def run(self):
"""
This is for assignment 6, the data is from 20 news groups
"""
model = BuildModel("../data/features")
count_vectors = model.count_vectors()
cm = ConfusionMatrix(labels=model.labels)
mm = MultinomialMixture(20, count_vectors, n_iterations=4, verbose=True, smoothing=True, confusion_matrix=cm,
document_types=model.document_types)
mm.learn_parameters()
cm.print_matrix()
# Oversamples the training data using SMOTE
'''smote = SMOTE(sampling_strategy = 'minority')
xtr, ytr = smote.fit_resample(x_train, y_train)
print('Oversamples data using SMOTE...')'''
# Create and train Mutlinomial Naive Bayes classifier
clf = LogisticRegression(solver='lbfgs',
multi_class='multinomial')
clf.fit(x_train, y_train)
print("Classifier trained...")
print()
# Evaluate the predictive accuracy
predicted = clf.predict(x_dev)
print("Mean Accuracy: " + str(np.mean(predicted == y_dev)))
print()
# Prints out the confusion matrix
labels = ['fp_ic', 'fp_terr', 'fp_other', 'dom', 'notapp']
cm = ConfusionMatrix(labels, y_dev, predicted)
cm.print_matrix()
print("Actual: " + str(cm.count_actual()))
print("Predicted: "+ str(cm.count_predicted()))
# Prints the classification report
print(classification_report(y_dev, predicted, target_names=labels))
