REFACTOR: support mypy checks in 'strict' mode (#346)

Author: j-ittner

.pre-commit-config.yaml

@@ -38,4 +38,4 @@ repos:
         additional_dependencies:
           - numpy~=1.22
           - gamma-pytools~=2.0,!=2.0.0
-          - sklearndf>=2.0.dev3,<3a
+          - sklearndf~=2.0

condabuild/meta.yaml

@@ -45,6 +45,7 @@ test:
     - typing_inspect {{ environ.get('FACET_V_TYPING_INSPECT') }}
     # additional requirements of shap
     - ipython        {{ environ.get('FACET_V_IPYTHON') }}
+    - numba          {{ environ.get('FACET_V_NUMBA') }}
   commands:
     - conda list
     - python -c 'import facet;

environment.yml

@@ -14,8 +14,8 @@ dependencies:
   - python ~= 3.8.12
   - scikit-learn ~= 1.0.2
   - scipy ~= 1.8
-  - shap ~=0.40
-  - sklearndf >= 2.0.dev3, < 3a
+  - shap ~= 0.41
+  - sklearndf ~= 2.0
   # build/test
   - conda-build ~= 3.21
   - conda-verify ~= 3.1

mypy.ini

@@ -1,6 +1,6 @@
 [mypy]
 show_error_codes = True
-allow_redefinition = True
+strict = True
 
 [mypy-catboost.*]
 ; TODO remove once PEP 561 is supported

pyproject.toml

@@ -14,14 +14,14 @@ dist-name = "gamma-facet"
 license = "Apache Software License v2.0"
 
 requires = [
-    "gamma-pytools  ~=2.0,>=2.0.1",
+    "gamma-pytools  ~=2.0",
     "matplotlib     ~=3.0",
     "numpy          >=1.21,<2a",  # cannot use ~= due to conda bug
     "packaging      >=20",
-    "pandas         >=1,<2a",  # cannot use ~= due to conda bug
+    "pandas         ~=1.0",
     "scipy          ~=1.2",
-    "shap           >=0.34,<0.41a",
-    "sklearndf      ~=2.0.dev3",
+    "shap           >=0.34,<0.42a",
+    "sklearndf      ~=2.0",
 ]
 
 requires-python = ">=3.7,<4a"
@@ -82,7 +82,7 @@ pandas         = "~=1.0.5"
 python         = ">=3.7.12,<3.8a"    # cannot use ~= due to conda bug
 scipy          = "~=1.4.1"
 shap           = "~=0.34.0"
-sklearndf      = "~=2.0.dev3"
+sklearndf      = "~=2.0.0"
 # additional minimum requirements of sklearndf
 boruta         = "~=0.3.0"
 lightgbm       = "~=3.0.0"
@@ -93,18 +93,19 @@ joblib         = "~=0.14.1"
 typing_inspect = "~=0.4.0"
 # additional minimum requirements of shap
 ipython        = "==7.0"
+numba          = "~=0.55"  # required to support numpy 1.21
 
 [build.matrix.max]
 # direct requirements of gamma-facet
 gamma-pytools  = "~=2.0,>=2.0.1"
 matplotlib     = "~=3.5"
-numpy          = ">=1.23,<2a"  # cannot use ~= due to conda bug
+numpy          = ">=1.22,<2a"  # cannot use ~= due to conda bug
 packaging      = ">=20"
 pandas         = "~=1.4"
 python         = ">=3.8.10,<4a"   # cannot use ~= due to conda bug
 scipy          = "~=1.8"
-shap           = "~=0.40.0"
-sklearndf      = ">=2.0.dev3,<3a"
+shap           = "~=0.41"
+sklearndf      = "~=2.0"
 # additional maximum requirements of sklearndf
 boruta         = "~=0.3"
 lightgbm       = "~=3.3"
@@ -115,6 +116,7 @@ joblib         = "~=1.1"
 typing_inspect = "~=0.7"
 # additional maximum requirements of shap
 ipython        = ">=7"
+numba          = ">=0.55.2"  # required to support numpy 1.22
 
 [tool.black]
 # quiet = "True"

src/facet/data/_sample.py

@@ -81,7 +81,7 @@ def __init__(
             observation
         """
 
-        def _ensure_columns_exist(column_type: str, columns: List[str]):
+        def _ensure_columns_exist(column_type: str, columns: List[str]) -> None:
             # check if all provided feature names actually exist in the observations df
             available_columns: pd.Index = observations.columns
             missing_columns = {
@@ -273,25 +273,25 @@ def subsample(
             )
         return subsample
 
-    def keep(self, *, feature_names: Union[str, Collection[str]]) -> "Sample":
+    def keep(self, *, feature_names: Union[str, Iterable[str]]) -> "Sample":
         """
         Return a new sample which only includes the features with the given names.
 
         :param feature_names: name(s) of the features to be selected
         :return: copy of this sample, containing only the features with the given names
         """
 
-        feature_names: List[str] = to_list(feature_names, element_type=str)
+        feature_names_list: List[str] = to_list(feature_names, element_type=str)
 
-        if not set(feature_names).issubset(self._feature_names):
+        if not set(feature_names_list).issubset(self._feature_names):
             raise ValueError(
                 "arg feature_names is not a subset of the features in this sample"
             )
 
         subsample = copy(self)
-        subsample._feature_names = feature_names
+        subsample._feature_names = feature_names_list
 
-        columns = [*feature_names, *self._target_names]
+        columns = [*feature_names_list, *self._target_names]
         weight = self._weight_name
         if weight and weight not in columns:
             columns.append(weight)
@@ -306,17 +306,17 @@ def drop(self, *, feature_names: Union[str, Collection[str]]) -> "Sample":
         :param feature_names: name(s) of the features to be dropped
         :return: copy of this sample, excluding the features with the given names
         """
-        feature_names: Set[str] = to_set(feature_names, element_type=str)
+        feature_names_set: Set[str] = to_set(feature_names, element_type=str)
 
-        unknown = feature_names.difference(self._feature_names)
+        unknown = feature_names_set.difference(self._feature_names)
         if unknown:
             raise ValueError(f"unknown features in arg feature_names: {unknown}")
 
         return self.keep(
             feature_names=[
                 feature
                 for feature in self._feature_names
-                if feature not in feature_names
+                if feature not in feature_names_set
             ]
         )