def test_automatically_find_variables_and_return_as_numeric(df_normal_dist):
# test case 1: automatically select variables, return_object=False
transformer = EqualFrequencyDiscretiser(q=10,
variables=None,
return_object=False)
X = transformer.fit_transform(df_normal_dist)
# output expected for fit attr
_, bins = pd.qcut(x=df_normal_dist["var"],
q=10,
retbins=True,
duplicates="drop")
bins[0] = float("-inf")
bins[len(bins) - 1] = float("inf")
# expected transform output
X_t = [x for x in range(0, 10)]
# test init params
assert transformer.q == 10
assert transformer.variables == ["var"]
assert transformer.return_object is False
# test fit attr
assert transformer.input_shape_ == (100, 1)
# test transform output
assert (transformer.binner_dict_["var"] == bins).all()
assert len([x for x in X["var"].unique() if x not in X_t]) == 0
# in equal frequency discretisation, all intervals get same proportion of values
assert len((X["var"].value_counts()).unique()) == 1
def test_automatically_find_variables_and_return_as_object(df_normal_dist):
# test case 2: return variables cast as object
transformer = EqualFrequencyDiscretiser(q=10,
variables=None,
return_object=True)
X = transformer.fit_transform(df_normal_dist)
assert X["var"].dtypes == "O"
def test_custom_models_template(scenario_with_custom_models_template):
aml, pipeline, param_grid = scenario_with_custom_models_template
final_pipes = aml._make_aml_combinations(pipeline, param_grid)
check = [Pipeline(steps=[('disc1', EqualFrequencyDiscretiser()),
('model1', LinearRegression())]),
Pipeline(steps=[('disc1', EqualFrequencyDiscretiser()),
('model2', RandomForestRegressor())]),
Pipeline(steps=[('disc2', EqualWidthDiscretiser()),
('model1', LinearRegression())]),
Pipeline(steps=[('disc2', EqualWidthDiscretiser()),
('model2', RandomForestRegressor())])]
assert str(final_pipes) == str(check)
def scenario_with_default_models_template():
pipeline = Pipeline([('disc1', EqualFrequencyDiscretiser()),
('disc2', EqualWidthDiscretiser()),
aml_basic_regressors[:2]])
param_grid = {}
aml = AMLGridSearchCV(pipeline, param_grid)
return aml, pipeline, param_grid
def scenario_with_grid_search_for_one_model():
pipeline = Pipeline([('disc1', EqualFrequencyDiscretiser()),
('disc2', EqualWidthDiscretiser()),
('model1', LinearRegression()),
('model2', RandomForestRegressor())])
param_grid = {'disc1__q': [5, 15], 'model2__*': []}
aml = AMLGridSearchCV(pipeline, param_grid)
return aml, pipeline, param_grid
def scenario_with_custom_models_template():
regressors = [('model1', LinearRegression()),
('model2', RandomForestRegressor())]
pipeline = Pipeline([('disc1', EqualFrequencyDiscretiser()),
('disc2', EqualWidthDiscretiser()), regressors])
param_grid = {}
aml = AMLGridSearchCV(pipeline, param_grid)
return aml, pipeline, param_grid
def scenario_without_params():
pipeline = Pipeline([('disc1', EqualFrequencyDiscretiser()),
('disc2', EqualWidthDiscretiser()),
('model1', LinearRegression()),
('model2', RandomForestRegressor())])
param_grid = {}
aml = AMLGridSearchCV(pipeline, param_grid)
return aml, pipeline, param_grid
def _make_discretiser(self):
"""
Instantiate the EqualWidthDiscretiser or EqualFrequencyDiscretiser.
"""
if self.strategy == "equal_width":
discretiser = EqualWidthDiscretiser(
bins=self.bins,
variables=self.variables_numerical_,
return_boundaries=True,
)
else:
discretiser = EqualFrequencyDiscretiser(
q=self.bins,
variables=self.variables_numerical_,
return_boundaries=True,
)
return discretiser
def _make_numerical_pipeline(self):
if self.strategy == "equal_width":
discretizer = EqualWidthDiscretiser(
bins=self.bins, variables=self.variables_numerical_, return_object=True
)
else:
discretizer = EqualFrequencyDiscretiser(
q=self.bins, variables=self.variables_numerical_, return_object=True
)
encoder = MeanEncoder(variables=self.variables_numerical_)
_pipeline_numerical = Pipeline(
[
("discretization", discretizer),
("encoder", encoder),
]
)
return _pipeline_numerical
def test_non_fitted_error(df_vartypes):
with pytest.raises(NotFittedError):
transformer = EqualFrequencyDiscretiser()
transformer.transform(df_vartypes)
def test_error_if_input_df_contains_na_in_fit(df_na):
# test case 3: when dataset contains na, fit method
with pytest.raises(ValueError):
transformer = EqualFrequencyDiscretiser()
transformer.fit(df_na)
def test_error_if_return_object_not_bool():
with pytest.raises(ValueError):
EqualFrequencyDiscretiser(return_object="other")
def test_error_when_q_not_number():
with pytest.raises(ValueError):
EqualFrequencyDiscretiser(q="other")
def fit(self, X: pd.DataFrame, y: pd.Series = None):
"""
Find features with high PSI values.
Parameters
----------
X : pandas dataframe of shape = [n_samples, n_features]
The training dataset.
y : pandas series. Default = None
y is not needed in this transformer. You can pass y or None.
"""
# check input dataframe
X = check_X(X)
# If required exclude variables that are not in the input dataframe
self._confirm_variables(X)
# find numerical variables or check those entered are present in the dataframe
self.variables_ = _find_or_check_numerical_variables(
X, self.variables_)
# Remove the split_col from the variables list. It might be added if the
# variables are not defined at initialization.
if self.split_col in self.variables_:
self.variables_.remove(self.split_col)
if self.missing_values == "raise":
# check if dataset contains na or inf
_check_contains_na(X, self.variables_)
_check_contains_inf(X, self.variables_)
# Split the dataframe into basis and test.
basis_df, test_df = self._split_dataframe(X)
# Check the shape of the returned dataframes for PSI calculations.
# The number of observations must be at least equal to the
# number of bins.
if min(basis_df.shape[0], test_df.shape[0]) < self.bins:
raise ValueError(
"The number of rows in the basis and test datasets that will be used "
f"in the PSI calculations must be at least larger than {self.bins}. "
"After slitting the original dataset based on the given cut_off or"
f"split_frac we have {basis_df.shape[0]} samples in the basis set, "
f"and {test_df.shape[0]} samples in the test set. "
"Please adjust the value of the cut_off or split_frac.")
# Switch basis and test dataframes if required.
if self.switch:
test_df, basis_df = basis_df, test_df
# set up the discretizer
if self.strategy == "equal_width":
bucketer = EqualWidthDiscretiser(bins=self.bins)
else:
bucketer = EqualFrequencyDiscretiser(q=self.bins)
# Compute the PSI by looping over the features
self.psi_values_ = {}
self.features_to_drop_ = []
for feature in self.variables_:
# Discretize the features.
basis_discrete = bucketer.fit_transform(basis_df[[feature
]].dropna())
test_discrete = bucketer.transform(test_df[[feature]].dropna())
# Determine percentage of observations per bin
basis_distrib, test_distrib = self._observation_frequency_per_bin(
basis_discrete, test_discrete)
# Calculate the PSI value
self.psi_values_[feature] = np.sum(
(test_distrib - basis_distrib) *
np.log(test_distrib / basis_distrib))
# Assess if feature should be dropped
if self.psi_values_[feature] > self.threshold:
self.features_to_drop_.append(feature)
# save input features
self._get_feature_names_in(X)
return self
def test_error_if_input_df_contains_na_in_transform(df_vartypes, df_na):
# test case 4: when dataset contains na, transform method
with pytest.raises(ValueError):
transformer = EqualFrequencyDiscretiser()
transformer.fit(df_vartypes)
transformer.transform(df_na[["Name", "City", "Age", "Marks", "dob"]])
import numpy as np
import pytest
from sklearn.utils.estimator_checks import check_estimator
from feature_engine.discretisation import (
ArbitraryDiscretiser,
DecisionTreeDiscretiser,
EqualFrequencyDiscretiser,
EqualWidthDiscretiser,
)
from tests.estimator_checks.estimator_checks import check_feature_engine_estimator
_estimators = [
DecisionTreeDiscretiser(regression=False),
EqualFrequencyDiscretiser(),
EqualWidthDiscretiser(),
ArbitraryDiscretiser(binning_dict={"0": [-np.Inf, 0, np.Inf]}),
]
@pytest.mark.parametrize("estimator", _estimators)
def test_check_estimator_from_sklearn(estimator):
return check_estimator(estimator)
@pytest.mark.parametrize("estimator", _estimators)
def test_check_estimator_from_feature_engine(estimator):
if estimator.__class__.__name__ == "ArbitraryDiscretiser":
estimator.set_params(binning_dict={"var_1": [-np.Inf, 0, np.Inf]})
return check_feature_engine_estimator(estimator)
[
('numeric_impute', MeanMedianImputer(imputation_method='median', variables=config.CONTINUOUS_FEATURES)),
('categorical_impute', CategoricalImputer(imputation_method='missing',
variables=config.CATEGORICAL_FEATURES+
config.DISCRETE_SET1_FEATURES+config.DISCRETE_SET2_FEATURES+
config.DISCRETE_SET3_FEATURES)),
('rare_label_encode', RareLabelEncoder(tol=0.02, n_categories=10,
variables=config.CATEGORICAL_FEATURES+
config.DISCRETE_SET1_FEATURES+config.DISCRETE_SET2_FEATURES+
config.DISCRETE_SET3_FEATURES,
replace_with='Rare')),
('categorical_encode1', OrdinalEncoder(encoding_method='arbitrary',
variables=config.CATEGORICAL_FEATURES+config.DISCRETE_SET2_FEATURES)),
('categorical_encode2', OrdinalEncoder(encoding_method='ordered',
variables=config.DISCRETE_SET1_FEATURES)),
('categorical_encode3', CountFrequencyEncoder(encoding_method='count',
variables=config.DISCRETE_SET3_FEATURES)),
('continuous_discretization', EqualFrequencyDiscretiser(q=20, variables=config.CONTINUOUS_FEATURES, return_object=True)),
('continuous_encoding', OrdinalEncoder(encoding_method='ordered', variables=config.CONTINUOUS_FEATURES)),
('scaling', StandardScaler()),
('clf', RandomForestClassifier(criterion='gini', max_depth=10, min_samples_split=10, random_state=0))
])
