def pipeline(config):
match_pipe = Pipeline([
('drop_fatures',
pp.DropUnecessaryFeatures(
variables_to_drop=config.variables.drop_features)),
('categorical_to_numerical',
pp.CategoricalToNumerical(
variables=config.variables.numerical_vars_from_numerical)),
('numerical_imputer', pp.NumericalImputer()),
('categorical_imputer',
pp.CategoricalImputer(variables=config.variables.categorical_vars)),
#('temporal_variable',
# pp.TemporalVariableEstimator(
# variables=config.TEMPORAL_VARS,
# reference_variable=config.DROP_FEATURES)),
('label extraction',
pp.LabelExtraction(
variables=config.variables.categorical_label_extraction)),
('rare label encoder',
pp.RareLabelCategoricalEncoder(
tol=0.01, variables=config.variables.categorical_vars)),
('categorical_encoder',
pp.CategoricalEncoder(variables=config.variables.categorical_vars)),
#('feature hashing',
# FeatureHasher(n_features=10, input_type='string')),
#('log_transformer',
# pp.LogTransformer()),
('scaler', MinMaxScaler()),
('classifier', LogisticRegression())
])
return match_pipe
# variables to log transform
NUMERICALS_LOG_VARS = ['LotFrontage', '1stFlrSF', 'GrLivArea']
# numerical variables with NA in train set
NUMERICAL_VARS_WITH_NA = ['LotFrontage']
# categorical variables to encode
CATEGORICAL_VARS = [
'MSZoning', 'Neighborhood', 'RoofStyle', 'MasVnrType', 'BsmtQual',
'BsmtExposure', 'HeatingQC', 'CentralAir', 'KitchenQual', 'FireplaceQu',
'GarageType', 'GarageFinish', 'PavedDrive'
]
price_pipe = Pipeline([
('categorical_imputer',
pp.CategoricalImputer(variables=CATEGORICAL_VARS_WITH_NA)),
('numerical_inputer',
pp.NumericalImputer(variables=NUMERICAL_VARS_WITH_NA)),
('temporal_variable',
pp.TemporalVariableEstimator(variables=TEMPORAL_VARS,
reference_variable=TEMPORAL_VARS)),
('rare_label_encoder',
pp.RareLabelCategoricalEncoder(tol=0.01, variables=CATEGORICAL_VARS)),
('categorical_encoder', pp.CategoricalEncoder(variables=CATEGORICAL_VARS)),
('log_transformer', pp.LogTransformer(variables=NUMERICALS_LOG_VARS)),
('drop_features',
pp.DropUnecessaryFeatures(variables_to_drop=DROP_FEATURES)),
('scaler', MinMaxScaler()),
('Linear_model', Lasso(alpha=0.005, random_state=0))
])
),
(
"numerical_inputer",
pp.NumericalImputer(variables=config.NUMERICAL_VARS_WITH_NA),
),
(
"temporal_variable",
pp.TemporalVariableEstimator(variables=config.TEMPORAL_VARS,
reference_variable=config.DROP_FEATURES),
),
(
"rare_label_encoder",
pp.RareLabelCategoricalEncoder(tol=0.01,
variables=config.CATEGORICAL_VARS),
),
(
"categorical_encoder",
pp.CategoricalEncoder(variables=config.CATEGORICAL_VARS),
),
# (
# "log_transformer",
# features.LogTransformer(variables=config.NUMERICALS_LOG_VARS),
# ),
(
"drop_features",
pp.DropUnecessaryFeatures(variables_to_drop=config.DROP_FEATURES),
),
("scaler", MinMaxScaler()),
("Linear_model", Lasso(alpha=0.005, random_state=0)),
])
import config
review_pipe = Pipeline([
("f1",
FeatureUnion([
("p1",
Pipeline([
('text_cleaner_1',
pp.TextCleaner(variables=config.TEXT_FEATURES)),
('text_lematizer_1',
pp.TextLematizer(variables=config.TEXT_FEATURES)),
('create_length_feature_1',
pp.CreateLengthFeature(variables=config.TEXT_FEATURES)),
('standrd_scaling_numeric_1',
pp.StandardScalarNumeric(variables=config.NUMERIC_FEATURES)),
('drop_features_1', pp.DropUnecessaryFeatures()),
])),
("p2",
Pipeline([
('text_cleaner_2',
pp.TextCleaner(variables=config.TEXT_FEATURES)),
('text_lematizer_2',
pp.TextLematizer(variables=config.TEXT_FEATURES)),
('tfidf_converter_text_2', pp.TfidfConverterText()),
])),
("p3",
Pipeline([
('text_cleaner_3',
pp.TextCleaner(variables=config.TEXT_FEATURES)),
('text_lematizer_3',
pp.TextLematizer(variables=config.TEXT_FEATURES)),
