def cls_create(xs, ys):
if algo == "SVM":
classifier = svm.SVC(C = self.parm, probability=True)
elif algo == "RF":
classifier = RandomForestClassifier(n_estimators = int(self.parm), criterion='entropy', n_jobs = 1)
#
#classifier = LDA()
new_xs = xs
"""
positive_count = len([y for y in ys if y > 0])
if positive_count >= 20:
#self.selector = svm.LinearSVC(C = 1, dual = False, penalty="l1")
self.selector = LDA()
new_xs = self.selector.fit_transform(xs, ys)
else:
self.selector = None
"""
classifier.fit(new_xs, ys)
probs = classifier.predict_proba(new_xs)
#self.pclassifier = svm.SVC(parm_val = 1.0)
#self.pclassifier.fit(probs, ys)
self.threshold, self.positive, self.negative = best_threshold_for_f1(probs, 20, ys)
return classifier
def cls_create(xs, ys):
if algo == "SVM":
classifier = svm.SVC(C = self.parm, probability=True)
elif algo == "RF":
classifier = RandomForestClassifier(n_estimators = int(self.parm), criterion='entropy', n_jobs = 1)
#
#classifier = LDA()
new_xs = xs
"""
positive_count = len([y for y in ys if y > 0])
if positive_count >= 20:
#self.selector = svm.LinearSVC(C = 1, dual = False, penalty="l1")
self.selector = LDA()
new_xs = self.selector.fit_transform(xs, ys)
else:
self.selector = None
"""
classifier.fit(new_xs, ys)
probs = classifier.predict_proba(new_xs)
#self.pclassifier = svm.SVC(parm_val = 1.0)
#self.pclassifier.fit(probs, ys)
self.threshold, self.positive, self.negative = best_threshold_for_f1(probs, 20, ys)
return classifier
def cls_create(xs, ys):
rf_cls = RandomForestClassifier(n_estimators = self.num_trees, criterion=self.criterion, n_jobs = 1)
new_xs, new_ys = over_sample(xs, ys)
rf_cls.fit(new_xs, new_ys)
""" Use original xs """
probs = rf_cls.predict_proba(xs)
self.threshold, self.positive, self.negative = best_threshold_for_f1(probs, 20, ys)
return rf_cls
def cls_create(xs, ys):
rf_cls = RandomForestClassifier(n_estimators=self.num_trees,
criterion=self.criterion,
n_jobs=1)
new_xs, new_ys = over_sample(xs, ys)
rf_cls.fit(new_xs, new_ys)
""" Use original xs """
probs = rf_cls.predict_proba(xs)
self.threshold, self.positive, self.negative = best_threshold_for_f1(
probs, 20, ys)
return rf_cls
def cls_create(xs, ys):
if algo == "SVM":
classifier = svm.SVC(C = self.parm, probability=True)
elif algo == "RF":
classifier = RandomForestClassifier(n_estimators = int(self.parm), criterion='entropy', n_jobs = 1)
new_xs, new_ys = over_sample(xs, ys)
classifier.fit(new_xs, new_ys)
probs = classifier.predict_proba(xs)
self.threshold, self.positive, self.negative = best_threshold_for_f1(probs, 5, ys)
return classifier
def cls_create(xs, ys):
#print("Training classifier")
if algo == "SVM":
classifier = svm.SVC(C = self.parm, probability=True)
elif algo == "RF":
classifier = RandomForestClassifier(n_estimators = int(self.parm), criterion='entropy', n_jobs = 1)
elif algo == "LogisticRegression":
classifier = LogisticRegression()
else:
raise Exception("Unknown algorithm: " + algo)
new_xs, new_ys = over_sample(xs, ys)
classifier.fit(new_xs, new_ys)
probs = classifier.predict_proba(xs)
self.threshold, self.positive, self.negative = best_threshold_for_f1(probs, 5, ys)
# Override threshold
return classifier