model_pipeline.py 文件源码

def get_pipeline_builder():

    pipe_builder = PipelineBuilder()

    # Feature Extraction
    params = {'ngram_range': [(1, 1), (1, 2), (1, 3)]}
    pipe_builder.add_extractor('CountVectorizer', CountVectorizer, 'Count Vectorizer', params)

    params = {}
    pipe_builder.add_extractor('HashingVectorizer', HashingVectorizer, 'Hashing Vectorizer', params)

    params = {}
    pipe_builder.add_extractor('TfidfVectorizer', TfidfVectorizer, 'TfIdf Vectorizer', params)

    # Dimension Reduction
    params = {}
    pipe_builder.add_reductor('No_Reduction', ModelNull, 'None', params)

    params = {}
    pipe_builder.add_reductor('TruncatedSVD', TruncatedSVD, 'Truncated SVD', params)

    # Normalization
    params = {}
    pipe_builder.add_normalizer('No_Normalization', ModelNull, 'None', params)

    params = {}
    pipe_builder.add_normalizer('Normalizer', Normalizer, 'Normalizer', params)

    # Classification Models
    params = {}
    pipe_builder.add_classifier('MultinomialNB', MultinomialNB, 'Multinomial Naive Bayes', params)

    params = {}
    pipe_builder.add_classifier('BernoulliNB', BernoulliNB, 'Bernoulli Naive Bayes', params)

    params = {}
    pipe_builder.add_classifier('KNeighborsClassifier', KNeighborsClassifier, 'K-Neighbors', params)

    params = {}
    pipe_builder.add_classifier('RadiusNeighborsClassifier', RadiusNeighborsClassifier, 'Radius Neighbors', params)

    return pipe_builder