[data] [docs] Datastream docs rename [5/n] (ray-project#34512)

Part 5 of ray-project#34235

README.rst

@@ -23,7 +23,7 @@ Ray is a unified framework for scaling AI and Python applications. Ray consists
 
 Learn more about `Ray AIR`_ and its libraries:
 
-- `Datasets`_: Distributed Data Preprocessing
+- `Data`_: Distributed ML Preprocessing
 - `Train`_: Distributed Training
 - `Tune`_: Scalable Hyperparameter Tuning
 - `RLlib`_: Scalable Reinforcement Learning
@@ -44,7 +44,7 @@ Install Ray with: ``pip install ray``. For nightly wheels, see the
 `Installation page <https://docs.ray.io/en/latest/installation.html>`__.
 
 .. _`Serve`: https://docs.ray.io/en/latest/serve/index.html
-.. _`Datasets`: https://docs.ray.io/en/latest/data/dataset.html
+.. _`Data`: https://docs.ray.io/en/latest/data/data.html
 .. _`Workflow`: https://docs.ray.io/en/latest/workflows/concepts.html
 .. _`Train`: https://docs.ray.io/en/latest/train/train.html
 .. _`Tune`: https://docs.ray.io/en/latest/tune/index.html

doc/BUILD

@@ -223,7 +223,7 @@ py_test_run_all_subdirectory(
     include = ["source/data/doc_code/*.py"],
     exclude = [
         "source/ray-air/doc_code/predictors.py",
-        "source/data/doc_code/creating_datasets_untested.py"
+        "source/data/doc_code/creating_datastreams_untested.py"
     ],
     extra_srcs = [],
     tags = ["exclusive", "team:core"],

doc/source/_static/js/custom.js

@@ -40,7 +40,7 @@ document.addEventListener("DOMContentLoaded", function() {
             "Ray Clusters", "Deploying on Kubernetes", "Deploying on VMs",
             "Applications Guide", "Ray Cluster Management API",
             "Ray AI Runtime (AIR)", "Ray AIR API",
-            "Ray Data", "Ray Datasets API", "Integrations",
+            "Ray Data", "Ray Data API", "Integrations",
             "Ray Train", "Ray Train API",
             "Ray Tune", "Ray Tune Examples", "Ray Tune API",
             "Ray Serve", "Ray Serve API",

doc/source/_static/js/top-navigation.js

@@ -77,7 +77,7 @@ librariesMenu.innerHTML = "<a href='#'>Libraries" + downCaret + "</a>"
 librariesList = document.createElement("ul")
 librariesList.innerHTML += "<li><a href='" + getNavURL("ray-core/walkthrough.html") + "'><span class='primary'>Ray Core</span><span class='secondary'>Scale general Python applications</span></a></li>"
 librariesList.innerHTML += "<li><a href='" + getNavURL("ray-air/getting-started.html") + "'><span class='primary'>Ray AIR</span><span class='secondary'>Scale AI applications</span></a></li>"
-librariesList.innerHTML += "<li><a href='" + getNavURL("data/dataset.html") + "'><span class='primary'>Ray Datasets</span><span class='secondary'>Scale data ingest and preprocessing</span></a></li>"
+librariesList.innerHTML += "<li><a href='" + getNavURL("data/data.html") + "'><span class='primary'>Ray Data</span><span class='secondary'>Scale data ingest and preprocessing</span></a></li>"
 librariesList.innerHTML += "<li><a href='" + getNavURL("train/train.html") + "'><span class='primary'>Ray Train</span><span class='secondary'>Scale machine learning training</span></a></li>"
 librariesList.innerHTML += "<li><a href='" + getNavURL("tune/index.html") + "'><span class='primary'>Ray Tune</span><span class='secondary'>Scale hyperparameter tuning</span></a></li>"
 librariesList.innerHTML += "<li><a href='" + getNavURL("serve/index.html") + "'><span class='primary'>Ray Serve</span><span class='secondary'>Scale model serving</span></a></li>"

doc/source/_toc.yml

@@ -84,7 +84,7 @@ parts:
           - file: ray-air/api/api
           - file: ray-air/benchmarks
 
-      - file: data/dataset
+      - file: data/data
         title: Ray Data
         sections:
           - file: data/getting-started
@@ -95,10 +95,9 @@ parts:
               - file: data/examples/nyc_taxi_basic_processing
                 title: Processing the NYC taxi dataset
               - file: data/examples/batch_training
-                title: Batch Training with Ray Datasets
+                title: Batch Training with Ray Data
               - file: data/examples/ocr_example
-                title: Scaling OCR with Ray Datasets
-              - file: data/examples/advanced-pipelines
+                title: Scaling OCR with Ray Data
               - file: data/examples/random-access
           - file: data/faq
           - file: data/api/api

doc/source/data/api/api.rst

@@ -1,18 +1,17 @@
 .. _data-api:
 
-Ray Datasets API
+Ray Data API
 ================
 
 .. toctree::
     :maxdepth: 2
 
     input_output.rst
-    dataset.rst
-    dataset_iterator.rst
-    dataset_pipeline.rst
+    datastream.rst
+    data_iterator.rst
     execution_options.rst
-    grouped_dataset.rst
-    dataset_context.rst
+    grouped_data.rst
+    data_context.rst
     data_representations.rst
     random_access_dataset.rst
     utility.rst

doc/source/data/api/dataset_context.rst → doc/source/data/api/data_context.rst

@@ -1,4 +1,4 @@
-.. _dataset-context-api:
+.. _data-context-api:
 
 DataContext API
 ===============

doc/source/data/api/data_representations.rst

@@ -1,7 +1,7 @@
 .. _data-representations:
 
-Data Representations
-====================
+Data Representations (internal)
+===============================
 
 .. currentmodule:: ray.data
 
@@ -34,7 +34,7 @@ Row API
 
    row.TableRow
 
-.. _dataset-tensor-extension-api:
+.. _datastream-tensor-extension-api:
 
 Tensor Column Extension API
 ---------------------------