started adding linters

Author: wegar-2

.flake8

@@ -0,0 +1,4 @@
+[flake8]
+max-line-length = 79
+extend-ignore = E203, W503
+exclude = .git,__pycache__,build,dist,.venv

moddata/__init__.py

@@ -2,4 +2,4 @@
 
 __all__ = [
     "load_data"
-]
+]

moddata/_utils.py

@@ -32,7 +32,8 @@ def _load_bankchurn() -> pd.DataFrame:
 
 
 def _load_btc():
-    path: Path = Path(kagglehub.dataset_download("prasoonkottarathil/btcinusd"))
+    path: Path = Path(
+        kagglehub.dataset_download("prasoonkottarathil/btcinusd"))
     datas: list[pd.DataFrame] = []
     for p in path.glob("*min.csv"):
         datas.append(

moddata/data/_setup_data.py

@@ -3,7 +3,6 @@
 from pathlib import Path
 from typing import Final
 
-import numpy as np
 import pandas as pd
 
 
@@ -32,9 +31,9 @@ def _extract_stooq_datas(file_to_ticker: dict[str, str]) -> pd.DataFrame:
     for file, ticker in file_to_ticker.items():
         datas.append(_extract_stooq_data(file=file, ticker=ticker))
     data: pd.DataFrame = reduce(
-        lambda l, r: pd.merge(
-            left=l,
-            right=r,
+        lambda l_, r_: pd.merge(
+            left=l_,
+            right=r_,
             left_index=True,
             right_index=True,
             how="outer"

moddata/extractor/bankchurn_extractor.py

@@ -3,6 +3,7 @@
 from moddata import load_data
 from moddata.src.constants import XyDataFrames
 
+
 class BankchurnExtractor:
 
     def extract(self) -> XyDataFrames:

moddata/sklearn_extensions/log_standard_scaler.py

@@ -57,7 +57,9 @@ def fit(self, X: pd.DataFrame):
 
     def transform(self, X: pd.DataFrame):
         if not isinstance(X, pd.DataFrame):
-            raise ValueError("This transformer only accepts pd.DataFrame input!")
+            raise ValueError(
+                "This transformer only accepts pd.DataFrame input!"
+            )
         X_log = self._log_transform(X=X)
         return self._standard_scaler.transform(X=X_log + self.shift)
 

moddata/src/extractor.py

@@ -5,4 +5,3 @@ class Extractor(Protocol):
 
     def extract(self, *args, **kwargs):
         pass
-    

moddata/src/pipeline.py

@@ -5,4 +5,3 @@ class Pipeline(Protocol):
 
     def run(self) -> Any:
         pass
-    

moddata/src/transformer.py

@@ -1,4 +1,4 @@
-from typing import Any, Protocol, TypeAlias, Union
+from typing import Any, Protocol, TypeAlias
 
 import pandas as pd
 

moddata/transformer/bankchurn_transformer.py

@@ -55,8 +55,10 @@ def _get_column_transformer(
         if encoding_and_scaling_model_type == "tree_like":
             return ColumnTransformer(
                 transformers=[
-                    ("ohe_gender_encoder", self._ohe_gender_encoder(), ["gender"]),
-                    ("ohe_encode_country", self._ohe_encode_country(), ["country"])
+                    ("ohe_gender_encoder", self._ohe_gender_encoder(),
+                     ["gender"]),
+                    ("ohe_encode_country", self._ohe_encode_country(),
+                     ["country"])
                 ],
                 remainder="passthrough",
                 force_int_remainder_cols=False,
@@ -66,10 +68,20 @@ def _get_column_transformer(
         elif encoding_and_scaling_model_type == "other":
             return ColumnTransformer(
                 transformers=[
-                    ("ohe_gender_encoder", self._ohe_gender_encoder(), ["gender"]),
-                    ("ohe_encode_country", self._ohe_encode_country(), ["country"]),
-                    ("credit_score_dist_scaler", self._credit_score_dist_scaler(), ["credit_score"]),
-                    ("estimated_salary_scaler", self._estimated_salary_scaler(), ["estimated_salary"]),
+                    ("ohe_gender_encoder", self._ohe_gender_encoder(),
+                     ["gender"]),
+                    ("ohe_encode_country", self._ohe_encode_country(),
+                     ["country"]),
+                    (
+                        "credit_score_dist_scaler",
+                        self._credit_score_dist_scaler(),
+                        ["credit_score"]
+                    ),
+                    (
+                        "estimated_salary_scaler",
+                        self._estimated_salary_scaler(),
+                        ["estimated_salary"]
+                    ),
                     ("age_scaler", self._age_scaler(), ["age"]),
                     ("balance_scaler", self._balance_scaler(), ["balance"])
                 ],
@@ -94,7 +106,9 @@ def transform(
         )
         if self._config.encoding_and_scaling_model_type is not None:
             col_trfm: ColumnTransformer = self._get_column_transformer(
-                encoding_and_scaling_model_type=self._config.encoding_and_scaling_model_type
+                encoding_and_scaling_model_type=(
+                    self._config.encoding_and_scaling_model_type
+                )
             )
             col_trfm.fit(X=X_train)
             X_train = pd.DataFrame(