def _fit_child(self, skf, xs_train, y_train):
"""Build stage0 models from the training set (xs_train, y_train).
Parameters
----------
skf: StratifiedKFold-like iterator
Use for cross validation blending.
xs_train : array-like or sparse matrix of shape = [n_samples, n_features]
The training input samples.
y_train : array-like, shape = [n_samples]
The target values (class labels in classification).
Returns
-------
blend_train : array-like, shape = [n_samples]
For stage1 model training.
blend_test : array-like, shape = [n_samples]
If you use TwoStageKFold, blended sample for test will be prepared.
"""
blend_train = None
blend_test = None
for j, clf in enumerate(self.clfs):
self._out_to_console('Training classifier [{0}]'.format(j), 0)
all_learner_key = str(type(clf)) + str(j)
self.all_learner[all_learner_key] = []
blend_train_j = None
for i, (train_index, cv_index) in enumerate(skf):
now_learner = clone(clf)
self.all_learner[all_learner_key].append(now_learner)
xs_now_train = xs_train[train_index]
y_now_train = y_train[train_index]
xs_cv = xs_train[cv_index]
#y_cv = y_train[cv_index] no use
if not hasattr(now_learner, 'id'):
now_learner.id = self.get_stage0_id(now_learner)
dump_file = util.get_cache_file(now_learner.id,
cv_index,
suffix='pkl')
if self.save_stage0 and self._is_saved(now_learner, cv_index):
print('Prediction cache exists: skip fitting.')
now_learner = joblib.load(dump_file)
self.all_learner[all_learner_key][-1] = now_learner
else:
self._out_to_console('Fold [{0}]'.format(i), 0)
now_learner.fit(xs_now_train, y_now_train)
if self.save_stage0:
joblib.dump(now_learner, dump_file, compress=True)
if blend_train_j is None:
blend_train_j = self._get_blend_init(y_train, now_learner)
blend_train_j[cv_index] = self._get_child_predict(
now_learner, xs_cv, cv_index)
blend_train = numpy_c_concatenate(blend_train, blend_train_j)
return blend_train, blend_test
def _fit_child(self, skf, xs_train, y_train):
"""Build stage0 models from the training set (xs_train, y_train).
Parameters
----------
skf: StratifiedKFold-like iterator
Use for cross validation blending.
xs_train : array-like or sparse matrix of shape = [n_samples, n_features]
The training input samples.
y_train : array-like, shape = [n_samples]
The target values (class labels in classification).
Returns
-------
blend_train : array-like, shape = [n_samples]
For stage1 model training.
blend_test : array-like, shape = [n_samples]
If you use TwoStageKFold, blended sample for test will be prepared.
"""
blend_train = None
blend_test = None
for j, clf in enumerate(self.clfs):
self._out_to_console('Training classifier [{0}]'.format(j), 0)
all_learner_key = str(type(clf)) + str(j)
self.all_learner[all_learner_key] = []
blend_train_j = None
for i, (train_index, cv_index) in enumerate(skf):
now_learner = clone(clf)
self.all_learner[all_learner_key].append(now_learner)
xs_now_train = xs_train[train_index]
y_now_train = y_train[train_index]
xs_cv = xs_train[cv_index]
#y_cv = y_train[cv_index] no use
if not hasattr(now_learner, 'id'):
now_learner.id = self.get_stage0_id(now_learner)
dump_file = util.get_cache_file(now_learner.id,
cv_index,
suffix='pkl')
if self.save_stage0 and self._is_saved(now_learner, cv_index):
print('Prediction cache exists: skip fitting.')
now_learner = joblib.load(dump_file)
self.all_learner[all_learner_key][-1] = now_learner
else:
self._out_to_console('Fold [{0}]'.format(i), 0)
now_learner.fit(xs_now_train, y_now_train)
if self.save_stage0:
joblib.dump(now_learner, dump_file, compress=True)
if blend_train_j is None:
blend_train_j = self._get_blend_init(y_train, now_learner)
blend_train_j[cv_index] = self._get_child_predict(now_learner, xs_cv, cv_index)
blend_train = numpy_c_concatenate(blend_train, blend_train_j)
return blend_train, blend_test
def fit(self, xs_train, y_train, index=None):
dump_file = ""
if index is not None:
dump_file = util.get_cache_file(self.estimator.id,
index,
cache_dir=self.cache_dir,
suffix='pkl')
if self.skip_refit and os.path.isfile(dump_file):
if index is not None:
self.estimator = joblib.load(dump_file)
else:
self.estimator.fit(xs_train, y_train)
if index is not None:
joblib.dump(self.estimator, dump_file, compress=True)
return self
def fit(self, xs_train, y_train, index=None):
dump_file = ""
if index is not None:
dump_file = util.get_cache_file(self.estimator.id,
index,
cache_dir=self.cache_dir,
suffix='pkl')
if self.skip_refit and os.path.isfile(dump_file):
if index is not None:
self.estimator = joblib.load(dump_file)
else:
self.estimator.fit(xs_train, y_train)
if index is not None:
joblib.dump(self.estimator, dump_file, compress=True)
return self
def _is_saved(self, model, index):
model_id = self.get_stage0_id(model)
return os.path.isfile(util.get_cache_file(model_id, index))
def _is_saved(self, model, index):
model_id = self.get_stage0_id(model)
return os.path.isfile(util.get_cache_file(model_id, index))