Download custom_transformers.py from Quantum9999/RetailSlesPredictionBackend: direct link, hf CLI and curl.
- Browser
- Download file 2.97 kB
-
https://huggingface.co/spaces/Quantum9999/RetailSlesPredictionBackend/resolve/main/custom_transformers.py
- Command line
-
hf download hf://spaces/Quantum9999/RetailSlesPredictionBackend/custom_transformers.py
-
curl -L -o custom_transformers.py https://huggingface.co/spaces/Quantum9999/RetailSlesPredictionBackend/resolve/main/custom_transformers.py
2.97 kB
| import pandas as pd | |
| from datetime import datetime | |
| from sklearn.base import BaseEstimator, TransformerMixin | |
| from sklearn.preprocessing import OrdinalEncoder, StandardScaler, OneHotEncoder, FunctionTransformer | |
| from sklearn.pipeline import Pipeline | |
| from sklearn.compose import ColumnTransformer | |
| # Custom transformer to extract Product Prefix | |
| class ProductPrefixExtractor(BaseEstimator, TransformerMixin): | |
| def __init__(self, input_column='Product_Id', output_column='Product_Prefix'): | |
| self.input_column = input_column | |
| self.output_column = output_column | |
| def fit(self, X, y=None): | |
| return self | |
| def transform(self, X): | |
| X_copy = X.copy() | |
| X_copy[self.output_column] = X_copy[self.input_column].str[:2] | |
| return X_copy | |
| # Convert Store_Establishment_Year to Store_Age | |
| def convert_year_to_age(df): | |
| current_year = datetime.now().year | |
| df = df.copy() | |
| df['Store_Age'] = current_year - df['Store_Establishment_Year'] | |
| return df.drop(columns=['Store_Establishment_Year']) | |
| store_age_transformer = FunctionTransformer(convert_year_to_age) | |
| # Custom transformer to bin Store_Age into categories | |
| class StoreAgeBinner(BaseEstimator, TransformerMixin): | |
| def __init__(self, bins=None, labels=None): | |
| self.bins = bins if bins is not None else [0, 10, 30, 100] | |
| self.labels = labels if labels is not None else ['New', 'Mid', 'Old'] | |
| def fit(self, X, y=None): | |
| return self | |
| def transform(self, X): | |
| X_copy = X.copy() | |
| X_copy['Store_Age_Bin'] = pd.cut(X_copy['Store_Age'], bins=self.bins, labels=self.labels, right=False) | |
| return X_copy | |
| store_age_binner = StoreAgeBinner() | |
| # Feature groups | |
| ordinal_features = ['Store_Size', 'Store_Location_City_Type', 'Store_Age_Bin'] | |
| ordinal_categories = [ | |
| ['Small', 'Medium', 'High'], | |
| ['Tier 3', 'Tier 2', 'Tier 1'], | |
| ['New', 'Mid', 'Old'] | |
| ] | |
| nominal_features = ['Store_Id', 'Store_Type', 'Product_Prefix', 'Product_Sugar_Content', 'Product_Type'] | |
| numerical_features = ['Product_Weight', 'Product_Allocated_Area', 'Product_MRP'] | |
| # Encoders and scaler | |
| ordinal_encoder = OrdinalEncoder(categories=ordinal_categories) | |
| onehot_encoder = OneHotEncoder(handle_unknown='ignore') | |
| scaler = StandardScaler() | |
| # Pipelines for numeric and categorical features | |
| numeric_pipeline = Pipeline([ | |
| ('scaler', scaler) | |
| ]) | |
| categorical_pipeline = ColumnTransformer( | |
| transformers=[ | |
| ('ord', ordinal_encoder, ordinal_features), | |
| ('onehot', onehot_encoder, nominal_features) | |
| ], | |
| remainder='drop' | |
| ) | |
| # Full preprocessing pipeline | |
| preprocessor = Pipeline([ | |
| ('extract_prefix', ProductPrefixExtractor(input_column='Product_Id')), | |
| ('convert_age', store_age_transformer), | |
| ('bin_age', store_age_binner), | |
| ('preprocess', ColumnTransformer([ | |
| ('num', numeric_pipeline, numerical_features), | |
| ('cat', categorical_pipeline, ordinal_features + nominal_features) | |
| ], remainder='drop')) | |
| ]) | |