fuzzy.py 文件源码

def compute_features(train_df, test_df):

    train_df[Fields.qratio] = train_df.apply(
        lambda row: fuzz.QRatio(str(row[FieldsTrain.question1]), str(row[FieldsTrain.question2])), axis=1)
    test_df[Fields.qratio] = test_df.apply(
        lambda row: fuzz.QRatio(str(row[FieldsTest.question1]), str(row[FieldsTest.question2])), axis=1)
    quality_qratio = compute_quality(train_df, Fields.qratio)

    train_df[Fields.wratio] = train_df.apply(
        lambda row: fuzz.WRatio(str(row[FieldsTrain.question1]), str(row[FieldsTrain.question2])), axis=1)
    test_df[Fields.wratio] = test_df.apply(
        lambda row: fuzz.WRatio(str(row[FieldsTest.question1]), str(row[FieldsTest.question2])), axis=1)
    quality_wratio = compute_quality(train_df, Fields.wratio)

    train_df[Fields.partial_ratio] = train_df.apply(
        lambda row: fuzz.partial_ratio(str(row[FieldsTrain.question1]), str(row[FieldsTrain.question2])), axis=1)
    test_df[Fields.partial_ratio] = test_df.apply(
        lambda row: fuzz.partial_ratio(str(row[FieldsTest.question1]), str(row[FieldsTest.question2])), axis=1)
    quality_partial_ratio = compute_quality(train_df, Fields.partial_ratio)

    train_df[Fields.partial_token_set_ratio] = train_df.apply(
        lambda row: fuzz.partial_token_set_ratio(str(row[FieldsTrain.question1]), str(row[FieldsTrain.question2])), axis=1)
    test_df[Fields.partial_token_set_ratio] = test_df.apply(
        lambda row: fuzz.partial_token_set_ratio(str(row[FieldsTest.question1]), str(row[FieldsTest.question2])), axis=1)
    quality_partial_token_set_ratio = compute_quality(train_df, Fields.partial_token_set_ratio)

    train_df[Fields.partial_token_sort_ratio] = train_df.apply(
        lambda row: fuzz.partial_token_sort_ratio(str(row[FieldsTrain.question1]), str(row[FieldsTrain.question2])), axis=1)
    test_df[Fields.partial_token_sort_ratio] = test_df.apply(
        lambda row: fuzz.partial_token_sort_ratio(str(row[FieldsTest.question1]), str(row[FieldsTest.question2])), axis=1)
    quality_partial_token_sort_ratio = compute_quality(train_df, Fields.partial_token_sort_ratio)

    train_df[Fields.token_set_ratio] = train_df.apply(
        lambda row: fuzz.token_set_ratio(str(row[FieldsTrain.question1]), str(row[FieldsTrain.question2])), axis=1)
    test_df[Fields.token_set_ratio] = test_df.apply(
        lambda row: fuzz.token_set_ratio(str(row[FieldsTest.question1]), str(row[FieldsTest.question2])), axis=1)
    quality_token_set_ratio = compute_quality(train_df, Fields.token_set_ratio)

    train_df[Fields.token_sort_ratio] = train_df.apply(
        lambda row: fuzz.token_sort_ratio(str(row[FieldsTrain.question1]), str(row[FieldsTrain.question2])), axis=1)
    test_df[Fields.token_sort_ratio] = test_df.apply(
        lambda row: fuzz.token_sort_ratio(str(row[FieldsTest.question1]), str(row[FieldsTest.question2])), axis=1)
    quality_token_sort_ratio = compute_quality(train_df, Fields.token_sort_ratio)

    quality = dict(
        quality_qratio=quality_qratio,
        quality_wratio=quality_wratio,
        quality_partial_ratio=quality_partial_ratio,
        quality_partial_token_set_ratio=quality_partial_token_set_ratio,
        quality_partial_token_sort_ratio=quality_partial_token_sort_ratio,
        quality_token_set_ratio=quality_token_set_ratio,
        quality_token_sort_ratio=quality_token_sort_ratio
    )

    return quality