stats.py 文件源码

def n1_fraction_borderline(data):

    def get_n1_for_round(sparse_matrix, y):
        Tcsr = minimum_spanning_tree(sparse_matrix)
        borders = set()
        a = Tcsr.nonzero()[0]
        b = Tcsr.nonzero()[1]

        for i in range(len(a)):
            if (y[a[i]] != y[b[i]]):
                borders.add(a[i])
                borders.add(b[i])
        n1 = len(borders)
        return n1

    features = data.columns[:-1, ]
    dist = pdist(data[features], 'euclidean')
    df_dist = pd.DataFrame(squareform(dist))
    sparse_matrix = csr_matrix(df_dist.values)

    labels = data.columns[-1]
    y = data[labels]

    n1 = 0
    rounds = 10

    for round in range(rounds):
        n1 = n1 + get_n1_for_round(sparse_matrix, y)

    n = len(data)
    n1 = (1.0 * n1) / (rounds * n)

    return n1