house_train1 = utils.drop_features(house_train, features_to_drop)
house_train1.info()
#build pipeline for categorical features
categorical_pipeline = pipeline.Pipeline([
('imputer', impute.SimpleImputer(strategy="most_frequent")),
('ohe', preprocessing.OneHotEncoder(sparse=False, handle_unknown='ignore'))
])
#build pipeline for numerical features
numerical_pipeline = pipeline.Pipeline([('imputer', impute.SimpleImputer()),
('scaler',
preprocessing.StandardScaler())])
#build preprocessing pipeline for all features
cat_features = utils.get_non_continuous_features(house_train1)
num_features = utils.get_continuous_features(house_train1)
preprocess_pipeline = compose.ColumnTransformer([
('cat', categorical_pipeline, cat_features),
('num', numerical_pipeline, num_features)
])
#build complete pipeline with feature selection and ml algorithms
complete_pipeline = pipeline.Pipeline([
('preprocess', preprocess_pipeline),
('zv_filter', feature_selection.VarianceThreshold()),
('feature_selector',
feature_selection.SelectFromModel(linear_model.Lasso())),
('pca', decomposition.PCA()),
('regressor', neighbors.KNeighborsRegressor())
path = 'E://'
house_train = pd.read_csv(os.path.join(path, "house_train.csv"))
house_train.shape
house_train.info()
house_test = pd.read_csv(os.path.join(path, "house_test.csv"))
house_test.shape
house_test.info()
house = pd.concat((house_train, house_test), axis=0)
house.shape
house.info()
print(utils.get_continuous_features(house))
print(utils.get_non_continuous_features(house))
sns.countplot(x='YearBuilt', data=house_train)
sns.jointplot(x="SalePrice", y="YearBuilt", data=house_train)
sns.FacetGrid(house_train, hue="YearBuilt",
size=8).map(sns.kdeplot, "SalePrice").add_legend()
sns.countplot(x='YrSold', data=house_train)
sns.jointplot(x="SalePrice", y="YrSold", data=house_train)
sns.FacetGrid(house_train, hue="YrSold", size=8).map(sns.kdeplot,
"SalePrice").add_legend()
features_to_cast = ['MSSubClass']
utils.cast_to_cat(house, features_to_cast)
features_to_drop = ['Id']
