modin-project · amyskov · Mar 2, 2022 · May 17, 2022 · May 19, 2022 · May 20, 2022
@@ -25,7 +25,7 @@ jobs:
           python-version: "3.8.x"
           architecture: "x64"
       - run: pip install black
-      - run: black --check --diff modin/ asv_bench/benchmarks scripts/doc_checker.py
+      - run: black --check --diff modin/ asv_bench/benchmarks scripts/doc_checker.py scripts/supported_apis.py
 
   build-docs:
     name: build docs
@@ -54,8 +54,8 @@ jobs:
           architecture: "x64"
       # The `numpydoc` version here MUST match the versions in the dev requirements files.
       - run: pip install pytest pytest-cov pydocstyle numpydoc==1.1.0 xgboost
-      - run: pytest scripts/test
       - run: pip install -e .[all]
+      - run: pytest scripts/test
       - run: |
           python scripts/doc_checker.py --add-ignore=D101,D102,D103,D105 --disable-numpydoc \
             modin/pandas/dataframe.py modin/pandas/series.py \
@@ -98,6 +98,7 @@ jobs:
           python scripts/doc_checker.py modin/core/execution/dispatching/factories/factories.py \
             modin/core/execution/dispatching/factories/dispatcher.py                            \
       - run: python scripts/doc_checker.py scripts/doc_checker.py
+      - run: python scripts/doc_checker.py scripts/supported_apis.py
       - run: |
           python scripts/doc_checker.py modin/experimental/pandas/io.py \
             modin/experimental/pandas/numpy_wrap.py modin/experimental/pandas/__init__.py
@@ -132,7 +133,7 @@ jobs:
           python-version: "3.8.x"
           architecture: "x64"
       - run: pip install flake8 flake8-print flake8-no-implicit-concat
-      - run: flake8 modin/ asv_bench/benchmarks scripts/doc_checker.py
+      - run: flake8 modin/ asv_bench/benchmarks scripts/doc_checker.py scripts/supported_apis.py
 
   test-api:
     runs-on: ubuntu-latest

@@ -0,0 +1,31 @@
+{% extends "!autosummary/class.rst" %}
+
+{% block methods %}
+{% if methods %}
+.. rubric:: {{ _('Methods') }}
+
+.. autosummary::
+    :toctree:
+    {% for item in all_methods %}
+    {%- if not item.startswith('_') %}
+    {{ name }}.{{ item }}
+    {%- endif -%}
+    {%- endfor %}
+
+{% endif %}
+{% endblock %}
+
+{% block attributes %}
+{% if attributes %}
+.. rubric:: {{ _('Attributes') }}
+
+.. autosummary::
+    :toctree:
+    {% for item in all_attributes %}
+    {%- if not item.startswith('_') %}
+    {{ name }}.{{ item }}
+    {%- endif -%}
+    {%- endfor %}
+
+{% endif %}
+{% endblock %}
@@ -42,12 +42,14 @@ def noop_decorator(*args, **kwargs):
 import modin
 
 from modin.config.__main__ import export_config_help
+from scripts.supported_apis import generate_supported_apis_csvs
 
 configs_file_path = os.path.abspath(
     os.path.join(os.path.dirname(__file__), "flow/modin/configs_help.csv")
 )
 # Export configs help to create configs table in the docs/flow/modin/config.rst
 export_config_help(configs_file_path)
+generate_supported_apis_csvs()
 
 project = "Modin"
 copyright = "2018-2022, Modin Developers."
@@ -76,6 +78,7 @@ def noop_decorator(*args, **kwargs):
     "sphinx.ext.mathjax",
     "sphinx.ext.githubpages",
     "sphinx.ext.graphviz",
+    "sphinx.ext.autosummary",
     "sphinxcontrib.plantuml",
     "sphinx_issues",
 ]
@@ -84,6 +87,9 @@ def noop_decorator(*args, **kwargs):
 # Add any paths that contain templates here, relative to this directory.
 templates_path = ["_templates"]
 
+# Turn on sphinx.ext.autosummary
+autosummary_generate = True
+
 # The suffix(es) of source filenames.
 # You can specify multiple suffix as a list of string:
 #

@@ -273,9 +273,13 @@ API
 The API is the outer-most layer that faces users. The following classes contain Modin's implementation of the pandas API:
 
 .. toctree::
+   :maxdepth: 1
+
    /flow/modin/pandas/base
    /flow/modin/pandas/dataframe
    /flow/modin/pandas/series
+   /flow/modin/pandas/io
+   /flow/modin/pandas/general
 
 Module/Class View
 -----------------

@@ -8,4 +8,3 @@ Public API
 
 .. autoclass:: modin.pandas.base.BasePandasDataset
   :noindex:
-  :members:
@@ -3,10 +3,12 @@
 DataFrame Module Overview
 """""""""""""""""""""""""
 
+.. currentmodule:: modin.pandas
+
 Modin's ``pandas.DataFrame`` API
 ''''''''''''''''''''''''''''''''
 
-Modin's ``pandas.DataFrame`` API is backed by a distributed object providing an identical
+Modin's ``pandas.DataFrame`` API is backed by a distributed object(s) providing an identical
 API to pandas. After the user calls some ``DataFrame`` function, this call is internally
 rewritten into a representation that can be processed in parallel by the partitions. These
 results can be e.g., reduced to single output, identical to the single threaded
@@ -19,7 +21,10 @@ pandas ``DataFrame`` method output.
 Public API
 ----------
 
-.. autoclass:: modin.pandas.dataframe.DataFrame
+.. autosummary::
+    :toctree: api/
+
+    DataFrame
 
 Usage Guide
 '''''''''''

@@ -0,0 +1,33 @@
+General Functions
+~~~~~~~~~~~~~~~~~
+
+.. currentmodule:: modin.pandas
+
+Modin's general functions API is backed by a distributed object(s) providing an identical
+API to pandas. After the user calls some general function, this call is internally
+rewritten into a representation that can be processed in parallel by the partitions. These
+results can be e.g., reduced to single output, identical to the single threaded
+pandas method output.
+
+.. autosummary::
+    :toctree: api/
+
+    concat
+    crosstab
+    get_dummies
+    isna
+    isnull
+    lreshape
+    melt
+    merge
+    merge_asof
+    merge_ordered
+    notna
+    notnull
+    pivot
+    pivot_table
+    to_datetime
+    to_numeric
+    unique
+    value_counts
+    wide_to_long
@@ -0,0 +1,36 @@
+Input/Output
+~~~~~~~~~~~~
+
+.. currentmodule:: modin.pandas
+
+Modin's I/O functions API is backed by a distributed object(s) providing an identical
+API to pandas. After the user calls some I/O function, this call is internally
+rewritten into a representation that can be processed in parallel by the partitions.
+Once I/O function call is finished, each partition will contain chunk of data, and then
+these partitions can be processed in parallel using Modin API.
+
+.. autosummary::
+    :toctree: api/
+
+    json_normalize
+    read_clipboard
+    read_csv
+    read_excel
+    read_feather
+    read_fwf
+    read_gbq
+    read_hdf
+    read_html
+    read_json
+    read_orc
+    read_parquet
+    read_pickle
+    read_sas
+    read_spss
+    read_sql
+    read_sql_query
+    read_sql_table
+    read_stata
+    read_table
+    read_xml
+    to_pickle
@@ -3,10 +3,12 @@
 Series Module Overview
 """"""""""""""""""""""
 
+.. currentmodule:: modin.pandas
+
 Modin's ``pandas.Series`` API
 '''''''''''''''''''''''''''''
 
-Modin's ``pandas.Series`` API is backed by a distributed object providing an identical
+Modin's ``pandas.Series`` API is backed by a distributed object(s) providing an identical
 API to pandas. After the user calls some ``Series`` function, this call is internally rewritten
 into a representation that can be processed in parallel by the partitions. These
 results can be e.g., reduced to single output, identical to the single threaded
@@ -19,7 +21,10 @@ pandas ``Series`` method output.
 Public API
 ----------
 
-.. autoclass:: modin.pandas.series.Series
+.. autosummary::
+    :toctree: api/
+
+    Series
 
 Usage Guide
 '''''''''''

@@ -13,3 +13,4 @@ git+https://github.com/modin-project/modin.git@master#egg=modin[all]
 sphinxcontrib_plantuml
 sphinx-issues
 xgboost
+numpydoc==1.1.0
Original file line number	Diff line number	Diff line change
Expand Up		@@ -8,4 +8,3 @@ Public API

		.. autoclass:: modin.pandas.base.BasePandasDataset
		:noindex:
		:members:
Copy link Collaborator YarShev May 16, 2022 Choose a reason for hiding this comment The reason will be displayed to describe this comment to others. Learn more. Why is this removed? Copy link Contributor alexander3774 May 17, 2022 Choose a reason for hiding this comment The reason will be displayed to describe this comment to others. Learn more. This is done to avoid excessive duplication since all `BasePandasDataset` methods already present in the `DataFrame` and `Series` sections. Copy link Collaborator YarShev May 18, 2022 Choose a reason for hiding this comment The reason will be displayed to describe this comment to others. Learn more. I see. We should probably add a note in the docstring of `BasePandasDataset` about the user shouldn't directly interact with this object. Also, we should correct the methods' docstrings of this object. For example, we say `Return a` BasePandasDataset `with absolute numeric value of each element.` for `abs` whereas the return object is either a `DataFrame` or `Series`. This looks like a separate issue. Could you create one for this please? Copy link Contributor alexander3774 May 31, 2022 Choose a reason for hiding this comment The reason will be displayed to describe this comment to others. Learn more. Yes, sure, note was added and issue #4512 created.