def __get_shrinkage_factor(self, X_group):
"""Get for all complete groups an array of shrinkages"""
group_colnames = X_group.columns.to_list()
counts = X_group.groupby(group_colnames).size()
# Groups that are split on all
most_granular_groups = [
grp for grp in self.groups_ if len(as_list(grp)) == len(group_colnames)
]
# For each hierarchy level in each most granular group, get the number of observations
hierarchical_counts = {
granular_group: [
counts[tuple(subgroup)].sum()
for subgroup in expanding_list(granular_group, tuple)
]
for granular_group in most_granular_groups
}
# For each hierarchy level in each most granular group, get the shrinkage factor
shrinkage_factors = {
group: self.shrinkage_function_(counts, **self.shrinkage_kwargs)
for group, counts in hierarchical_counts.items()
}
# Make sure that the factors sum to one
shrinkage_factors = {
group: value / value.sum() for group, value in shrinkage_factors.items()
}
return shrinkage_factors
def fit(self, X, y=None):
"""
Fit the model using X, y as training data. Will also learn the groups that exist within the dataset.
:param X: array-like, shape=(n_columns, n_samples,) training data.
:param y: array-like, shape=(n_samples,) training data.
:return: Returns an instance of self.
"""
X, y = self.__prepare_input_data(X, y)
if self.shrinkage is not None:
self.__set_shrinkage_function()
self.group_colnames_ = [str(_) for _ in as_list(self.groups)]
if self.value_columns is not None:
self.value_colnames_ = [
str(_) for _ in as_list(self.value_columns)
]
else:
self.value_colnames_ = [
_ for _ in X.columns if _ not in self.group_colnames_
]
self.__validate(X, y)
# List of all hierarchical subsets of columns
self.group_colnames_hierarchical_ = expanding_list(
self.group_colnames_, list)
self.fallback_ = None
if self.shrinkage is None and self.use_global_model:
subset_x = X[self.value_colnames_]
self.fallback_ = clone(self.estimator).fit(subset_x, y)
if self.shrinkage is not None:
self.estimators_ = {}
for level_colnames in self.group_colnames_hierarchical_:
self.estimators_.update(
self.__fit_grouped_estimator(X, y, self.value_colnames_,
level_colnames))
else:
self.estimators_ = self.__fit_grouped_estimator(
X, y, self.value_colnames_, self.group_colnames_)
self.groups_ = as_list(self.estimators_.keys())
if self.shrinkage is not None:
self.shrinkage_factors_ = self.__get_shrinkage_factor(X)
return self
def fit(self, X, y=None):
"""
Fit the model using X, y as training data. Will also learn the groups that exist within the dataset.
:param X: array-like, shape=(n_columns, n_samples,) training data.
:param y: array-like, shape=(n_samples,) training data.
:return: Returns an instance of self.
"""
X_group, X_value = _split_groups_and_values(X,
self.groups,
min_value_cols=0,
check_X=self.check_X,
**self._check_kwargs)
X_group = self.__add_shrinkage_column(X_group)
if y is not None:
y = check_array(y, ensure_2d=False)
if self.shrinkage is not None:
self.__set_shrinkage_function()
# List of all hierarchical subsets of columns
self.group_colnames_hierarchical_ = expanding_list(
X_group.columns, list)
self.fallback_ = None
if self.shrinkage is None and self.use_global_model:
self.fallback_ = clone(self.estimator).fit(X_value, y)
if self.shrinkage is not None:
self.estimators_ = self.__fit_shrinkage_groups(X_group, X_value, y)
else:
self.estimators_ = self.__fit_grouped_estimator(
X_group, X_value, y)
self.groups_ = as_list(self.estimators_.keys())
if self.shrinkage is not None:
self.shrinkage_factors_ = self.__get_shrinkage_factor(X_group)
return self