validate.py 文件源码

def predict(testSet,PP,PN,positive_probabilities,negative_probabilities,unseen_pos_prob,unseen_neg_prob):
    predicted_class = []
    for review in testSet:
        negative_probab = math.log10(PN)
        positive_probab = math.log10(PP)
        review_words = word_tokenize(review)
        for w in review_words:
            if w in negative_probabilities:
                negative_probab = negative_probab + math.log10(negative_probabilities[w])
            else:
                negative_probab = negative_probab + math.log10(unseen_neg_prob)
            if w in positive_probabilities:
                positive_probab = positive_probab + math.log10(positive_probabilities[w])
            else:
                positive_probab = positive_probab + math.log10(unseen_pos_prob)
        if(negative_probab > positive_probab):
            result = '-'
        else:
            result = '+'
        predicted_class.append(result)
    return predicted_class