thesis-anne/NaiveBayes.py

'''
Naive Bayes Classifier
======================

Naive Bayes is a probabilistic classifier that is able to predict a
probability distribution over a set of classes, rather than only
outputting the most likely class that the observation should belong to
'Naive' means, that it assumes that the value of a particular feature
(word in an article) is independent of the value of any other feature,
given the label. It considers each of these features to contribute
independently to the probability that it belongs to its category,
regardless of any possible correlations between these features.
'''

from BagOfWords import BagOfWords
from CsvHandler import CsvHandler

from sklearn.feature_extraction.text import CountVectorizer
from sklearn.feature_selection import SelectPercentile
from sklearn.metrics import recall_score, precision_score
from sklearn.model_selection import StratifiedKFold
from sklearn.naive_bayes import GaussianNB

class NaiveBayes:

    def make_naive_bayes(dataset):
        '''fits naive bayes model with StratifiedKFold,
        uses my BOW
        '''
        print('# fitting model')
        print('# ...')

        # split data into text and label set
        # join title and text
        X = dataset['Title'] + ' ' + dataset['Text']
        y = dataset['Label']

        cv = CountVectorizer()

        # use stratified k-fold cross-validation as split method
        skf = StratifiedKFold(n_splits = 10, shuffle=True)

        classifier = GaussianNB()

        # lists for metrics
        recall_scores = []
        precision_scores = []
        f1_scores = []

        # for each fold
        n = 0
        for train, test in skf.split(X,y):

            n += 1
            print('# split no. ' + str(n))

            # eigenes BOW => schlechtere ergebnisse
            vocab = BagOfWords.make_vocab(X[train])
            # fit the training data and then return the matrix
            training_data = BagOfWords.make_matrix(X[train], vocab)
            # transform testing data and return the matrix
            testing_data = BagOfWords.make_matrix(X[test], vocab)

            # # # using CountVectorizer:
            # # fit the training data and then return the matrix
            # training_data = cv.fit_transform(X[train], y[train]).toarray()
            # # transform testing data and return the matrix
            # testing_data = cv.transform(X[test]).toarray()

            # # apply select percentile
            # selector = SelectPercentile(percentile=25)
            # selector.fit(training_data, y[train])

            # training_data_r = selector.transform(training_data)
            # testing_data_r = selector.transform(testing_data)

            # #fit classifier
            # classifier.fit(training_data_r, y[train])
            # #predict class
            # predictions_train = classifier.predict(training_data_r)
            # predictions_test = classifier.predict(testing_data_r)

            #fit classifier
            classifier.fit(training_data, y[train])
            #predict class
            predictions_train = classifier.predict(training_data)
            predictions_test = classifier.predict(testing_data)

            #print and store metrics
            rec = recall_score(y[test], predictions_test)
            print('rec: ' + str(rec))
            recall_scores.append(rec)
            prec = precision_score(y[train], predictions_train)
            print('prec: ' + str(prec))
            print('#')
            precision_scores.append(prec)
            # equation for f1 score
            f1_scores.append(2 * (prec * rec)/(prec + rec))

        ##########################
        #print metrics of test set
        print('-------------------------')
        print('prediction of testing set:')
        print('Precision score: min = {}, max = {}, average = {}'
                .format(min(precision_scores),
                        max(precision_scores),
                        sum(precision_scores)/float(len(precision_scores))))
        print('Recall score: min = {}, max = {}, average = {}'
                .format(min(recall_scores),
                        max(recall_scores),
                        sum(recall_scores)/float(len(recall_scores))))
        print('F1 score: min = {}, max = {}, average = {}'
                .format(min(f1_scores),
                        max(f1_scores),
                        sum(f1_scores)/float(len(f1_scores))))
        print()

        ##### nur für overfit testing ###########
        #print('overfit testing: prediction of training set')
        #print('F1 score: min = {0:.2f}, max = {0:.2f}, average = {0:.2f}'.
        #format(min(f1_scores_train), max(f1_scores_train),
        #sum(f1_scores_train)/float(len(f1_scores_train))))
        #print()

    ######## nur für resubstitutionsfehler benötigt ########
    def analyze_errors(dataset):
        '''calculates resubstitution error
        shows indices of false classified articles
        uses Gaussian Bayes with train test split
        '''
        X_train_test = dataset['Title'] + ' ' + dataset['Text']
        y_train_test = dataset['Label']

        count_vector = CountVectorizer()
        # fit the training data and then return the matrix
        training_data = count_vector.fit_transform(X_train_test).toarray()
        # transform testing data and return the matrix
        testing_data = count_vector.transform(X_train_test).toarray()

        # Naive Bayes
        classifier = GaussianNB()
        # fit classifier
        classifier.fit(training_data, y_train_test)

        # Predict class
        predictions = classifier.predict(testing_data)
        print('Errors at index:')
        print()
        n = 0
        for i in range(len(y_train_test)):
            if y_train_test[i] != predictions[i]:
                n += 1
                print('error no.{}'.format(n))
                print('prediction at index {} is: {}, but actual is: {}'
                .format(i, predictions[i], y_train_test[i]))
                print(X_train_test[i])
                print(y_train_test[i])
                print()
        #print metrics
        print('F1 score: ', format(f1_score(y_train_test, predictions)))

    #################################
    print('# starting naive bayes')
    print('# ...')

    file = 'classification_labelled_corrected.csv'

    # read csv file
    print('# reading dataset')
    print('# ...')

    dataset = CsvHandler.read_csv(file)

    make_naive_bayes(dataset)

    print('#')
    print('# ending naive bayes')