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())
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))
])
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 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'))),
from sklearn.pipeline import Pipeline
import preprocessors as pp
CATEGORICAL_VARS = [
'MSZoning', 'Neighborhood', 'RoofStyle', 'MasVnrType', 'BsmtQual',
'BsmtExposure', 'HeatingQC', 'CentralAir', 'KitchenQual', 'FireplaceQu',
'GarageType', 'GarageFinish', 'PavedDrive'
]
PIPELINE_NAME = 'lasso_regression'
price_pipe = Pipeline([
('categorical_imputer', pp.CategoricalImputer(variables=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
('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.compose import TransformedTargetRegressor
from sklearn.preprocessing import StandardScaler
from sklearn.pipeline import Pipeline, make_union
from xgboost.sklearn import XGBRegressor
# %%
discrete_vars_pipeline = Pipeline([
('discrete_vars_select', pp.ItemsSelector(features=config.DISCRETE_VARS))
])
cat_vars_pipeline = Pipeline([
('cat_vars_select', pp.ItemsSelector(features=config.CATEGORICAL_VARS)),
('categorical_imputer',
pp.CategoricalImputer(features=config.CATEGORICAL_VARS)),
('other_label_encoder',
pp.OtherLabelCategoricalEncoder(features=config.CATEGORICAL_VARS)),
('categorical_encoder',
pp.CategoricalEncoder(features=config.CATEGORICAL_VARS))
])
numerical_vars_pipeline = Pipeline([
('numerical_vars_select',
pp.ItemsSelector(features=config.NUMERICAL_VARS)),
('numerical_imputer', pp.NumericalImputer(features=config.NUMERICAL_VARS)),
('power_transformer',
pp.SelectedFeaturesPowerTransformer(features=config.NUMERICAL_VARS))
])
temporal_vars_pipeline = Pipeline([
