def run_training():
"""Train the model."""
data = pd.read_csv('titanic.csv')
X_train, X_test, y_train, y_test = train_test_split(data.drop('survived',
axis=1),
data['survived'],
test_size=0.2,
random_state=0)
print(X_train.head())
test_pipeline_1 = pp.CategoricalImputer(variables=config.CATEGORICAL_VARS)
test_pipeline_2 = pp.NumericalImputer(
variables=config.NUMERICAL_VARS_WITH_NA)
test_pipeline_3 = pp.ExtractFirstLetter(variables=config.CABIN)
test_pipeline_4 = pp.CategoricalEncoder(variables=config.CATEGORICAL_VARS)
X_train = test_pipeline_1.fit_transform(X_train)
X_train = test_pipeline_2.fit_transform(X_train)
X_train = test_pipeline_3.fit_transform(X_train)
print()
print(X_train.head())
print()
X_train = test_pipeline_4.fit_transform(X_train)
print(X_train.head())
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)),
('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
[('categorical_imputer',
pp.CategoricalImputer(variables=config.CATEGORICAL_VARS)),
('missing_indicator',
pp.MissingIndicator(variables=config.NUMERICAL_VARS)),
('numerical_imputer',
pp.NumericalImputer(variables=config.NUMERICAL_VARS)),
('cabin_variable', pp.ExtractFirstLetter(variables=config.CABIN)),
('rare_label_encoder',
pp.RareLabelCategoricalEncoder(tol=0.01,
variables=config.CATEGORICAL_VARS)),
('categorical_encoder',
pp.CategoricalEncoder(variables=config.CATEGORICAL_VARS)),
('scaler', StandardScaler()),
('Linear_model', LogisticRegression(C=0.0005, random_state=0))])
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_imputer',
pp.NumericalImputer(variables=config.NUMERICAL_VARS)),
('first_word_extractor', pp.ExtractFirstLetter(variables=config.CABIN)),
('frequent_label_encoder',
pp.RareLabelCategoricalEncoder(variables=config.CATEGORICAL_VARS)),
('categorical_encoder',
pp.CategoricalEncoder(variables=config.CATEGORICAL_VARS)),
('scaler', StandardScaler()),
('logistic_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)),
('numerical_imputer',
pp.NumericalImputer(variables=config.NUMERICAL_VARS)),
('extract_first_letter', pp.ExtractFirstLetter(variables=config.CABIN)),
('categorical_imputer',
pp.CategoricalImputer(variables=config.CATEGORICAL_VARS)),
('rare_label_categorical',
pp.RareLabelCategoricalEncoder(variables=config.CATEGORICAL_VARS)),
('categorical_encoder',
pp.CategoricalEncoder(variables=config.CATEGORICAL_VARS)),
('scaler', StandardScaler()),
('logistic_regression', 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
import config
titanic_pipe = Pipeline(
[('categorical_imputer', pp.CategoricalImputer(config.CATEGORICAL_VARS)),
('missing_indicator', pp.MissingIndicator(config.NUMERICAL_VARS)),
('numerical_imputer', pp.NumericalImputer(config.NUMERICAL_VARS)),
('extract_first_letter', pp.ExtractFirstLetter(config.CABIN)),
('rare_label_categorical_encoder',
pp.RareLabelCategoricalEncoder(0.05, config.CATEGORICAL_VARS)),
('categorical_encoder', pp.CategoricalEncoder(config.CATEGORICAL_VARS)),
('scaler', StandardScaler()),
('linear_model', LogisticRegression(C=0.0005, random_state=0))]
# complete with the list of steps from the preprocessors file
# and the list of variables from the config
)
import preprocessors as pp
import config
titanic_pipe = Pipeline(
[
('missing_indicator',
pp.MissingIndicator(variables = config.NUMERICAL_VARS_WITH_NA)),
('categorical_imputer',
pp.CategoricalImputer(variables = config.CATEGORICAL_VARS)),
('numerical_imputer',
pp.NumericalImputer(variables = config.NUMERICAL_VARS_WITH_NA)),
('extract_first_letter',
pp.ExtractFirstLetter(variables = config.CABIN)),
('rare_label_encoding',
pp.ExtractFirstLetter(variables = config.CATEGORICAL_VARS)),
('categorical_encoding',
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(
# complete with the list of steps from the preprocessors file
# and the list of variables from the config
[('missing_indicator',
pp.MissingIndicator(variables=config.CATEGORICAL_VARS +
config.NUMERICAL_VARS)),
('categorical_imputer',
pp.CategoricalImputer(variables=config.CATEGORICAL_VARS)),
('numerical_imputer',
pp.NumericalImputer(variables=config.NUMERICAL_VARS)),
('extract_first_letter', pp.ExtractFirstLetter(variables=[
'cabin',
])),
('rare_label_categorical_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(
[
('Extract_First_Letter', pp.ExtractFirstLetter(variables=['cabin'])),
('Numerical_Imputer', pp.NumericalImputer(variables=config.NUMERICAL_VARS)),
('Categorical_Imputer', pp.CategoricalImputer(variables=config.CATEGORICAL_VARS)),
('Rare_Label_Categorical_Encoder', pp.RareLabelCategoricalEncoder(variables=config.CATEGORICAL_VARS)),
('Categorical_Encoder', pp.CategoricalEncoder(variables=config.CATEGORICAL_VARS)),
('scaler', StandardScaler()),
('Linear_model', LogisticRegression(C=0.005, random_state=0))
],
verbose=True
)
