naive-bayes.py

from getEmbeddings import getEmbeddings
from sklearn.naive_bayes import GaussianNB
import numpy as np
import matplotlib.pyplot as plt
import scikitplot.plotters as skplt
import pickle


def save_classifier(classifier, classifier_fname):
    classifier_file = open(classifier_fname, 'wb')
    pickle.dump(classifier, classifier_file)
    classifier_file.close()


def plot_cmat(yte, ypred):
    '''Plotting confusion matrix'''
    skplt.plot_confusion_matrix(yte, ypred)
    plt.show()


xtr, xte, ytr, yte = getEmbeddings("datasets/train.csv")
np.save('./xtr', xtr)
np.save('./xte', xte)
np.save('./ytr', ytr)
np.save('./yte', yte)

xtr = np.load('./xtr.npy')
xte = np.load('./xte.npy')
ytr = np.load('./ytr.npy')
yte = np.load('./yte.npy')

gnb = GaussianNB()
gnb.fit(xtr, ytr)
y_pred = gnb.predict(xte)
m = yte.shape[0]
n = (yte != y_pred).sum()
print("Accuracy = " + format((m - n) / m * 100, '.2f') + "%")  # 72.94%

plot_cmat(yte, y_pred)
save_classifier(gnb, "gaussian-nb_model.pickle")