def rakeld_ensemble(vec, label):
problem_transform_classifier = LabelPowerset(classifier=LinearSVC(),
require_dense=[False, True])
classifier = RakelD(classifier=problem_transform_classifier,
labelset_size=5)
classifier.fit(vec, label)
return classifier
def RAkELd(dataset_train_x, dataset_train_y, dataset_test_x, dataset_test_y,
base_clasif, num_labels):
classifier = RakelD(base_classifier=base_clasif, labelset_size=num_labels)
classifier.fit(dataset_train_x, dataset_train_y)
predictions = classifier.predict(dataset_test_x)
Metrics_Accuracy("RAkELd", predictions, dataset_test_y)
def build_Rake(X_train, y_train, X_test, y_test):
classifier = RakelD(base_classifier=GaussianNB(),
base_classifier_require_dense=[True, True],
labelset_size=4)
classifier.fit(X_train, y_train)
prediction = classifier.predict(X_test)
print('Test accuracy is {}'.format(accuracy_score(y_test, prediction)))
def RAkELd(dataset_train_x, dataset_train_y, dataset_test_x, dataset_test_y,
base_clasif, num_labels):
classifier = RakelD(base_classifier=base_clasif, labelset_size=num_labels)
start_time = time.time()
classifier.fit(dataset_train_x, dataset_train_y)
stop_time = time.time()
time_lapsed = stop_time - start_time
predictions = classifier.predict(dataset_test_x)
Metrics_Accuracy("RAkELd", predictions, dataset_test_y)
print("Execution time: {}s".format(time_lapsed))
def run(classifier, train_test_set):
X_train, X_test, y_train, y_test = train_test_set
# init model and fit to train data
rakel = RakelD(base_classifier=classifier)
rakel.fit(X_train, y_train)
# make predictions
y_pred = rakel.predict(X_test)
print('\n--------Rakel with {:}'.format(rakel))
return y_test, y_pred
def RAkEL_fit(clfs, steps, X_train, y_train, X_test, y_test):
metrics = {}
for key, clf in zip(clfs.keys(), clfs.values()):
acc = []
prec_micro = []
prec_macro = []
hamm_loss = []
f1_micro = []
f1_macro = []
print('Fitting RAkEL with Base Classifier: %s' % key)
for k in steps:
classifier = RakelD(base_classifier=clf, labelset_size=k)
classifier.fit(X_train, y_train)
prediction = classifier.predict(X_test)
acc.append(accuracy_score(y_test, prediction))
prec_micro.append(precision_score(y_test, prediction, average='micro'))
prec_macro.append(precision_score(y_test, prediction, average='macro'))
hamm_loss.append(hamming_loss(y_test, prediction))
f1_micro.append(f1_score(y_test, prediction, average='micro'))
f1_macro.append(f1_score(y_test, prediction, average='macro'))
metrics[key] = [acc, hamm_loss, f1_micro, f1_macro, prec_micro, prec_macro]
return metrics
from sklearn.metrics import f1_score
from sklearn.metrics import jaccard_similarity_score
from sklearn.metrics import precision_score
from sklearn.metrics import recall_score
from sklearn.naive_bayes import GaussianNB
from skmultilearn.ensemble import RakelD
from datetime import timedelta
import time
start = time.time()
classifier = RakelD(base_classifier=GaussianNB(),
base_classifier_require_dense=[True, True],
labelset_size=4)
classifier.fit(x_train, y_train)
predictions = classifier.predict(x_test)
# accuracy
print("Accuracy = ", accuracy_score(y_test, predictions))
print("\n")
print("F1 = ", f1_score(y_test, predictions, average='micro'))
print("\n")
print("Jaccard = ", jaccard_similarity_score(y_test, predictions))
print("\n")
print("Precision = ", precision_score(y_test, predictions, average='micro'))
print("\n")
print("Recall = ", recall_score(y_test, predictions, average='micro'))