utils.py 文件源码

def transformTFIDF(X_train_all, X_test_all):
    """Transform bag-of-events using TF-IDF.

    Arguments
    ---------
    X_train_all: pandas DataFrame
    X_test_all: pandas DataFrame

    Returns
    -------
    X_train_t: CSR matrix
    X_test_t: CSR matrix
    """

    tfidf_t = TfidfTransformer(norm='l2',
                               use_idf=True,
                               sublinear_tf=True,
                               smooth_idf=True)
    X_train = scipy.sparse.csr_matrix(X_train_all)
    X_test = scipy.sparse.csr_matrix(X_test_all)
    # Fit TFIDF using training data.
    tfidf_t.fit(X_train)
    # Transform both training and test data.
    X_train_t = tfidf_t.transform(X_train)
    X_test_t = tfidf_t.transform(X_test)
    return X_train_t, X_test_t