def fit(self, X_train, y_train):
self.n_classes = len(np.unique(y_train))
self.estimators_levels = []
klass = self.base_estimator.__class__
predictions_levels = []
self.classes = np.unique(y_train)
#first level
estimators = [klass(**params) for params in self.params_list]
self.estimators_levels.append(estimators)
predictions = []
for estimator in estimators:
estimator.fit(X_train, y_train)
if self.k_fold > 1: # use cv
predict_ = cvp(estimator, X_train, y_train, cv=self.k_fold)
else: #use oob
predict_ = estimator.oob_decision_function_
#fill default value if meet nan
inds = np.where(np.isnan(predict_))
predict_[inds] = 1. / self.n_classes
predictions.append(predict_)
attr_to_next_level = np.hstack(predictions)
y_pre = self.classes.take(np.argmax(np.array(predictions).mean(axis=0),
axis=1),
axis=0)
self.max_accuracy = self.evaluate(y_pre, y_train)
#cascade step
while True:
print('level {}, CV accuracy: {}'.format(
len(self.estimators_levels), self.max_accuracy))
estimators = [klass(**params) for params in self.params_list]
self.estimators_levels.append(estimators)
predictions = []
X_train_step = np.hstack((attr_to_next_level, X_train))
for estimator in estimators:
estimator.fit(X_train_step, y_train)
if self.k_fold > 1: # use cv
predict_ = cvp(estimator,
X_train_step,
y_train,
cv=self.k_fold)
else: #use oob
predict_ = estimator.oob_decision_function_
#fill default value if meet nan
inds = np.where(np.isnan(predict_))
predict_[inds] = 1. / self.n_classes
predictions.append(predict_)
attr_to_next_level = np.hstack(predictions)
y_pre = self.classes.take(np.argmax(
np.array(predictions).mean(axis=0), axis=1),
axis=0)
accuracy = self.evaluate(y_pre, y_train)
if accuracy > self.max_accuracy:
self.max_accuracy = accuracy
else:
self.estimators_levels.pop()
break
def predict(self, X, y):
"""
Returns a generator containing the predictions for each of the
internal models (using cross_val_predict and a CV=12).
"""
for model in self.models:
yield cvp(model, X, y, cv=12)
def predict(self, X, y):
"""
Returns a generator containing the predictions for each of the
internal models (using cross_val_predict and a CV=12).
"""
for model in self.models:
yield cvp(model, X, y, cv=12)
def scan_fit(self, X, y):
self.n_classes = len(np.unique(y))
newX, newy, scan_round_total = self._sample_slicer(X, y)
sample_vector_list = []
for estimator in self.estimators:
estimator.fit(newX, newy)
if self.k_fold > 1: # use cv
predict_ = cvp(estimator, newX, newy, cv=self.k_fold)
else: #use oob
predict_ = estimator.oob_decision_function_
#fill default value if meet nan
inds = np.where(np.isnan(predict_))
predict_[inds] = 1. / self.n_classes
sample_vector = predict_.reshape(
(len(X), scan_round_total * self.n_classes))
sample_vector_list.append(sample_vector)
return np.hstack(sample_vector_list)
def predict(self, X, y):
"""
Returns a generator containing the predictions for each of the
internal models (using cross_val_predict and a CV=12).
Parameters
----------
X : ndarray or DataFrame of shape n x m
A matrix of n instances with m features
y : ndarray or Series of length n
An array or series of target or class values
kwargs: dict
keyword arguments passed to Scikit-Learn API.
"""
for model in self.models:
yield cvp(model, X, y, cv=12)