TEST-#2966: add script for testing docs

.github/workflows/ci.yml

@@ -32,7 +32,7 @@ jobs:
           python-version: "3.7.x"
           architecture: "x64"
       - run: pip install black
-      - run: black --check --diff modin/ asv_bench/benchmarks
+      - run: black --check --diff modin/ asv_bench/benchmarks scripts/doc_checker.py
 
   lint-pydocstyle:
     name: lint (pydocstyle)
@@ -45,13 +45,32 @@ jobs:
         with:
           python-version: "3.7.x"
           architecture: "x64"
-      - run: pip install pydocstyle
-      - run: pydocstyle --convention=numpy --add-ignore=D101,D102,D105 modin/pandas/dataframe.py modin/pandas/series.py modin/pandas/groupby.py modin/pandas/base.py
-      - run: pydocstyle --convention=numpy --add-ignore=D101,D103,D105 modin/pandas/io.py
-      - run: pydocstyle --convention=numpy --add-ignore=D101,D102 modin/pandas/series_utils.py
-      - run: pydocstyle --convention=numpy --add-ignore=D103 modin/pandas/general.py
-      - run: pydocstyle --convention=numpy modin/pandas/plotting.py modin/pandas/utils.py modin/pandas/iterator.py modin/pandas/indexing.py
-      - run: pydocstyle --convention=numpy --add-ignore=D100,D104 modin/engines/base/frame
+      - run: pip install pytest pytest-cov pydocstyle numpydoc
+      - run: pytest scripts/test
+      - run: pip install -e .[all]
+      - run: |
+          python scripts/doc_checker.py --add-ignore=D101,D102,D105 --disable-numpydoc \
+            modin/pandas/dataframe.py modin/pandas/series.py \
+            modin/pandas/groupby.py modin/pandas/base.py
+      - run: python scripts/doc_checker.py modin/pandas/io.py
+      - run: |
+          python scripts/doc_checker.py --add-ignore=D101,D102 --disable-numpydoc \
+            modin/pandas/series_utils.py
+      - run: |
+          python scripts/doc_checker.py --add-ignore=D103 --disable-numpydoc \
+            modin/pandas/general.py
+      - run: |
+          python scripts/doc_checker.py --disable-numpydoc \
+            modin/pandas/plotting.py modin/pandas/utils.py \
+            modin/pandas/iterator.py modin/pandas/indexing.py
+      - run: |
+          python scripts/doc_checker.py --add-ignore=D100,D104 --disable-numpydoc \
+            modin/engines/base/frame
+      - run: |
+          python scripts/doc_checker.py asv_bench/benchmarks/utils.py \
+            asv_bench/benchmarks/__init__.py asv_bench/benchmarks/io/__init__.py \
+            asv_bench/benchmarks/scalability/__init__.py
+      - run: python scripts/doc_checker.py scripts/doc_checker.py
 
   lint-flake8:
     name: lint (flake8)
@@ -65,7 +84,7 @@ jobs:
           python-version: "3.7.x"
           architecture: "x64"
       - run: pip install flake8 flake8-print
-      - run: flake8 --enable=T modin/ asv_bench/benchmarks
+      - run: flake8 --enable=T modin/ asv_bench/benchmarks scripts/doc_checker.py
 
   test-api:
     runs-on: ubuntu-latest

asv_bench/benchmarks/__init__.py

@@ -11,4 +11,4 @@
 # ANY KIND, either express or implied. See the License for the specific language
 # governing permissions and limitations under the License.
 
-"""Modin benchmarks"""
+"""Modin benchmarks."""

asv_bench/benchmarks/benchmarks.py

@@ -11,7 +11,7 @@
 # ANY KIND, either express or implied. See the License for the specific language
 # governing permissions and limitations under the License.
 
-"""General modin benchmarks"""
+"""General Modin benchmarks."""
 
 # define `MODIN_CPUS` env var to control the number of partitions
 # it should be defined before modin.pandas import (in case of using os.environ)

asv_bench/benchmarks/io/__init__.py

@@ -11,4 +11,4 @@
 # ANY KIND, either express or implied. See the License for the specific language
 # governing permissions and limitations under the License.
 
-"""IO modin benchmarks"""
+"""IO Modin benchmarks."""

asv_bench/benchmarks/io/csv.py

@@ -26,10 +26,6 @@
     get_shape_id,
 )
 
-# ray init
-if ASV_USE_IMPL == "modin":
-    pd.DataFrame([])
-
 
 class BaseReadCsv:
     # test data file can de created only once
@@ -44,6 +40,9 @@ def setup_cache(self, test_filename="io_test_file"):
         return test_filenames
 
     def setup(self, test_filenames, shape, *args, **kwargs):
+        # ray init
+        if ASV_USE_IMPL == "modin":
+            pd.DataFrame([])
         self.shape_id = get_shape_id(shape)
 
 
@@ -121,6 +120,9 @@ def setup_cache(self, test_filename="io_test_file_csv_names_dtype"):
         return cache
 
     def setup(self, cache, shape, names, dtype):
+        # ray init
+        if ASV_USE_IMPL == "modin":
+            pd.DataFrame([])
         file_id = self._get_file_id(shape, dtype)
         self.filename, self.names, self.dtype = cache[file_id]
 

asv_bench/benchmarks/scalability/__init__.py

@@ -11,4 +11,4 @@
 # ANY KIND, either express or implied. See the License for the specific language
 # governing permissions and limitations under the License.
 
-"""Benchmarks measuring how Modin performance scales when MODIN_CPUS are changed"""
+"""Benchmarks measuring how Modin performance scales when MODIN_CPUS are changed."""