classifier.py 文件源码

def get_pipeline(name):
    x = TrainingSet.objects.filter(classifier=name).values_list('body',
                                                                flat=True)
    y = TrainingSet.objects.filter(classifier=name).values_list('target',
                                                                flat=True)
    pipeline = Pipeline([
         ('vector', CountVectorizer()),
         ('transform', TfidfTransformer()),
         ('bayes', MultinomialNB())
    ])

    pipeline.fit(x, y)

    return pipeline