def randomForest():
print("Random forest classifier")
start = time.time()
classifier = BinaryRelevance(classifier=RandomForestClassifier(),
require_dense=[False, True])
filename = "randomForest"
classifier.fit(train_x, train_y)
# save
pickle.dump(classifier, open(filename, 'wb'))
# load the model from disk
classifier = pickle.load(open(filename, 'rb'))
print('training time taken: ', round(time.time() - start, 0), 'seconds')
predictions_new = classifier.predict(test_x)
accuracy(test_y, predictions_new)
def supportVectorMachineChain():
print("Support vector machine")
start = time.time()
classifier = ClassifierChain(classifier=svm.SVC(),
require_dense=[False, True])
filename = "SupportVectorMachine"
classifier.fit(train_x, train_y)
# save
pickle.dump(classifier, open(filename, 'wb'))
# load the model from disk
classifier = pickle.load(open(filename, 'rb'))
print('training time taken: ', round(time.time() - start, 0), 'seconds')
predictions_new = classifier.predict(test_x)
accuracy(test_y, predictions_new)
def knnBinary(m):
print("knn binary")
start = time.time()
classifier = BinaryRelevance(KNeighborsClassifier(n_neighbors=m))
filename = "knnBinary"
classifier.fit(train_x, train_y)
# save
pickle.dump(classifier, open(filename, 'wb'))
# load the model from disk
classifier = pickle.load(open(filename, 'rb'))
print('training time taken: ', round(time.time() - start, 0), 'seconds')
predictions_new = classifier.predict(test_x)
accuracy(test_y, predictions_new)
def knnClassifierChain():
print("knn classifier chain")
start = time.time()
classifier = ClassifierChain(KNeighborsClassifier())
filename = "knnChain"
classifier.fit(train_x, train_y)
# save
pickle.dump(classifier, open(filename, 'wb'))
# load the model from disk
classifier = pickle.load(open(filename, 'rb'))
print('training time taken: ', round(time.time() - start, 0), 'seconds')
predictions_new = classifier.predict(test_x)
accuracy(test_y, predictions_new)
def gaussianNaiveBayes():
print("Gaussian naive bayes")
start = time.time()
classifier = ClassifierChain(GaussianNB())
filename = "gaussianNaiveBayes"
classifier.fit(train_x, train_y)
# save
pickle.dump(classifier, open(filename, 'wb'))
# load the model from disk
classifier = pickle.load(open(filename, 'rb'))
print('training time taken: ', round(time.time() - start, 0), 'seconds')
predictions_new = classifier.predict(test_x)
accuracy(test_y, predictions_new)
def multinomialLogisticRegressionChain():
# Train multi-classification model with logistic regression
print("Logisticka regresija chain")
start = time.time()
classifier = BinaryRelevance(classifier=linear_model.LogisticRegression(
multi_class='multinomial', solver='newton-cg'),
require_dense=[False, True])
filename = "logistickaRegresija.sav"
classifier.fit(train_x, train_y)
# save
pickle.dump(classifier, open(filename, 'wb'))
# load the model from disk
classifier = pickle.load(open(filename, 'rb'))
print('training time taken: ', round(time.time() - start, 0), 'seconds')
predictions_new = classifier.predict(test_x)
accuracy(test_y, predictions_new)