Refactoring

.github/workflows/main.yaml

@@ -6,8 +6,8 @@ jobs:
   main:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v3
-      - uses: actions/setup-python@v3
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
         with:
           python-version: 3.12.4
           cache: "pip"

.gitignore

@@ -6,7 +6,7 @@
 docs/Makefile
 docs/make.bat
 datasets
-
+.DS_Store/
 
 # Byte-compiled / optimized / DLL files
 __pycache__/

configs/models_configs.py

@@ -8,43 +8,35 @@
 XGBRegressorConfig = (
     xgb.XGBRegressor,
     {
-        "n_estimators": [100, 200, 500],
         "learning_rate": np.logspace(-2, -1, 3),
         "max_depth": [3, 5, 7],
-        "subsample": np.linspace(0.7, 1.0, 3),
-        "colsample_bytree": np.linspace(0.7, 1.0, 3),
     },
 )
 
-LassoConfig = (Lasso, {"alpha": np.logspace(-4, 1, 6)})
+LassoConfig = (Lasso, {"alpha": np.logspace(-3, 2, 6)})
 
-RidgeConfig = (Ridge, {"alpha": np.logspace(-1, 3, 5)})
+RidgeConfig = (Ridge, {"alpha": np.logspace(-3, 2, 5)})
 
 GradientBoostingRegressorConfig = (
     GradientBoostingRegressor,
     {
-        "n_estimators": [100, 200, 500],
         "learning_rate": np.logspace(-2, -1, 3),
         "max_depth": [3, 5, 7],
-        "subsample": np.linspace(0.7, 1.0, 3),
     },
 )
 
 KNeighborsRegressorConfig = (
     KNeighborsRegressor,
     {
         "n_neighbors": [3, 5, 10, 15],
-        "weights": ["uniform", "distance"],
-        "metric": ["euclidean", "manhattan", "minkowski"],
     },
 )
 
 SVRConfig = (
     SVR,
-    {"C": np.logspace(-1, 2, 4), "epsilon": np.linspace(0.01, 0.5, 4), "kernel": ["linear", "rbf", "poly"]},
+    {"C": np.logspace(-1, 2, 4), "epsilon": np.linspace(0.01, 0.5, 4)},
 )
 
-
 ModelsConfigs = {
     "XGBRegressor": XGBRegressorConfig,
     "Lasso": LassoConfig,

requirements.dev.txt

@@ -1,6 +1,8 @@
-mypy~=1.10.0
-black~=24.4.2
-isort~=5.13.2
-pytest~=7.4.4
-pandas-stubs~=2.2.3.250308
-hypothesis~=6.115.6
+mypy>=1.10.0
+black>=24.4.2
+isort>=5.13.2
+pytest>=7.4.4
+pandas-stubs>=2.2.3.250308
+hypothesis>=6.115.6
+seaborn >= 0.13.2
+matplotlib>=3.8.4

requirements.txt

@@ -1,5 +1,6 @@
-numpy~=1.26.4
-scipy~=1.13.1
-matplotlib~=3.8.4
-scikit-learn~=1.6.1
-pandas~=2.2.3
+numpy>=2.1.3
+scipy>=1.15.2
+scikit-learn>=1.6.1
+pandas>=2.2.3
+xgboost >= 3.0.0
+workalendar >= 17.0.0

src/models/time_series_model.py

@@ -143,6 +143,7 @@ def predict(self, X: pd.DataFrame) -> pd.DataFrame:
             forecast_list.extend(zip(X.loc[mask, self.keys_index], X.loc[mask, self.date_index], forecast_values))
         forecast_df = pd.DataFrame(forecast_list, columns=[self.keys_index, self.date_index, "Forecast"])
         X = X.merge(forecast_df, on=[self.keys_index, self.date_index], how="left")
+        X["Forecast"] = X["Forecast"].apply(lambda x: x if x >= 0 else 0)
         return X
 
     def score(
@@ -265,20 +266,10 @@ def _setup_searchers(self) -> tuple[GridSearchCV, GridSearchCV]:
         s_models = self._create_pipelines(self.seasonal_models)
 
         grid_search_trend = GridSearchCV(
-            trend_pipe,
-            t_models,
-            cv=self.cv,
-            scoring=self.scoring,
-            verbose=0,
-            n_jobs=-1,
+            trend_pipe, t_models, cv=self.cv, scoring=self.scoring, verbose=0, n_jobs=-1, refit=True
         )
         grid_search_seasonal = GridSearchCV(
-            seasonal_pipe,
-            s_models,
-            cv=self.cv,
-            scoring=self.scoring,
-            verbose=0,
-            n_jobs=-1,
+            seasonal_pipe, s_models, cv=self.cv, scoring=self.scoring, verbose=0, n_jobs=-1, refit=True
         )
         return grid_search_trend, grid_search_seasonal
 

src/special_preprocessing/transformers/features_extraction.py → src/special_preprocessing/date_transformers/features_extraction.py

@@ -3,7 +3,10 @@
 
 import pandas as pd
 from sklearn.base import BaseEstimator, TransformerMixin
+from sklearn.compose import ColumnTransformer
 from sklearn.exceptions import NotFittedError
+from sklearn.pipeline import Pipeline
+from sklearn.preprocessing import OneHotEncoder
 from statsmodels.tsa.deterministic import CalendarFourier, DeterministicProcess
 from workalendar.europe import Russia
 
@@ -113,3 +116,46 @@ def transform(self, X: pd.DataFrame) -> pd.DataFrame:
         X.drop(columns=columns_to_drop, inplace=True, errors="ignore")
 
         return X
+
+
+class FeatureExtractionTransformer(BaseEstimator, TransformerMixin):
+    def __init__(self) -> None:
+        self.pipe: Optional[Pipeline] = None
+
+    def fit(self, X: pd.DataFrame, y: Optional[pd.DataFrame] = None) -> "FeatureExtractionTransformer":
+        self.pipe = self.features_pipeline()
+        self.pipe.fit(X, y)
+        return self
+
+    @staticmethod
+    def features_pipeline() -> Pipeline:
+        ohe = ColumnTransformer(
+            transformers=[
+                (
+                    "ohe",
+                    OneHotEncoder(handle_unknown="ignore", sparse_output=False),
+                    ["holiday"],
+                )
+            ],
+            remainder="passthrough",
+            verbose_feature_names_out=False,
+            force_int_remainder_cols=False,
+        )
+        ohe.set_output(transform="pandas")
+        pipline = Pipeline(
+            steps=[
+                ("date_feature_transform", HolidayTransformer()),
+                ("ohe", ohe),
+                ("mean_ship_feature", MeanWeekMonthTransformer()),
+                (
+                    "fourier_features",
+                    FourierFeaturesTransformer(),
+                ),
+            ]
+        )
+        return pipline
+
+    def transform(self, X: pd.DataFrame) -> pd.DataFrame:
+        if self.pipe is None:
+            raise NotFittedError()
+        return self.pipe.transform(X)

src/special_preprocessing/transformers/series_comp.py → src/special_preprocessing/date_transformers/series_comp.py

@@ -30,8 +30,11 @@ def transform(self, X: pd.DataFrame) -> pd.DataFrame:
 
 
 class DateRangeFilledTransformer(BaseEstimator, TransformerMixin):
+    def __init__(self) -> None:
+        self._is_fitted_: bool = False
+
     def fit(self, X: pd.DataFrame, y: Optional[pd.DataFrame] = None) -> "DateRangeFilledTransformer":
-        self._is_fitted_: bool = True
+        self._is_fitted_ = True
         return self
 
     def transform(self, X: pd.DataFrame) -> pd.DataFrame:

src/special_preprocessing/preprocessing_pipeline.py → src/special_preprocessing/first_special_pipeline/pipeline.py

@@ -2,46 +2,15 @@
 from sklearn.pipeline import Pipeline
 from sklearn.preprocessing import OneHotEncoder
 
-from src.special_preprocessing.transformers.features_extraction import (
-    FourierFeaturesTransformer,
-    HolidayTransformer,
-    MeanWeekMonthTransformer,
-)
-from src.special_preprocessing.transformers.preprocessing import (
+from src.special_preprocessing.date_transformers.features_extraction import FeatureExtractionTransformer
+from src.special_preprocessing.date_transformers.series_comp import DateRangeFilledTransformer, GroupByDateTransformer
+from src.special_preprocessing.date_transformers.series_decomposition import Separation, SeriesDecompositionTransformer
+from src.special_preprocessing.first_special_pipeline.preprocessing import (
     ChangeTypesTransformer,
     DropDuplicatesTransformer,
     KeyIndexTransformer,
     NaNHandlerTransformer,
 )
-from src.special_preprocessing.transformers.series_comp import DateRangeFilledTransformer, GroupByDateTransformer
-from src.special_preprocessing.transformers.series_decomposition import Separation, SeriesDecompositionTransformer
-
-
-def features() -> Pipeline:
-    ohe = ColumnTransformer(
-        transformers=[
-            (
-                "ohe",
-                OneHotEncoder(handle_unknown="ignore", sparse_output=False),
-                ["holiday"],
-            )
-        ],
-        remainder="passthrough",
-        verbose_feature_names_out=False,
-    )
-    ohe.set_output(transform="pandas")
-    pipline = Pipeline(
-        steps=[
-            ("date_feature_transform", HolidayTransformer()),
-            ("ohe", ohe),
-            ("mean_ship_feature", MeanWeekMonthTransformer()),
-            (
-                "fourier_features",
-                FourierFeaturesTransformer(),
-            ),
-        ]
-    )
-    return pipline
 
 
 def preprocessing() -> Pipeline:
@@ -56,6 +25,7 @@ def preprocessing() -> Pipeline:
         ],
         remainder="passthrough",
         verbose_feature_names_out=False,
+        force_int_remainder_cols=False,
     )
     ohe.set_output(transform="pandas")
     pipline = Pipeline(
@@ -75,7 +45,7 @@ def preprocessing() -> Pipeline:
         ("base preprocessing", preprocessing()),
         ("fill_data_range", DateRangeFilledTransformer()),
         ("grouping", GroupByDateTransformer()),
-        ("features extraction", features()),
+        ("features extraction", FeatureExtractionTransformer()),
         ("decomposition", SeriesDecompositionTransformer()),
         ("separation", Separation()),
     ]

src/special_preprocessing/second_special_pipeline/pipeline.py

@@ -0,0 +1,24 @@
+from sklearn.pipeline import Pipeline
+
+from src.special_preprocessing.date_transformers.features_extraction import FeatureExtractionTransformer
+from src.special_preprocessing.date_transformers.series_decomposition import Separation, SeriesDecompositionTransformer
+from src.special_preprocessing.second_special_pipeline.preprocessing import (
+    CategoricalFeaturesTransform,
+    DateRangeFilledTransformerSec,
+    DiscountTransformer,
+    KeyTransformer,
+    RenameColumns,
+)
+
+preprocessing_pipeline = Pipeline(
+    steps=[
+        ("rename", RenameColumns()),
+        ("key", KeyTransformer()),
+        ("discount", DiscountTransformer()),
+        ("fill_data_range", DateRangeFilledTransformerSec()),
+        ("categorical_features_prep", CategoricalFeaturesTransform()),
+        ("features extraction", FeatureExtractionTransformer()),
+        ("decomposition", SeriesDecompositionTransformer()),
+        ("separation", Separation()),
+    ]
+)