ci(mypy): add mypy check and adjust code for types (#439)

* ci(mypy): add mypy check and adjust code for types

* remove redefinitions config

* update stubs and ignores

* update output for compression typing

* update expanduser types for cell_locations

* add ignore for change in types

* adjust for typing

* update celllocations typing

* remove ignores

* add missing library ignore settings; fix aggregate

* add test condition for aggregate

.github/workflows/integration-test.yml

@@ -56,6 +56,28 @@ jobs:
         uses: pre-commit/[email protected]
         with:
           extra_args: --all-files
+  python-type-checks:
+    # This job is used to check Python types
+    name: Python type checks
+    # Avoid fail-fast to retain output
+    strategy:
+      fail-fast: false
+    runs-on: ubuntu-22.04
+    if: github.event_name != 'schedule'
+    steps:
+      - name: Checkout repo
+        uses: actions/checkout@v4
+      - name: Setup python, and check pre-commit cache
+        uses: ./.github/actions/setup-env
+        with:
+          python-version: ${{ env.TARGET_PYTHON_VERSION }}
+          cache-pre-commit: false
+          cache-venv: true
+          setup-poetry: true
+          install-deps: true
+      - name: Run mypy
+        run: |
+          poetry run mypy .
   integration-test:
     name: Pytest (Python ${{ matrix.python-version }} on ${{ matrix.os }})
     # Runs pytest on all tested versions of python and OSes

pycytominer/aggregate.py

@@ -83,7 +83,7 @@ def aggregate(
     # Only extract single object column in preparation for count
     if compute_object_count:
         count_object_df = (
-            population_df.loc[:, np.union1d(strata, [object_feature])]
+            population_df.loc[:, list(np.union1d(strata, [object_feature]))]
             .groupby(strata)[object_feature]
             .count()
             .reset_index()
@@ -92,7 +92,9 @@ def aggregate(
 
     if features == "infer":
         features = infer_cp_features(population_df)
-    population_df = population_df[features]
+
+    # recast as dataframe to protect against scenarios where a series may be returned
+    population_df = pd.DataFrame(population_df[features])
 
     # Fix dtype of input features (they should all be floats!)
     population_df = population_df.astype(float)
@@ -101,7 +103,9 @@ def aggregate(
     population_df = pd.concat([strata_df, population_df], axis="columns")
 
     # Perform aggregating function
-    population_df = population_df.groupby(strata, dropna=False)
+    # Note: type ignore added below to address the change in variable types for
+    # label `population_df`.
+    population_df = population_df.groupby(strata, dropna=False)  # type: ignore[assignment]
 
     if operation == "median":
         population_df = population_df.median().reset_index()
@@ -118,10 +122,10 @@ def aggregate(
         for column in population_df.columns
         if column in ["ImageNumber", "ObjectNumber"]
     ]:
-        population_df = population_df.drop([columns_to_drop], axis="columns")
+        population_df = population_df.drop(columns=columns_to_drop, axis="columns")
 
     if output_file is not None:
-        output(
+        return output(
             df=population_df,
             output_filename=output_file,
             output_type=output_type,

pycytominer/cyto_utils/DeepProfiler_processing.py

@@ -7,8 +7,9 @@
 import pandas as pd
 import warnings
 
-from pycytominer import aggregate, normalize
-from pycytominer.cyto_utils import (
+# use mypy ignores below to avoid duplicate import warnings
+from pycytominer import aggregate, normalize  # type: ignore[no-redef]
+from pycytominer.cyto_utils import (  # type: ignore[no-redef]
     load_npz_features,
     load_npz_locations,
     infer_cp_features,

pycytominer/cyto_utils/cell_locations.py

@@ -106,7 +106,9 @@ def __init__(
             "s3", config=botocore.config.Config(signature_version=botocore.UNSIGNED)
         )
 
-    def _expanduser(self, obj: Union[str, None]):
+    def _expanduser(
+        self, obj: Union[str, pd.DataFrame, sqlalchemy.engine.Engine, None]
+    ):
         """Expand the user home directory in a path"""
         if obj is not None and isinstance(obj, str) and not obj.startswith("s3://"):
             return pathlib.Path(obj).expanduser().as_posix()

pycytominer/cyto_utils/cells.py

@@ -714,7 +714,7 @@ def merge_single_cells(
         """
 
         # Load the single cell dataframe by merging on the specific linking columns
-        sc_df = ""
+        left_compartment_loaded = False
         linking_check_cols = []
         merge_suffix_rename = []
         for left_compartment in self.compartment_linking_cols:
@@ -737,7 +737,7 @@ def merge_single_cells(
                     left_compartment
                 ]
 
-                if isinstance(sc_df, str):
+                if not left_compartment_loaded:
                     sc_df = self.load_compartment(compartment=left_compartment)
 
                     if compute_subsample:
@@ -752,6 +752,8 @@ def merge_single_cells(
                             sc_df, how="left", on=subset_logic_df.columns.tolist()
                         ).reindex(sc_df.columns, axis="columns")
 
+                    left_compartment_loaded = True
+
                 sc_df = sc_df.merge(
                     self.load_compartment(compartment=right_compartment),
                     left_on=[*self.merge_cols, left_link_col],
@@ -804,11 +806,13 @@ def merge_single_cells(
 
             normalize_args["features"] = features
 
-            sc_df = normalize(profiles=sc_df, **normalize_args)
+            # ignore mypy warnings below as these reference root package imports
+            sc_df = normalize(profiles=sc_df, **normalize_args)  # type: ignore[operator]
 
         # In case platemap metadata is provided, use pycytominer.annotate for metadata
         if platemap is not None:
-            sc_df = annotate(
+            # ignore mypy warnings below as these reference root package imports
+            sc_df = annotate(  # type: ignore[operator]
                 profiles=sc_df, platemap=platemap, output_file=None, **kwargs
             )
 

pycytominer/cyto_utils/collate.py

@@ -131,7 +131,7 @@ def collate(
         with sqlite3.connect(cache_backend_file, isolation_level=None) as connection:
             cursor = connection.cursor()
             if column:
-                if print:
+                if printtoscreen:
                     print(f"Adding a Metadata_Plate column based on column {column}")
                 cursor.execute("ALTER TABLE Image ADD COLUMN Metadata_Plate TEXT;")
                 cursor.execute(f"UPDATE image SET Metadata_Plate ={column};")