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 booster(self):
"""Get the underlying xgboost Booster of this model.
This will raise an exception when fit was not called
Returns
-------
booster : a xgboost booster of underlying model
"""
if self._Booster is None:
raise XGBoostError('need to call fit beforehand')
return self._Booster
def __init__(self,
max_depth=3,
learning_rate=0.1,
n_estimators=100,
silent=True,
objective="reg:linear",
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,
num_boost_round=1):
if not SKLEARN_INSTALLED:
raise XGBoostError(
'sklearn needs to be installed in order to use this module')
self.max_depth = max_depth
self.learning_rate = learning_rate
self.n_estimators = n_estimators
self.silent = silent
self.objective = objective
self.nthread = nthread
self.gamma = gamma
self.min_child_weight = min_child_weight
self.max_delta_step = max_delta_step
self.subsample = subsample
self.colsample_bytree = colsample_bytree
self.colsample_bylevel = colsample_bylevel
self.reg_alpha = reg_alpha
self.reg_lambda = reg_lambda
self.scale_pos_weight = scale_pos_weight
self.base_score = base_score
self.seed = seed
self.missing = missing if missing is not None else np.nan
self.num_boost_round = num_boost_round
self._Booster = None
def cv(params,
dtrain,
num_boost_round=10,
nfold=3,
stratified=False,
folds=None,
metrics=(),
obj=None,
feval=None,
maximize=False,
early_stopping_rounds=None,
fpreproc=None,
as_pandas=True,
verbose_eval=None,
show_stdv=True,
seed=0,
callbacks=None,
shuffle=True):
# pylint: disable = invalid-name
"""Cross-validation with given parameters.
Parameters
----------
params : dict
Booster params.
dtrain : DMatrix
Data to be trained.
num_boost_round : int
Number of boosting iterations.
nfold : int
Number of folds in CV.
stratified : bool
Perform stratified sampling.
folds : a KFold or StratifiedKFold instance
Sklearn KFolds or StratifiedKFolds.
metrics : string or list of strings
Evaluation metrics to be watched in CV.
obj : function
Custom objective function.
feval : function
Custom evaluation function.
maximize : bool
Whether to maximize feval.
early_stopping_rounds: int
Activates early stopping. CV error needs to decrease at least
every <early_stopping_rounds> round(s) to continue.
Last entry in evaluation history is the one from best iteration.
fpreproc : function
Preprocessing function that takes (dtrain, dtest, param) and returns
transformed versions of those.
as_pandas : bool, default True
Return pd.DataFrame when pandas is installed.
If False or pandas is not installed, return np.ndarray
verbose_eval : bool, int, or None, default None
Whether to display the progress. If None, progress will be displayed
when np.ndarray is returned. If True, progress will be displayed at
boosting stage. If an integer is given, progress will be displayed
at every given `verbose_eval` boosting stage.
show_stdv : bool, default True
Whether to display the standard deviation in progress.
Results are not affected, and always contains std.
seed : int
Seed used to generate the folds (passed to numpy.random.seed).
callbacks : list of callback functions
List of callback functions that are applied at end of each iteration.
It is possible to use predefined callbacks by using xgb.callback module.
Example: [xgb.callback.reset_learning_rate(custom_rates)]
shuffle : bool
Shuffle data before creating folds.
Returns
-------
evaluation history : list(string)
"""
if stratified is True and not SKLEARN_INSTALLED:
raise XGBoostError(
'sklearn needs to be installed in order to use stratified cv')
if isinstance(metrics, str):
metrics = [metrics]
if isinstance(params, list):
_metrics = [x[1] for x in params if x[0] == 'eval_metric']
params = dict(params)
if 'eval_metric' in params:
params['eval_metric'] = _metrics
else:
params = dict((k, v) for k, v in params.items())
if len(metrics) == 0 and 'eval_metric' in params:
if isinstance(params['eval_metric'], list):
metrics = params['eval_metric']
else:
metrics = [params['eval_metric']]
params.pop("eval_metric", None)
results = {}
cvfolds = mknfold(dtrain, nfold, params, seed, metrics, fpreproc,
stratified, folds, shuffle)
# setup callbacks
callbacks = [] if callbacks is None else callbacks
if early_stopping_rounds is not None:
callbacks.append(
callback.early_stop(early_stopping_rounds,
maximize=maximize,
verbose=False))
if isinstance(verbose_eval, bool) and verbose_eval:
callbacks.append(callback.print_evaluation(show_stdv=show_stdv))
else:
if isinstance(verbose_eval, int):
callbacks.append(
callback.print_evaluation(verbose_eval, show_stdv=show_stdv))
callbacks_before_iter = [
cb for cb in callbacks if cb.__dict__.get('before_iteration', False)
]
callbacks_after_iter = [
cb for cb in callbacks
if not cb.__dict__.get('before_iteration', False)
]
for i in range(num_boost_round):
for cb in callbacks_before_iter:
cb(
CallbackEnv(model=None,
cvfolds=cvfolds,
iteration=i,
begin_iteration=0,
end_iteration=num_boost_round,
rank=0,
evaluation_result_list=None))
for fold in cvfolds:
fold.update(i, obj)
res = aggcv([f.eval(i, feval) for f in cvfolds])
for key, mean, std in res:
if key + '-mean' not in results:
results[key + '-mean'] = []
if key + '-std' not in results:
results[key + '-std'] = []
results[key + '-mean'].append(mean)
results[key + '-std'].append(std)
try:
for cb in callbacks_after_iter:
cb(
CallbackEnv(model=None,
cvfolds=cvfolds,
iteration=i,
begin_iteration=0,
end_iteration=num_boost_round,
rank=0,
evaluation_result_list=res))
except EarlyStopException as e:
for k in results.keys():
results[k] = results[k][:(e.best_iteration + 1)]
break
if as_pandas:
try:
import pandas as pd
results = pd.DataFrame.from_dict(results)
except ImportError:
pass
return (results, cvfolds)