from sklearn.pipeline import Pipeline
from sklearn.preprocessing import MinMaxScaler
from regression_model.processing import preprocessors as pp
from regression_model.processing import features
from regression_model.config import config
import logging
_logger = logging.getLogger(__name__)
price_pipe = Pipeline([
('categorical_imputer',
pp.CategoricalImputer(variables=config.CATEGORICAL_VARS_WITH_NA)),
('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()), ('forest', Lasso(random_state=0))
])
# -*- coding: utf-8 -*-
"""
Created on Wed Aug 12 13:02:04 2020
@author: rkbra
"""
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import MinMaxScaler
from sklearn.ensemble import RandomForestRegressor
from regression_model.processing import preprocessors as pp
from regression_model.processing import features
from regression_model.config import config
pipeline = Pipeline(
[
('duration_transformer', features.DurationTransformer()),
('journey_data_transformer', features.JourneyDateTransformer()),
('departure_time_transformer', features.DepartureTimeTransformer()),
('arival_time_transformer', features.ArrivalTimeTransformer()),
('total_stop_transformer', pp.TotalStopTransformer()),
('rare_label_encoder', pp.RareLabelCategoricalEncoder(tol=0.0015, variables=config.FEATURE_WITH_RARE_LABELS)),
('encoder', pp.Encoder(variables=config.CATEGORICAL_FEATURES)),
('scaler', MinMaxScaler()),
('model', RandomForestRegressor(n_estimators=100))
]
)
from sklearn.ensemble import RandomForestRegressor
from sklearn.pipeline import Pipeline
from regression_model.processing import preprocessors as pp
from regression_model.config import config
marathon_pipeline = Pipeline([
(
"categorical_imputer",
pp.CategoricalImputer(variables=config.CATEGORICAL_VARS_WITH_NA),
),
(
"rare_label_encoder",
pp.RareLabelCategoricalEncoder(variables=config.CATEGORICAL_VARS),
),
("ordinal_encoder",
pp.CategoricalEncoder(variables=config.CATEGORICAL_VARS)),
("regressor",
RandomForestRegressor(max_depth=4, n_estimators=100, random_state=0))
])
from regression_model.processing import features
from regression_model.processing import preprocessors as pp
from regression_model.config import config
import logging
_logger = logging.getLogger(__name__)
price_pipe = Pipeline([
(
"categorical_imputer",
pp.CategoricalImputer(variables_path=config.CATEGORICAL_VARS_FILE),
),
(
"numerical_inputer",
pp.NumericalImputer(variables_path=config.NUMERICAL_VARS_FILE),
),
(
"rare_label_encoder",
pp.RareLabelCategoricalEncoder(
tol=0.01, variables_path=config.CATEGORICAL_VARS_FILE),
),
("log_transformer",
features.LogTransformer(variables_path=config.NUMERICAL_LOG_VARS_FILE)),
(
"scaler",
MinMaxScaler(),
),
("Linear_model", Lasso(alpha=0.005, random_state=0)),
])
