from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
import preprocessors as pp
import utils as ut
config = ut.read_config_file('config.yaml')
titanic_pipe = Pipeline(
# complete with the list of steps from the preprocessors file
# and the list of variables from the config
[('categorical_imputer',
pp.CategoricalImputer(
variables=config[2]['Feature_Groups'].get('categorical_vars'))),
('missing_indicator',
pp.MissingIndicator(
variables=config[2]['Feature_Groups'].get('numerical_to_impute'))),
('numerical_imputer',
pp.NumericalImputer(
variables=config[2]['Feature_Groups'].get('numerical_to_impute'))),
('cabin_variable',
pp.ExtractFirstLetter(
variables=config[2]['Feature_Groups'].get('categorical_vars')[1])),
('rare_label_encoder',
pp.RareLabelCategoricalEncoder(
tol=0.05,
variables=config[2]['Feature_Groups'].get('categorical_vars'))),
('categorical_encoder',
pp.CategoricalEncoder(
variables=config[2]['Feature_Groups'].get('categorical_vars'))),
('scaler', StandardScaler()),
('linear_model', LogisticRegression(C=0.0005, random_state=0))])
from sklearn.linear_model import LogisticRegression
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
import preprocessors as pp
import config
titanic_pipe = Pipeline(
# complete with the list of steps from the preprocessors file
# and the list of variables from the config
[
('missing_indicator',
pp.MissingIndicator(variables=config.NUMERICAL_VARS)),
('categorical_imputer',
pp.CategoricalImputer(variables=config.CATEGORICAL_VARS)),
('numerical_inputer',
pp.NumericalImputer(variables=config.NUMERICAL_VARS)),
('extract_firstletter',
pp.ExtractFirstLetter(variables=config.CABIN)),
('rare_label_encoder',
pp.RareLabelCategoricalEncoder(
tol=0.05,
variables=config.CATEGORICAL_VARS)),
('categorical_encoder',
pp.CategoricalEncoder(variables=config.CATEGORICAL_VARS)),
from sklearn.linear_model import LogisticRegression
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
import preprocessors as pp
import config
titanic_pipe = Pipeline(
# complete with the list of steps from the preprocessors file
# and the list of variables from the config
[
('extract_cabin_letter',
pp.ExtractFirstLetter(variables=config.CABIN)),
('missing_indicator',
pp.MissingIndicator(variables=config.INDICATE_MISSING_VARS)),
('impute_categorical',
pp.CategoricalImputer(variables=config.CATEGORICAL_VARS)),
('impute_numerical',
pp.NumericalImputer(variables=config.NUMERICAL_VARS)),
('encode_rare',
pp.RareLabelCategoricalEncoder(variables=config.CATEGORICAL_VARS,
tol=0.05)),
('encode_categorical',
pp.CategoricalEncoder(variables=config.CATEGORICAL_VARS)),
('scaler', StandardScaler()),
('model', LogisticRegression(C=0.0005, random_state=0)),
])
from sklearn.linear_model import LogisticRegression
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
import preprocessors as pp
import config
titanic_pipe = Pipeline([
# complete with the list of steps from the preprocessors file
# and the list of variables from the config
('categorical_imputer', pp.CategoricalImputer(config.CATEGORICAL_VARS)),
('missing_indicator', pp.MissingIndicator(config.NUMERICAL_VARS)),
('numerical_imputer', pp.NumericalImputer(config.NUMERICAL_VARS)),
('cabin_extractor', pp.ExtractFirstLetter(config.CABIN)),
('rare_labels',
pp.RareLabelCategoricalEncoder(tol=0.05,
variables=config.CATEGORICAL_VARS)),
('categorical_encoder',
pp.CategoricalEncoder(variables=config.CATEGORICAL_VARS)),
('scaler', StandardScaler()),
('model', LogisticRegression(C=0.0005, random_state=0))
])
from sklearn.linear_model import LogisticRegression
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
import preprocessors as pp
from config import *
titanic_pipe = Pipeline(
[
('categorical_imputer', pp.CategoricalImputer(variables=CATEGORICAL_VARS)),
('missing_indicator', pp.MissingIndicator(variables=NUMERICAL_VARS)),
('numerical_imputer', pp.NumericalImputer(variables=NUMERICAL_VARS)),
('extract_first_letter', pp.ExtractFirstLetter(variables=CABIN_VAR)),
('rare_label_encoding', pp.RareLabelCategoricalEncoder(tol=0.05, variables=CATEGORICAL_VARS)),
('categorical_encoding', pp.CategoricalEncoder(variables=CATEGORICAL_VARS)),
('scaler', StandardScaler()),
('model', LogisticRegression(C=0.0005, random_state=0))
]
)
from sklearn.linear_model import LogisticRegression
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
import preprocessors as pp
import config
titanic_pipe = Pipeline([
('first_letter_extractor', pp.ExtractFirstLetter(variables=config.CABIN)),
('missing_indicator',
pp.MissingIndicator(variables=config.CATEGORICAL_VARS)),
('categorical_imputer',
pp.CategoricalImputer(variables=config.CATEGORICAL_VARS)),
('numerical_inputer',
pp.NumericalImputer(variables=config.NUMERICAL_VARS)),
('rare_label_encoder',
pp.RareLabelCategoricalEncoder(tol=0.05,
variables=config.CATEGORICAL_VARS)),
('categorical_encoder',
pp.CategoricalEncoder(variables=config.CATEGORICAL_VARS)),
('scaler', StandardScaler()),
('Linear_model', LogisticRegression(C=0.0005, random_state=0))
])
from sklearn.linear_model import LogisticRegression
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
import preprocessors as pp
import config
titanic_pipe = Pipeline(
# complete with the list of steps from the preprocessors file
# and the list of variables from the config
[('first_letter_extractor', pp.ExtractFirstLetter(variables=config.CABIN)),
('missing_indicator',
pp.MissingIndicator(variables=config.NUMERICAL_VARS_TO_IMPUTE)),
('numerical_imputer',
pp.NumericalImputer(variables=config.NUMERICAL_VARS)),
('categorical_imputer',
pp.CategoricalImputer(variables=config.CATEGORICAL_VARS)),
('rare_label_encoder',
pp.RareLabelCategoricalEncoder(tol=0.05,
variables=config.CATEGORICAL_VARS)),
('categorical_encoding',
pp.CategoricalEncoder(variables=config.CATEGORICAL_VARS)),
('scaler', StandardScaler()),
('Logistic_model', LogisticRegression(C=0.0005, random_state=0))])
