fdd10.py

fdd10.py

from sklearn import set_config

set_config(display="diagram")
numeric_columns = X.select_dtypes(exclude='object').columns
numeric_transformer = Pipeline(steps = [("scalar", StandardScaler())])

unordered_columns =['transmission', 'fuel_type']
unordered_transformer = Pipeline(steps = [('onehot',  OneHotEncoder(handle_unknown='ignore', sparse=False))])

ordered_columns = ['year', 'model']
ordered_transformer = Pipeline(steps = [('ordinal', OrdinalEncoder())])

preprocessor = ColumnTransformer(
    transformers=[
        ('numeric_transformer', numeric_transformer, numeric_columns),
        ('unordered_transformer', unordered_transformer, unordered_columns),
        ('ordered_transformer', ordered_transformer, ordered_columns)
    ]
)

reg = Pipeline(
    steps=[
        ('preprocessor', preprocessor),
        ('regressor', ElasticNet())
    ]
)
y = df['price']
X = df.drop('price', axis = 1)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=0)

reg.fit(X_train, y_train)

preds = reg.predict(X_test)
score = np.sqrt(mean_squared_error(y_test, preds))