bm25.py 文件源码

def _class_frequencies(X, y):
    """Count the number of non-zero values for each class y in sparse X."""

    labels = np.unique(y)
    if len(labels) > 2:
        raise ValueError("Delta works only with binary classification problems")

    # Indices for each type of labels in y
    N1 = np.where(y == labels[0])[0]
    N2 = np.where(y == labels[1])[0]

    # Number of positive documents that each term appears on
    df1 = np.bincount(X[N1].nonzero()[1], minlength=X.shape[1])
    # Number of negative documents that each term appears on
    df2 = np.bincount(X[N2].nonzero()[1], minlength=X.shape[1])

    return N1.shape[0], df1, N2.shape[0], df2