https://informationcorners.com/ml-001-name-text-gender-predictor-classifier/

Applying Machine learning algorithm.md

def train_and_test(train_percent=0.80):
    feature_set = prepare_data_set()
    validate_data_set(feature_set)
    random.shuffle(feature_set)
    total = len(feature_set)
    cut_point = int(total * train_percent)
    # splitting Dataset into train and test
    train_set = feature_set[:cut_point]
    test_set = feature_set[cut_point:]

    # fitting feature matrix to the model
    classifier = NaiveBayesClassifier.train(train_set)

    print('{} Accuracy- {}'.format('Naive Bayes', classify.accuracy(classifier, test_set)))
    print('Most informative features')
    informative_features = classifier.most_informative_features(n=5)
    for feature in informative_features:
        print("\t {} = {} ".format(*feature))
    return classifier