pipeline.py

from sklearn.compose import ColumnTransformer
from sklearn.pipeline import Pipeline
from sklearn.ensemble import RandomForestRegressor, StackingRegressor
from sklearn.linear_model import Ridge, LinearRegression
from sklearn.preprocessing import OneHotEncoder, MinMaxScaler, StandardScaler
from sklearn.model_selection import train_test_split
from xgboost import XGBRegressor


preprocessor = ColumnTransformer(
    transformers=[
        ('logtransform', LogTransformer(), num_features),
        ('standardize', StandardScaler(), num_features), 
        ('onehotencode', OneHotEncoder(handle_unknown='ignore'), cat_features),
    ])

xgb_pipeline = Pipeline([
    ('preprocessor', preprocessor),
    ('regressor', XGBRegressor(tree_method='gpu_hist', objective='reg:squarederror', random_state=42))
])

rf_pipeline = Pipeline([
    ('preprocessor', preprocessor),
    ('regressor', RandomForestRegressor(random_state=42))
])

ridge_pipeline = Pipeline([
    ('preprocessor', preprocessor),
    ('regressor', Ridge(random_state=42))
])