class XGBCEarlyStoppingCV(XGBClassifier):
def fit(self, X, y,
# sample_weight=None,
eval_metric=None,
early_stopping_rounds=None,
verbose=True,
nfold=3,
seed=1):
xgb_options = self.get_xgb_params()
self._le = LabelEncoder().fit(y)
training_labels = self._le.transform(y)
train_dmatrix = DMatrix(X, label=training_labels, missing=self.missing)
evaluation_history = cv(
xgb_options,
train_dmatrix,
num_boost_round=self.n_estimators,
nfold=nfold,
stratified=True,
# folds=None,
metrics=(eval_metric),
# obj=None,
# feval=None,
# maximize=False,
early_stopping_rounds=early_stopping_rounds,
# fpreproc=None,
# as_pandas=True,
verbose_eval=verbose,
show_stdv=False,
seed=seed
)
best_iteration = evaluation_history.index[-1]
self._Booster = train(
xgb_options,
train_dmatrix,
num_boost_round=best_iteration,
verbose_eval=verbose,
)
return self
def fit(self, X, y, sample_weight=None, eval_set=None, eval_metric=None,
early_stopping_rounds=None, verbose=True):
# pylint: disable = attribute-defined-outside-init,arguments-differ
"""
Fit gradient boosting classifier
Parameters
----------
X : array_like
Feature matrix
y : array_like
Labels
sample_weight : array_like
Weight for each instance
eval_set : list, optional
A list of (X, y) pairs to use as a validation set for
early-stopping
eval_metric : str, callable, optional
If a str, should be a built-in evaluation metric to use. See
doc/parameter.md. If callable, a custom evaluation metric. The call
signature is func(y_predicted, y_true) where y_true will be a
DMatrix object such that you may need to call the get_label
method. It must return a str, value pair where the str is a name
for the evaluation and value is the value of the evaluation
function. This objective is always minimized.
early_stopping_rounds : int, optional
Activates early stopping. Validation error needs to decrease at
least every <early_stopping_rounds> round(s) to continue training.
Requires at least one item in evals. If there's more than one,
will use the last. Returns the model from the last iteration
(not the best one). If early stopping occurs, the model will
have two additional fields: bst.best_score and bst.best_iteration.
verbose : bool
If `verbose` and an evaluation set is used, writes the evaluation
metric measured on the validation set to stderr.
"""
evals_result = {}
self.classes_ = list(np.unique(y))
self.n_classes_ = len(self.classes_)
if self.n_classes_ > 2:
# Switch to using a multiclass objective in the underlying XGB instance
self.objective = "multi:softprob"
xgb_options = self.get_xgb_params()
xgb_options['num_class'] = self.n_classes_
else:
xgb_options = self.get_xgb_params()
feval = eval_metric if callable(eval_metric) else None
if eval_metric is not None:
if callable(eval_metric):
eval_metric = None
else:
xgb_options.update({"eval_metric": eval_metric})
if eval_set is not None:
# TODO: use sample_weight if given?
evals = list(DMatrix(x[0], label=x[1]) for x in eval_set)
nevals = len(evals)
eval_names = ["validation_{}".format(i) for i in range(nevals)]
evals = list(zip(evals, eval_names))
else:
evals = ()
self._le = LabelEncoder().fit(y)
training_labels = self._le.transform(y)
if sample_weight is not None:
train_dmatrix = DMatrix(X, label=training_labels, weight=sample_weight,
missing=self.missing)
else:
train_dmatrix = DMatrix(X, label=training_labels,
missing=self.missing)
self._Booster = train(xgb_options, train_dmatrix, self.n_estimators,
evals=evals,
early_stopping_rounds=early_stopping_rounds,
evals_result=evals_result, feval=feval,
verbose_eval=verbose)
if evals_result:
for val in evals_result.items():
evals_result_key = list(val[1].keys())[0]
evals_result[val[0]][evals_result_key] = val[1][evals_result_key]
self.evals_result_ = evals_result
if early_stopping_rounds is not None:
self.best_score = self._Booster.best_score
self.best_iteration = self._Booster.best_iteration
return self
class XGBClassifier(XGBModel, XGBClassifierBase):
# pylint: disable=missing-docstring,too-many-arguments,invalid-name
__doc__ = """Implementation of the scikit-learn API for XGBoost classification.
""" + '\n'.join(XGBModel.__doc__.split('\n')[2:])
def __init__(self, max_depth=3, learning_rate=0.1,
n_estimators=100, silent=True,
objective="binary:logistic",
nthread=-1, gamma=0, min_child_weight=1,
max_delta_step=0, subsample=1, colsample_bytree=1, colsample_bylevel=1,
reg_alpha=0, reg_lambda=1, scale_pos_weight=1,
base_score=0.5, seed=0, missing=None):
super(XGBClassifier, self).__init__(max_depth, learning_rate,
n_estimators, silent, objective,
nthread, gamma, min_child_weight,
max_delta_step, subsample,
colsample_bytree, colsample_bylevel,
reg_alpha, reg_lambda,
scale_pos_weight, base_score, seed, missing)
def fit(self, X, y, sample_weight=None, eval_set=None, eval_metric=None,
early_stopping_rounds=None, verbose=True):
# pylint: disable = attribute-defined-outside-init,arguments-differ
"""
Fit gradient boosting classifier
Parameters
----------
X : array_like
Feature matrix
y : array_like
Labels
sample_weight : array_like
Weight for each instance
eval_set : list, optional
A list of (X, y) pairs to use as a validation set for
early-stopping
eval_metric : str, callable, optional
If a str, should be a built-in evaluation metric to use. See
doc/parameter.md. If callable, a custom evaluation metric. The call
signature is func(y_predicted, y_true) where y_true will be a
DMatrix object such that you may need to call the get_label
method. It must return a str, value pair where the str is a name
for the evaluation and value is the value of the evaluation
function. This objective is always minimized.
early_stopping_rounds : int, optional
Activates early stopping. Validation error needs to decrease at
least every <early_stopping_rounds> round(s) to continue training.
Requires at least one item in evals. If there's more than one,
will use the last. Returns the model from the last iteration
(not the best one). If early stopping occurs, the model will
have two additional fields: bst.best_score and bst.best_iteration.
verbose : bool
If `verbose` and an evaluation set is used, writes the evaluation
metric measured on the validation set to stderr.
"""
evals_result = {}
self.classes_ = list(np.unique(y))
self.n_classes_ = len(self.classes_)
if self.n_classes_ > 2:
# Switch to using a multiclass objective in the underlying XGB instance
self.objective = "multi:softprob"
xgb_options = self.get_xgb_params()
xgb_options['num_class'] = self.n_classes_
else:
xgb_options = self.get_xgb_params()
feval = eval_metric if callable(eval_metric) else None
if eval_metric is not None:
if callable(eval_metric):
eval_metric = None
else:
xgb_options.update({"eval_metric": eval_metric})
if eval_set is not None:
# TODO: use sample_weight if given?
evals = list(DMatrix(x[0], label=x[1]) for x in eval_set)
nevals = len(evals)
eval_names = ["validation_{}".format(i) for i in range(nevals)]
evals = list(zip(evals, eval_names))
else:
evals = ()
self._le = LabelEncoder().fit(y)
training_labels = self._le.transform(y)
if sample_weight is not None:
train_dmatrix = DMatrix(X, label=training_labels, weight=sample_weight,
missing=self.missing)
else:
train_dmatrix = DMatrix(X, label=training_labels,
missing=self.missing)
self._Booster = train(xgb_options, train_dmatrix, self.n_estimators,
evals=evals,
early_stopping_rounds=early_stopping_rounds,
evals_result=evals_result, feval=feval,
verbose_eval=verbose)
if evals_result:
for val in evals_result.items():
evals_result_key = list(val[1].keys())[0]
evals_result[val[0]][evals_result_key] = val[1][evals_result_key]
self.evals_result_ = evals_result
if early_stopping_rounds is not None:
self.best_score = self._Booster.best_score
self.best_iteration = self._Booster.best_iteration
return self
def predict(self, data, output_margin=False, ntree_limit=0):
test_dmatrix = DMatrix(data, missing=self.missing)
class_probs = self.booster().predict(test_dmatrix,
output_margin=output_margin,
ntree_limit=ntree_limit)
if len(class_probs.shape) > 1:
column_indexes = np.argmax(class_probs, axis=1)
else:
column_indexes = np.repeat(0, class_probs.shape[0])
column_indexes[class_probs > 0.5] = 1
return self._le.inverse_transform(column_indexes)
def predict_proba(self, data, output_margin=False, ntree_limit=0):
test_dmatrix = DMatrix(data, missing=self.missing)
class_probs = self.booster().predict(test_dmatrix,
output_margin=output_margin,
ntree_limit=ntree_limit)
if self.objective == "multi:softprob":
return class_probs
else:
classone_probs = class_probs
classzero_probs = 1.0 - classone_probs
return np.vstack((classzero_probs, classone_probs)).transpose()
def evals_result(self):
"""Return the evaluation results.
If eval_set is passed to the `fit` function, you can call evals_result() to
get evaluation results for all passed eval_sets. When eval_metric is also
passed to the `fit` function, the evals_result will contain the eval_metrics
passed to the `fit` function
Returns
-------
evals_result : dictionary
Example
-------
param_dist = {'objective':'binary:logistic', 'n_estimators':2}
clf = xgb.XGBClassifier(**param_dist)
clf.fit(X_train, y_train,
eval_set=[(X_train, y_train), (X_test, y_test)],
eval_metric='logloss',
verbose=True)
evals_result = clf.evals_result()
The variable evals_result will contain:
{'validation_0': {'logloss': ['0.604835', '0.531479']},
'validation_1': {'logloss': ['0.41965', '0.17686']}}
"""
if self.evals_result_:
evals_result = self.evals_result_
else:
raise XGBoostError('No results.')
return evals_result
def fit(self,
X,
y,
sample_weight=None,
eval_set=None,
eval_metric=None,
early_stopping_rounds=None,
verbose=True):
# pylint: disable = attribute-defined-outside-init,arguments-differ
"""
Fit gradient boosting classifier
Parameters
----------
X : array_like
Feature matrix
y : array_like
Labels
sample_weight : array_like
Weight for each instance
eval_set : list, optional
A list of (X, y) pairs to use as a validation set for
early-stopping
eval_metric : str, callable, optional
If a str, should be a built-in evaluation metric to use. See
doc/parameter.md. If callable, a custom evaluation metric. The call
signature is func(y_predicted, y_true) where y_true will be a
DMatrix object such that you may need to call the get_label
method. It must return a str, value pair where the str is a name
for the evaluation and value is the value of the evaluation
function. This objective is always minimized.
early_stopping_rounds : int, optional
Activates early stopping. Validation error needs to decrease at
least every <early_stopping_rounds> round(s) to continue training.
Requires at least one item in evals. If there's more than one,
will use the last. Returns the model from the last iteration
(not the best one). If early stopping occurs, the model will
have two additional fields: bst.best_score and bst.best_iteration.
verbose : bool
If `verbose` and an evaluation set is used, writes the evaluation
metric measured on the validation set to stderr.
"""
evals_result = {}
self.classes_ = list(np.unique(y))
self.n_classes_ = len(self.classes_)
if self.n_classes_ > 2:
# Switch to using a multiclass objective in the underlying XGB instance
self.objective = "multi:softprob"
xgb_options = self.get_xgb_params()
xgb_options['num_class'] = self.n_classes_
else:
xgb_options = self.get_xgb_params()
feval = eval_metric if callable(eval_metric) else None
if eval_metric is not None:
if callable(eval_metric):
eval_metric = None
else:
xgb_options.update({"eval_metric": eval_metric})
if eval_set is not None:
# TODO: use sample_weight if given?
evals = list(DMatrix(x[0], label=x[1]) for x in eval_set)
nevals = len(evals)
eval_names = ["validation_{}".format(i) for i in range(nevals)]
evals = list(zip(evals, eval_names))
else:
evals = ()
self._le = LabelEncoder().fit(y)
training_labels = self._le.transform(y)
if sample_weight is not None:
train_dmatrix = DMatrix(X,
label=training_labels,
weight=sample_weight,
missing=self.missing)
else:
train_dmatrix = DMatrix(X,
label=training_labels,
missing=self.missing)
self._Booster = train(xgb_options,
train_dmatrix,
self.n_estimators,
evals=evals,
early_stopping_rounds=early_stopping_rounds,
evals_result=evals_result,
feval=feval,
verbose_eval=verbose)
if evals_result:
for val in evals_result.items():
evals_result_key = list(val[1].keys())[0]
evals_result[
val[0]][evals_result_key] = val[1][evals_result_key]
self.evals_result_ = evals_result
if early_stopping_rounds is not None:
self.best_score = self._Booster.best_score
self.best_iteration = self._Booster.best_iteration
return self
class XGBClassifier(XGBModel, XGBClassifierBase):
# pylint: disable=missing-docstring,too-many-arguments,invalid-name
__doc__ = """Implementation of the scikit-learn API for XGBoost classification.
""" + '\n'.join(XGBModel.__doc__.split('\n')[2:])
def __init__(self,
max_depth=3,
learning_rate=0.1,
n_estimators=100,
silent=True,
objective="binary:logistic",
nthread=-1,
gamma=0,
min_child_weight=1,
max_delta_step=0,
subsample=1,
colsample_bytree=1,
colsample_bylevel=1,
reg_alpha=0,
reg_lambda=1,
scale_pos_weight=1,
base_score=0.5,
seed=0,
missing=None):
super(XGBClassifier,
self).__init__(max_depth, learning_rate, n_estimators, silent,
objective, nthread, gamma, min_child_weight,
max_delta_step, subsample, colsample_bytree,
colsample_bylevel, reg_alpha, reg_lambda,
scale_pos_weight, base_score, seed, missing)
def fit(self,
X,
y,
sample_weight=None,
eval_set=None,
eval_metric=None,
early_stopping_rounds=None,
verbose=True):
# pylint: disable = attribute-defined-outside-init,arguments-differ
"""
Fit gradient boosting classifier
Parameters
----------
X : array_like
Feature matrix
y : array_like
Labels
sample_weight : array_like
Weight for each instance
eval_set : list, optional
A list of (X, y) pairs to use as a validation set for
early-stopping
eval_metric : str, callable, optional
If a str, should be a built-in evaluation metric to use. See
doc/parameter.md. If callable, a custom evaluation metric. The call
signature is func(y_predicted, y_true) where y_true will be a
DMatrix object such that you may need to call the get_label
method. It must return a str, value pair where the str is a name
for the evaluation and value is the value of the evaluation
function. This objective is always minimized.
early_stopping_rounds : int, optional
Activates early stopping. Validation error needs to decrease at
least every <early_stopping_rounds> round(s) to continue training.
Requires at least one item in evals. If there's more than one,
will use the last. Returns the model from the last iteration
(not the best one). If early stopping occurs, the model will
have two additional fields: bst.best_score and bst.best_iteration.
verbose : bool
If `verbose` and an evaluation set is used, writes the evaluation
metric measured on the validation set to stderr.
"""
evals_result = {}
self.classes_ = list(np.unique(y))
self.n_classes_ = len(self.classes_)
if self.n_classes_ > 2:
# Switch to using a multiclass objective in the underlying XGB instance
self.objective = "multi:softprob"
xgb_options = self.get_xgb_params()
xgb_options['num_class'] = self.n_classes_
else:
xgb_options = self.get_xgb_params()
feval = eval_metric if callable(eval_metric) else None
if eval_metric is not None:
if callable(eval_metric):
eval_metric = None
else:
xgb_options.update({"eval_metric": eval_metric})
if eval_set is not None:
# TODO: use sample_weight if given?
evals = list(DMatrix(x[0], label=x[1]) for x in eval_set)
nevals = len(evals)
eval_names = ["validation_{}".format(i) for i in range(nevals)]
evals = list(zip(evals, eval_names))
else:
evals = ()
self._le = LabelEncoder().fit(y)
training_labels = self._le.transform(y)
if sample_weight is not None:
train_dmatrix = DMatrix(X,
label=training_labels,
weight=sample_weight,
missing=self.missing)
else:
train_dmatrix = DMatrix(X,
label=training_labels,
missing=self.missing)
self._Booster = train(xgb_options,
train_dmatrix,
self.n_estimators,
evals=evals,
early_stopping_rounds=early_stopping_rounds,
evals_result=evals_result,
feval=feval,
verbose_eval=verbose)
if evals_result:
for val in evals_result.items():
evals_result_key = list(val[1].keys())[0]
evals_result[
val[0]][evals_result_key] = val[1][evals_result_key]
self.evals_result_ = evals_result
if early_stopping_rounds is not None:
self.best_score = self._Booster.best_score
self.best_iteration = self._Booster.best_iteration
return self
def predict(self, data, output_margin=False, ntree_limit=0):
test_dmatrix = DMatrix(data, missing=self.missing)
class_probs = self.booster().predict(test_dmatrix,
output_margin=output_margin,
ntree_limit=ntree_limit)
if len(class_probs.shape) > 1:
column_indexes = np.argmax(class_probs, axis=1)
else:
column_indexes = np.repeat(0, class_probs.shape[0])
column_indexes[class_probs > 0.5] = 1
return self._le.inverse_transform(column_indexes)
def predict_proba(self, data, output_margin=False, ntree_limit=0):
test_dmatrix = DMatrix(data, missing=self.missing)
class_probs = self.booster().predict(test_dmatrix,
output_margin=output_margin,
ntree_limit=ntree_limit)
if self.objective == "multi:softprob":
return class_probs
else:
classone_probs = class_probs
classzero_probs = 1.0 - classone_probs
return np.vstack((classzero_probs, classone_probs)).transpose()
def evals_result(self):
"""Return the evaluation results.
If eval_set is passed to the `fit` function, you can call evals_result() to
get evaluation results for all passed eval_sets. When eval_metric is also
passed to the `fit` function, the evals_result will contain the eval_metrics
passed to the `fit` function
Returns
-------
evals_result : dictionary
Example
-------
param_dist = {'objective':'binary:logistic', 'n_estimators':2}
clf = xgb.XGBClassifier(**param_dist)
clf.fit(X_train, y_train,
eval_set=[(X_train, y_train), (X_test, y_test)],
eval_metric='logloss',
verbose=True)
evals_result = clf.evals_result()
The variable evals_result will contain:
{'validation_0': {'logloss': ['0.604835', '0.531479']},
'validation_1': {'logloss': ['0.41965', '0.17686']}}
"""
if self.evals_result_:
evals_result = self.evals_result_
else:
raise XGBoostError('No results.')
return evals_result
