def run(emotion):
training_vectors, test_vectors, training_labels, test_labels = fetch_data(
emotion)
classifier = GaussianNB()
classifier.fit(training_vectors.toarray(), training_labels)
print(emotion, ':: Naive Bayes Accuracy:',
classifier.score(test_vectors.toarray(), test_labels))
def run(emotion):
training_vectors, test_vectors, training_labels, test_labels = fetch_data(emotion)
n_neighbors = [3, 5, 7, 8, 10, 12, 15]
accuracies = []
for n in n_neighbors:
classifier = KNeighborsClassifier(n_neighbors=n)
classifier.fit(training_vectors, training_labels)
accuracies.append(classifier.score(test_vectors, test_labels))
plt.plot(n_neighbors, accuracies, label=emotion)
def run(emotion):
training_vectors, test_vectors, training_labels, test_labels = fetch_data(
emotion)
alphas = [0.0001, 0.001, 0.01, 0.1]
accuracies = []
for a in alphas:
classifier = MLPClassifier(alpha=a)
classifier.fit(training_vectors, training_labels)
accuracies.append(classifier.score(test_vectors, test_labels))
plt.plot(alphas, accuracies, label=emotion)
def run(emotion):
training_vectors, test_vectors, training_labels, test_labels = fetch_data(
emotion)
estimators = [10, 50, 100, 1000]
accuracies = []
for estimator in estimators:
classifier = RandomForestClassifier(n_estimators=estimator)
classifier.fit(training_vectors, training_labels)
accuracies.append(classifier.score(test_vectors, test_labels))
print(accuracies)
plt.plot(estimators, accuracies, label=emotion)
def run(emotion):
training_vectors, test_vectors, training_labels, test_labels = fetch_data(
emotion)
learning_rates = [
0.1, 0.25, 0.5, 0.7, 0.9, 1, 1.1, 1.25, 1.5, 1.75, 2, 2.1, 2.25, 2.5,
3, 3.1, 3.5
]
accuracies = []
for n in learning_rates:
classifier = AdaBoostClassifier(learning_rate=n)
classifier.fit(training_vectors, training_labels)
accuracies.append(classifier.score(test_vectors, test_labels))
plt.plot(learning_rates, accuracies, label=emotion)
if self.model_name:
from pyfasttext import FastText
predictor = FastText()
predictor.load_model('ft_extras/'+self.model_name+'.bin')
predicted_labels = predictor.predict_proba(test_set)
if report_accuracy and test_labels_vector:
test_set_size = len(test_set)
correct_predictions = 0
invalid_labels = 0
for index, labels in enumerate(predicted_labels):
if len(labels) != 0:
best_label = max(labels,key=lambda label:label[1])
if best_label[0] == test_labels_vector[index]:
correct_predictions += 1
else:
invalid_labels += 1
continue
print('Prediction accuracy:{}\n'.format(correct_predictions / (test_set_size - invalid_labels)))
else:
print('Please use the train method to train a model first.')
return
if __name__ == '__main__':
emotions = ['joy', 'fear', 'anger', 'sadness']
classifier = Classifier()
from classifier.preclassifier import fetch_data
for emotion in emotions:
print('Predicting for {}:'.format(emotion))
train_tweets, test_tweets, train_labels, test_labels = fetch_data(emotion,vectorize=False)
classifier.train(train_tweets,train_labels)
classifier.predict(test_tweets,test_labels)