def setUp(self):
self.mnb = NaiveBayes(multinomial=True)
self.skmnb = MultinomialNB()
self.bnb = NaiveBayes(bernoulli=True)
self.skbnb = BernoulliNB()
self.cnb = NaiveBayes(multinomial=True, cnb=True)
self.wcnb = NaiveBayes(multinomial=True, wcnb=True)
def naive_bayes_metrics(x, y, x_labels, y_labels):
nb = NaiveBayes(x, y, x_labels, y_labels)
label = 'Gaussian Naive Bayes'
y_pred = nb.crossval_gaussian_navie_bayes()
nb.show_basic_metrics(y_pred, label=label)
cm = nb.plot_confusion_matrix(y_pred, label=label)
acc, f1 = nb.count_basic_metrics(y_pred)
return [[label, acc, f1, y_pred, cm]]
class NBTest(unittest.TestCase):
def setUp(self):
self.mnb = NaiveBayes(multinomial=True)
self.skmnb = MultinomialNB()
self.bnb = NaiveBayes(bernoulli=True)
self.skbnb = BernoulliNB()
self.cnb = NaiveBayes(multinomial=True, cnb=True)
self.wcnb = NaiveBayes(multinomial=True, wcnb=True)
def test_count_vectorized(self):
self.mnb.fit(X_count, train_targets)
self.skmnb.fit(X_count, train_targets)
self.assertEqual(self.mnb.score(X_count_test,test_targets),self.skmnb.score(X_count_test,test_targets))
def test_tfidf_vectorized(self):
self.mnb.fit(X_tfidf, train_targets)
self.skmnb.fit(X_tfidf, train_targets)
self.assertEqual(self.mnb.score(X_tfidf_test, test_targets), self.skmnb.score(X_tfidf_test, test_targets))
def test_cnb(self):
self.cnb.fit(X_count, train_targets)
self.mnb.fit(X_count, train_targets)
cnb_score = self.cnb.score(X_count_test, test_targets)
mnb_score = self.mnb.score(X_count_test, test_targets)
print "CNB: {}, MNB: {}".format(cnb_score, mnb_score)
assert (cnb_score - mnb_score) > -0.1
def test_wcnb(self):
self.wcnb.fit(X_count, train_targets)
self.mnb.fit(X_count, train_targets)
wcnb_score = self.wcnb.score(X_count_test, test_targets)
mnb_score = self.mnb.score(X_count_test, test_targets)
print "WCNB: {}, MNB: {}".format(wcnb_score, mnb_score)
assert (wcnb_score - mnb_score) > -0.5
from misc.constants import *
def model_output(classification_model: ClassificationModel, tune_start, tune_end):
classification_model.tune(tune_start, tune_end)
classification_model.fit()
classification_model.evaluate_model()
excel_writer = ExcelWriter(classification_model.name)
excel_writer.edit_sheet(classification_model.report_dict)
if __name__ == '__main__':
if os.path.exists(WORK_BOOK_PATH):
os.remove(WORK_BOOK_PATH)
input_parser = InputParser()
data_tuple = input_parser.get_samples_and_labels()
samples, labels = np.array(data_tuple[0]), np.array(data_tuple[1])
training_samples, test_samples, training_labels, test_labels = train_test_split(samples, labels,
test_size=TEST_SIZE,
random_state=0)
model_output(NaiveBayes(training_samples, test_samples, training_labels, test_labels), None, None)
model_output(KNearest(training_samples, test_samples, training_labels, test_labels), MIN_N_NEIGHBOUR,
MAX_N_NEIGHBOUR)
model_output(RandomForest(training_samples, test_samples, training_labels, test_labels), MIN_N_ESTIMATE,
MAX_N_ESTIMATE)
model_output(DecisionTree(training_samples, test_samples, training_labels, test_labels), None, None)
model_output(AdaBoost(training_samples, test_samples, training_labels, test_labels), MIN_N_ESTIMATE, MAX_N_ESTIMATE)
"""Prediction on the data set"""
import pandas as pd
from classifiers.naive_bayes import NaiveBayes
from classifiers.util import train_test_split, confusion_matrix, accuracy_score
# reading the data set
df = pd.read_csv("./dataset/processed.csv")
X = df.drop("Outcome", axis=1).values
y = df["Outcome"].values
# making sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=20)
# training the model
nb = NaiveBayes(X_train, y_train)
nb.fit(X_train, y_train)
# getting the predictions
y_predictions = nb.predict(X_test)
print(f"The accuracy score :: {accuracy_score(y_predictions, y_test) * 100} %")
# confusion matrix
print("Confusion Matrix ::")
print(f"{confusion_matrix(y_test, y_predictions)}")
