from defs import (SelectKBest, LogisticRegressionCV, GroupKFold,
cross_validate, make_pipeline, X, y, my_groups, my_weights,
my_other_weights)
# %%
# Case A: weighted scoring and fitting
lr = LogisticRegressionCV(
cv=GroupKFold(),
scoring='accuracy',
prop_routing={
'cv': ['groups'],
'scoring': ['sample_weight'],
}
# one question here is whether we need to explicitly route sample_weight
# to LogisticRegressionCV's fitting...
)
# Alternative syntax, which assumes cv receives 'groups' by default, and that a
# method-based API is provided on meta-estimators:
# lr = LogisticRegressionCV(
# cv=GroupKFold(),
# scoring='accuracy',
# ).add_prop_route(scoring='sample_weight')
cross_validate(
lr,
X,
y,
cv=GroupKFold(),
props={
def wrapped_weighted_acc(est, X, y, sample_weight=None):
return acc_scorer(est, X, y, sample_weight=MY_WEIGHTS.loc[X.index])
lr = WeightedLogisticRegressionCV(
cv=wrapped_group_cv,
scoring=wrapped_weighted_acc,
).set_props_request(['sample_weight'])
cross_validate(lr, X, y, cv=wrapped_group_cv, scoring=wrapped_weighted_acc)
# %%
# Case B: weighted scoring and unweighted fitting
lr = LogisticRegressionCV(
cv=wrapped_group_cv,
scoring=wrapped_weighted_acc,
).set_props_request(['sample_weight'])
cross_validate(lr, X, y, cv=wrapped_group_cv, scoring=wrapped_weighted_acc)
# %%
# Case C: unweighted feature selection
lr = WeightedLogisticRegressionCV(
cv=wrapped_group_cv,
scoring=wrapped_weighted_acc,
).set_props_request(['sample_weight'])
sel = SelectKBest()
pipe = make_pipeline(sel, lr)
cross_validate(pipe, X, y, cv=wrapped_group_cv, scoring=wrapped_weighted_acc)
# %%
from defs import (accuracy_score, GroupKFold, make_scorer, SelectKBest,
LogisticRegressionCV, cross_validate, make_pipeline, X, y,
my_groups, my_weights, my_other_weights)
# %%
# Case A: weighted scoring and fitting
# Here we presume that GroupKFold requests `groups` by default.
# We need to explicitly request weights in make_scorer and for
# LogisticRegressionCV. Both of these consumers understand the meaning
# of the key "sample_weight".
weighted_acc = make_scorer(accuracy_score, request_props=['sample_weight'])
lr = LogisticRegressionCV(
cv=GroupKFold(),
scoring=weighted_acc,
).set_props_request(['sample_weight'])
cross_validate(lr,
X,
y,
cv=GroupKFold(),
props={
'sample_weight': my_weights,
'groups': my_groups
},
scoring=weighted_acc)
# Error handling: if props={'sample_eight': my_weights, ...} was passed,
# cross_validate would raise an error, since 'sample_eight' was not requested
# by any of its children.
from defs import (accuracy, group_cv, make_scorer, SelectKBest,
LogisticRegressionCV, cross_validate, make_pipeline, X, y,
my_groups, my_weights, my_other_weights)
# %%
# Case A: weighted scoring and fitting
# Here we presume that GroupKFold requests `groups` by default.
# We need to explicitly request weights in make_scorer and for
# LogisticRegressionCV. Both of these consumers understand the meaning
# of the key "sample_weight".
weighted_acc = make_scorer(accuracy, request_props=['sample_weight'])
lr = LogisticRegressionCV(
cv=group_cv,
scoring=weighted_acc,
).request_sample_weight(fit=['sample_weight'])
cross_validate(lr,
X,
y,
cv=group_cv,
props={
'sample_weight': my_weights,
'groups': my_groups
},
scoring=weighted_acc)
# Error handling: if props={'sample_eight': my_weights, ...} was passed,
# cross_validate would raise an error, since 'sample_eight' was not requested
# by any of its children.
from defs import (accuracy_score, GroupKFold, make_scorer, SelectKBest,
LogisticRegressionCV, cross_validate, make_pipeline, X, y,
my_groups, my_weights, my_other_weights)
# %%
# Case A: weighted scoring and fitting
lr = LogisticRegressionCV(
cv=GroupKFold(),
scoring='accuracy',
)
cross_validate(lr,
X,
y,
cv=GroupKFold(),
props={
'sample_weight': my_weights,
'groups': my_groups
},
scoring='accuracy')
# Error handling: if props={'sample_eight': my_weights, ...} was passed
# instead, the estimator would fit and score without weight, silently failing.
# %%
# Case B: weighted scoring and unweighted fitting
class MyLogisticRegressionCV(LogisticRegressionCV):
def fit(self, X, y, props=None):
props = props.copy()
from defs import (GroupKFold, SelectKBest, LogisticRegressionCV,
cross_validate, make_pipeline, X, y, my_groups,
my_weights, my_other_weights)
# %%
# Case A: weighted scoring and fitting
lr = LogisticRegressionCV(
cv=GroupKFold(),
scoring='accuracy',
)
props = {'cv__groups': my_groups,
'estimator__cv__groups': my_groups,
'estimator__sample_weight': my_weights,
'scoring__sample_weight': my_weights,
'estimator__scoring__sample_weight': my_weights}
cross_validate(lr, X, y, cv=GroupKFold(),
props=props,
scoring='accuracy')
# error handling: if props={'estimator__sample_eight': my_weights, ...} was
# passed instead, the estimator would raise an error.
# %%
# Case B: weighted scoring and unweighted fitting
lr = LogisticRegressionCV(
cv=GroupKFold(),
scoring='accuracy',
)
props = {'cv__groups': my_groups,
from defs import (accuracy, group_cv, make_scorer, SelectKBest,
LogisticRegressionCV, cross_validate, make_pipeline, X, y,
my_groups, my_weights, my_other_weights)
# %%
# Case A: weighted scoring and fitting
lr = LogisticRegressionCV(
cv=group_cv,
scoring='accuracy',
)
cross_validate(lr,
X,
y,
cv=group_cv,
props={
'sample_weight': my_weights,
'groups': my_groups
},
scoring='accuracy')
# Error handling: if props={'sample_eight': my_weights, ...} was passed
# instead, the estimator would fit and score without weight, silently failing.
# %%
# Case B: weighted scoring and unweighted fitting
class MyLogisticRegressionCV(LogisticRegressionCV):
def fit(self, X, y, props=None):
props = props.copy()
from defs import (accuracy_score, GroupKFold, make_scorer, SelectKBest,
LogisticRegressionCV, cross_validate, make_pipeline, X, y,
my_groups, my_weights, my_other_weights)
# %%
# Case A: weighted scoring and fitting
# Here we presume that GroupKFold requests `groups` by default.
# We need to explicitly request weights in make_scorer and for
# LogisticRegressionCV. Both of these consumers understand the meaning
# of the key "sample_weight".
weighted_acc = make_scorer(accuracy_score, request_metadata=['sample_weight'])
group_cv = GroupKFold()
lr = LogisticRegressionCV(
cv=group_cv,
scoring=weighted_acc,
).request_sample_weight(fit=True) # same as `fit=['sample_weight']`
cross_validate(lr,
X,
y,
cv=group_cv,
metadata={
'sample_weight': my_weights,
'groups': my_groups
},
scoring=weighted_acc)
# Here lr.get_metadata_request() would return
# {'fit': {'groups': {'groups'}, 'sample_weight': {'sample_weight'}},
# 'predict': {},
# 'transform': {},
from defs import (group_cv, SelectKBest, LogisticRegressionCV, cross_validate,
make_pipeline, X, y, my_groups, my_weights, my_other_weights)
# %%
# Case A: weighted scoring and fitting
lr = LogisticRegressionCV(
cv=group_cv,
scoring='accuracy',
)
props = {
'cv__groups': my_groups,
'estimator__cv__groups': my_groups,
'estimator__sample_weight': my_weights,
'scoring__sample_weight': my_weights,
'estimator__scoring__sample_weight': my_weights
}
cross_validate(lr, X, y, cv=group_cv, props=props, scoring='accuracy')
# error handling: if props={'estimator__sample_eight': my_weights, ...} was
# passed instead, the estimator would raise an error.
# %%
# Case B: weighted scoring and unweighted fitting
lr = LogisticRegressionCV(
cv=group_cv,
scoring='accuracy',
)
props = {
'cv__groups': my_groups,