Generate Docs for 0.7.10 (#593)

* generated docs * generated docs * updated docs * updated docs * updated docs * updated docs * updated readme * update_documentation.py * updated docs * updated docs * updated docs * updated docs * updated docs
capitalone · Aug 9, 2022 · c07fd68 · c07fd68
1 parent 8cb7ccd
commit c07fd68
Show file tree

Hide file tree

Showing 276 changed files with 67,267 additions and 1 deletion.
diff --git a/docs/0.7.10/doctrees/API.doctree b/docs/0.7.10/doctrees/API.doctree
diff --git a/docs/0.7.10/doctrees/add_new_model_to_data_labeler.doctree b/docs/0.7.10/doctrees/add_new_model_to_data_labeler.doctree
diff --git a/docs/0.7.10/doctrees/data_labeling.doctree b/docs/0.7.10/doctrees/data_labeling.doctree
diff --git a/docs/0.7.10/doctrees/data_reader.doctree b/docs/0.7.10/doctrees/data_reader.doctree
diff --git a/docs/0.7.10/doctrees/data_readers.doctree b/docs/0.7.10/doctrees/data_readers.doctree
diff --git a/docs/0.7.10/doctrees/dataprofiler.data_readers.avro_data.doctree b/docs/0.7.10/doctrees/dataprofiler.data_readers.avro_data.doctree
diff --git a/docs/0.7.10/doctrees/dataprofiler.data_readers.base_data.doctree b/docs/0.7.10/doctrees/dataprofiler.data_readers.base_data.doctree
diff --git a/docs/0.7.10/doctrees/dataprofiler.data_readers.csv_data.doctree b/docs/0.7.10/doctrees/dataprofiler.data_readers.csv_data.doctree
diff --git a/docs/0.7.10/doctrees/dataprofiler.data_readers.data.doctree b/docs/0.7.10/doctrees/dataprofiler.data_readers.data.doctree
diff --git a/docs/0.7.10/doctrees/dataprofiler.data_readers.data_utils.doctree b/docs/0.7.10/doctrees/dataprofiler.data_readers.data_utils.doctree
diff --git a/docs/0.7.10/doctrees/dataprofiler.data_readers.doctree b/docs/0.7.10/doctrees/dataprofiler.data_readers.doctree
diff --git a/docs/0.7.10/doctrees/dataprofiler.data_readers.filepath_or_buffer.doctree b/docs/0.7.10/doctrees/dataprofiler.data_readers.filepath_or_buffer.doctree
diff --git a/docs/0.7.10/doctrees/dataprofiler.data_readers.graph_data.doctree b/docs/0.7.10/doctrees/dataprofiler.data_readers.graph_data.doctree
diff --git a/docs/0.7.10/doctrees/dataprofiler.data_readers.json_data.doctree b/docs/0.7.10/doctrees/dataprofiler.data_readers.json_data.doctree
diff --git a/docs/0.7.10/doctrees/dataprofiler.data_readers.parquet_data.doctree b/docs/0.7.10/doctrees/dataprofiler.data_readers.parquet_data.doctree
diff --git a/docs/0.7.10/doctrees/dataprofiler.data_readers.structured_mixins.doctree b/docs/0.7.10/doctrees/dataprofiler.data_readers.structured_mixins.doctree
diff --git a/docs/0.7.10/doctrees/dataprofiler.data_readers.text_data.doctree b/docs/0.7.10/doctrees/dataprofiler.data_readers.text_data.doctree
diff --git a/docs/0.7.10/doctrees/dataprofiler.doctree b/docs/0.7.10/doctrees/dataprofiler.doctree
diff --git a/docs/0.7.10/doctrees/dataprofiler.dp_logging.doctree b/docs/0.7.10/doctrees/dataprofiler.dp_logging.doctree
diff --git a/docs/0.7.10/doctrees/dataprofiler.labelers.base_data_labeler.doctree b/docs/0.7.10/doctrees/dataprofiler.labelers.base_data_labeler.doctree
diff --git a/docs/0.7.10/doctrees/dataprofiler.labelers.base_model.doctree b/docs/0.7.10/doctrees/dataprofiler.labelers.base_model.doctree
diff --git a/docs/0.7.10/doctrees/dataprofiler.labelers.char_load_tf_model.doctree b/docs/0.7.10/doctrees/dataprofiler.labelers.char_load_tf_model.doctree
diff --git a/docs/0.7.10/doctrees/dataprofiler.labelers.character_level_cnn_model.doctree b/docs/0.7.10/doctrees/dataprofiler.labelers.character_level_cnn_model.doctree
diff --git a/docs/0.7.10/doctrees/dataprofiler.labelers.classification_report_utils.doctree b/docs/0.7.10/doctrees/dataprofiler.labelers.classification_report_utils.doctree
diff --git a/docs/0.7.10/doctrees/dataprofiler.labelers.data_labelers.doctree b/docs/0.7.10/doctrees/dataprofiler.labelers.data_labelers.doctree
diff --git a/docs/0.7.10/doctrees/dataprofiler.labelers.data_processing.doctree b/docs/0.7.10/doctrees/dataprofiler.labelers.data_processing.doctree
diff --git a/docs/0.7.10/doctrees/dataprofiler.labelers.doctree b/docs/0.7.10/doctrees/dataprofiler.labelers.doctree
diff --git a/docs/0.7.10/doctrees/dataprofiler.labelers.labeler_utils.doctree b/docs/0.7.10/doctrees/dataprofiler.labelers.labeler_utils.doctree
diff --git a/docs/0.7.10/doctrees/dataprofiler.labelers.regex_model.doctree b/docs/0.7.10/doctrees/dataprofiler.labelers.regex_model.doctree
diff --git a/docs/0.7.10/doctrees/dataprofiler.profilers.base_column_profilers.doctree b/docs/0.7.10/doctrees/dataprofiler.profilers.base_column_profilers.doctree
diff --git a/docs/0.7.10/doctrees/dataprofiler.profilers.categorical_column_profile.doctree b/docs/0.7.10/doctrees/dataprofiler.profilers.categorical_column_profile.doctree
diff --git a/docs/0.7.10/doctrees/dataprofiler.profilers.column_profile_compilers.doctree b/docs/0.7.10/doctrees/dataprofiler.profilers.column_profile_compilers.doctree
diff --git a/docs/0.7.10/doctrees/dataprofiler.profilers.data_labeler_column_profile.doctree b/docs/0.7.10/doctrees/dataprofiler.profilers.data_labeler_column_profile.doctree
diff --git a/docs/0.7.10/doctrees/dataprofiler.profilers.datetime_column_profile.doctree b/docs/0.7.10/doctrees/dataprofiler.profilers.datetime_column_profile.doctree
diff --git a/docs/0.7.10/doctrees/dataprofiler.profilers.doctree b/docs/0.7.10/doctrees/dataprofiler.profilers.doctree
diff --git a/docs/0.7.10/doctrees/dataprofiler.profilers.float_column_profile.doctree b/docs/0.7.10/doctrees/dataprofiler.profilers.float_column_profile.doctree
diff --git a/docs/0.7.10/doctrees/dataprofiler.profilers.graph_profiler.doctree b/docs/0.7.10/doctrees/dataprofiler.profilers.graph_profiler.doctree
diff --git a/docs/0.7.10/doctrees/dataprofiler.profilers.helpers.doctree b/docs/0.7.10/doctrees/dataprofiler.profilers.helpers.doctree
diff --git a/docs/0.7.10/doctrees/dataprofiler.profilers.helpers.report_helpers.doctree b/docs/0.7.10/doctrees/dataprofiler.profilers.helpers.report_helpers.doctree
diff --git a/docs/0.7.10/doctrees/dataprofiler.profilers.histogram_utils.doctree b/docs/0.7.10/doctrees/dataprofiler.profilers.histogram_utils.doctree
diff --git a/docs/0.7.10/doctrees/dataprofiler.profilers.int_column_profile.doctree b/docs/0.7.10/doctrees/dataprofiler.profilers.int_column_profile.doctree
diff --git a/docs/0.7.10/doctrees/dataprofiler.profilers.numerical_column_stats.doctree b/docs/0.7.10/doctrees/dataprofiler.profilers.numerical_column_stats.doctree
diff --git a/docs/0.7.10/doctrees/dataprofiler.profilers.order_column_profile.doctree b/docs/0.7.10/doctrees/dataprofiler.profilers.order_column_profile.doctree
diff --git a/docs/0.7.10/doctrees/dataprofiler.profilers.profile_builder.doctree b/docs/0.7.10/doctrees/dataprofiler.profilers.profile_builder.doctree
diff --git a/docs/0.7.10/doctrees/dataprofiler.profilers.profiler_options.doctree b/docs/0.7.10/doctrees/dataprofiler.profilers.profiler_options.doctree
diff --git a/docs/0.7.10/doctrees/dataprofiler.profilers.text_column_profile.doctree b/docs/0.7.10/doctrees/dataprofiler.profilers.text_column_profile.doctree
diff --git a/docs/0.7.10/doctrees/dataprofiler.profilers.unstructured_data_labeler_column_profile.doctree b/docs/0.7.10/doctrees/dataprofiler.profilers.unstructured_data_labeler_column_profile.doctree
diff --git a/docs/0.7.10/doctrees/dataprofiler.profilers.unstructured_labeler_profile.doctree b/docs/0.7.10/doctrees/dataprofiler.profilers.unstructured_labeler_profile.doctree
diff --git a/docs/0.7.10/doctrees/dataprofiler.profilers.unstructured_text_profile.doctree b/docs/0.7.10/doctrees/dataprofiler.profilers.unstructured_text_profile.doctree
diff --git a/docs/0.7.10/doctrees/dataprofiler.profilers.utils.doctree b/docs/0.7.10/doctrees/dataprofiler.profilers.utils.doctree
diff --git a/docs/0.7.10/doctrees/dataprofiler.reports.doctree b/docs/0.7.10/doctrees/dataprofiler.reports.doctree
diff --git a/docs/0.7.10/doctrees/dataprofiler.reports.graphs.doctree b/docs/0.7.10/doctrees/dataprofiler.reports.graphs.doctree
diff --git a/docs/0.7.10/doctrees/dataprofiler.reports.utils.doctree b/docs/0.7.10/doctrees/dataprofiler.reports.utils.doctree
diff --git a/docs/0.7.10/doctrees/dataprofiler.settings.doctree b/docs/0.7.10/doctrees/dataprofiler.settings.doctree
diff --git a/docs/0.7.10/doctrees/dataprofiler.validators.base_validators.doctree b/docs/0.7.10/doctrees/dataprofiler.validators.base_validators.doctree
diff --git a/docs/0.7.10/doctrees/dataprofiler.validators.doctree b/docs/0.7.10/doctrees/dataprofiler.validators.doctree
diff --git a/docs/0.7.10/doctrees/dataprofiler.version.doctree b/docs/0.7.10/doctrees/dataprofiler.version.doctree
diff --git a/docs/0.7.10/doctrees/environment.pickle b/docs/0.7.10/doctrees/environment.pickle
diff --git a/docs/0.7.10/doctrees/examples.doctree b/docs/0.7.10/doctrees/examples.doctree
diff --git a/docs/0.7.10/doctrees/graphs.doctree b/docs/0.7.10/doctrees/graphs.doctree
diff --git a/docs/0.7.10/doctrees/index.doctree b/docs/0.7.10/doctrees/index.doctree
diff --git a/docs/0.7.10/doctrees/install.doctree b/docs/0.7.10/doctrees/install.doctree
diff --git a/docs/0.7.10/doctrees/labeler.doctree b/docs/0.7.10/doctrees/labeler.doctree
diff --git a/docs/0.7.10/doctrees/merge_profile_list.doctree b/docs/0.7.10/doctrees/merge_profile_list.doctree
diff --git a/docs/0.7.10/doctrees/modules.doctree b/docs/0.7.10/doctrees/modules.doctree
diff --git a/docs/0.7.10/doctrees/nbsphinx/add_new_model_to_data_labeler.ipynb b/docs/0.7.10/doctrees/nbsphinx/add_new_model_to_data_labeler.ipynb
diff --git a/docs/0.7.10/doctrees/nbsphinx/data_reader.ipynb b/docs/0.7.10/doctrees/nbsphinx/data_reader.ipynb
diff --git a/docs/0.7.10/doctrees/nbsphinx/labeler.ipynb b/docs/0.7.10/doctrees/nbsphinx/labeler.ipynb
diff --git a/docs/0.7.10/doctrees/nbsphinx/merge_profile_list.ipynb b/docs/0.7.10/doctrees/nbsphinx/merge_profile_list.ipynb
@@ -0,0 +1,159 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "60af5256",
+   "metadata": {},
+   "source": [
+    "# Merge List of Profiles\n",
+    "\n",
+    "This is an example of a new utils in the dataprofiler for distributed merging of profile objects. This assumes the user is providing a list of profile objects to the utils function for merging all the profiles together."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "7eee37ff",
+   "metadata": {},
+   "source": [
+    "## Imports\n",
+    "\n",
+    "Let's start by importing the necessary packages..."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f0d27009",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "import sys\n",
+    "import json\n",
+    "\n",
+    "import pandas as pd\n",
+    "import tensorflow as tf\n",
+    "\n",
+    "try:\n",
+    "    sys.path.insert(0, '..')\n",
+    "    import dataprofiler as dp\n",
+    "    from dataprofiler.profilers.utils import merge_profile_list\n",
+    "except ImportError:\n",
+    "    import dataprofiler as dp\n",
+    "    from dataprofiler.profilers.utils import merge_profile_list\n",
+    "\n",
+    "# remove extra tf loggin\n",
+    "tf.compat.v1.logging.set_verbosity(tf.compat.v1.logging.ERROR)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b4369e64",
+   "metadata": {},
+   "source": [
+    "## Setup the Data and Profiler"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "410c3c4d",
+   "metadata": {},
+   "source": [
+    "This section shows the basic example of the Data Profiler. \n",
+    "\n",
+    "1. Instantiate a Pandas dataframe with dummy data\n",
+    "2. Pass the dataframe to the `Profiler` and instantiate two separate profilers in a list"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d3567c82",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "d = {'col1': [1, 2], 'col2': [3, 4]}\n",
+    "df = pd.DataFrame(data=d)\n",
+    "\n",
+    "list_of_profiles = [dp.Profiler(df), dp.Profiler(df)]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "350502eb",
+   "metadata": {},
+   "source": [
+    "Take a look at the list of profiles... "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b649db32",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "list_of_profiles"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4ed4fc12",
+   "metadata": {},
+   "source": [
+    "## Run Merge on List of Profiles\n",
+    "\n",
+    "Now let's merge the list of profiles into a `single_profile`"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4a636047",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "single_profile = merge_profile_list(list_of_profiles=list_of_profiles)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0aa88720",
+   "metadata": {},
+   "source": [
+    "And check out the `.report` on the single profile:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "34059c21",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "single_profile.report()"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "dataprofiler",
+   "language": "python",
+   "name": "dataprofiler"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}