:37:33 INFO:topic diff=6.797042, rho=0.377964\n",
+      "05:37:33 INFO:PROGRESS: pass 6, at document #2500/2500\n",
+      "05:37:33 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "05:37:40 DEBUG:2500/2500 documents converged within 50 iterations\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "05:37:40 DEBUG:updating topics\n",
+      "05:37:40 INFO:topic #76 (0.007): 0.005*\"china\" + 0.004*\"hong_kong\" + 0.004*\"price\" + 0.003*\"kong\" + 0.003*\"hong\" + 0.003*\"tonne\" + 0.003*\"world\" + 0.003*\"analyst\" + 0.002*\"chinese\" + 0.002*\"Hong Kong\"\n",
+      "05:37:40 INFO:topic #31 (0.007): 0.008*\"franc\" + 0.007*\"french\" + 0.006*\"china\" + 0.006*\"billion\" + 0.005*\"shanghai\" + 0.005*\"analyst\" + 0.004*\"share\" + 0.004*\"government\" + 0.004*\"plan\" + 0.004*\"exchange\"\n",
+      "05:37:40 INFO:topic #140 (0.007): 0.026*\"china\" + 0.020*\"beijing\" + 0.016*\"chinese\" + 0.013*\"official\" + 0.010*\"wang\" + 0.006*\"foreign\" + 0.005*\"right\" + 0.005*\"human\" + 0.005*\"washington\" + 0.005*\"state\"\n",
+      "05:37:40 INFO:topic #46 (0.007): 0.004*\"hong\" + 0.004*\"kong\" + 0.003*\"china\" + 0.003*\"Hong Kong\" + 0.002*\"official\" + 0.002*\"hong_kong\" + 0.002*\"chinese\" + 0.002*\"singapore\" + 0.002*\"united\" + 0.002*\"plan\"\n",
+      "05:37:40 INFO:topic #148 (0.007): 0.001*\"network\" + 0.001*\"analyst\" + 0.001*\"stock\" + 0.001*\"share\" + 0.001*\"price\" + 0.001*\"remote\" + 0.001*\"recent\" + 0.001*\"industry\" + 0.001*\"chinese\" + 0.001*\"billion\"\n",
+      "05:37:40 INFO:topic diff=5.743502, rho=0.353553\n",
+      "05:37:40 INFO:PROGRESS: pass 7, at document #2500/2500\n",
+      "05:37:40 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "05:37:46 DEBUG:2500/2500 documents converged within 50 iterations\n",
+      "05:37:46 DEBUG:updating topics\n",
+      "05:37:47 INFO:topic #99 (0.007): 0.003*\"czech\" + 0.003*\"world\" + 0.003*\"team\" + 0.002*\"win\" + 0.002*\"game\" + 0.002*\"play\" + 0.002*\"second\" + 0.002*\"stock\" + 0.002*\"billion\" + 0.002*\"end\"\n",
+      "05:37:47 INFO:topic #81 (0.007): 0.003*\"pound\" + 0.002*\"share\" + 0.002*\"profit\" + 0.002*\"million_pound\" + 0.002*\"sale\" + 0.001*\"business\" + 0.001*\"analyst\" + 0.001*\"rise\" + 0.001*\"group\" + 0.001*\"fall\"\n",
+      "05:37:47 INFO:topic #97 (0.007): 0.001*\"analyst\" + 0.001*\"business\" + 0.001*\"china\" + 0.001*\"internet\" + 0.001*\"stock\" + 0.001*\"sale\" + 0.001*\"service\" + 0.001*\"chairman\" + 0.001*\"continue\" + 0.001*\"base\"\n",
+      "05:37:47 INFO:topic #28 (0.007): 0.000*\"large\" + 0.000*\"share\" + 0.000*\"stock\" + 0.000*\"property\" + 0.000*\"analyst\" + 0.000*\"taiwan\" + 0.000*\"china\" + 0.000*\"bank\" + 0.000*\"news\" + 0.000*\"billion\"\n",
+      "05:37:47 INFO:topic #93 (0.007): 0.020*\"ibm\" + 0.018*\"internet\" + 0.016*\"computer\" + 0.013*\"pc\" + 0.012*\"service\" + 0.011*\"analyst\" + 0.009*\"industry\" + 0.009*\"software\" + 0.009*\"quarter\" + 0.009*\"consumer\"\n",
+      "05:37:47 INFO:topic diff=4.844379, rho=0.333333\n",
+      "05:37:47 INFO:PROGRESS: pass 8, at document #2500/2500\n",
+      "05:37:47 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "05:37:53 DEBUG:2500/2500 documents converged within 50 iterations\n",
+      "05:37:53 DEBUG:updating topics\n",
+      "05:37:54 INFO:topic #97 (0.007): 0.001*\"analyst\" + 0.001*\"business\" + 0.001*\"china\" + 0.001*\"internet\" + 0.001*\"stock\" + 0.001*\"sale\" + 0.001*\"service\" + 0.001*\"chairman\" + 0.001*\"continue\" + 0.001*\"base\"\n",
+      "05:37:54 INFO:topic #77 (0.007): 0.002*\"computer\" + 0.002*\"internet\" + 0.002*\"quarter\" + 0.002*\"business\" + 0.002*\"service\" + 0.002*\"analyst\" + 0.001*\"share\" + 0.001*\"system\" + 0.001*\"cost\" + 0.001*\"industry\"\n",
+      "05:37:54 INFO:topic #70 (0.007): 0.024*\"share\" + 0.023*\"shanghai\" + 0.021*\"china\" + 0.015*\"bank\" + 0.013*\"b\" + 0.013*\"analyst\" + 0.012*\"foreign\" + 0.010*\"exchange\" + 0.010*\"investor\" + 0.010*\"stock\"\n",
+      "05:37:54 INFO:topic #26 (0.007): 0.003*\"business\" + 0.002*\"analyst\" + 0.001*\"share\" + 0.001*\"billion\" + 0.001*\"stock\" + 0.001*\"continue\" + 0.001*\"states\" + 0.001*\"chemical\" + 0.001*\"united\" + 0.001*\"internet\"\n",
+      "05:37:54 INFO:topic #145 (0.007): 0.019*\"analyst\" + 0.015*\"sale\" + 0.013*\"share\" + 0.012*\"quarter\" + 0.009*\"business\" + 0.008*\"base\" + 0.007*\"earning\" + 0.007*\"stock\" + 0.007*\"drug\" + 0.006*\"amp\"\n",
+      "05:37:54 INFO:topic diff=4.081138, rho=0.316228\n",
+      "05:37:54 INFO:PROGRESS: pass 9, at document #2500/2500\n",
+      "05:37:54 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "05:38:00 DEBUG:2500/2500 documents converged within 50 iterations\n",
+      "05:38:00 DEBUG:updating topics\n",
+      "05:38:00 INFO:topic #116 (0.007): 0.003*\"x\" + 0.002*\"bre\" + 0.002*\"analyst\" + 0.002*\"Bre-X\" + 0.002*\"bre_x\" + 0.001*\"government\" + 0.001*\"barrick\" + 0.001*\"gold\" + 0.001*\"mining\" + 0.001*\"indonesian\"\n",
+      "05:38:00 INFO:topic #67 (0.007): 0.002*\"hong\" + 0.002*\"china\" + 0.002*\"kong\" + 0.001*\"hong_kong\" + 0.001*\"Hong Kong\" + 0.001*\"beijing\" + 0.001*\"legislature\" + 0.001*\"rule\" + 0.001*\"chinese\" + 0.001*\"plan\"\n",
+      "05:38:00 INFO:topic #69 (0.007): 0.001*\"tibet\" + 0.001*\"chen\" + 0.001*\"dalai_lama\" + 0.001*\"china\" + 0.001*\"beijing\" + 0.001*\"group\" + 0.001*\"dalai\" + 0.000*\"lama\" + 0.000*\"billion\" + 0.000*\"region\"\n",
+      "05:38:00 INFO:topic #146 (0.007): 0.001*\"hong_kong\" + 0.001*\"analyst\" + 0.000*\"share\" + 0.000*\"hong\" + 0.000*\"kong\" + 0.000*\"china\" + 0.000*\"news\" + 0.000*\"Hong Kong\" + 0.000*\"billion\" + 0.000*\"price\"\n",
+      "05:38:00 INFO:topic #66 (0.007): 0.001*\"bank\" + 0.001*\"china\" + 0.000*\"hong\" + 0.000*\"government\" + 0.000*\"hong_kong\" + 0.000*\"plan\" + 0.000*\"bre\" + 0.000*\"x\" + 0.000*\"kong\" + 0.000*\"financial\"\n",
+      "05:38:00 INFO:topic diff=3.435844, rho=0.301511\n",
+      "05:38:00 INFO:PROGRESS: pass 10, at document #2500/2500\n",
+      "05:38:00 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "05:38:06 DEBUG:2500/2500 documents converged within 50 iterations\n",
+      "05:38:06 DEBUG:updating topics\n",
+      "05:38:06 INFO:topic #80 (0.007): 0.019*\"analyst\" + 0.015*\"microsoft\" + 0.013*\"quarter\" + 0.011*\"business\" + 0.010*\"computer\" + 0.009*\"sale\" + 0.008*\"revenue\" + 0.008*\"windows\" + 0.008*\"share\" + 0.008*\"system\"\n",
+      "05:38:06 INFO:topic #44 (0.007): 0.001*\"sale\" + 0.001*\"china\" + 0.001*\"analyst\" + 0.001*\"share\" + 0.001*\"service\" + 0.000*\"plan\" + 0.000*\"bank\" + 0.000*\"deal\" + 0.000*\"billion\" + 0.000*\"world\"\n",
+      "05:38:06 INFO:topic #58 (0.007): 0.001*\"shanghai\" + 0.001*\"china\" + 0.001*\"bank\" + 0.001*\"chinese\" + 0.000*\"city\" + 0.000*\"stock\" + 0.000*\"chen\" + 0.000*\"beijing\" + 0.000*\"analyst\" + 0.000*\"modern\"\n",
+      "05:38:06 INFO:topic #36 (0.007): 0.022*\"penny\" + 0.022*\"bid\" + 0.021*\"analyst\" + 0.018*\"share\" + 0.014*\"electric\" + 0.012*\"price\" + 0.012*\"electricity\" + 0.012*\"offer\" + 0.012*\"pound\" + 0.011*\"northern\"\n",
+      "05:38:06 INFO:topic #143 (0.007): 0.018*\"mci\" + 0.012*\"analyst\" + 0.012*\"allen\" + 0.011*\"long\" + 0.011*\"billion\" + 0.011*\"distance\" + 0.010*\"long_distance\" + 0.009*\"stock\" + 0.009*\"share\" + 0.009*\"executive\"\n",
+      "05:38:06 INFO:topic diff=2.892181, rho=0.288675\n",
+      "05:38:06 INFO:PROGRESS: pass 11, at document #2500/2500\n",
+      "05:38:06 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "05:38:12 DEBUG:2500/2500 documents converged within 50 iterations\n",
+      "05:38:12 DEBUG:updating topics\n",
+      "05:38:13 INFO:topic #141 (0.007): 0.006*\"internet\" + 0.005*\"bank\" + 0.003*\"law\" + 0.003*\"congress\" + 0.003*\"court\" + 0.002*\"service\" + 0.002*\"export\" + 0.002*\"security\" + 0.002*\"member\" + 0.002*\"credit\"\n",
+      "05:38:13 INFO:topic #33 (0.007): 0.000*\"billion\" + 0.000*\"service\" + 0.000*\"plan\" + 0.000*\"industry\" + 0.000*\"china\" + 0.000*\"internet\" + 0.000*\"tonne\" + 0.000*\"price\" + 0.000*\"chinese\" + 0.000*\"share\"\n",
+      "05:38:13 INFO:topic #49 (0.007): 0.001*\"eurotunnel\" + 0.001*\"service\" + 0.000*\"billion\" + 0.000*\"share\" + 0.000*\"fire\" + 0.000*\"pound\" + 0.000*\"tunnel\" + 0.000*\"debt\" + 0.000*\"group\" + 0.000*\"financial\"\n",
+      "05:38:13 INFO:topic #116 (0.007): 0.002*\"x\" + 0.001*\"bre\" + 0.001*\"analyst\" + 0.001*\"Bre-X\" + 0.001*\"bre_x\" + 0.001*\"government\" + 0.001*\"barrick\" + 0.001*\"gold\" + 0.001*\"mining\" + 0.001*\"indonesian\"\n",
+      "05:38:13 INFO:topic #83 (0.007): 0.001*\"beijing\" + 0.001*\"chinese\" + 0.001*\"billion\" + 0.001*\"profit\" + 0.001*\"tell\" + 0.001*\"china\" + 0.001*\"bank\" + 0.001*\"analyst\" + 0.001*\"australian\" + 0.001*\"share\"\n",
+      "05:38:13 INFO:topic diff=2.435570, rho=0.277350\n",
+      "05:38:13 INFO:PROGRESS: pass 12, at document #2500/2500\n",
+      "05:38:13 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "05:38:19 DEBUG:2500/2500 documents converged within 50 iterations\n",
+      "05:38:19 DEBUG:updating topics\n",
+      "05:38:19 INFO:topic #138 (0.007): 0.000*\"china\" + 0.000*\"beijing\" + 0.000*\"share\" + 0.000*\"states\" + 0.000*\"news\" + 0.000*\"analyst\" + 0.000*\"long\" + 0.000*\"chinese\" + 0.000*\"trade\" + 0.000*\"the United States\"\n",
+      "05:38:19 INFO:topic #125 (0.007): 0.000*\"analyst\" + 0.000*\"share\" + 0.000*\"bank\" + 0.000*\"problem\" + 0.000*\"billion\" + 0.000*\"sale\" + 0.000*\"loan\" + 0.000*\"plant\" + 0.000*\"gm\" + 0.000*\"corp\"\n",
+      "05:38:19 INFO:topic #21 (0.007): 0.024*\"stock\" + 0.021*\"toronto\" + 0.018*\"share\" + 0.017*\"bank\" + 0.016*\"canada\" + 0.013*\"gold\" + 0.012*\"billion\" + 0.012*\"index\" + 0.011*\"close\" + 0.010*\"point\"\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "05:38:19 INFO:topic #5 (0.007): 0.002*\"china\" + 0.001*\"beijing\" + 0.001*\"chen\" + 0.001*\"official\" + 0.001*\"trade\" + 0.001*\"economic\" + 0.001*\"chinese\" + 0.001*\"party\" + 0.001*\"survey\" + 0.001*\"month\"\n",
+      "05:38:19 INFO:topic #31 (0.007): 0.002*\"franc\" + 0.002*\"french\" + 0.002*\"china\" + 0.002*\"billion\" + 0.001*\"shanghai\" + 0.001*\"analyst\" + 0.001*\"share\" + 0.001*\"government\" + 0.001*\"plan\" + 0.001*\"exchange\"\n",
+      "05:38:19 INFO:topic diff=2.053082, rho=0.267261\n",
+      "05:38:19 INFO:PROGRESS: pass 13, at document #2500/2500\n",
+      "05:38:19 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "05:38:26 DEBUG:2500/2500 documents converged within 50 iterations\n",
+      "05:38:26 DEBUG:updating topics\n",
+      "05:38:26 INFO:topic #3 (0.007): 0.000*\"pound\" + 0.000*\"billion\" + 0.000*\"share\" + 0.000*\"group\" + 0.000*\"british\" + 0.000*\"deal\" + 0.000*\"bank\" + 0.000*\"sale\" + 0.000*\"mci\" + 0.000*\"service\"\n",
+      "05:38:26 INFO:topic #42 (0.007): 0.000*\"technology\" + 0.000*\"russia\" + 0.000*\"computer\" + 0.000*\"industry\" + 0.000*\"russian\" + 0.000*\"internet\" + 0.000*\"analyst\" + 0.000*\"world\" + 0.000*\"price\" + 0.000*\"software\"\n",
+      "05:38:26 INFO:topic #104 (0.007): 0.044*\"cent\" + 0.043*\"bank\" + 0.028*\"cent_share\" + 0.022*\"league\" + 0.019*\"football\" + 0.016*\"share\" + 0.014*\"card\" + 0.013*\"earning\" + 0.012*\"cos\" + 0.011*\"canada\"\n",
+      "05:38:26 INFO:topic #69 (0.007): 0.000*\"tibet\" + 0.000*\"chen\" + 0.000*\"dalai_lama\" + 0.000*\"china\" + 0.000*\"beijing\" + 0.000*\"group\" + 0.000*\"dalai\" + 0.000*\"lama\" + 0.000*\"billion\" + 0.000*\"region\"\n",
+      "05:38:26 INFO:topic #115 (0.007): 0.000*\"share\" + 0.000*\"stock\" + 0.000*\"billion\" + 0.000*\"analyst\" + 0.000*\"china\" + 0.000*\"industry\" + 0.000*\"month\" + 0.000*\"rise\" + 0.000*\"big\" + 0.000*\"deal\"\n",
+      "05:38:26 INFO:topic diff=1.733322, rho=0.258199\n",
+      "05:38:26 INFO:PROGRESS: pass 14, at document #2500/2500\n",
+      "05:38:26 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "05:38:32 DEBUG:2500/2500 documents converged within 50 iterations\n",
+      "05:38:32 DEBUG:updating topics\n",
+      "05:38:33 INFO:topic #82 (0.007): 0.001*\"china\" + 0.000*\"tonne\" + 0.000*\"chinese\" + 0.000*\"trader\" + 0.000*\"copper\" + 0.000*\"price\" + 0.000*\"source\" + 0.000*\"kong\" + 0.000*\"shanghai\" + 0.000*\"metal\"\n",
+      "05:38:33 INFO:topic #122 (0.007): 0.000*\"share\" + 0.000*\"analyst\" + 0.000*\"quarter\" + 0.000*\"pc\" + 0.000*\"computer\" + 0.000*\"ibm\" + 0.000*\"profit\" + 0.000*\"service\" + 0.000*\"industry\" + 0.000*\"compaq\"\n",
+      "05:38:33 INFO:topic #126 (0.007): 0.000*\"group\" + 0.000*\"europe\" + 0.000*\"plan\" + 0.000*\"air\" + 0.000*\"model\" + 0.000*\"pound\" + 0.000*\"hong\" + 0.000*\"month\" + 0.000*\"japan\" + 0.000*\"Hong Kong\"\n",
+      "05:38:33 INFO:topic #1 (0.007): 0.005*\"bank\" + 0.004*\"stock\" + 0.004*\"billion\" + 0.004*\"japan\" + 0.003*\"analyst\" + 0.003*\"financial\" + 0.003*\"asset\" + 0.003*\"japanese\" + 0.002*\"big\" + 0.002*\"yen\"\n",
+      "05:38:33 INFO:topic #120 (0.007): 0.022*\"stiff\" + 0.019*\"court\" + 0.018*\"rating\" + 0.018*\"frequently\" + 0.012*\"mercury\" + 0.012*\"williams\" + 0.012*\"remove\" + 0.011*\"judge\" + 0.011*\"armed\" + 0.009*\"ford\"\n",
+      "05:38:33 INFO:topic diff=1.466340, rho=0.250000\n",
+      "05:38:33 DEBUG:Setting topics to those of the model: AuthorTopicModel(num_terms=3914, num_topics=150, num_authors=50, decay=0.5, chunksize=2500)\n",
+      "05:38:33 INFO:CorpusAccumulator accumulated stats from 1000 documents\n",
+      "05:38:33 INFO:CorpusAccumulator accumulated stats from 2000 documents\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "-1.90810257282\n"
+     ]
+    }
+   ],
+   "source": [
+    "atmodel_150topics = train_model(train_corpus_50_20, train_author2doc, train_dictionary_50_20, num_topics=150, eval_every=0, iterations=50, passes=15)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Precision@k: top_n=1\n",
+      "Prediction accuracy: 0.6004\n",
+      "Precision@k: top_n=2\n",
+      "Prediction accuracy: 0.7632\n",
+      "Precision@k: top_n=3\n",
+      "Prediction accuracy: 0.8452\n",
+      "Precision@k: top_n=4\n",
+      "Prediction accuracy: 0.8796\n",
+      "Precision@k: top_n=5\n",
+      "Prediction accuracy: 0.8988\n",
+      "Precision@k: top_n=6\n",
+      "Prediction accuracy: 0.914\n",
+      "Precision@k: top_n=8\n",
+      "Prediction accuracy: 0.9324\n",
+      "Precision@k: top_n=10\n",
+      "Prediction accuracy: 0.9464\n"
+     ]
+    },
+    {
+     "data": {
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYgAAAEWCAYAAAB8LwAVAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDIuMS4yLCBo\ndHRwOi8vbWF0cGxvdGxpYi5vcmcvNQv5yAAAIABJREFUeJzs3Xd4FWX2wPHvSUiBQEIPJTSlE3oX\n6boquCD8FGV1BQvYVt1VEXYtINhWXQtrWUUXsAJiAV2sSAQEFUSUItJbEiAEEpKQnvP7Y25CQi7k\nkuTmppzP89znzsydO++ZK87JvO/MGVFVjDHGmNP5+ToAY4wx5ZMlCGOMMW5ZgjDGGOOWJQhjjDFu\nWYIwxhjjliUIY4wxblmCMKYIIrJFRIYUsU5zEUkWEf8yCstjIrJXRC7ydRym4rEEYSos14Ev1XVg\nPiwi80SkZmm3o6qdVDWqiHX2q2pNVc0u7fbPRkRmiMjbZdmmqTosQZiK7o+qWhPoAfQCHjx9BXHY\nv3VjzpH9T2MqBVWNBj4DIgFEJEpEHhOR74CTwHkiEiYib4hIrIhEi8ij+buERGSSiPwmIkkislVE\neriW53XRiEgfEVkvIidcZy3Pupa3FBEVkWqu+SYislREjonIThGZlK+dGSKySETedLW1RUR6nWnf\nROQFETngavMnERnoWn4p8A/gatdZ1C9F/U4i0kFE9ojI+HP9jU3VYwnCVAoi0gwYAfycb/GfgclA\nLWAfMA/IAloD3YE/ADe7vn8VMAO4HggFRgHxbpp6AXhBVUOB84FFZwhpAXAQaAJcCTwuIsPyfT7K\ntU5tYCnw4ll2bx3QDagLvAu8LyLBqvo58Diw0NW91fUs28CV8L4A7lTV9862rjFgCcJUfB+LSAKw\nGvgW54CZa56qblHVLJyD6wjgr6qaoqpHgOeAa1zr3gw8parr1LFTVfe5aS8TaC0i9VU1WVW/P30F\nV7IaAExV1TRV3Qi8jpN8cq1W1WWuMYu3gDMe3FX1bVWNV9UsVf0XEAS08+THyWcgTiK6XlU/Pcfv\nmirKEoSp6K5Q1dqq2kJVb1fV1HyfHcg33QIIAGJFJMGVVF4FGro+bwbs8qC9m4C2wDYRWScil7tZ\npwlwTFWT8i3bBzTNN38o3/RJIDi3e+p0InKfq+sr0RV3GFDfg1jzuxVYU9RguzH5WYIwlVn+UsUH\ngHSgviuh1FbVUFXtlO/z84vcoOoOVR2Pk1j+CSwWkZDTVosB6opIrXzLmgPR57oDrvGG+4FxQB1V\nrQ0kApIbkoebuhVoLiLPnWsMpuqyBGGqBFWNBb4E/iUioSLiJyLni8hg1yqvA/eJSE/XVU+tRaTF\n6dsRketEpIGq5gAJrsU5p7V1AFgDPCEiwSLSBefMoziXo9bCGTeJA6qJyMM4YyS5DgMtPbhKKwm4\nFBgkIk8WIw5TBVmCMFXJ9UAgsBU4DiwGGgOo6vvAYziDwEnAxzjjFqe7FNgiIsk4A9bXnNatlWs8\n0BLnbOIjYLqqfl2MmL8APge243RTpVGw6+x913u8iGw424ZUNQG4GLhMRGYVIxZTxYg9MMgYY4w7\ndgZhjDHGLa8lCBH5r4gcEZHN+ZbVFZGvRGSH672Oa7mIyGzXDUW/5t6gZIwxxne8eQYxD6e/Nr9p\nwHJVbQMsd80DXAa0cb0mA694MS5jjDEe8FqCUNWVwLHTFo8G5rum5wNX5Fv+pusGpe+B2iLS2Fux\nGWOMKZrbG3O8KNx1uSE4NwqFu6abUvDKjIOuZbGcRkQm45xlUL169Z7NmjXzXrRnkZOTg59f2Q/h\nVLV2fdl2VdxnX6pq++zL/d2+fftRVW1Q5Iqq6rUXzmV+m/PNJ5z2+XHX+6fAhfmWLwd6FbX9nj17\nqq+sWLHC2q3kbVfFffalqrbPvtxfYL16cAwv6/R1OLfryPV+xLU8GqfUQa4IinHXqTHGmNJT1gli\nKTDBNT0BWJJv+fWuq5n6AYl6qivKGGOMD3htDEJE3gOGAPVF5CAwHXgSWCQiN+HcFTrOtfoynEqb\nO3EKl93grbiMMcZ4xmsJQp2CZu4Md7OuAnd4KxZjjDHnrupcMmCMMeacWIIwxhjjliUIY4wxblmC\nMMYY45YlCGOMMW5ZgjDGGOOWJQhjjDFuWYIwxhjjliUIY4wpS78uguciGRx1BTwX6cyXU2Vd7tsY\nY6quXxfBJ3dBZioCkHjAmQfoMu5s3/QJSxDGGFOK0jKzSTiZyfGTGSSczCQxNYPjJzNJOJnJn9Y8\nRFhmasEvZKbC8pmWIIwxpqI424E+ITWDxAKfnZpOz8o54zZvCTqMc+pwmsSD3tuRErAEYYzxrV8X\nwfKZDE48CD9HwPCHS/WvaW8c6AP9/QirEUBoYCDVqwVQU2pQOzgM/2qBaEYAOamBZCYHkHYigJTj\ngSTFB5AYF0j0iAiahR4ovMGwiFLb39JkCcIY4zvn0CfvtQN99QBqBgRQvVog1alBaGAYrSQQTQ8g\n62QgGckBpJ8IIPl4IElHA0g4HEjMUT92pLg7FXCIQJ06ULeu82pQB9o1g+U8zJ+zbsW/WvapldXf\nSYrlkCUIY0yZy8jKIT4lnXpfziDQTZ98/NIHuH1tM48P9AH+foQFBxASEEAN/0CCqEFTvzCaBQei\nac6BPj0pgLRE5y/6E0cDOH44gOg4f7KyznygDwo6dZCvWxfObwx1OhZclj8R5L5CQ8Ht46ZjB8LI\ndBjkB2ECiQqrsuC2QcX8Jb3LEoQxplTk5CgJqZnEJaU7r+S0U9NJ6cQln5o+fjITgN1B0W775Otk\nxZGQAIHUoDFhNK4WiGadOtCfTAggOf7Ugf7EMX/cd+47wsIKHsjPawt1+xU+uJ8+X716Kf9Is2bB\nliz4OePUssBAZ/lLL5VyYyVnCcIYc1Yp6VmFDvDuDvpHk9PJytFC3w+q5kf9kCBqBQRRgxDOD6hL\nTmAw6QlBHPFvQqOAmELf2Z8QwZeP9C+wrFq1ggfy5nWhbssz/xWfu6x2bee75cLatZCRUXBZRgas\nWeObeIpQXn42Y0wZyszOIT45o8i/9OOS0knJyC70fT+B+jWDqB8SRM2AINqG1aJD9SCyU4JITwwi\nOS6IYzFBHNkfxP591dieVviv+3r14Lk+j/BY91upFnCqjZxsfw5HPszy5QUP9jVrOn37FdrPP+dN\nRkVFMWTIEN/F4gFLEMaUJyW4okdVSTiZWfgvfTfzx1Iy3G4jNLgaDWoF0aBmEG3q1yaybhB+Gc6B\nPy3h1IH/0L5AdscI6+ILbyM4GJo2dV59ukPTy53pJk1OLW/c2FnPXZ+836os+v5vEDQqwe9oSoUl\nCGPKizNc0ZORlcOhFqMK/aV/5LQEcDQ5nczswl08gdX8aFgriAa1gmhRrwZdm9YhKCcISQ8iK9k5\n8J84EkR8dBCHov3ZEQ0rYyErq+B2RCA83DnAn9cKLhxw6oCf/+Bfu/Y5/KVfwfrkqxpLEMb42MmM\nLHbHpXDeZw9Tw80VPUc+foBBGbUKLBaBeiHOQb9BrSDaNKxFvZAggtR14E8K4uSxIJKOBHFkfzVi\nooVtMbA8GpKSCscQGnrqQD90aMEDfu50o0Ze6MuvYH3yVY0lCGPKgKpy+EQ6u+KS2RWXzO64FGf6\nSDIxiWkA7A6KdXshTlO/eGZc1gXSgsg8EUTq8SCOHwrkULQf0dGwJRpiYuDwYdDTTiCqVTt1gO/U\nCf7wh8J/8Tdp4vTv+0QF65OvanySIETkbmASzv8Oc1T1eRGpCywEWgJ7gXGqetwX8RlTXGmZ2eyN\nT2HXkRR2u5LBrjhnOv9gb0igP+c3rEmfVvVoXDOEmjk1Sfm1KbWyogttc39iBDcMaVZoeb16pw7y\n3bu77+6pX/8M1+Mb44EyTxAiEomTHPoAGcDnIvIpMBlYrqpPisg0YBowtazjM6aogWJV5WhyhisB\npBQ4Kzhw/GSBv+KbhFWnSa0QLmjcjKD0EHISapIcW5PD+4LYsU9Yvh9OnnTW/S5yBvP/eCsBgacS\nSXaWP6uDHubZZwse/PMGeY3xIl+cQXQAflDVkwAi8i0wFhgNDHGtMx+IwhKEKWtuBoqzl9zJ8t8O\n86XfoLxuoRNpp0ZwA/39aBhck5o5YXTIaUrG0Zok7g8hdnsI3x+oVqjbp2FDaN4cOnaESy+FFi2c\n+fNrDKTaPwpe0eO/Kotr7Yoe4yOip//r9XaDIh2AJUB/IBVYDqwH/qyqtV3rCHA8d/6070/GOdsg\nPDy854IFC8oq9AKSk5Op6YOO26rWblm1nZal7E/K4arNk6mTfbTQ5wdz6jM87WUCUoPJTggh9XAt\nEvaHkRwbSvaJ6uQOHgQE5NCgQTrh4WmEh6fRsGE6DRum0aiR896wYTpBQe5LRrR57jkaL1uGX77L\nh3KqVSN25Eh2/PWvXtnv8sSX/8Z8wZf7O3To0J9UtVdR65V5ggAQkZuA24EUYAuQDkzMnxBE5Liq\n1jnbdnr16qXr16/3aqxn4qsBtarWrjfaTkzNZEtMIluiT7A5JpHN0YnsPpqCKuwO+hN+bgaKc1Tw\nn5lA3bqn/uJv3rzgdPPmzmWgxe7z794dNm4svLxbtwKDuZVVVRuk9uX+iohHCcIng9Sq+gbwBoCI\nPA4cBA6LSGNVjRWRxsARX8RmKpf45HS2xJxKBJujT7D/2Mm8z2v5BeOfFEbWjqbE7wjlwKgIWoQV\nrs2fFRJBUpKXr/axK3pMOeOrq5gaquoREWmOM/7QD2gFTACedL0v8UVspuI6ciKNTa4ksDkmkS3R\niXmXkALUD65B9bRQau9rxt6fw0jaH0pOahAtWsDAC2DAPSC170a33ocE5DuNyFQC+99NYNXp/TAG\n8N19EB+ISD0gE7hDVRNE5Elgkav7aR9Q/p6/Z8rWGa4mUlWiE1LZHH2CLblnBjEniEtKB5ybyCJC\nQ6ibU5eQlDD2bQxl17ow9qUHUK2a05Mz8VIYMAAuuMC5KijP7RthbSYMrnaqHPO3WZCwEQb65mcw\nxld81cVU6H81VY0HhvsgHFMeubmaKPPjO5kTtZM5Cb3yykX7+wnn169Ju7AGtM0K5dDWMH5ZGcrq\nQ84/7Tp1nCQw8WEnIfTuDTVqnKXdtWthYxoUGgqwO3tN1WN3UptyR1XJ+GIGQaeVnQjISePKhP+y\nrdXlBCSHEb8zjN/W1iJqvT+ZTr6gbVsYdZmTFAYMgHbtznHQ2MYBjMljCcKUG78fSmLJxmiW/hLD\nypPuHyRTP/so/76+C+A87at3b7jnHich9O8PDRqUcdDGVGKWIIxPHTh2kk9+jWHpxhi2HUrC308Y\n0Lo+qUcaE5IWW2j9o5kRPPOMc3bQo4dT+NMY4x2WIEyZi09OZ9mmWJZsjGH9PqfcVo/mtXlkVCcG\ntWrMojeDuHfpTP49pGDZCVV/Gl7zMPd28VXkxlQtliBMmUhOz+LLLYdY+ksMq3YcJTtHaRtekymX\ntGNU1yaE+tfg3/+GXs/BsWMwfshA/D9Lh8Gnyk5IOX64uzGVkSUI4zXpWdl8+3scS36JYflvh0nL\nzKFp7epMHnQeo7s1oX2jUI4dgxdecF6JiXD55fDQQ9Bn3ix4Iws22oNkjPEVSxCmVGXnKD/siWfp\nxhiWbYrlRFoWdUMCGderGaO6NqFH8zr4+QlxcfCPf8CLLzoPsBkzBh580BlXAOAWe5CMMb5mCcKU\nmKqyOfoESzZG88mvMRw+kU5IoD+XdGrEqG5NGNC6PgH+zrWmhw7BM8/AK69AaipcdZWTGDp3Pm2j\ndrmpMT5nCcKc3VmejbA7LpklG2NY+ksMe46mEOAvDGnXkNHdmjC8fTjVA/3zNhMdDU89Ba+95pwI\njB8PDzwAHTr4aseMMUWxBGHOzM3dzDlL7yJq2xGeO9yNTdGJiEC/VvW4ZdB5XBbZmLAaAQU2sX8/\nPPkkvPEGZGfD9dfD3/8Obdr4ZI+MMefAEoQ5s+Uz4bS7mf2yUmm7+Tmk4XweHNmBy7s0oVFY4Ueb\n7d4NTzwB8+c78zfcANOmQatWZRG4MaY0WIIwZ5ZYuOw1QFO/eJb+5UK3n23fDo8/Dm+/DdWqweTJ\ncP/9zrMSjDEViyUIc0aZNZsQkBxdaLmERRRatnUrPPooLFzolMC4806YMsV5hrIxpmIq7rOvTCW3\n/LfD/OPEGFIJKvhBQHVnoNrll1+cK5EiI2HpUrj3XtizB557zpKDMRWdJQhTgKoyZ+Vubn5zPb81\nuJT0S5+DsGYoAmHN4I+zocs4fvoJrrjCeRrmF1849zTs3etcqRQe7uu9MMaUButiMnkysnJ48ONN\nLFp/kBGdG/Gvq7pRPXAgtBhG4qWXUvuLL/h+byNmjYRly6B2bZgxA+66y3nugjGmcrEEYQA4lpLB\nrW//xI97jnHXsNb89aK2+Pm56m3PmkXYpk0s7T2L0Qdfol49eOwxuOMOCAvzbdzGGO+xBGHYcTiJ\nm+av59CJNF64phuju516Bmf63ljktbkEqnLxwbm89NBDXH9/I2ra85mNqfRsDKKKi/r9CGNfXsPJ\njGwWTO5XIDlER8OnfWeRk50DQHBgNrfHz7LkYEwVYQmiilJV5n23hxvnrSOibg2W/GUAPZqfGkhY\nvRou6xbLiCNzCcYpmicZGTB3rlNQyRhT6VmCqIIys3N48OPNzPhkK8Pah7P41v40rV0dAFWnmvbQ\noTA1YxZBATkFv5yd7ZTcNsZUejYGUcUknMzg9nc2sGZXPLcOPp/7L2mXNxidlga33Qbz5sHIkXD1\n/rX4bbKS28ZUVT45gxCRv4nIFhHZLCLviUiwiLQSkR9EZKeILBQRe9pwKdsdl8yYl9ewbu8xnrmq\nK9Mua5+XHA4cgIEDneTw8MPOTW/Vfv3ZOaVQJWrFirzp/KW4jTGVV5knCBFpCtwF9FLVSMAfuAb4\nJ/CcqrYGjgM3lXVsldl3O49yxUvfkZiaybuT+nFlz1PlMqKioGdP+P13+PhjeOQR8LPOR2OqvCIP\nAyJy+qNcSkM1oLqIVANqALHAMGCx6/P5wBVeaLdKevv7fVz/3x9pFBbMkjsG0LtlXcA5GXj+ebjo\nIqhXD378EUaP9nGwxphyQ1T17CuIrAKCgHnAO6qaWOJGRe4GHgNSgS+Bu4HvXWcPiEgz4DPXGcbp\n350MTAYIDw/vuWDBgpKGUyzJycnU9MH1nufSbnaO8t62DL7en0WXBv7c1jWI6tVyxxv8+Ne/2vH1\n1+FceGEc06ZtIyQku1TaLW0V4beuTG37SlXbZ1/u79ChQ39S1V5FrqiqRb6ANsATwE7gXeBiT753\nhm3VAb4BGgABwMfAdcDOfOs0AzYXta2ePXuqr6xYsaJct5twMkOve/17bTH1U531yRbNys7J+2zP\nHtVu3VRFVGfNUs3OLr12vaG8/9aVrW1fqWr77Mv9BdarB8drj65iUtUdIvIgsB6YDXQXEQH+oaof\nnkPiArgI2KOqcQAi8iEwAKgtItVUNQuIAArXmTYe2Xs0hZvmr2Nf/EmeHNuZa/qcehjD11/D1Vc7\nV6t++imMGOHDQI0x5ZonYxBdROQ54DeccYI/qmoH1/RzxWhzP9BPRGq4ksxwYCuwArjStc4EYEkx\ntl3lfb87nite/o74lAzeuqlvXnJQhaefhksugcaNYd06Sw7GmLPz5FqVfwMbgK6qeoeqbgBQ1Rjg\nwXNtUFV/wBmM3gBscsXwGjAVuEdEdgL1gDfOddtV3cJ1+7nu9R+oFxLIx7cPoP/59QBISYFrrnGe\n7DZ2LHz/vT0T2hhTNE+6mEYCqaqaDSAifkCwqp5U1beK06iqTgemn7Z4N9CnONur6rJzlCeW/cbr\nq/cwsE19XvxTD8KqBwCwaxeMGQNbtsA//+k85U3ExwEbYyoETxLE1zjjBsmu+Ro4Vx5d4K2gjOeS\n0jK5672fWfF7HBP6t+ChyztSzd85Mfz8cxg/3kkIn30Gf/iDj4M1xlQoniSIYFXNTQ6oarKI1PBi\nTMZDB46d5Kb569gVl8Ks0Z34c/+WgDPe8MQT8OCD0LkzfPQRnHeeb2M1xlQ8niSIFBHpkTv2ICI9\nce5fMD60bu8xbnnrJ7Kyc5h/Qx8ubFMfgKQkmDgRPvzQOXuYMwdCQnwbqzGmYvIkQfwVeF9EYgAB\nGgFXezUqU9ivi2D5TAYnHiTlh0a8l/R/hNW+mNcn9OL8Bs7NNtu3O8+J3r4dnn0W/vpXG28wxhRf\nkQlCVdeJSHugnWvR76qa6d2wTAG/LoJP7oLMVAQISY3liYA5ZA3pRIgrOXz6KVx7LQQGwpdfwrBh\nvg3ZGFPxeVqSrR3QEegBjBeR670Xkilk+UzILNirF6TphKx6nJwcp7jeH/8IrVvD+vWWHIwxpaPI\nMwgRmQ4MwUkQy4DLgNXAm16NzJySeNDtYk08yJgxTmnu66+H//wHqlcv49iMMZWWJ2cQV+Lc7XxI\nVW8AugJhXo3KFJAT2tTt8piUCJYtg3//23mOgyUHY0xp8iRBpKpqDpAlIqHAEZxieqaMfNn4Fk5q\nwecnncyszqw1D7N8OfzlLzYYbYwpfZ4kiPUiUhuYA/yEUyJjrVejMnkOHDvJ3VvasLDRFDSrBqrK\niYQQntgymwcXjmPQIF9HaIyprM46BuEqpveEqiYA/xGRz4FQVf21TKIzzPx0K/5+wqXDryaz43QC\ns9MI9s/igZ2DCI4o+vvGGFNcZz2DcNUNX5Zvfq8lh7LzzbbDfLX1MHcNb0PG3/5JTnYOAAH+2QQ/\nPcvH0RljKjtPupg2iEhvr0diCkjLzGbG0q2c3yCEayOCCf9sLsFkACAZGTB3Lhw65OMojTGVmScJ\noi+wVkR2icivIrJJROwswste/XY3+4+dZOboSHZc+xhoTsEVsrNhlp1FGGO8x5NSG5d4PQpTwP74\nk7wctZPLuzSmZfX6HP1xbd7ZQ56MDFizxjcBGmOqBE/OIPQML+Mlj3yyBX8/4cGRHZk6FfoG/szu\nXQqqRK1Y4ZRrVYWff/Z1qMaYSsyTM4j/4SQEAYKBVsDvQCcvxlVlfb31MMu3HeEfI9qzc1Mw77zj\nlO22ct3GmLLmSbG+zvnnRaQHcLvXIqrC0jKzmfHJFto0rMn1/VrRvy80awZ//7uvIzPGVEWenEEU\noKobRKSvN4Kp6l6O2sXB46m8N6kfc9/wY+NGWLgQatjjmYwxPuBJsb578s364VR0jfFaRFXU3qMp\n/OfbXYzu1oS2tetx+YMwdChcdZWvIzPGVFWenEHUyjedhTMm8YF3wqmaVJUZn2wh0N+Pf4zowEPT\nIDERZs+2GkvGGN/xZAzikbIIpCr7authon6P48GRHYjdHcyrrzoF+CIjfR2ZMaYqK/IyVxH5ylWs\nL3e+joh8UdwGRaSdiGzM9zohIn8Vkbqutna43usUt42KJDUjm0c+2Uq78Fpc378ld94JdevCjBm+\njswYU9V5ch9EA1exPgBU9TjQsLgNqurvqtpNVbsBPYGTwEfANGC5qrYBlrvmK72Xo3YSnZDKzNGd\nWLzIj9Wr4YknoE6VSI/GmPLMkwSRLSLNc2dEpAWld6PccGCXqu4DRgPzXcvnA1eUUhvl1p6jKbz6\n7W7GdG9Kp4b1mDIFevWCG2/0dWTGGOPZIPUDwGoR+RbnZrmBwORSav8a4D3XdLiqxrqmDwHhpdRG\nuaSqTF+6haBqfvx9RHsefRRiYuCDD8DP0yeFG2OMF4lT0buIlUTqA/1cs9+r6tESNywSiHO5bCdV\nPSwiCaqaf6zjuKoW6mgRkcm4ElR4eHjPBQsWlDSUYklOTqZmzZrF/v76Q1m8uDGdP7UPpIN/KDfe\n2Jvhw48wbdo2r7ZbXL5q15dtV8V99qWqts++3N+hQ4f+pKq9ilxRVc/6AsYAYfnmawNXFPU9D7Y7\nGvgy3/zvQGPXdGPg96K20bNnT/WVFStWFPu7KemZ2v/xr/WS577VzKxsHTFCtVYt1dhY77ZbEr5q\n15dtV8V99qWqts++3F9gvXpwnPakM2O6qibmSygJwPRzSFZnMp5T3UsAS4EJrukJwJJSaKNcevGb\nncQkpjFzdCSff+bHsmXOVUuNGvk6MmOMOcWTMQh3SeScS3TkJyIhwMXALfkWPwksEpGbgH3AuJK0\nUV7tiktmzqrdjO3RlC6N6xJ5MXToAHfe6evIjDGmIE8O9OtF5FngJdf8HcBPJWlUVVOAeqcti8e5\nqqnSUlVmLN1CcIA/f7+sA88+C7t2wZdfQkCAr6MzxpiCPOliuhPIABa6Xuk4ScKco882H2LVjqPc\n94d2pCcG8dhjMGYMXHyxryMzxpjCPCm1kUIVuWnNm1LSs5j16VY6Ng7l2r7N+fN1kJMDzz7r68iM\nMcY9T6q5NgDux3lAUHDuclUd5sW4Kp1/f7OT2MQ0XvxTd75b7ceCBTB9OrRs6evIjDHGPU+6mN4B\ntuE8Se4RYC+wzosxVTo7jyTx+qrdXNUzgq5N63LnndC8Odx/v68jM8aYM/MkQdRT1TeATFX9VlVv\nBOzswUPqumO6RqA/Uy9rz6uvwqZNTteSPQjIGFOeeXIVU6brPVZERuLc/VzXeyFVLv/bFMt3O+OZ\nNboTpAXx0EMwfDiMHevryIwx5uw8SRCPikgYcC/wbyAU+JtXo6okkl0D052ahPKnvi24/TY4ccIe\nBGSMqRg8uYrpU9dkIjDUu+FULrOX7+DwiXReua4nG38W5syBu++Gjh19HZkxxhStRHdEmzPbfjiJ\n/67ew9W9mtG9WR0GXAMNGtiDgIwxFYclCC9QVR5espmQoGrcf2k73n4b1q6F//4XwsJ8HZ0xxnjG\nnjzgBUt/ieH73ce4/9J2BOQEcf/90KcPTJhQ9HeNMaa88ORGuSDg/4CW+ddX1ZneC6viSkrL5LH/\n/UaXiDCu6d2caVPh0CFYssQeBGSMqVg86WJagjNA/RNOHSZzFi98vYO45HTmXN+LHduF5593HiHa\np4+vIzPGmHPjSYKIUNVLvR5JJfD7oSTmrtnLNb2b0yWiNpdd5twM98QTvo7MGGPOnSedHmtEpLPX\nI6ngVJWHlmymVnA17r+kHUuXwhdfwCOPQMOGvo7OGGPOnSdnEBcCE0VkD04XkwCqql28GlkFs2Rj\nDD/uOcYTYzsT7BfI3/7m3O/4Lc+WAAAgAElEQVRwhxVGN8ZUUJ4kiMu8HkUFdyItk8eW/UbXZrW5\nulczHn8c9uyB5cvtQUDGmIqryC4mVd0H1Ab+6HrVdi0zLs99tZ2jyenMGt2JgweFxx+HK6+EYVbS\n0BhTgRWZIETkbpyS3w1dr7dFxJ6g7LI15gTz1+zlT32cgen77nOWP/OMb+MyxpiS8qSL6Sagr+vJ\ncojIP4G1OIX7qrTcO6bDqgcw5ZJ2fPMNvP++MzDdooWvozPGmJLx5ComAbLzzWe7llV5H26IZv2+\n40y7rD01AwO56y7nCXFTpvg6MmOMKTlPziDmAj+IyEeu+SuAN7wXUsWQkqk88dlvdG9em6t6NuPF\nF2HLFvjoI6he3dfRGWNMyXlS7vtZEYnCudwV4AZV/bkkjYpIbeB1IBJQ4Ebgd2AhTkmPvcA4VT1e\nkna84tdFsHwmIxIP0lXroZ0e4ujRATz8MFx8MYwe7esAjTGmdJyxi0lEQl3vdXEO2G+7Xvtcy0ri\nBeBzVW0PdAV+A6YBy1W1DbDcNV++/LoIPrkLEg8gKBFylGarp7Fk1iJSUuxBQMaYyuVsZxDvApfj\n1GDSfMvFNX9ecRp0PZ1uEDARQFUzgAwRGQ0Mca02H4gCphanDa9ZPhMyUwsuy0zlYv+Z3H33ONq3\n901YxhjjDWdMEKp6ueu9VSm32QqIA+aKSFecBHQ3EK6qsa51DgHhpdxuySUedLu4edhBHr63jGMx\nxhgvE1U9+woiy1V1eFHLPG5QpBfwPTBAVX8QkReAE8Cdqlo733rHVbWOm+9PBiYDhIeH91ywYEFx\nwiiWfmtvJjg9rtDy4zmN+GXYq2USQ3JyMjVr1iyTtspDu75suyrusy9VtX325f4OHTr0J1XtVeSK\nqur2BQQDdYFfgDqu6bo4g8jbzvS9ol5AI2BvvvmBwP9wBqkbu5Y1Bn4vals9e/bUMvXLQtVHw1Wn\nh+a9Tj4YrtkbF5ZZCCtWrCiztspDu75suyrusy9VtX325f4C69WD4/XZ7oO4Baf7p73rPfe1BHjx\nnNJVwYR0CDggIu1ci4YDW4GlQO4z1ya42ilfuoyDP86GsGbkqLA3oRmxvWbj13WcryMzxphSd7Yx\niBeAF0TkTlUt7bum7wTeEZFAYDdwA84VVYtE5CZgH1A+j7pdxrEjYSCxg69m6bWLeGZ0I19HZIwx\nXuHJjXI5IlJbVRMARKQOMF5VXy5uo6q6EXDX/1WscY2ypAq//WkWI/mO3oGzgJd8HZIxxniFJ6U2\nJuUmBwB1bl6b5L2Qyrdv3onl4ui5+JND9QVznQdOG2NMJeRJgvAXOXX7l4j4A4HeC6l8G7J6FgH+\nOc5MdjbMmuXbgIwxxks8SRCfAwtFZLiIDAfecy2remJj8Z8/l2rZGc58RgbMtbMIY0zl5EmCmAqs\nAG5zvZYD93szqHJr1izIySm4zM4ijDGVlCfF+nKAV1yvqm3tWuesIb+MDFizxjfxGGOMF50xQYjI\nIlUdJyKbKFiLCQBV7eLVyMqjn08VsY2KimLIkCG+i8UYY7zsbGcQd7veLy+LQIwxxpQvZ7tRLtb1\nvq/swjHGGFNenK2LKQk3XUu5VDXUKxEZY4wpF852BlELQERmAbHAWzjPgrgWp5ieMcaYSsyTy1xH\nqerLqpqkqidU9RXAHqxpjDGVnCcJIkVErhURfxHxE5FrgRRvB2aMMca3PEkQf8KprHrY9brKtcwY\nY0wl5smNcnuxLiVjjKlyijyDEJG2IrJcRDa75ruIyIPeD80YY4wvedLFNAf4O5AJoKq/Atd4Myhj\njDG+50mCqKGqP562LMsbwRhjjCk/PEkQR0XkfFw3zYnIlTj3RRhjjKnEPHnk6B3Aa0B7EYkG9uDc\nLGeMMaYSO2uCEBE/oJeqXiQiIYCfqiaVTWjGGGN86awJQlVzROR+YJGq2s1xxpQREWHPnj2kpaX5\nOpQyExYWxm+//ebrMMpMWexvcHAwERERBAQEFOv7nnQxfS0i9wELyXcHtaoeK1aLxpgihYSEUKtW\nLVq2bEm+R8JXaklJSdSqVcvXYZQZb++vqhIfH8/Bgwdp1apVsbbhSYK42vV+R/62gfOK1aIxpkj+\n/v7Uq1evyiQHU/pEhHr16hEXF1fsbXhyJ3XxUs9ZiMheIAnIBrJUtZeI1MU5S2kJ7AXGqerx0m7b\nmIrCkoMpqZL+G/LkTupgEblHRD4UkQ9E5K8iElyiVh1DVbWbqvZyzU8DlqtqG2C5a94YY4yPeHIf\nxJtAJ+DfwIuu6be8EMtoYL5rej5whRfaMMZ46MYbb6Rhw4ZERkYWWH7s2DEuvvhi2rRpw8UXX8zx\n486Jvqpy11130bp1a7p06cKGDRsKbTMhIYGXX365RHGNGDGChISEEm3DeEZUz/jQOGcFka2q2rGo\nZefUqMge4DjOWMarqvqaiCSoam3X5wIcz50/7buTgckA4eHhPRcsWFDcMEokOTmZmjVrWruVuG1f\n7nNoaCht2rTxSdu5vvvuO0JCQrjlllv44Ycf8pY/9NBD1KlTh3vuuYdnn32WhIQEZs6cyRdffMGr\nr77KBx98wLp165g6dSorVqwosM19+/Yxbty4AtvLlZ2djb+/v9f3q7woq/3duXMniYmJBZYNHTr0\np3y9N2emqmd9AW8D/fLN9wXeLOp7RWyzqeu9IfALMAhIOG2d40Vtp2fPnuorK1assHYredu+3OcN\nGzbkTd99t+rgwaX7uvtuz+LYs2ePdurUqcCytm3bakxMjKqqxsTEaNu2bVVVdfLkyfruu++6XS/X\n1VdfrcHBwdq1a1e97777NCcnR++77z7t1KmTduzYURcsWKCqzm8/cOBAHTFihLZt21ZvueUWzc7O\nVlXVFi1aaFxcnKqqzp8/Xzt37qxdunTR6667TlVVFy1apJ06ddIuXbrowIEDPdtRHzhx4kSZtLN1\n69ZCy4D16sGx2pOrmHoCa0Rkv2u+OfC7iGxy8ot28WAbpyelaNf7ERH5COgDHBaRxqoaKyKNgSPn\nul1jjPcdPnyYxo2dpw43atSIw4cPAxAdHU2zZs3y1ouIiCA6OjpvXYAnn3ySzZs3s3HjRgA++OAD\nNm7cyC+//MLevXsZOnQogwYNAuDHH39k69attGjRgksvvZQPP/yQK6+8Mm9bW7Zs4dFHH2XNmjXU\nr1+fY8ecK+9zz2aaNm1qXVEl5EmCuLQ0G8x/R7Zr+g/ATGApMAF40vW+pDTbNaaiev55X0dwZiJS\noitlVq9ezfjx4/H396dhw4YMHjyYdevWERoaSp8+fTjvPOdq+vHjx7N69eoCCeKbb77hqquuon79\n+gDUrVsXgAEDBjBx4kTGjRvH2LFjS7B3xpPLXPeVcpvhwEeuf1TVgHdV9XMRWQcsEpGbgH04T7Ez\nxpQz4eHhxMbG0rhxY2JjY2nYsCEATZs25cCBA3nrHTx4kKZNmxa7ndMTj6eJ6D//+Q8//PAD//vf\n/+jZsyc//fQT9erVK3YcVZknVzGVKlXdrapdXa9OqvqYa3m8qg5X1TaqepHandrGlEujRo1i/nzn\ngsP58+czevTovOVvvvkmqsr3339PWFhYge4lgFq1apGUdKqc28CBA1m4cCHZ2dkcPXqUlStX0qdP\nH8DpYtqzZw85OTksXLiQCy+8sMC2hg0bxvvvv098fDxAXhfTrl276Nu3LzNnzqRBgwYFkpY5N2We\nIIwxFcP48ePp378/v//+OxEREbzxxhsATJs2ja+++oo2bdrw9ddfM22ac8vSiBEjOO+882jdujWT\nJk1yezlrvXr1GDBgAJGRkUyZMoUxY8bQpUsXunbtyuWXX85TTz1Fo0aNAOjduzd/+ctf6NChA61a\ntWLMmDEFttWpUyceeOABBg8eTNeuXbnnnnsAmDJlCp07dyYyMpILLriArl27evNnqtQ8GYMwxlRB\n7733ntvl9erVY/ny5YWWiwgvvfRSkdt99913C8w//fTTPP3004VqE4WGhvLpp58W+v7evXvzpidM\nmMCECRMKfP7hhx8WGYPxjJ1BGGOMccvOIIwx5c6QIUMYMmSIr8Oo8uwMwhhjjFuWIIwxxrhlCcIY\nY4xbliCMMca4ZQnCmMoiNhYGD4ZDh0plc1Wl3PfEiRNZvHjxWdeZN28eMTExpdamO+vXr+euu+46\n6zql8fudC0sQxlQWs2bB6tXOeymYOHEin3/+eaHlTz75JMOHD2fHjh0MHz6cJ598EoDPPvuMHTt2\nsGPHDl577TVuu+22Qt8tjQPcsmXLqF270JMAvKosEkSvXr2YPXv2WdexBGGMOXexsTB3LuTkOO+l\ncBYxaNCgvAJ4+S1ZsiTv5rQJEybw8ccf5y2//vrrERH69etHQkICsbGxBb47bdo0du3aRbdu3Zgy\nZQqqypQpU4iMjKRfv34sXLgQgKioKAYNGsTIkSNp164dt956Kzk5OQC0bNmSo0ePAvDmm2/m3Yn9\n5z//GYD333+fyMhIunbtmlcZNj9V5S9/+Qvt2rXjoosu4siRU4WjZ86cSe/evYmMjGTy5MmoKosX\nL2b9+vVce+21dOvWjdTUVLfrnW7ixInceuut9OrVi7Zt2+bd9JeWlsYNN9xAv3796N69e94zM6Ki\norj88ssBmDFjBjfeeCNDhgzhvPPOy0scp/9+sbGxDBo0iG7duhEZGcmqVas8+m/rMU9qgpfXlz0P\novK368u2y8vzIDxy222qgYGq4LzffnupxOHueRBhYWF50zk5OXnzI0eO1FWrVuV9NmzYMF23bt1Z\nt7d48WK96KKLNCsrS3fu3KnNmjXTmJgYXbFihQYFBemuXbs0KytLL7roIn3//fdV9dTzIDZv3qxt\n2rTJezZEfHy8qqpGRkbqwYMHVVX1+PHjhfbpgw8+yGszOjpaw8LC8raduw1V1euuu06XLl2qqqqD\nBw8usC9nWi+/CRMm6CWXXKLZ2dm6fft2bdq0qaampuozzzyjN9xwg544cUJ/++03bdasmaampuqK\nFSt05MiRqqo6ffp07d+/v6alpWlcXJzWrVtXMzIyCv1+zzzzjD766KOqqpqVleX2GRMleR6EnUEY\nU9Hlnj1kZDjzGRmldhZRFG+V+wbyyn37+/vnlfvOr6hy33PmzCE7O7tQmytXrsxrs0mTJgwbNizv\nsxUrVtC3b186d+7MN998w5YtW9zG7el648aNw8/PjzZt2nDeeeexbds2Vq9ezXXXXQdA+/btadGi\nBdu3by/03ZEjRxIUFET9+vVp2LBh3nM38uvduzdz585lxowZbNq0qUCpktJgCcKYim7WLKdrKb/s\n7FIbizhdbrlvoNyW+3700Uc5cOAAPXv2zKv2WpS0tDRuv/12Fi9ezKZNm5g0aRJpaWnFXq8k+wAQ\nFBSUN+3v709WVlahdQYNGsTKlStp2rQpEydO5M033/R4+56wBGFMRbd27amzh1wZGbBmjVeaq+jl\nvgcNGpTXZmxsbN4YQO5Bvn79+iQnJxe4sil/3Gdb73Tvv/8+OTk57Nq1i927d9OuXTsGDhzIO++8\nA8D27dvZv38/7dq1O/uPfobfb9++fYSHhzNp0iRuvvlmt1eOlYTVYjKmovv5Z69sdvz48URFRXH0\n6FEiIiJ45JFHuOmmm5g2bRrjxo3jjTfeoEWLFixatAhwLj9dtmwZrVu3pkaNGsydO7fQNvOX+77s\nsst46qmnWLt2LV27dkVV88p9b9u2La/c986dOxk6dOhZy337+/vTvXt35s2bx5QpU9ixYweqyvDh\nwwuV+x4zZgzffPMNHTt2pHnz5vTv3x+A2rVrM2nSJCIjI2nUqBG9e/fO+07ugHP16tVZu3btGdc7\nXfPmzenTpw8nTpzgP//5D8HBwdx+++3cdttt9OvXj8DAQObNm1fgbOFsTv/9IiMjefrppwkICKBm\nzZqlfgbh84HmkrxskLryt+vLtivUIHUlkH+ANf+AbUU1YcKEvMFvd9wNKHuDDVIbY4wpddbFZIwp\ndypDue958+b5OoQSszMIY4wxblmCMMYY45YlCGOMMW75LEGIiL+I/Cwin7rmW4nIDyKyU0QWikig\nr2Izxhjj2zOIu4Hf8s3/E3hOVVsDx4GbfBKVMQY4c7nvGTNm0LRpU7p160a3bt1YtmxZ3mdPPPEE\nrVu3pl27dnzxxRdut/v444+XKK6bb76ZrVu3lmgbxjM+SRAiEgGMBF53zQswDMi9JXE+cIUvYjPG\nOM5U7hvgb3/7Gxs3bmTjxo2MGDECgK1bt7JgwQK2bNnC559/zu233+62FlJJE8Trr79Ox44dS7QN\n4xlfXeb6PHA/kFtZqh6QoKq5xUYOAm6LuIjIZGAyODVhoqKivBvpGSQnJ/uk7arWri/b9uU+h4aG\n5pVU+OeXu9h2OLlUt98+vCZT/3D+Wdfp3r07+/btIycnp0B5h/T0dAICAgosA1i0aBFjxowhIyOD\n+vXr07Jly7yidrmmT59OamoqXbp0oX379rzxxhu8+OKLvPXWW6gqEyZM4I477mDfvn2MHTuWbt26\n8csvv9ChQwdeffVVatSowYgRI3j00Ufp0aMHX331FTNnziQ7O5t69erxySefsHr1aqZOnQo4tY8+\n++yzUi9iVxqys7ML/YbekJaWVux/x2WeIETkcuCIqv4kIkPO9fuq+hrwGkCvXr3UV9dKR0VF+eQ6\n7arWri/b9uU+//zzz3kHtYDAAPz9/Ut1+wGBAR4dNGvWrImfn1+BdYOCgpgzZw4LFy6kV69e/Otf\n/6JOnTocPXqUfv365a3bsmVLEhISCnz32Wef5bXXXuPXX38F4KeffuLdd99l3bp1nDhxgosuuohL\nLrmEOnXqsGPHDubOncuAAQO48cYbeeutt7jvvvvw9/cnJCSEtLQ07r77blauXEmrVq04duwYtWrV\n4uWXX+aVV15hwIABJCcnExwcTLVq5e+Wr6SkpDJJXMHBwXTv3r1Y3/XFrzYAGCUiI4BgIBR4Aagt\nItVcZxERQLQPYjOm3Jn+x06+DqGA2267jYceeggR4aGHHuLee+/lv//9b7G2tXr1asaMGUNISAg5\nOTmMHTuWVatWMWrUKJo1a8aAAQMAuO6665g9ezb33Xdf3ne///57Bg0aRKtWrYCC5b7vuecerr32\nWsaOHUtEREQJ97jqKvMxCFX9u6pGqGpL4BrgG1W9FlgBXOlabQKwpKxjM8YULTw8HH9/f/z8/Jg0\naRI//vgjUH7KfU+bNo3XX3+d1NRUBgwYwLZt24odQ1VXnu6DmArcIyI7ccYk3vBxPMYYN/I/RvSj\njz7Ku8pp1KhRLFiwgPT0dPbs2cOOHTvySnfnFxAQQGZmJuCU+/744485efIkKSkpfPTRRwwcOBCA\n/fv3s3btWgDefffdQuW++/Xrx8qVK9mzZw9QsNx3586dmTp1Kr1797YEUQI+7ZhT1SggyjW9Gyj8\nr8kY4xNnKvd9//33s3HjRkSEli1b8uqrrwJO+e1x48bRsWNHqlWrxksvveR27GTy5Ml06dKFHj16\n8M477zBx4kT69OlDTk4OkydPpnv37uzdu5d27drx0ksvceONN9KxY0duu+22Attp0KABr732GmPH\njiUnJ4eGDRvy1Vdf8fzzz7NixQr8/Pzo1KkTl112WZn8XpWSJyVfy+vLyn1X/nZ92baV+y5b+ctf\nu3sWdmVj5b6NMcZUWJYgjDHlTsuWLdm8ebOvw6jyLEEYY4xxyxKEMcYYtyxBGGOMccsShDHGGLcs\nQRhTGfy6CJ6LhBm1nfdfF5V4k1Wl3PeMGTN45plnzrrOxx9/7PUS4zExMVx55ZVFrlfS3+9cWIIw\npqL7dRF8chckHgDUef/krhInCSv3fUpZJIgmTZqwePHiItezBGGM8dzymZCZWnBZZqqzvAQGDRqU\nVwDPE0uWLOGaa64hKCiIVq1a0bp167w6TbmmTZtGamoq3bp149prrwWcCq+RkZH07duX559/HoC9\ne/fSvn17rr32Wjp06MCVV17JyZMnARgyZAjr168H4PPPP6dHjx507dqV4cOHA/Dtt9/mnd10797d\nbUntxx57jLZt23LhhRfy+++/5y2fM2cOvXv3pmvXrvzf//0fJ0+eZM2aNSxdupQpU6bQrVs3du3a\n5Xa9082YMYM///nP9O/fnzZt2jBnzhzAuTl5ypQp9O3bl86dO7Nw4cK8fc49W5s3bx5jx47l0ksv\npU2bNtx///1uf7+UlBRGjhxJ165diYyMzNtWqfHkbrry+rI7qSt/u75su8LcST09THV6qJtXWInj\ncHdH8/Tp07VFixbauXNnveGGG/TYsWOqqnrHHXfoW2+9lbfejTfeqO+//36hbYaEhORNr1+/XiMj\nIzU5OVljYmK0Y8eOumHDBt2zZ48Cunr1alVVveGGG/Tpp59WVdXBgwfrunXr9MiRIxoREaG7d+9W\nVdX4+HhVVb388svzvpeUlKSZmZkF2s9tMyUlRRMTE/X888/P2/bRo0fz1nvggQd09uzZqqo6YcKE\nAvtypvVO/526dOmiJ0+e1Li4OI2IiNDo6GhdvHixXnTRRXr8+HE9dOiQNmvWTGNiYgr81nPnztVW\nrVppQkKCpqamavPmzXX//v2Ffr/FixfrzTffnDefkJBQKA67k9qYqizsDOWsz7S8hG677TZ27drF\nxo0bady4Mffee2+xt5W/3HfNmjXzyn0Dhcp9r169usB3iyr3PXv2bBISEgo9C2LVqlWMGTOGGjVq\nEBoayqhRo/I+27x5MwMHDqRz58688847bNmyxW3cnq43evRoqlevTv369Rk6dCg//vgjq1evZvz4\n8fj7+xMeHs7gwYNZt25doe8OHz6csLAwgoOD6dixI/v27Su0TufOnfnqq6+YOnUqq1atIiwszG0c\nxWUJwpiKbvjDEFC94LKA6s5yL6jM5b4nTpzIiy++yKZNm5g+fTppaWklWq+4+wDOg5ly+fv7k5WV\nVWidtm3bsmHDBjp37syDDz7IzJkl61Y8nSUIYyq6LuPgj7MhrBkgzvsfZzvLvaCil/seNGgQH3/8\nMampqSQlJfHJJ5/kfZaUlETjxo3JzMzknXfeyVteq1atAmMZZ1rvdEuWLCEtLY34+HiioqLo3bs3\nAwcOZOHChWRnZxMXF8fKlSvd/k5nkv/3i4mJoUaNGlx33XVMmTKFDRs2eLwdT5S/5/AZY85dl3Gl\nnhAqa7nvHj16cPXVV9O1a1caNmxI79698z6bNWsWffv2pUGDBvTt2zcvKVxzzTVMmjSJ2bNns3jx\n4jOud7ouXbowdOhQjh49ykMPPUSTJk0YM2YMa9eu5YILLsDf35+nnnqKRo0asXfvXo/+u+T//a6/\n/nqmTJmCn58fAQEBvPLKKx5tw2OeDFSU15cNUlf+dn3ZdoUZpK4kKlu57+nTp+cNfrtj5b6NMcZU\nWNbFZIwpdypDue8ZM2b4OoQSszMIY8oppyfAmOIr6b8hSxDGlEPZ2dnEx8dbkjDFpqrEx8cTHBxc\n7G1YF5Mx5VBKSgpJSUnExcX5OpQyk5aWVqKDWUVTFvsbHBxMRETxb5i0BGFMOaSqeXcIVxVRUVF0\n797d12GUmYqwv2XexSQiwSLyo4j8IiJbROQR1/JWIvKDiOwUkYUiEljWsRljjDnFF2MQ6cAwVe0K\ndAMuFZF+wD+B51S1NXAcuMkHsRljjHEp8wThuk8j2TUb4HopMAzILYY+H7iirGMzxhhzik/GIETE\nH/gJaA28BOwCElQ1txrVQcBtlS8RmQxMds0mi8jv7tYrA/WBo9ZupW67Ku6zL1W1ffbl/rbwZCWf\nJAhVzQa6iUht4COg/Tl89zXgNW/F5ikRWa+qvazdytt2VdxnX6pq+1wR9ten90GoagKwAugP1BaR\n3IQVAUT7LDBjjDE+uYqpgevMARGpDlwM/IaTKHKf2D0BWFLWsRljjDnFF11MjYH5rnEIP2CRqn4q\nIluBBSLyKPAz8IYPYjsXvurmqmrt+rLtqrjPvlTV9rnc76/YrfzGGGPcsVpMxhhj3LIEYYwxxi1L\nEOdARP4rIkdEpMwL1YtIMxFZISJbXSVK7i6jdt2WRikrIuIvIj+LyKdl3O5eEdkkIhtFZH0Ztltb\nRBaLyDYR+U1E+pdV274iIn9z/dvaLCLviUilq9jn7tghInVF5CsR2eF6r+PLGN2xBHFu5gGX+qjt\nLOBeVe0I9APuEJGOZdDumUqjlJW7ca5y84WhqtqtjK9VfwH4XFXbA13x3b6XCRFpCtwF9FLVSMAf\nuMa3UXnFPAofO6YBy1W1DbDcNV+uWII4B6q6Ejjmo7ZjVXWDazoJ58Dh9m7zUm73TKVRvE5EIoCR\nwOtl0Z6viUgYMAjXFXyqmuG6V6iyqwZUd90HVQOI8XE8pe4Mx47ROGWFoJyWF7IEUQGJSEugO/BD\nGbXnLyIbgSPAV6paJu0CzwP3Azll1F5+CnwpIj+5yruUhVZAHDDX1a32uoiElFHbPqGq0cAzwH4g\nFkhU1S99G1WZCVfVWNf0ISDcl8G4YwmighGRmsAHwF9V9URZtKmq2araDecO9z4iEuntNkXkcuCI\nqv7k7bbO4EJV7QFchtOdN6gM2qwG9ABeUdXuQArlsNuhNLn63UfjJMcmQIiIXOfbqMqeOvcblLt7\nDixBVCAiEoCTHN5R1Q/Luv18pVHKYhxmADBKRPYCC4BhIvJ2GbQL5P1li6oewakX1qcMmj0IHMx3\nhrYYJ2FUZhcBe1Q1TlUzgQ+BC3wcU1k5LCKNAVzvR3wcTyGWICoIERGcvunfVPXZMmzXXWmUbd5u\nV1X/rqoRqtoSZ9DyG1Utk78sRSRERGrlTgN/ALx+5ZqqHgIOiEg716LhwFZvt+tj+4F+Iv/f3v2E\nSF2HcRx/f5AEhYiiECNE8CBSQaBB0KWMLloisaei8hJBFF2kY8yl0KgIDImCSFBqcU9bomJg0UaU\n/dlaJKSDxObNgxTLokySw9oAAAMYSURBVBs+Hb7PsD+378zutDkjO58XLPyY3/Ob73eHmXnmO7/5\nPY/W5nP8EVb4ifmGcUpZIbhByws5QfRA0sfAN8BmSX9I6mdToweBpymfpCfzb0cfxl0PnJb0C3CG\ncg6irz85HYB1wISkn4HvgGMRcaJPY78EHMnH+z7g9T6NOxC5WhoDfgSmKO9JN3wJil51eO/YBzwq\n6TfKSmrfIOdY41IbZmZW5RWEmZlVOUGYmVmVE4SZmVU5QZiZWZUThJmZVTlBmA2IpD2S7lzmfbQk\n7f2/5mTW5ARh1kUWkLte9lDKSyzZdZ6P2TWcIGxFk7Qxeyscyf4KY5LW5r5XJZ3JPgTv55W8SPpC\n0jvZB+JlSY9L+jYL6H0uaV3GtSQdkvSVpN8lPSHpjewjcSJLoyBpq6Qvs/DfSUnrJY0A2ygXxU1K\nWlOLq82ny//6nKTjecW72bI5Qdgw2AwcjIgtwJ/AC3n7uxFxf/YhWAM81jhmdURsi4i3gAnggSyg\n9wmlwmzbJmA7sAs4DJyOiHuBWWBnJokDwEhEbAU+BF6LiDHge+CpLIT4dy2uw3z+RdKLOf/dETH7\nXx4ks4W8XLVhMB0RX+f2YUqDmjeBhyW9QulBcBtwFvg040Ybx98FjOYn+tXA+ca+4xExJ2mK0uym\nXZJjCthISU73AKdygbKKUtZ6ocXiRivHtD0DTFOSw1yXOLOeOEHYMFhYTyayreVBSiezaUktoNnq\ncqaxfQB4OyLGJT0EtBr7LgNExFVJczFfu+Yq5fUl4GxELNY6dLG4mQ63Q0lG7XLs57vEmfXEXzHZ\nMNig+d7OT1K+Mmong4vZY2Oky/G3ABdy+9kucTXngDva40u6SdLdue8v4OYlxC3mJ+B5YHy5v4oy\na3KCsGFwjtL051fgVkpDnkvAB5Qy3icplWo7aQFHJf0AXOxl4Ii4Qkk++7M67CTz/Q4+At7Lbn2r\nusQtZZwJYC9wTNLtvczRrBNXc7UVTaU962d5ItrMeuAVhJmZVXkFYWZmVV5BmJlZlROEmZlVOUGY\nmVmVE4SZmVU5QZiZWdU/xRfoqRlfjesAAAAASUVORK5CYII=\n",
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x14de666a0>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "accuracy_scores_150topic={}\n",
+    "for i in [1,2,3,4,5,6,8,10]:\n",
+    "    accuracy, k = prediction_accuracy(test_author2doc, test_corpus_50_20, atmodel_150topics, k=i)\n",
+    "    accuracy_scores_150topic[k] = accuracy\n",
+    "    \n",
+    "plot_accuracy(scores1=accuracy_scores_100topic, label1=\"100 topics\", scores2=accuracy_scores_150topic, label2=\"150 topics\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "The 150-topic model is also slightly better, especially in the lower end of k. But we clearly see convergence. We try with 200 topic to be sure."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "05:43:01 INFO:Vocabulary consists of 3914 words.\n",
+      "05:43:01 INFO:using symmetric alpha at 0.005\n",
+      "05:43:01 INFO:using symmetric eta at 0.005\n",
+      "05:43:05 INFO:running online author-topic training, 200 topics, 50 authors, 15 passes over the supplied corpus of 2500 documents, updating model once every 2500 documents, evaluating perplexity every 0 documents, iterating 50x with a convergence threshold of 0.001000\n",
+      "05:43:05 INFO:PROGRESS: pass 0, at document #2500/2500\n",
+      "05:43:05 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "05:43:25 DEBUG:2/2500 documents converged within 50 iterations\n",
+      "05:43:25 DEBUG:updating topics\n",
+      "05:43:26 INFO:topic #198 (0.005): 0.006*\"plant\" + 0.006*\"analyst\" + 0.006*\"gm\" + 0.005*\"sale\" + 0.005*\"group\" + 0.005*\"service\" + 0.004*\"share\" + 0.004*\"internet\" + 0.004*\"plan\" + 0.004*\"uaw\"\n",
+      "05:43:26 INFO:topic #186 (0.005): 0.009*\"pound\" + 0.007*\"quarter\" + 0.007*\"analyst\" + 0.007*\"share\" + 0.006*\"group\" + 0.006*\"business\" + 0.005*\"million_pound\" + 0.005*\"software\" + 0.005*\"sale\" + 0.005*\"industry\"\n",
+      "05:43:26 INFO:topic #188 (0.005): 0.011*\"share\" + 0.010*\"analyst\" + 0.008*\"billion\" + 0.007*\"sale\" + 0.007*\"stock\" + 0.006*\"mci\" + 0.006*\"business\" + 0.005*\"british\" + 0.005*\"quarter\" + 0.005*\"deal\"\n",
+      "05:43:26 INFO:topic #162 (0.005): 0.012*\"analyst\" + 0.008*\"business\" + 0.007*\"quarter\" + 0.006*\"share\" + 0.006*\"industry\" + 0.006*\"sale\" + 0.005*\"base\" + 0.005*\"billion\" + 0.005*\"high\" + 0.005*\"price\"\n",
+      "05:43:26 INFO:topic #22 (0.005): 0.039*\"bank\" + 0.011*\"rate\" + 0.011*\"day\" + 0.011*\"cut\" + 0.010*\"analyst\" + 0.008*\"australia\" + 0.008*\"profit\" + 0.008*\"financial\" + 0.007*\"ltd\" + 0.007*\"merger\"\n",
+      "05:43:26 INFO:topic diff=65.500588, rho=1.000000\n",
+      "05:43:26 INFO:PROGRESS: pass 1, at document #2500/2500\n",
+      "05:43:26 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "05:43:36 DEBUG:2494/2500 documents converged within 50 iterations\n",
+      "05:43:36 DEBUG:updating topics\n",
+      "05:43:37 INFO:topic #77 (0.005): 0.013*\"internet\" + 0.011*\"computer\" + 0.009*\"business\" + 0.009*\"quarter\" + 0.009*\"service\" + 0.008*\"revenue\" + 0.007*\"analyst\" + 0.007*\"cost\" + 0.007*\"industry\" + 0.006*\"compaq\"\n",
+      "05:43:37 INFO:topic #25 (0.005): 0.010*\"share\" + 0.007*\"analyst\" + 0.007*\"service\" + 0.007*\"business\" + 0.006*\"growth\" + 0.006*\"mci\" + 0.006*\"billion\" + 0.006*\"long\" + 0.005*\"distance\" + 0.005*\"stock\"\n",
+      "05:43:37 INFO:topic #133 (0.005): 0.011*\"group\" + 0.011*\"share\" + 0.010*\"pound\" + 0.009*\"billion\" + 0.007*\"profit\" + 0.007*\"business\" + 0.006*\"sale\" + 0.005*\"good\" + 0.005*\"bank\" + 0.005*\"analyst\"\n",
+      "05:43:37 INFO:topic #180 (0.005): 0.011*\"billion\" + 0.006*\"venture\" + 0.006*\"quarter\" + 0.005*\"investment\" + 0.005*\"industry\" + 0.005*\"analyst\" + 0.004*\"price\" + 0.003*\"group\" + 0.003*\"high\" + 0.003*\"rise\"\n",
+      "05:43:37 INFO:topic #1 (0.005): 0.018*\"japan\" + 0.014*\"japanese\" + 0.013*\"billion\" + 0.011*\"yen\" + 0.011*\"stock\" + 0.011*\"bank\" + 0.010*\"life\" + 0.010*\"financial\" + 0.010*\"big\" + 0.008*\"profit\"\n",
+      "05:43:37 INFO:topic diff=17.080447, rho=0.577350\n",
+      "05:43:37 INFO:PROGRESS: pass 2, at document #2500/2500\n",
+      "05:43:37 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "05:43:46 DEBUG:2499/2500 documents converged within 50 iterations\n",
+      "05:43:46 DEBUG:updating topics\n",
+      "05:43:47 INFO:topic #92 (0.005): 0.013*\"analyst\" + 0.011*\"share\" + 0.007*\"sale\" + 0.006*\"profit\" + 0.005*\"pound\" + 0.004*\"high\" + 0.004*\"revenue\" + 0.004*\"quarter\" + 0.004*\"billion\" + 0.004*\"cent\"\n",
+      "05:43:47 INFO:topic #117 (0.005): 0.015*\"access\" + 0.012*\"local\" + 0.011*\"internet\" + 0.011*\"fee\" + 0.010*\"distance\" + 0.010*\"long\" + 0.008*\"long_distance\" + 0.008*\"service\" + 0.007*\"issue\" + 0.006*\"provider\"\n",
+      "05:43:47 INFO:topic #81 (0.005): 0.011*\"pound\" + 0.010*\"profit\" + 0.009*\"share\" + 0.008*\"sale\" + 0.007*\"million_pound\" + 0.006*\"analyst\" + 0.006*\"business\" + 0.006*\"rise\" + 0.005*\"group\" + 0.005*\"fall\"\n",
+      "05:43:47 INFO:topic #97 (0.005): 0.025*\"internet\" + 0.018*\"bill\" + 0.014*\"administration\" + 0.014*\"product\" + 0.012*\"key\" + 0.011*\"policy\" + 0.011*\"export\" + 0.010*\"law\" + 0.008*\"access\" + 0.008*\"bank\"\n",
+      "05:43:47 INFO:topic #24 (0.005): 0.005*\"crop\" + 0.005*\"price\" + 0.005*\"share\" + 0.004*\"tonne\" + 0.004*\"analyst\" + 0.004*\"exporter\" + 0.004*\"cocoa\" + 0.003*\"ivory_coast\" + 0.003*\"government\" + 0.003*\"reuters\"\n",
+      "05:43:47 INFO:topic diff=14.773285, rho=0.500000\n",
+      "05:43:47 INFO:PROGRESS: pass 3, at document #2500/2500\n",
+      "05:43:47 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "05:43:56 DEBUG:2499/2500 documents converged within 50 iterations\n",
+      "05:43:56 DEBUG:updating topics\n",
+      "05:43:56 INFO:topic #16 (0.005): 0.003*\"group\" + 0.003*\"billion\" + 0.002*\"gm\" + 0.002*\"hong_kong\" + 0.002*\"pound\" + 0.002*\"kong\" + 0.002*\"china\" + 0.002*\"bid\" + 0.002*\"analyst\" + 0.002*\"hong\"\n",
+      "05:43:56 INFO:topic #133 (0.005): 0.012*\"group\" + 0.011*\"pound\" + 0.010*\"share\" + 0.008*\"billion\" + 0.007*\"business\" + 0.006*\"profit\" + 0.005*\"good\" + 0.005*\"sale\" + 0.005*\"add\" + 0.005*\"cost\"\n",
+      "05:43:56 INFO:topic #23 (0.005): 0.017*\"boeing\" + 0.010*\"billion\" + 0.009*\"analyst\" + 0.006*\"share\" + 0.006*\"microsoft\" + 0.006*\"industry\" + 0.005*\"quarter\" + 0.005*\"jet\" + 0.005*\"windows\" + 0.005*\"mcdonnell\"\n",
+      "05:43:56 INFO:topic #156 (0.005): 0.005*\"analyst\" + 0.004*\"bank\" + 0.003*\"share\" + 0.003*\"service\" + 0.003*\"internet\" + 0.002*\"china\" + 0.002*\"plan\" + 0.002*\"profit\" + 0.002*\"billion\" + 0.002*\"cost\"\n",
+      "05:43:56 INFO:topic #131 (0.005): 0.024*\"analyst\" + 0.017*\"share\" + 0.013*\"price\" + 0.011*\"business\" + 0.011*\"penny\" + 0.009*\"bid\" + 0.007*\"electric\" + 0.006*\"offer\" + 0.006*\"add\" + 0.006*\"northern\"\n",
+      "05:43:56 INFO:topic diff=12.542799, rho=0.447214\n",
+      "05:43:56 INFO:PROGRESS: pass 4, at document #2500/2500\n",
+      "05:43:56 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "05:44:05 DEBUG:2500/2500 documents converged within 50 iterations\n",
+      "05:44:05 DEBUG:updating topics\n",
+      "05:44:05 INFO:topic #92 (0.005): 0.009*\"analyst\" + 0.008*\"share\" + 0.005*\"sale\" + 0.004*\"profit\" + 0.003*\"pound\" + 0.003*\"high\" + 0.003*\"revenue\" + 0.003*\"quarter\" + 0.003*\"billion\" + 0.003*\"cent\"\n",
+      "05:44:05 INFO:topic #86 (0.005): 0.029*\"cargo\" + 0.021*\"kong\" + 0.020*\"hong\" + 0.020*\"hong_kong\" + 0.016*\"air\" + 0.015*\"Hong Kong\" + 0.015*\"airline\" + 0.009*\"service\" + 0.009*\"route\" + 0.009*\"airport\"\n",
+      "05:44:05 INFO:topic #80 (0.005): 0.017*\"analyst\" + 0.014*\"microsoft\" + 0.013*\"quarter\" + 0.010*\"computer\" + 0.010*\"business\" + 0.009*\"windows\" + 0.008*\"revenue\" + 0.008*\"internet\" + 0.007*\"system\" + 0.007*\"sale\"\n",
+      "05:44:05 INFO:topic #23 (0.005): 0.015*\"boeing\" + 0.009*\"billion\" + 0.008*\"analyst\" + 0.006*\"share\" + 0.005*\"microsoft\" + 0.005*\"industry\" + 0.005*\"quarter\" + 0.005*\"jet\" + 0.004*\"windows\" + 0.004*\"mcdonnell\"\n",
+      "05:44:05 INFO:topic #177 (0.005): 0.011*\"investment\" + 0.010*\"pound\" + 0.010*\"group\" + 0.008*\"cable\" + 0.008*\"british\" + 0.007*\"fleming\" + 0.007*\"management\" + 0.006*\"fund\" + 0.006*\"share\" + 0.006*\"merger\"\n",
+      "05:44:05 INFO:topic diff=10.561281, rho=0.408248\n",
+      "05:44:05 INFO:PROGRESS: pass 5, at document #2500/2500\n",
+      "05:44:05 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "05:44:14 DEBUG:2500/2500 documents converged within 50 iterations\n",
+      "05:44:14 DEBUG:updating topics\n",
+      "05:44:15 INFO:topic #61 (0.005): 0.038*\"boeing\" + 0.017*\"billion\" + 0.016*\"jet\" + 0.013*\"analyst\" + 0.012*\"mcdonnell\" + 0.011*\"microsoft\" + 0.010*\"airbus\" + 0.010*\"order\" + 0.010*\"douglas\" + 0.009*\"share\"\n",
+      "05:44:15 INFO:topic #73 (0.005): 0.001*\"bank\" + 0.001*\"china\" + 0.001*\"group\" + 0.001*\"big\" + 0.001*\"analyst\" + 0.001*\"sale\" + 0.001*\"shanghai\" + 0.001*\"deal\" + 0.001*\"gm\" + 0.001*\"pound\"\n",
+      "05:44:15 INFO:topic #147 (0.005): 0.012*\"czech\" + 0.011*\"crown\" + 0.010*\"week\" + 0.009*\"analyst\" + 0.009*\"point\" + 0.008*\"investor\" + 0.007*\"round\" + 0.007*\"prague\" + 0.007*\"billion\" + 0.006*\"second\"\n",
+      "05:44:15 INFO:topic #50 (0.005): 0.006*\"british\" + 0.006*\"telecom\" + 0.006*\"deal\" + 0.005*\"analyst\" + 0.005*\"drug\" + 0.004*\"share\" + 0.004*\"mci\" + 0.004*\"billion\" + 0.004*\"group\" + 0.003*\"sale\"\n",
+      "05:44:15 INFO:topic #99 (0.005): 0.003*\"stock\" + 0.002*\"business\" + 0.002*\"share\" + 0.002*\"analyst\" + 0.002*\"end\" + 0.002*\"day\" + 0.002*\"sale\" + 0.002*\"world\" + 0.002*\"billion\" + 0.001*\"quarter\"\n",
+      "05:44:15 INFO:topic diff=8.863923, rho=0.377964\n",
+      "05:44:15 INFO:PROGRESS: pass 6, at document #2500/2500\n",
+      "05:44:15 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "05:44:23 DEBUG:2500/2500 documents converged within 50 iterations\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "05:44:23 DEBUG:updating topics\n",
+      "05:44:24 INFO:topic #70 (0.005): 0.011*\"stock\" + 0.010*\"shanghai\" + 0.008*\"share\" + 0.008*\"exchange\" + 0.007*\"trading\" + 0.007*\"china\" + 0.007*\"bank\" + 0.006*\"future\" + 0.006*\"beijing\" + 0.005*\"index\"\n",
+      "05:44:24 INFO:topic #177 (0.005): 0.011*\"investment\" + 0.010*\"pound\" + 0.010*\"group\" + 0.008*\"cable\" + 0.008*\"british\" + 0.007*\"fleming\" + 0.007*\"management\" + 0.007*\"share\" + 0.006*\"fund\" + 0.006*\"merger\"\n",
+      "05:44:24 INFO:topic #37 (0.005): 0.015*\"bank\" + 0.012*\"czech\" + 0.008*\"crown\" + 0.006*\"prague\" + 0.005*\"foreign\" + 0.005*\"billion\" + 0.004*\"state\" + 0.004*\"deficit\" + 0.004*\"communist\" + 0.004*\"central\"\n",
+      "05:44:24 INFO:topic #56 (0.005): 0.032*\"kong\" + 0.031*\"hong\" + 0.031*\"hong_kong\" + 0.022*\"Hong Kong\" + 0.016*\"china\" + 0.007*\"fund\" + 0.007*\"Hong Kong's\" + 0.006*\"chinese\" + 0.005*\"tung\" + 0.005*\"british\"\n",
+      "05:44:24 INFO:topic #32 (0.005): 0.004*\"china\" + 0.003*\"beijing\" + 0.002*\"taiwan\" + 0.002*\"bre\" + 0.002*\"bre_x\" + 0.002*\"share\" + 0.002*\"x\" + 0.002*\"chinese\" + 0.002*\"analyst\" + 0.002*\"party\"\n",
+      "05:44:24 INFO:topic diff=7.433677, rho=0.353553\n",
+      "05:44:24 INFO:PROGRESS: pass 7, at document #2500/2500\n",
+      "05:44:24 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "05:44:32 DEBUG:2500/2500 documents converged within 50 iterations\n",
+      "05:44:32 DEBUG:updating topics\n",
+      "05:44:33 INFO:topic #194 (0.005): 0.024*\"cocoa\" + 0.020*\"tonne\" + 0.019*\"exporter\" + 0.012*\"ivory\" + 0.012*\"ivory_coast\" + 0.012*\"coast\" + 0.011*\"crop\" + 0.011*\"price\" + 0.010*\"buyer\" + 0.009*\"export\"\n",
+      "05:44:33 INFO:topic #116 (0.005): 0.004*\"x\" + 0.003*\"analyst\" + 0.003*\"bre\" + 0.003*\"Bre-X\" + 0.002*\"bre_x\" + 0.002*\"share\" + 0.002*\"government\" + 0.002*\"bank\" + 0.002*\"billion\" + 0.002*\"sale\"\n",
+      "05:44:33 INFO:topic #174 (0.005): 0.001*\"quarter\" + 0.001*\"venture\" + 0.001*\"china\" + 0.001*\"billion\" + 0.001*\"beijing\" + 0.000*\"investment\" + 0.000*\"share\" + 0.000*\"level\" + 0.000*\"chinese\" + 0.000*\"official\"\n",
+      "05:44:33 INFO:topic #169 (0.005): 0.001*\"china\" + 0.001*\"tell\" + 0.001*\"service\" + 0.001*\"hong_kong\" + 0.001*\"billion\" + 0.001*\"share\" + 0.001*\"beijing\" + 0.001*\"group\" + 0.001*\"kong\" + 0.001*\"analyst\"\n",
+      "05:44:33 INFO:topic #88 (0.005): 0.024*\"franc\" + 0.023*\"french\" + 0.022*\"air\" + 0.021*\"france\" + 0.017*\"thomson\" + 0.014*\"billion\" + 0.011*\"group\" + 0.010*\"telecom\" + 0.010*\"billion_franc\" + 0.009*\"government\"\n",
+      "05:44:33 INFO:topic diff=6.234229, rho=0.333333\n",
+      "05:44:33 INFO:PROGRESS: pass 8, at document #2500/2500\n",
+      "05:44:33 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "05:44:41 DEBUG:2500/2500 documents converged within 50 iterations\n",
+      "05:44:41 DEBUG:updating topics\n",
+      "05:44:42 INFO:topic #149 (0.005): 0.010*\"china\" + 0.005*\"chinese\" + 0.005*\"official\" + 0.004*\"beijing\" + 0.004*\"metre\" + 0.003*\"world\" + 0.003*\"trade\" + 0.003*\"foreign\" + 0.003*\"united_states\" + 0.003*\"united\"\n",
+      "05:44:42 INFO:topic #62 (0.005): 0.002*\"property\" + 0.002*\"increase\" + 0.002*\"month\" + 0.002*\"klaus\" + 0.001*\"social\" + 0.001*\"commission\" + 0.001*\"pound\" + 0.001*\"analyst\" + 0.001*\"large\" + 0.001*\"party\"\n",
+      "05:44:42 INFO:topic #38 (0.005): 0.016*\"analyst\" + 0.014*\"australian\" + 0.014*\"ltd\" + 0.013*\"share\" + 0.012*\"australia\" + 0.011*\"profit\" + 0.011*\"sydney\" + 0.009*\"news\" + 0.009*\"group\" + 0.009*\"corp\"\n",
+      "05:44:42 INFO:topic #155 (0.005): 0.002*\"china\" + 0.001*\"fund\" + 0.001*\"stock\" + 0.001*\"billion\" + 0.001*\"economic\" + 0.001*\"hong\" + 0.001*\"bank\" + 0.001*\"group\" + 0.001*\"kong\" + 0.001*\"canada\"\n",
+      "05:44:42 INFO:topic #130 (0.005): 0.019*\"mci\" + 0.012*\"analyst\" + 0.011*\"service\" + 0.011*\"share\" + 0.011*\"long\" + 0.010*\"billion\" + 0.009*\"long_distance\" + 0.009*\"distance\" + 0.009*\"corp\" + 0.008*\"deal\"\n",
+      "05:44:42 INFO:topic diff=5.231049, rho=0.316228\n",
+      "05:44:42 INFO:PROGRESS: pass 9, at document #2500/2500\n",
+      "05:44:42 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "05:44:50 DEBUG:2500/2500 documents converged within 50 iterations\n",
+      "05:44:51 DEBUG:updating topics\n",
+      "05:44:51 INFO:topic #166 (0.005): 0.001*\"oil\" + 0.001*\"russian\" + 0.001*\"russia\" + 0.001*\"internet\" + 0.001*\"export\" + 0.001*\"world\" + 0.001*\"service\" + 0.001*\"tonne\" + 0.001*\"analyst\" + 0.001*\"output\"\n",
+      "05:44:51 INFO:topic #187 (0.005): 0.033*\"china\" + 0.011*\"beijing\" + 0.011*\"official\" + 0.010*\"chinese\" + 0.008*\"state\" + 0.008*\"foreign\" + 0.008*\"trade\" + 0.006*\"united\" + 0.005*\"united_states\" + 0.005*\"states\"\n",
+      "05:44:51 INFO:topic #139 (0.005): 0.013*\"drug\" + 0.012*\"group\" + 0.010*\"pound\" + 0.010*\"sale\" + 0.009*\"plc\" + 0.009*\"british\" + 0.009*\"share\" + 0.008*\"product\" + 0.008*\"profit\" + 0.008*\"analyst\"\n",
+      "05:44:51 INFO:topic #43 (0.005): 0.001*\"tonne\" + 0.001*\"cocoa\" + 0.001*\"china\" + 0.000*\"share\" + 0.000*\"bank\" + 0.000*\"government\" + 0.000*\"exporter\" + 0.000*\"stock\" + 0.000*\"plan\" + 0.000*\"close\"\n",
+      "05:44:51 INFO:topic #71 (0.005): 0.025*\"fcc\" + 0.018*\"phone\" + 0.016*\"carrier\" + 0.015*\"local\" + 0.012*\"rule\" + 0.011*\"long\" + 0.011*\"service\" + 0.011*\"distance\" + 0.010*\"tv\" + 0.010*\"long_distance\"\n",
+      "05:44:51 INFO:topic diff=4.391602, rho=0.301511\n",
+      "05:44:51 INFO:PROGRESS: pass 10, at document #2500/2500\n",
+      "05:44:51 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "05:44:59 DEBUG:2500/2500 documents converged within 50 iterations\n",
+      "05:44:59 DEBUG:updating topics\n",
+      "05:45:00 INFO:topic #156 (0.005): 0.001*\"analyst\" + 0.001*\"bank\" + 0.001*\"share\" + 0.001*\"service\" + 0.000*\"internet\" + 0.000*\"china\" + 0.000*\"plan\" + 0.000*\"profit\" + 0.000*\"billion\" + 0.000*\"cost\"\n",
+      "05:45:00 INFO:topic #63 (0.005): 0.037*\"oil\" + 0.029*\"russia\" + 0.026*\"russian\" + 0.016*\"tonne\" + 0.016*\"aluminium\" + 0.015*\"smelter\" + 0.014*\"output\" + 0.012*\"world\" + 0.012*\"export\" + 0.010*\"western\"\n",
+      "05:45:00 INFO:topic #83 (0.005): 0.001*\"profit\" + 0.001*\"bank\" + 0.001*\"australian\" + 0.001*\"analyst\" + 0.001*\"billion\" + 0.001*\"australia\" + 0.001*\"share\" + 0.001*\"tell\" + 0.001*\"ltd\" + 0.001*\"beijing\"\n",
+      "05:45:00 INFO:topic #144 (0.005): 0.001*\"computer\" + 0.001*\"software\" + 0.001*\"site\" + 0.001*\"quarter\" + 0.001*\"technology\" + 0.001*\"internet\" + 0.001*\"industry\" + 0.001*\"web\" + 0.001*\"product\" + 0.001*\"high\"\n",
+      "05:45:00 INFO:topic #84 (0.005): 0.015*\"klaus\" + 0.014*\"czech\" + 0.014*\"bank\" + 0.011*\"billion\" + 0.011*\"crown\" + 0.009*\"state\" + 0.009*\"price\" + 0.008*\"minister\" + 0.007*\"tell\" + 0.007*\"low\"\n",
+      "05:45:00 INFO:topic diff=3.689287, rho=0.288675\n",
+      "05:45:00 INFO:PROGRESS: pass 11, at document #2500/2500\n",
+      "05:45:00 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "05:45:08 DEBUG:2500/2500 documents converged within 50 iterations\n",
+      "05:45:08 DEBUG:updating topics\n",
+      "05:45:09 INFO:topic #50 (0.005): 0.001*\"british\" + 0.001*\"telecom\" + 0.001*\"deal\" + 0.001*\"analyst\" + 0.001*\"drug\" + 0.001*\"share\" + 0.001*\"mci\" + 0.001*\"billion\" + 0.001*\"group\" + 0.001*\"sale\"\n",
+      "05:45:09 INFO:topic #194 (0.005): 0.024*\"cocoa\" + 0.020*\"tonne\" + 0.020*\"exporter\" + 0.012*\"ivory\" + 0.012*\"coast\" + 0.012*\"ivory_coast\" + 0.011*\"crop\" + 0.011*\"price\" + 0.010*\"buyer\" + 0.009*\"export\"\n",
+      "05:45:09 INFO:topic #138 (0.005): 0.001*\"china\" + 0.000*\"beijing\" + 0.000*\"share\" + 0.000*\"news\" + 0.000*\"states\" + 0.000*\"chinese\" + 0.000*\"analyst\" + 0.000*\"month\" + 0.000*\"long\" + 0.000*\"the United States\"\n",
+      "05:45:09 INFO:topic #100 (0.005): 0.001*\"chinese\" + 0.001*\"china\" + 0.001*\"beijing\" + 0.000*\"hong\" + 0.000*\"hong_kong\" + 0.000*\"official\" + 0.000*\"tibet\" + 0.000*\"magazine\" + 0.000*\"kong\" + 0.000*\"lama\"\n",
+      "05:45:09 INFO:topic #94 (0.005): 0.000*\"share\" + 0.000*\"stock\" + 0.000*\"election\" + 0.000*\"analyst\" + 0.000*\"low\" + 0.000*\"bank\" + 0.000*\"havel\" + 0.000*\"government\" + 0.000*\"high\" + 0.000*\"large\"\n",
+      "05:45:09 INFO:topic diff=3.102101, rho=0.277350\n",
+      "05:45:09 INFO:PROGRESS: pass 12, at document #2500/2500\n",
+      "05:45:09 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "05:45:17 DEBUG:2500/2500 documents converged within 50 iterations\n",
+      "05:45:17 DEBUG:updating topics\n",
+      "05:45:18 INFO:topic #122 (0.005): 0.000*\"share\" + 0.000*\"analyst\" + 0.000*\"plant\" + 0.000*\"gm\" + 0.000*\"industry\" + 0.000*\"quarter\" + 0.000*\"service\" + 0.000*\"law\" + 0.000*\"month\" + 0.000*\"large\"\n",
+      "05:45:18 INFO:topic #20 (0.005): 0.029*\"gold\" + 0.019*\"bre\" + 0.019*\"x\" + 0.018*\"bre_x\" + 0.014*\"price\" + 0.014*\"analyst\" + 0.011*\"Bre-X\" + 0.010*\"busang\" + 0.010*\"barrick\" + 0.010*\"toronto\"\n",
+      "05:45:18 INFO:topic #107 (0.005): 0.031*\"russia\" + 0.027*\"oil\" + 0.016*\"russian\" + 0.014*\"export\" + 0.012*\"output\" + 0.010*\"moscow\" + 0.009*\"tonne\" + 0.009*\"domestic\" + 0.009*\"world\" + 0.008*\"western\"\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "05:45:18 INFO:topic #130 (0.005): 0.019*\"mci\" + 0.012*\"analyst\" + 0.011*\"service\" + 0.011*\"share\" + 0.010*\"long\" + 0.010*\"billion\" + 0.009*\"long_distance\" + 0.009*\"distance\" + 0.009*\"corp\" + 0.008*\"deal\"\n",
+      "05:45:18 INFO:topic #151 (0.005): 0.012*\"billion\" + 0.008*\"sale\" + 0.007*\"computer\" + 0.007*\"industry\" + 0.006*\"good\" + 0.006*\"analyst\" + 0.006*\"product\" + 0.006*\"quarter\" + 0.005*\"forecast\" + 0.005*\"internet\"\n",
+      "05:45:18 INFO:topic diff=2.611657, rho=0.267261\n",
+      "05:45:18 INFO:PROGRESS: pass 13, at document #2500/2500\n",
+      "05:45:18 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "05:45:28 DEBUG:2500/2500 documents converged within 50 iterations\n",
+      "05:45:28 DEBUG:updating topics\n",
+      "05:45:28 INFO:topic #74 (0.005): 0.036*\"china\" + 0.029*\"tonne\" + 0.021*\"chinese\" + 0.021*\"trader\" + 0.018*\"price\" + 0.014*\"import\" + 0.013*\"source\" + 0.011*\"copper\" + 0.010*\"official\" + 0.010*\"million_tonne\"\n",
+      "05:45:28 INFO:topic #138 (0.005): 0.000*\"china\" + 0.000*\"beijing\" + 0.000*\"share\" + 0.000*\"news\" + 0.000*\"states\" + 0.000*\"chinese\" + 0.000*\"analyst\" + 0.000*\"month\" + 0.000*\"long\" + 0.000*\"the United States\"\n",
+      "05:45:28 INFO:topic #60 (0.005): 0.000*\"half\" + 0.000*\"financial\" + 0.000*\"northern\" + 0.000*\"policy\" + 0.000*\"official\" + 0.000*\"group\" + 0.000*\"product\" + 0.000*\"draft\" + 0.000*\"administration\" + 0.000*\"stock\"\n",
+      "05:45:28 INFO:topic #42 (0.005): 0.000*\"russia\" + 0.000*\"russian\" + 0.000*\"industry\" + 0.000*\"technology\" + 0.000*\"oil\" + 0.000*\"world\" + 0.000*\"export\" + 0.000*\"price\" + 0.000*\"diamond\" + 0.000*\"analyst\"\n",
+      "05:45:28 INFO:topic #36 (0.005): 0.026*\"bid\" + 0.025*\"penny\" + 0.016*\"analyst\" + 0.015*\"electric\" + 0.015*\"share\" + 0.014*\"electricity\" + 0.013*\"pound\" + 0.013*\"offer\" + 0.011*\"northern\" + 0.011*\"british\"\n",
+      "05:45:28 INFO:topic diff=2.202422, rho=0.258199\n",
+      "05:45:28 INFO:PROGRESS: pass 14, at document #2500/2500\n",
+      "05:45:28 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "05:45:36 DEBUG:2500/2500 documents converged within 50 iterations\n",
+      "05:45:36 DEBUG:updating topics\n",
+      "05:45:36 INFO:topic #89 (0.005): 0.001*\"bre_x\" + 0.001*\"x\" + 0.001*\"bre\" + 0.001*\"analyst\" + 0.001*\"barrick\" + 0.001*\"Bre-X\" + 0.001*\"government\" + 0.001*\"gold\" + 0.001*\"indonesian\" + 0.001*\"billion\"\n",
+      "05:45:36 INFO:topic #121 (0.005): 0.000*\"time\" + 0.000*\"share\" + 0.000*\"second\" + 0.000*\"tobacco\" + 0.000*\"group\" + 0.000*\"industry\" + 0.000*\"action\" + 0.000*\"month\" + 0.000*\"plan\" + 0.000*\"hand\"\n",
+      "05:45:36 INFO:topic #188 (0.005): 0.015*\"sale\" + 0.013*\"analyst\" + 0.011*\"share\" + 0.008*\"mercury\" + 0.008*\"bank\" + 0.007*\"stock\" + 0.007*\"billion\" + 0.006*\"amp\" + 0.006*\"think\" + 0.006*\"base\"\n",
+      "05:45:36 INFO:topic #80 (0.005): 0.016*\"microsoft\" + 0.015*\"analyst\" + 0.013*\"quarter\" + 0.010*\"windows\" + 0.010*\"computer\" + 0.009*\"business\" + 0.009*\"revenue\" + 0.009*\"sale\" + 0.008*\"system\" + 0.008*\"software\"\n",
+      "05:45:36 INFO:topic #56 (0.005): 0.033*\"hong\" + 0.033*\"kong\" + 0.032*\"hong_kong\" + 0.023*\"Hong Kong\" + 0.017*\"china\" + 0.007*\"Hong Kong's\" + 0.006*\"chinese\" + 0.006*\"tung\" + 0.006*\"british\" + 0.004*\"government\"\n",
+      "05:45:36 INFO:topic diff=1.861192, rho=0.250000\n",
+      "05:45:36 DEBUG:Setting topics to those of the model: AuthorTopicModel(num_terms=3914, num_topics=200, num_authors=50, decay=0.5, chunksize=2500)\n",
+      "05:45:37 INFO:CorpusAccumulator accumulated stats from 1000 documents\n",
+      "05:45:37 INFO:CorpusAccumulator accumulated stats from 2000 documents\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "-1.93149366596\n"
+     ]
+    }
+   ],
+   "source": [
+    "atmodel_200topics = train_model(train_corpus_50_20, train_author2doc, train_dictionary_50_20, num_topics=200, eval_every=0, iterations=50, passes=15)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Precision@k: top_n=1\n",
+      "Prediction accuracy: 0.6232\n",
+      "Precision@k: top_n=2\n",
+      "Prediction accuracy: 0.7664\n",
+      "Precision@k: top_n=3\n",
+      "Prediction accuracy: 0.8456\n",
+      "Precision@k: top_n=4\n",
+      "Prediction accuracy: 0.8816\n",
+      "Precision@k: top_n=5\n",
+      "Prediction accuracy: 0.9032\n",
+      "Precision@k: top_n=6\n",
+      "Prediction accuracy: 0.9164\n",
+      "Precision@k: top_n=8\n",
+      "Prediction accuracy: 0.9368\n",
+      "Precision@k: top_n=10\n",
+      "Prediction accuracy: 0.9464\n"
+     ]
+    },
+    {
+     "data": {
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYgAAAEWCAYAAAB8LwAVAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x117a975c0>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "accuracy_scores_200topic={}\n",
+    "for i in [1,2,3,4,5,6,8,10]:\n",
+    "    accuracy, k = prediction_accuracy(test_author2doc, test_corpus_50_20, atmodel_200topics, k=i)\n",
+    "    accuracy_scores_200topic[k] = accuracy\n",
+    "    \n",
+    "plot_accuracy(scores1=accuracy_scores_150topic, label1=\"150 topics\", scores2=accuracy_scores_200topic, label2=\"200 topics\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "collapsed": true
+   },
+   "source": [
+    "The 200-topic seems to be performing a bit better for lower k, might be due to a slight overrepresentation with high topic number. So let us stop here with the topic number increase and focus some more on the dictionary. We choose either one of the models.\n",
+    "Currently we are filtering out tokens, that appear in more 50% of all documents and no more than 20 times overall, which drastically decreaces the size of our dictionary. \n",
+    "We know about this dataset, that the underlying topic are not so diverse and are structed around corporate/industrial topic class. Thus it makes sense to increase the dictionary by filtering less tokens."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "We set the parameters set max_freq=25%, min_wordcount=10"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "06:18:50 INFO:adding document #0 to Dictionary(0 unique tokens: [])\n",
+      "06:18:51 INFO:built Dictionary(46905 unique tokens: ['$83.4 million', 'boarder', '$2.72 billion', 'checking', 'suzuki']...) from 2500 documents (total 786032 corpus positions)\n",
+      "06:18:51 INFO:discarding 40690 tokens: [('$15', 3), ('$17.25', 1), ('$380 million', 2), ('12.5 cents', 7), ('Big B', 3), ('Big B Inc.', 2), (\"Big B's\", 3), ('Big B. I', 1), ('Dwayne Hoven', 1), ('Eckerd Corp.', 1)]...\n",
+      "06:18:51 INFO:keeping 6215 tokens which were in no less than 10 and no more than 625 (=25.0%) documents\n",
+      "06:18:51 DEBUG:rebuilding dictionary, shrinking gaps\n",
+      "06:18:51 INFO:resulting dictionary: Dictionary(6215 unique tokens: ['offshoot', 'shore', 'loss', 'merger', 'disappointing']...)\n"
+     ]
+    }
+   ],
+   "source": [
+    "train_corpus_25_10, train_dictionary_25_10 = create_corpus_dictionary(train_docs, 0.25, 10)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "test_corpus_25_10 = create_test_corpus(train_dictionary_25_10, test_docs)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 32,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Number of unique tokens: 6215\n"
+     ]
+    }
+   ],
+   "source": [
+    "print('Number of unique tokens: %d' % len(train_dictionary_25_10))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "We now have now nearly doubled the tokens. Let's train and evaluate."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 33,
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "06:18:53 INFO:Vocabulary consists of 6215 words.\n",
+      "06:18:53 INFO:using symmetric alpha at 0.006666666666666667\n",
+      "06:18:53 INFO:using symmetric eta at 0.006666666666666667\n",
+      "06:18:57 INFO:running online author-topic training, 150 topics, 50 authors, 15 passes over the supplied corpus of 2500 documents, updating model once every 2500 documents, evaluating perplexity every 0 documents, iterating 50x with a convergence threshold of 0.001000\n",
+      "06:18:57 INFO:PROGRESS: pass 0, at document #2500/2500\n",
+      "06:18:57 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "06:19:11 DEBUG:17/2500 documents converged within 50 iterations\n",
+      "06:19:11 DEBUG:updating topics\n",
+      "06:19:12 INFO:topic #141 (0.007): 0.031*\"gm\" + 0.016*\"plant\" + 0.011*\"worker\" + 0.010*\"uaw\" + 0.009*\"strike\" + 0.009*\"truck\" + 0.008*\"local\" + 0.007*\"automaker\" + 0.006*\"part\" + 0.005*\"contract\"\n",
+      "06:19:12 INFO:topic #105 (0.007): 0.013*\"china\" + 0.010*\"tonne\" + 0.009*\"chinese\" + 0.008*\"trader\" + 0.007*\"copper\" + 0.007*\"product\" + 0.005*\"drug\" + 0.005*\"hong_kong\" + 0.004*\"soybean\" + 0.004*\"hong\"\n",
+      "06:19:12 INFO:topic #15 (0.007): 0.006*\"china\" + 0.004*\"network\" + 0.003*\"drug\" + 0.003*\"trade\" + 0.003*\"united\" + 0.003*\"states\" + 0.003*\"boeing\" + 0.003*\"chinese\" + 0.003*\"beijing\" + 0.002*\"product\"\n",
+      "06:19:12 INFO:topic #30 (0.007): 0.010*\"amp\" + 0.009*\"bank\" + 0.005*\"ernst\" + 0.005*\"claim\" + 0.005*\"bre\" + 0.004*\"bre_x\" + 0.004*\"gold\" + 0.003*\"rate\" + 0.003*\"x\" + 0.003*\"pay\"\n",
+      "06:19:12 INFO:topic #114 (0.007): 0.019*\"bank\" + 0.010*\"japan\" + 0.009*\"pound\" + 0.008*\"problem\" + 0.008*\"loan\" + 0.007*\"financial\" + 0.006*\"yen\" + 0.005*\"bt\" + 0.005*\"million_pound\" + 0.005*\"japanese\"\n",
+      "06:19:12 INFO:topic diff=61.971494, rho=1.000000\n",
+      "06:19:12 INFO:PROGRESS: pass 1, at document #2500/2500\n",
+      "06:19:12 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "06:19:19 DEBUG:2491/2500 documents converged within 50 iterations\n",
+      "06:19:19 DEBUG:updating topics\n",
+      "06:19:19 INFO:topic #45 (0.007): 0.006*\"property\" + 0.004*\"china\" + 0.003*\"holding\" + 0.003*\"survey\" + 0.003*\"sector\" + 0.002*\"bank\" + 0.002*\"gold\" + 0.002*\"fall\" + 0.002*\"debt\" + 0.002*\"air\"\n",
+      "06:19:19 INFO:topic #139 (0.007): 0.024*\"colombia\" + 0.021*\"drug\" + 0.008*\"guerrilla\" + 0.008*\"colombian\" + 0.007*\"police\" + 0.006*\"extradition\" + 0.005*\"late\" + 0.005*\"anti\" + 0.005*\"congress\" + 0.005*\"contract\"\n",
+      "06:19:19 INFO:topic #15 (0.007): 0.005*\"china\" + 0.003*\"network\" + 0.002*\"drug\" + 0.002*\"trade\" + 0.002*\"united\" + 0.002*\"states\" + 0.002*\"boeing\" + 0.002*\"chinese\" + 0.002*\"beijing\" + 0.002*\"product\"\n",
+      "06:19:19 INFO:topic #2 (0.007): 0.004*\"bre_x\" + 0.004*\"x\" + 0.003*\"bid\" + 0.003*\"bre\" + 0.003*\"product\" + 0.003*\"Bre-X\" + 0.003*\"drug\" + 0.003*\"gold\" + 0.002*\"mining\" + 0.002*\"pound\"\n",
+      "06:19:19 INFO:topic #116 (0.007): 0.007*\"china\" + 0.006*\"bank\" + 0.004*\"tonne\" + 0.004*\"problem\" + 0.004*\"hong_kong\" + 0.003*\"trader\" + 0.003*\"chinese\" + 0.003*\"loan\" + 0.003*\"kong\" + 0.003*\"hong\"\n",
+      "06:19:19 INFO:topic diff=11.411593, rho=0.577350\n",
+      "06:19:19 INFO:PROGRESS: pass 2, at document #2500/2500\n",
+      "06:19:19 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "06:19:26 DEBUG:2499/2500 documents converged within 50 iterations\n",
+      "06:19:26 DEBUG:updating topics\n",
+      "06:19:26 INFO:topic #116 (0.007): 0.005*\"china\" + 0.005*\"bank\" + 0.003*\"tonne\" + 0.003*\"problem\" + 0.003*\"hong_kong\" + 0.002*\"trader\" + 0.002*\"chinese\" + 0.002*\"loan\" + 0.002*\"kong\" + 0.002*\"hong\"\n",
+      "06:19:26 INFO:topic #79 (0.007): 0.030*\"china\" + 0.020*\"beijing\" + 0.014*\"chinese\" + 0.009*\"taiwan\" + 0.008*\"trade\" + 0.008*\"wang\" + 0.007*\"foreign\" + 0.006*\"united\" + 0.006*\"washington\" + 0.006*\"states\"\n",
+      "06:19:26 INFO:topic #58 (0.007): 0.006*\"pound\" + 0.004*\"million_pound\" + 0.003*\"hong_kong\" + 0.002*\"hong\" + 0.002*\"kong\" + 0.002*\"pay\" + 0.002*\"china\" + 0.002*\"Hong Kong\" + 0.002*\"shareholder\" + 0.002*\"service\"\n",
+      "06:19:26 INFO:topic #19 (0.007): 0.036*\"bre\" + 0.035*\"x\" + 0.033*\"bre_x\" + 0.031*\"gold\" + 0.026*\"Bre-X\" + 0.019*\"barrick\" + 0.015*\"busang\" + 0.013*\"indonesian\" + 0.011*\"mining\" + 0.009*\"deposit\"\n",
+      "06:19:26 INFO:topic #112 (0.007): 0.005*\"bank\" + 0.003*\"russia\" + 0.002*\"x\" + 0.002*\"diamond\" + 0.002*\"bre\" + 0.002*\"bre_x\" + 0.002*\"canada\" + 0.002*\"export\" + 0.002*\"canadian\" + 0.002*\"Bre-X\"\n",
+      "06:19:26 INFO:topic diff=9.522079, rho=0.500000\n",
+      "06:19:26 INFO:PROGRESS: pass 3, at document #2500/2500\n",
+      "06:19:26 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "06:19:32 DEBUG:2500/2500 documents converged within 50 iterations\n",
+      "06:19:32 DEBUG:updating topics\n",
+      "06:19:33 INFO:topic #38 (0.007): 0.003*\"block\" + 0.002*\"quarter\" + 0.002*\"service\" + 0.002*\"compuserve\" + 0.002*\"china\" + 0.002*\"pound\" + 0.002*\"loss\" + 0.001*\"chinese\" + 0.001*\"time_warner\" + 0.001*\"cent\"\n",
+      "06:19:33 INFO:topic #148 (0.007): 0.018*\"franc\" + 0.015*\"french\" + 0.014*\"airbus\" + 0.014*\"france\" + 0.013*\"thomson\" + 0.009*\"air\" + 0.009*\"billion_franc\" + 0.007*\"boeing\" + 0.007*\"state\" + 0.007*\"air_france\"\n",
+      "06:19:33 INFO:topic #9 (0.007): 0.023*\"shanghai\" + 0.021*\"china\" + 0.018*\"bank\" + 0.014*\"b\" + 0.014*\"foreign\" + 0.011*\"investor\" + 0.011*\"exchange\" + 0.011*\"b_share\" + 0.010*\"beijing\" + 0.010*\"shenzhen\"\n",
+      "06:19:33 INFO:topic #11 (0.007): 0.013*\"tobacco\" + 0.010*\"florida\" + 0.009*\"quick\" + 0.008*\"state\" + 0.007*\"car\" + 0.007*\"amp\" + 0.007*\"trial\" + 0.006*\"cigarette\" + 0.006*\"television\" + 0.006*\"maker\"\n",
+      "06:19:33 INFO:topic #116 (0.007): 0.004*\"china\" + 0.003*\"bank\" + 0.002*\"tonne\" + 0.002*\"problem\" + 0.002*\"hong_kong\" + 0.002*\"trader\" + 0.002*\"chinese\" + 0.002*\"loan\" + 0.001*\"kong\" + 0.001*\"hong\"\n",
+      "06:19:33 INFO:topic diff=7.935955, rho=0.447214\n",
+      "06:19:33 INFO:PROGRESS: pass 4, at document #2500/2500\n",
+      "06:19:33 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "06:19:39 DEBUG:2500/2500 documents converged within 50 iterations\n",
+      "06:19:39 DEBUG:updating topics\n",
+      "06:19:39 INFO:topic #118 (0.007): 0.003*\"tonne\" + 0.002*\"cocoa\" + 0.002*\"exporter\" + 0.001*\"chad\" + 0.001*\"bank\" + 0.001*\"coast\" + 0.001*\"ivory\" + 0.001*\"crop\" + 0.001*\"ivory_coast\" + 0.001*\"cable\"\n",
+      "06:19:39 INFO:topic #134 (0.007): 0.038*\"bank\" + 0.020*\"canada\" + 0.017*\"canadian\" + 0.011*\"toronto\" + 0.009*\"fund\" + 0.008*\"cent\" + 0.007*\"molson\" + 0.006*\"earning\" + 0.005*\"royal_bank\" + 0.005*\"royal\"\n",
+      "06:19:39 INFO:topic #7 (0.007): 0.002*\"soybean\" + 0.002*\"china\" + 0.002*\"monsanto\" + 0.002*\"director\" + 0.002*\"adm\" + 0.002*\"hong\" + 0.002*\"crop\" + 0.001*\"hong_kong\" + 0.001*\"united\" + 0.001*\"equipment\"\n",
+      "06:19:39 INFO:topic #93 (0.007): 0.005*\"earning\" + 0.005*\"point\" + 0.004*\"quarter\" + 0.004*\"investor\" + 0.004*\"fund\" + 0.004*\"growth\" + 0.003*\"exchange\" + 0.003*\"investment\" + 0.003*\"strong\" + 0.003*\"trade\"\n",
+      "06:19:39 INFO:topic #26 (0.007): 0.012*\"bank\" + 0.010*\"yen\" + 0.008*\"billion_yen\" + 0.005*\"financial\" + 0.005*\"affiliate\" + 0.004*\"daiwa\" + 0.004*\"non\" + 0.004*\"non_bank\" + 0.004*\"half\" + 0.004*\"post\"\n",
+      "06:19:39 INFO:topic diff=6.627219, rho=0.408248\n",
+      "06:19:39 INFO:PROGRESS: pass 5, at document #2500/2500\n",
+      "06:19:39 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "06:19:45 DEBUG:2500/2500 documents converged within 50 iterations\n",
+      "06:19:45 DEBUG:updating topics\n",
+      "06:19:46 INFO:topic #16 (0.007): 0.030*\"toronto\" + 0.020*\"index\" + 0.019*\"bank\" + 0.018*\"canada\" + 0.016*\"point\" + 0.015*\"gold\" + 0.012*\"canadian\" + 0.011*\"toronto_stock\" + 0.011*\"fall\" + 0.010*\"gain\"\n",
+      "06:19:46 INFO:topic #114 (0.007): 0.010*\"bank\" + 0.005*\"japan\" + 0.005*\"pound\" + 0.004*\"problem\" + 0.004*\"loan\" + 0.003*\"financial\" + 0.003*\"yen\" + 0.003*\"bt\" + 0.003*\"million_pound\" + 0.003*\"japanese\"\n",
+      "06:19:46 INFO:topic #52 (0.007): 0.019*\"bank\" + 0.017*\"airbus\" + 0.008*\"canada\" + 0.006*\"fund\" + 0.006*\"canadian\" + 0.006*\"service\" + 0.005*\"boeing\" + 0.004*\"aircraft\" + 0.004*\"aerospace\" + 0.004*\"office\"\n",
+      "06:19:46 INFO:topic #146 (0.007): 0.007*\"china\" + 0.005*\"party\" + 0.004*\"pound\" + 0.003*\"british\" + 0.003*\"plc\" + 0.003*\"stg\" + 0.003*\"drug\" + 0.002*\"million_pound\" + 0.002*\"country\" + 0.002*\"technology\"\n",
+      "06:19:46 INFO:topic #47 (0.007): 0.009*\"tonne\" + 0.008*\"smelter\" + 0.007*\"oil\" + 0.007*\"aluminium\" + 0.006*\"state\" + 0.006*\"plant\" + 0.006*\"russia\" + 0.006*\"trader\" + 0.006*\"source\" + 0.005*\"metal\"\n",
+      "06:19:46 INFO:topic diff=5.554374, rho=0.377964\n",
+      "06:19:46 INFO:PROGRESS: pass 6, at document #2500/2500\n",
+      "06:19:46 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "06:19:51 DEBUG:2500/2500 documents converged within 50 iterations\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "06:19:51 DEBUG:updating topics\n",
+      "06:19:52 INFO:topic #44 (0.007): 0.007*\"internet\" + 0.004*\"committee\" + 0.003*\"proposal\" + 0.003*\"address\" + 0.003*\"trade\" + 0.003*\"china\" + 0.003*\"congress\" + 0.002*\"member\" + 0.002*\"financial\" + 0.002*\"name\"\n",
+      "06:19:52 INFO:topic #131 (0.007): 0.009*\"bank\" + 0.008*\"internet\" + 0.007*\"court\" + 0.005*\"exchange\" + 0.004*\"foreign\" + 0.004*\"currency\" + 0.004*\"trading\" + 0.004*\"policy\" + 0.003*\"law\" + 0.003*\"security\"\n",
+      "06:19:52 INFO:topic #112 (0.007): 0.001*\"bank\" + 0.001*\"russia\" + 0.001*\"x\" + 0.001*\"diamond\" + 0.001*\"bre\" + 0.001*\"bre_x\" + 0.001*\"canada\" + 0.001*\"export\" + 0.001*\"canadian\" + 0.001*\"Bre-X\"\n",
+      "06:19:52 INFO:topic #49 (0.007): 0.008*\"bid\" + 0.008*\"penny\" + 0.005*\"pound\" + 0.004*\"northern\" + 0.004*\"electric\" + 0.003*\"midlands\" + 0.003*\"offer\" + 0.003*\"sector\" + 0.003*\"electricity\" + 0.003*\"east\"\n",
+      "06:19:52 INFO:topic #61 (0.007): 0.008*\"china\" + 0.008*\"tibet\" + 0.005*\"chinese\" + 0.005*\"beijing\" + 0.005*\"foreign\" + 0.004*\"wang\" + 0.004*\"hong_kong\" + 0.004*\"kong\" + 0.003*\"hong\" + 0.003*\"region\"\n",
+      "06:19:52 INFO:topic diff=4.666072, rho=0.353553\n",
+      "06:19:52 INFO:PROGRESS: pass 7, at document #2500/2500\n",
+      "06:19:52 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "06:19:58 DEBUG:2500/2500 documents converged within 50 iterations\n",
+      "06:19:58 DEBUG:updating topics\n",
+      "06:19:58 INFO:topic #8 (0.007): 0.001*\"french\" + 0.001*\"bank\" + 0.001*\"service\" + 0.001*\"financial\" + 0.001*\"internet\" + 0.001*\"china\" + 0.000*\"mfs\" + 0.000*\"sell\" + 0.000*\"state\" + 0.000*\"product\"\n",
+      "06:19:58 INFO:topic #45 (0.007): 0.001*\"property\" + 0.000*\"china\" + 0.000*\"holding\" + 0.000*\"survey\" + 0.000*\"sector\" + 0.000*\"bank\" + 0.000*\"gold\" + 0.000*\"fall\" + 0.000*\"debt\" + 0.000*\"air\"\n",
+      "06:19:58 INFO:topic #22 (0.007): 0.016*\"pound\" + 0.012*\"drug\" + 0.011*\"plc\" + 0.011*\"british\" + 0.011*\"million_pound\" + 0.008*\"product\" + 0.007*\"penny\" + 0.006*\"cancer\" + 0.006*\"stg\" + 0.005*\"biotech\"\n",
+      "06:19:58 INFO:topic #10 (0.007): 0.023*\"bank\" + 0.015*\"pound\" + 0.008*\"society\" + 0.006*\"banking\" + 0.006*\"fund\" + 0.006*\"shareholder\" + 0.005*\"investment\" + 0.005*\"eurotunnel\" + 0.005*\"lloyds\" + 0.005*\"debt\"\n",
+      "06:19:58 INFO:topic #11 (0.007): 0.013*\"tobacco\" + 0.012*\"florida\" + 0.009*\"quick\" + 0.009*\"state\" + 0.008*\"car\" + 0.007*\"amp\" + 0.007*\"trial\" + 0.007*\"television\" + 0.006*\"news\" + 0.006*\"maker\"\n",
+      "06:19:58 INFO:topic diff=3.925478, rho=0.333333\n",
+      "06:19:58 INFO:PROGRESS: pass 8, at document #2500/2500\n",
+      "06:19:58 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "06:20:04 DEBUG:2500/2500 documents converged within 50 iterations\n",
+      "06:20:04 DEBUG:updating topics\n",
+      "06:20:04 INFO:topic #9 (0.007): 0.024*\"shanghai\" + 0.022*\"china\" + 0.018*\"bank\" + 0.014*\"b\" + 0.014*\"foreign\" + 0.011*\"investor\" + 0.011*\"exchange\" + 0.011*\"b_share\" + 0.010*\"beijing\" + 0.010*\"shenzhen\"\n",
+      "06:20:04 INFO:topic #42 (0.007): 0.001*\"news\" + 0.000*\"china\" + 0.000*\"corp\" + 0.000*\"net\" + 0.000*\"property\" + 0.000*\"news_corp\" + 0.000*\"value\" + 0.000*\"shareholder\" + 0.000*\"bre_x\" + 0.000*\"x\"\n",
+      "06:20:04 INFO:topic #131 (0.007): 0.006*\"bank\" + 0.005*\"internet\" + 0.004*\"court\" + 0.003*\"exchange\" + 0.003*\"foreign\" + 0.003*\"currency\" + 0.002*\"trading\" + 0.002*\"policy\" + 0.002*\"law\" + 0.002*\"security\"\n",
+      "06:20:04 INFO:topic #99 (0.007): 0.011*\"mci\" + 0.007*\"digital\" + 0.007*\"camera\" + 0.006*\"rockwell\" + 0.005*\"technology\" + 0.005*\"kong\" + 0.005*\"hand\" + 0.005*\"hong_kong\" + 0.005*\"system\" + 0.004*\"trade\"\n",
+      "06:20:04 INFO:topic #5 (0.007): 0.018*\"bt\" + 0.013*\"telecom\" + 0.011*\"pound\" + 0.010*\"british\" + 0.008*\"mci\" + 0.007*\"service\" + 0.006*\"merger\" + 0.005*\"penny\" + 0.005*\"britain\" + 0.005*\"ntt\"\n",
+      "06:20:04 INFO:topic diff=3.304076, rho=0.316228\n",
+      "06:20:04 INFO:PROGRESS: pass 9, at document #2500/2500\n",
+      "06:20:04 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "06:20:10 DEBUG:2500/2500 documents converged within 50 iterations\n",
+      "06:20:10 DEBUG:updating topics\n",
+      "06:20:10 INFO:topic #108 (0.007): 0.005*\"gm\" + 0.004*\"computer\" + 0.004*\"quarter\" + 0.004*\"ibm\" + 0.004*\"car\" + 0.004*\"technology\" + 0.004*\"france\" + 0.003*\"thomson\" + 0.003*\"plant\" + 0.003*\"service\"\n",
+      "06:20:11 INFO:topic #111 (0.007): 0.008*\"computer\" + 0.006*\"software\" + 0.005*\"apple\" + 0.005*\"quarter\" + 0.004*\"microsoft\" + 0.003*\"technology\" + 0.003*\"design\" + 0.003*\"pc\" + 0.002*\"oracle\" + 0.002*\"financial\"\n",
+      "06:20:11 INFO:topic #82 (0.007): 0.003*\"china\" + 0.002*\"shanghai\" + 0.002*\"future\" + 0.002*\"exchange\" + 0.001*\"b\" + 0.001*\"index\" + 0.001*\"authority\" + 0.001*\"investor\" + 0.001*\"trading\" + 0.001*\"foreign\"\n",
+      "06:20:11 INFO:topic #89 (0.007): 0.016*\"internet\" + 0.015*\"computer\" + 0.014*\"technology\" + 0.010*\"quarter\" + 0.010*\"software\" + 0.009*\"product\" + 0.008*\"microsoft\" + 0.008*\"sun\" + 0.007*\"netscape\" + 0.007*\"web\"\n",
+      "06:20:11 INFO:topic #101 (0.007): 0.001*\"china\" + 0.001*\"kong\" + 0.001*\"hong\" + 0.001*\"hong_kong\" + 0.000*\"Hong Kong\" + 0.000*\"macau\" + 0.000*\"tung\" + 0.000*\"chinese\" + 0.000*\"formula\" + 0.000*\"beijing\"\n",
+      "06:20:11 INFO:topic diff=2.781140, rho=0.301511\n",
+      "06:20:11 INFO:PROGRESS: pass 10, at document #2500/2500\n",
+      "06:20:11 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "06:20:16 DEBUG:2500/2500 documents converged within 50 iterations\n",
+      "06:20:16 DEBUG:updating topics\n",
+      "06:20:17 INFO:topic #60 (0.007): 0.011*\"oil\" + 0.009*\"colombia\" + 0.008*\"colombian\" + 0.008*\"paramilitary\" + 0.008*\"country\" + 0.008*\"drug\" + 0.008*\"police\" + 0.007*\"attack\" + 0.007*\"force\" + 0.007*\"medellin\"\n",
+      "06:20:17 INFO:topic #99 (0.007): 0.010*\"mci\" + 0.008*\"digital\" + 0.007*\"camera\" + 0.007*\"rockwell\" + 0.005*\"technology\" + 0.005*\"hand\" + 0.005*\"system\" + 0.005*\"agreement\" + 0.005*\"personal\" + 0.005*\"trade\"\n",
+      "06:20:17 INFO:topic #109 (0.007): 0.025*\"pound\" + 0.016*\"million_pound\" + 0.012*\"life\" + 0.011*\"insurance\" + 0.011*\"scotam\" + 0.009*\"offer\" + 0.009*\"abbey\" + 0.007*\"policyholder\" + 0.007*\"british\" + 0.006*\"scottish\"\n",
+      "06:20:17 INFO:topic #55 (0.007): 0.028*\"internet\" + 0.027*\"court\" + 0.019*\"foreign\" + 0.017*\"exchange\" + 0.017*\"currency\" + 0.014*\"case\" + 0.014*\"foreign_currency\" + 0.014*\"trading\" + 0.012*\"amendment\" + 0.012*\"address\"\n",
+      "06:20:17 INFO:topic #9 (0.007): 0.024*\"shanghai\" + 0.022*\"china\" + 0.018*\"bank\" + 0.014*\"b\" + 0.014*\"foreign\" + 0.011*\"investor\" + 0.011*\"exchange\" + 0.011*\"b_share\" + 0.010*\"beijing\" + 0.010*\"shenzhen\"\n",
+      "06:20:17 INFO:topic diff=2.340896, rho=0.288675\n",
+      "06:20:17 INFO:PROGRESS: pass 11, at document #2500/2500\n",
+      "06:20:17 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "06:20:22 DEBUG:2500/2500 documents converged within 50 iterations\n",
+      "06:20:22 DEBUG:updating topics\n",
+      "06:20:23 INFO:topic #20 (0.007): 0.000*\"china\" + 0.000*\"de\" + 0.000*\"russia\" + 0.000*\"chinese\" + 0.000*\"beijing\" + 0.000*\"diamond\" + 0.000*\"kong\" + 0.000*\"export\" + 0.000*\"oil\" + 0.000*\"service\"\n",
+      "06:20:23 INFO:topic #7 (0.007): 0.000*\"soybean\" + 0.000*\"china\" + 0.000*\"monsanto\" + 0.000*\"director\" + 0.000*\"adm\" + 0.000*\"hong\" + 0.000*\"crop\" + 0.000*\"hong_kong\" + 0.000*\"united\" + 0.000*\"equipment\"\n",
+      "06:20:23 INFO:topic #24 (0.007): 0.024*\"czech\" + 0.011*\"crown\" + 0.011*\"bank\" + 0.010*\"prague\" + 0.010*\"klaus\" + 0.008*\"party\" + 0.006*\"havel\" + 0.006*\"foreign\" + 0.006*\"country\" + 0.006*\"election\"\n",
+      "06:20:23 INFO:topic #80 (0.007): 0.025*\"king\" + 0.021*\"silver\" + 0.013*\"network\" + 0.012*\"station\" + 0.012*\"shopping\" + 0.012*\"home_shopping\" + 0.012*\"television\" + 0.009*\"latin\" + 0.009*\"news\" + 0.009*\"home\"\n",
+      "06:20:23 INFO:topic #82 (0.007): 0.001*\"china\" + 0.001*\"shanghai\" + 0.001*\"future\" + 0.001*\"exchange\" + 0.001*\"b\" + 0.001*\"index\" + 0.001*\"authority\" + 0.001*\"investor\" + 0.001*\"trading\" + 0.001*\"foreign\"\n",
+      "06:20:23 INFO:topic diff=1.970765, rho=0.277350\n",
+      "06:20:23 INFO:PROGRESS: pass 12, at document #2500/2500\n",
+      "06:20:23 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "06:20:29 DEBUG:2500/2500 documents converged within 50 iterations\n",
+      "06:20:29 DEBUG:updating topics\n",
+      "06:20:30 INFO:topic #123 (0.007): 0.021*\"china\" + 0.013*\"wang\" + 0.011*\"beijing\" + 0.010*\"chinese\" + 0.007*\"tibet\" + 0.006*\"dissident\" + 0.006*\"state\" + 0.006*\"party\" + 0.005*\"communist\" + 0.005*\"court\"\n",
+      "06:20:30 INFO:topic #86 (0.007): 0.015*\"internet\" + 0.014*\"computer\" + 0.014*\"ibm\" + 0.012*\"quarter\" + 0.011*\"service\" + 0.009*\"pc\" + 0.008*\"software\" + 0.007*\"system\" + 0.007*\"consumer\" + 0.006*\"network\"\n",
+      "06:20:30 INFO:topic #50 (0.007): 0.034*\"hong_kong\" + 0.033*\"kong\" + 0.033*\"hong\" + 0.029*\"china\" + 0.021*\"Hong Kong\" + 0.018*\"tung\" + 0.013*\"beijing\" + 0.012*\"chinese\" + 0.012*\"Hong Kong's\" + 0.010*\"britain\"\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "06:20:30 INFO:topic #9 (0.007): 0.025*\"shanghai\" + 0.022*\"china\" + 0.018*\"bank\" + 0.014*\"b\" + 0.014*\"foreign\" + 0.011*\"investor\" + 0.011*\"exchange\" + 0.011*\"b_share\" + 0.010*\"beijing\" + 0.010*\"shenzhen\"\n",
+      "06:20:30 INFO:topic #24 (0.007): 0.024*\"czech\" + 0.011*\"crown\" + 0.011*\"bank\" + 0.010*\"prague\" + 0.009*\"klaus\" + 0.008*\"party\" + 0.006*\"havel\" + 0.006*\"foreign\" + 0.006*\"country\" + 0.006*\"election\"\n",
+      "06:20:30 INFO:topic diff=1.660230, rho=0.267261\n",
+      "06:20:30 INFO:PROGRESS: pass 13, at document #2500/2500\n",
+      "06:20:30 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "06:20:37 DEBUG:2500/2500 documents converged within 50 iterations\n",
+      "06:20:37 DEBUG:updating topics\n",
+      "06:20:38 INFO:topic #108 (0.007): 0.003*\"gm\" + 0.002*\"computer\" + 0.002*\"quarter\" + 0.002*\"ibm\" + 0.002*\"car\" + 0.002*\"technology\" + 0.002*\"france\" + 0.002*\"thomson\" + 0.002*\"plant\" + 0.002*\"service\"\n",
+      "06:20:38 INFO:topic #116 (0.007): 0.000*\"china\" + 0.000*\"bank\" + 0.000*\"tonne\" + 0.000*\"problem\" + 0.000*\"hong_kong\" + 0.000*\"trader\" + 0.000*\"chinese\" + 0.000*\"loan\" + 0.000*\"kong\" + 0.000*\"hong\"\n",
+      "06:20:38 INFO:topic #59 (0.007): 0.000*\"pound\" + 0.000*\"lloyds\" + 0.000*\"bank\" + 0.000*\"pension\" + 0.000*\"insurance\" + 0.000*\"amp\" + 0.000*\"bhp\" + 0.000*\"claim\" + 0.000*\"million_pound\" + 0.000*\"scottish\"\n",
+      "06:20:38 INFO:topic #19 (0.007): 0.034*\"bre\" + 0.033*\"x\" + 0.032*\"bre_x\" + 0.031*\"gold\" + 0.025*\"Bre-X\" + 0.018*\"barrick\" + 0.015*\"busang\" + 0.013*\"indonesian\" + 0.011*\"mining\" + 0.008*\"exploration\"\n",
+      "06:20:38 INFO:topic #112 (0.007): 0.000*\"bank\" + 0.000*\"russia\" + 0.000*\"x\" + 0.000*\"diamond\" + 0.000*\"bre\" + 0.000*\"bre_x\" + 0.000*\"canada\" + 0.000*\"export\" + 0.000*\"canadian\" + 0.000*\"Bre-X\"\n",
+      "06:20:38 INFO:topic diff=1.400248, rho=0.258199\n",
+      "06:20:38 INFO:PROGRESS: pass 14, at document #2500/2500\n",
+      "06:20:38 DEBUG:performing inference on a chunk of 2500 documents\n",
+      "06:20:47 DEBUG:2500/2500 documents converged within 50 iterations\n",
+      "06:20:47 DEBUG:updating topics\n",
+      "06:20:47 INFO:topic #43 (0.007): 0.001*\"czech\" + 0.001*\"party\" + 0.001*\"klaus\" + 0.001*\"coalition\" + 0.001*\"election\" + 0.001*\"havel\" + 0.000*\"house\" + 0.000*\"crown\" + 0.000*\"prague\" + 0.000*\"parliament\"\n",
+      "06:20:47 INFO:topic #49 (0.007): 0.001*\"bid\" + 0.001*\"penny\" + 0.001*\"pound\" + 0.001*\"northern\" + 0.001*\"electric\" + 0.000*\"midlands\" + 0.000*\"offer\" + 0.000*\"sector\" + 0.000*\"electricity\" + 0.000*\"east\"\n",
+      "06:20:47 INFO:topic #122 (0.007): 0.000*\"wang\" + 0.000*\"china\" + 0.000*\"beijing\" + 0.000*\"law\" + 0.000*\"trial\" + 0.000*\"death\" + 0.000*\"dissident\" + 0.000*\"pound\" + 0.000*\"hong\" + 0.000*\"sentence\"\n",
+      "06:20:47 INFO:topic #132 (0.007): 0.001*\"bank\" + 0.000*\"crown\" + 0.000*\"klaus\" + 0.000*\"czech\" + 0.000*\"social\" + 0.000*\"banka\" + 0.000*\"party\" + 0.000*\"minister\" + 0.000*\"state\" + 0.000*\"billion_crown\"\n",
+      "06:20:47 INFO:topic #16 (0.007): 0.030*\"toronto\" + 0.020*\"index\" + 0.019*\"bank\" + 0.019*\"canada\" + 0.017*\"gold\" + 0.016*\"point\" + 0.012*\"canadian\" + 0.011*\"toronto_stock\" + 0.011*\"fall\" + 0.010*\"gain\"\n",
+      "06:20:47 INFO:topic diff=1.182972, rho=0.250000\n",
+      "06:20:47 DEBUG:Setting topics to those of the model: AuthorTopicModel(num_terms=6215, num_topics=150, num_authors=50, decay=0.5, chunksize=2500)\n",
+      "06:20:47 INFO:CorpusAccumulator accumulated stats from 1000 documents\n",
+      "06:20:48 INFO:CorpusAccumulator accumulated stats from 2000 documents\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "-2.83261288295\n"
+     ]
+    }
+   ],
+   "source": [
+    "atmodel_150topics_25_10 = train_model(train_corpus_25_10, train_author2doc, train_dictionary_25_10, num_topics=150, eval_every=0, iterations=50, passes=15)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 35,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Precision@k: top_n=1\n",
+      "Prediction accuracy: 0.6176\n",
+      "Precision@k: top_n=2\n",
+      "Prediction accuracy: 0.7712\n",
+      "Precision@k: top_n=3\n",
+      "Prediction accuracy: 0.8268\n",
+      "Precision@k: top_n=4\n",
+      "Prediction accuracy: 0.8656\n",
+      "Precision@k: top_n=5\n",
+      "Prediction accuracy: 0.8916\n",
+      "Precision@k: top_n=6\n",
+      "Prediction accuracy: 0.9112\n",
+      "Precision@k: top_n=8\n",
+      "Prediction accuracy: 0.9308\n",
+      "Precision@k: top_n=10\n",
+      "Prediction accuracy: 0.9408\n"
+     ]
+    },
+    {
+     "data": {
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYgAAAEWCAYAAAB8LwAVAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x11713ec18>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "accuracy_scores_150topic_25_10={}\n",
+    "for i in [1,2,3,4,5,6,8,10]:\n",
+    "    accuracy, k = prediction_accuracy(test_author2doc, test_corpus_25_10, atmodel_150topics_25_10, k=i)\n",
+    "    accuracy_scores_150topic_25_10[k] = accuracy\n",
+    "    \n",
+    "plot_accuracy(scores1=accuracy_scores_150topic_25_10, label1=\"150 topics, max_freq=25%, min_wordcount=10\", scores2=accuracy_scores_150topic, label2=\"150 topics, standard\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "The results seem rather ambigious and do not show a clear trend. Which is why we would stop here for the iterations."
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.5.0"
   }
-  _remove_token_from_url();
-</script>
-</body>
-
-</html>
\ No newline at end of file
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}