refactor: apply flake8-simplify checks

This commit applies flake8-simplify checks to the codebase. The non-style refactoring included in this commit is primarily condensing nested ifs and using or/and instead.

pycytominer/cyto_utils/annotate_custom.py

@@ -82,14 +82,13 @@ def annotate_cmap(
                 "Metadata_mg_per_ml",
             ] = 0
 
-    if perturbation_mode == "genetic":
-        if "Metadata_pert_name" in annotated.columns:
-            annotated = annotated.assign(
-                Metadata_broad_sample_type=[
-                    "control" if x == "EMPTY" else "trt"
-                    for x in annotated.Metadata_pert_name
-                ]
-            )
+    if perturbation_mode == "genetic" and "Metadata_pert_name" in annotated.columns:
+        annotated = annotated.assign(
+            Metadata_broad_sample_type=[
+                "control" if x == "EMPTY" else "trt"
+                for x in annotated.Metadata_pert_name
+            ]
+        )
 
     if "Metadata_broad_sample_type" in annotated.columns:
         annotated = annotated.assign(

pycytominer/cyto_utils/cells.py

@@ -124,7 +124,7 @@ def __init__(
 
         # Check that the subsample_frac is between 0 and 1
         assert (
-            0 < subsample_frac and 1 >= subsample_frac
+            subsample_frac > 0 and subsample_frac <= 1
         ), "subsample_frac must be between 0 and 1"
 
         self.sql_file = sql_file
@@ -795,9 +795,9 @@ def merge_single_cells(
             if normalize_args is None:
                 normalize_args = {}
                 features = infer_cp_features(sc_df, compartments=self.compartments)
-            elif "features" not in normalize_args:
-                features = infer_cp_features(sc_df, compartments=self.compartments)
-            elif normalize_args["features"] == "infer":
+            elif ("features" not in normalize_args) or (
+                normalize_args["features"] == "infer"
+            ):
                 features = infer_cp_features(sc_df, compartments=self.compartments)
             else:
                 features = normalize_args["features"]
@@ -860,8 +860,7 @@ def aggregate_profiles(
         if output_file is not None:
             self.set_output_file(output_file)
 
-        compartment_idx = 0
-        for compartment in self.compartments:
+        for compartment_idx, compartment in enumerate(self.compartments):
             if compartment_idx == 0:
                 aggregated = self.aggregate_compartment(
                     compartment=compartment,
@@ -879,7 +878,6 @@ def aggregate_profiles(
                     on=self.strata,
                     how="inner",
                 )
-            compartment_idx += 1
 
         self.is_aggregated = True
 

pycytominer/cyto_utils/cp_image_features.py

@@ -126,7 +126,7 @@ def aggregate_image_features(
         )
 
     # Aggregate other image features
-    if not len(np.setdiff1d(image_feature_categories, [count_prefix])) == 0:
+    if len(np.setdiff1d(image_feature_categories, [count_prefix])) != 0:
         image_features_df = image_features_df.drop(
             remove_cols, axis="columns", errors="ignore"
         )

pyproject.toml

@@ -131,7 +131,7 @@ select = [
     # flake8-debugger
     # "T10",
     # flake8-simplify
-    # "SIM",
+    "SIM",
     # isort
     # "I",
     # mccabe

tests/test_cyto_utils/test_cell_locations.py

@@ -26,8 +26,8 @@ def test_output_shape_and_required_columns(
     )
 
     # verify that the Nuclear_Location_Center_X and Nuclear_Location_Center_Y columns are present
-    assert "Nuclei_Location_Center_X" in cell_loc["CellCenters"][0][0].keys()
-    assert "Nuclei_Location_Center_Y" in cell_loc["CellCenters"][0][0].keys()
+    assert "Nuclei_Location_Center_X" in cell_loc["CellCenters"][0][0]
+    assert "Nuclei_Location_Center_Y" in cell_loc["CellCenters"][0][0]
 
 
 @pytest.mark.parametrize("cell_loc", ["cell_loc1", "cell_loc2", "cell_loc3"])

tests/test_cyto_utils/test_cells.py

@@ -311,7 +311,7 @@ def test_load_compartment():
         # note: pd.api.types.is_integer sometimes is unable to detect int64
         or CELLS_DF[colname].dtype == "int64"
         # avoid recasting the metadata_types
-        and colname not in metadata_types.keys()
+        and colname not in metadata_types
     }
 
     # create deep copy of CELLS_DF with manually re-typed float columns as float32

tests/test_cyto_utils/test_load.py

@@ -95,9 +95,9 @@
 platemap_df.to_csv(output_platemap_file_gzip, sep="\t", index=False, compression="gzip")
 
 # Write npz temp files
-key_values = {k: npz_metadata_dict[k] for k in npz_metadata_dict.keys()}
+key_values = {k: npz_metadata_dict[k] for k in npz_metadata_dict}
 npz_metadata_dict.update(npz_model_key)
-key_with_model_values = {k: npz_metadata_dict[k] for k in npz_metadata_dict.keys()}
+key_with_model_values = {k: npz_metadata_dict[k] for k in npz_metadata_dict}
 
 np.savez_compressed(output_npz_file, features=npz_feats, metadata=key_values)
 np.savez_compressed(