Update docstring and user guides, some bug fix(#84)

hitsz-ids · Dec 20, 2023 · e636c80 · e636c80
1 parent b3b6aee
commit e636c80
Show file tree

Hide file tree

Showing 19 changed files with 440 additions and 65 deletions.
diff --git a/README.md b/README.md
@@ -80,27 +80,24 @@ from sdgx.models.ml.single_table.ctgan import CTGANSynthesizerModel
 from sdgx.synthesizer import Synthesizer
 from sdgx.utils import download_demo_data
 
+# This will download demo data to ./dataset
 dataset_csv = download_demo_data()
+
+# Create data connector for csv file
 data_connector = CsvConnector(path=dataset_csv)
+
+# Initialize synthesizer, use CTGAN model
 synthesizer = Synthesizer(
     model=CTGANSynthesizerModel(epochs=1),  # For quick demo
     data_connector=data_connector,
 )
 
+# Fit the model
 synthesizer.fit()
-sampled_data = synthesizer.sample(1000)
-synthesizer.cleanup()  # Clean all cache
-
-# Optional, use JSD for mectics
-from sdgx.metrics.column.jsd import JSD
 
-JSD = JSD()
-
-selected_columns = ["workclass"]
-isDiscrete = True
-metrics = JSD.calculate(data_connector.read(), sampled_data, selected_columns, isDiscrete)
-
-print("JSD metric of column %s: %g" % (selected_columns[0], metrics))
+# Sample
+sampled_data = synthesizer.sample(1000)
+print(sampled_data)
 ```
 
 #### Comparison

diff --git a/README_ZH_CN.md b/README_ZH_CN.md
@@ -79,27 +79,24 @@ from sdgx.models.ml.single_table.ctgan import CTGANSynthesizerModel
 from sdgx.synthesizer import Synthesizer
 from sdgx.utils import download_demo_data
 
+# This will download demo data to ./dataset
 dataset_csv = download_demo_data()
+
+# Create data connector for csv file
 data_connector = CsvConnector(path=dataset_csv)
+
+# Initialize synthesizer, use CTGAN model
 synthesizer = Synthesizer(
     model=CTGANSynthesizerModel(epochs=1),  # For quick demo
     data_connector=data_connector,
 )
 
+# Fit the model
 synthesizer.fit()
-sampled_data = synthesizer.sample(1000)
-synthesizer.cleanup()  # Clean all cache
-
-# Optional, use JSD for mectics
-from sdgx.metrics.column.jsd import JSD
 
-JSD = JSD()
-
-selected_columns = ["workclass"]
-isDiscrete = True
-metrics = JSD.calculate(data_connector.read(), sampled_data, selected_columns, isDiscrete)
-
-print("JSD metric of column %s: %g" % (selected_columns[0], metrics))
+# Sample
+sampled_data = synthesizer.sample(1000)
+print(sampled_data)
 ```
 
 #### 对比

diff --git a/docs/source/api_reference/data_connectors/index.rst b/docs/source/api_reference/data_connectors/index.rst
@@ -1,13 +1,17 @@
 DataConnector
 ========================================================
 
+.. toctree::
+    :maxdepth: 1
+
+    Base Class for DataConnector <base>
+
 Built-in DataConnector
 -----------------------------
 
 .. toctree::
     :maxdepth: 2
 
-    DataConnector <base>
     CsvConnector <csv_connector>
     GeneratorConnector <generator_connector>
 

diff --git a/docs/source/api_reference/data_models/inspectors/index.rst b/docs/source/api_reference/data_models/inspectors/index.rst
@@ -1,13 +1,17 @@
 Inspectors
 ========================================================
 
+.. toctree::
+    :maxdepth: 1
+
+    Base Class for Inspector <base>
+
 Built-in Inspector
 -----------------------------
 
 .. toctree::
     :maxdepth: 2
 
-    Inspector <base>
     DiscreteInspector <discrete>
 
 

diff --git a/docs/source/api_reference/data_processors/index.rst b/docs/source/api_reference/data_processors/index.rst
@@ -1,13 +1,18 @@
 DataProcessor
 ========================================================
 
+.. toctree::
+    :maxdepth: 1
+
+    Base Class for DataProcessor <base>
+
+
 Built-in DataProcessor
 -----------------------------
 
 .. toctree::
     :maxdepth: 2
 
-    DataProcessor <base>
 
 Custom DataProcessor Relevant
 -----------------------------

diff --git a/docs/source/api_reference/index.rst b/docs/source/api_reference/index.rst
@@ -8,6 +8,7 @@ API Reference
 
     Synthesizer <synthesizer>
     Data Connector <data_connectors/index>
+    Data Models <data_models/index>
     Data Loader <data_loader>
     Cacher for DataLoader <cachers/index>
     Data Processor <data_processors/index>

diff --git a/docs/source/api_reference/models/index.rst b/docs/source/api_reference/models/index.rst
@@ -2,9 +2,9 @@ Models
 ========================================================
 
 .. toctree::
-    :maxdepth: 2
+    :maxdepth: 1
 
-    SynthesizerModel <base>
+    Base Class for SynthesizerModel <base>
 
 
 Built-in ML Models

diff --git a/docs/source/conf.py b/docs/source/conf.py
@@ -17,7 +17,7 @@
 
 # -- Project information -----------------------------------------------------
 
-project = "synthetic-data-generator"
+project = "Synthetic Data Generator"
 copyright = "2023, hitsz-ids"
 author = "hitsz-ids"
 
@@ -61,13 +61,23 @@
 # The theme to use for HTML and HTML Help pages.  See the documentation for
 # a list of builtin themes.
 #
-html_theme = "sphinx_rtd_theme"
+html_theme = "pydata_sphinx_theme"
 
 # Add any paths that contain custom static files (such as style sheets) here,
 # relative to this directory. They are copied after the builtin static files,
 # so a file named "default.css" will overwrite the builtin "default.css".
 html_static_path = ["_static"]
 
 todo_include_todos = True
-
 html_logo = "_static/sdg_logo.png"
+html_theme_options = {
+    "github_url": "https://github.com/hitsz-ids/synthetic-data-generator",
+    "use_edit_page_button": True,
+}
+
+html_context = {
+    "github_user": "hitsz-ids",
+    "github_repo": "synthetic-data-generator",
+    "github_version": "main",
+    "doc_path": "docs/source",
+}
diff --git a/docs/source/index.rst b/docs/source/index.rst
@@ -52,10 +52,39 @@ Or install our python package with pip
 In order to use the GPU for synthesis, you may need to refer to `Torch's GPU installation guide <https://pytorch.org/get-started/locally/>`_.
 
 
-Use sdgx for generating synthetic data
+Quick demo
 ====================================================================
 
-.. TODO: The tutorials and feature introduction.
+.. code-block:: python
+
+   """
+   Example for CTGAN
+   """
+
+   from sdgx.data_connectors.csv_connector import CsvConnector
+   from sdgx.models.ml.single_table.ctgan import CTGANSynthesizerModel
+   from sdgx.synthesizer import Synthesizer
+   from sdgx.utils import download_demo_data
+
+   # This will download demo data to ./dataset
+   dataset_csv = download_demo_data()
+
+   # Create data connector for csv file
+   data_connector = CsvConnector(path=dataset_csv)
+
+   # Initialize synthesizer, use CTGAN model
+   synthesizer = Synthesizer(
+      model=CTGANSynthesizerModel(epochs=1),  # For quick demo
+      data_connector=data_connector,
+   )
+
+   # Fit the model
+   synthesizer.fit()
+
+   # Sample
+   sampled_data = synthesizer.sample(1000)
+   print(sampled_data)
+
 
 You can refer our user guides for more details.
 

diff --git a/docs/source/user_guides/index.rst b/docs/source/user_guides/index.rst
@@ -3,11 +3,13 @@
 Guides for users
 ==================================================
 
+The Guides for users section includes SDG usage for different scenarios.
+
 .. toctree::
     :maxdepth: 2
 
         Use CLI directly <cli>
-        Use sdgx as a library <library>
+        Use SDG as a library <library>
         Synthetic single-table data <single_table>
         Synthetic multi-table data <multi_table>
         Evaluation synthetic data <evaluation>