Set up Github Action tests & lints

Signed-off-by: Michal Siedlaczek <[email protected]>

.github/workflows/lint.yml

@@ -0,0 +1,31 @@
+name: Lints
+
+on:
+  workflow_dispatch:
+  push:
+    branches:
+      - main
+  pull_request:
+
+jobs:
+  build:
+
+    runs-on: "ubuntu-22.04"
+
+    steps:
+    - uses: actions/checkout@v3
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v3
+      with:
+        python-version: "3.10"
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        python -m pip install poetry
+        poetry install
+    - name: Pylint
+      run: |
+        poetry run pylint ibm_data_engine
+    - name: Formatting (black)
+      run: |
+        poetry run black --check ibm_data_engine

.github/workflows/publish.yml

@@ -0,0 +1,29 @@
+name: Upload Python Package
+
+on:
+  release:
+    types: [published]
+
+permissions:
+  contents: read
+
+jobs:
+  deploy:
+
+    runs-on: ubuntu-22.04
+
+    steps:
+    - uses: actions/checkout@v3
+    - name: Set up Python
+      uses: actions/setup-python@v3
+      with:
+        python-version: '3.x'
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        python -m pip install poetry
+        poetry install
+    - name: Build package
+      run: poetry build
+    - name: Publish package
+      run: poetry publish -u __token__ -p ${{ secrets.PYPI_API_TOKEN }}

.github/workflows/test.yml

@@ -0,0 +1,34 @@
+name: Unit tests
+
+on:
+  workflow_dispatch:
+  push:
+    branches:
+      - main
+  pull_request:
+
+jobs:
+  build:
+
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.8", "3.9", "3.10"]
+        runner: ["ubuntu-22.04", "windows-2022", "macos-12"]
+
+    runs-on: ${{ matrix.runner }}
+
+    steps:
+    - uses: actions/checkout@v3
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v3
+      with:
+        python-version: ${{ matrix.python-version }}
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        python -m pip install poetry
+        poetry install
+    - name: Test with pytest
+      run: |
+        poetry run pytest

.gitignore

@@ -158,6 +158,6 @@ cython_debug/
 
 # End of https://www.toptal.com/developers/gitignore/api/python
 
-.pylintrc
 pyrightconfig.json
 .envrc
+.python-version

.pylintrc

@@ -0,0 +1,6 @@
+[MESSAGES CONTROL]
+disable=too-few-public-methods,
+        too-many-instance-attributes
+
+[FORMAT]
+good-names=T,F,df,k,tf,b,k1,db,fs,fv

ibm_data_engine/data_engine_offline_store.py

@@ -399,7 +399,7 @@ def pull_latest_from_table_or_query(
         join_key_columns: List[str],
         feature_name_columns: List[str],
         timestamp_field: str,
-        created_timestamp_column: Optional[str],
+        created_timestamp_column: Optional[str],  # pylint: disable=unused-argument
         start_date: datetime,
         end_date: datetime,
     ) -> RetrievalJob:
@@ -423,7 +423,8 @@ def retrieve_df():
             where_clause = _where(join_key_columns, aliases=("de_a", "de_b"))
             sql_query = (
                 f"SELECT {fields} FROM {data_source.get_table_query_string()} as de_a "
-                f"JOIN ({inner()}) as de_b WHERE {where_clause} AND de_a.{timestamp_field} = de_b.timestamp"
+                f"JOIN ({inner()}) as de_b WHERE {where_clause} "
+                f"AND de_a.{timestamp_field} = de_b.timestamp"
             )
             return _sql_builder(config).run_sql(sql_query)
 
@@ -508,6 +509,7 @@ def _upload_entity_df(
             return copy_to
 
     elif isinstance(entity_df, str):
+        # pylint: disable=fixme
         # TODO: If the entity_df is a string (SQL query), create a  table out of it
         raise NotImplementedError
 
@@ -517,23 +519,24 @@ def _upload_entity_df(
 
 def _get_entity_schema(
     entity_df: Union[pd.DataFrame, str],
-    config: RepoConfig,
+    config: RepoConfig,  # pylint: disable=unused-argument
 ) -> Dict[str, np.dtype]:
     if isinstance(entity_df, pd.DataFrame):
         return dict(zip(entity_df.columns, entity_df.dtypes))
 
-    elif isinstance(entity_df, str):
+    if isinstance(entity_df, str):
         # If the entity_df is a string (SQL query)
-        # TODO:provide implementation for string entity
+        # pylint: disable=fixme
+        # TODO: provide implementation for string entity
         raise NotImplementedError
-    else:
-        raise InvalidEntityType(type(entity_df))
+
+    raise InvalidEntityType(type(entity_df))
 
 
 def _get_entity_df_event_timestamp_range(
     entity_df: Union[pd.DataFrame, str],
     entity_df_event_timestamp_col: str,
-    config: RepoConfig,
+    config: RepoConfig,  # pylint: disable=unused-argument
 ) -> Tuple[datetime, datetime]:
     if isinstance(entity_df, pd.DataFrame):
         entity_df_event_timestamp = entity_df.loc[:, entity_df_event_timestamp_col].infer_objects()
@@ -545,7 +548,8 @@ def _get_entity_df_event_timestamp_range(
         )
     elif isinstance(entity_df, str):
         # If the entity_df is a string (SQL query), determine range
-        # TODO:provide implementation for string query
+        # pylint: disable=fixme
+        # TODO: provide implementation for string query
         raise NotImplementedError
     else:
         raise InvalidEntityType(type(entity_df))