stats.py 文件源码

def n2_ratio_intra_extra_class_nearest_neighbor_distance(data):

    features = data.columns[:-1,]
    labels = data.columns[-1]

    dist    = pdist(data[features], 'euclidean')
    df_dist = pd.DataFrame(squareform(dist))

    max_size = df_dist.copy( )
    max_size.iloc[:, :] = False

    classes = data.iloc[ :, -1].unique()
    n = data.shape[0]

    n2 = 0
    cl = 'bla'
    intra_min = 0
    inter_min = 0
    for i in range(data.shape[0]):
        ci = data.iloc[i, -1]
        if ci != cl:
            cl = ci
            intra_idx = data[data[labels] == ci].index.values.tolist()
            inter_idx = data[data[labels] != ci].index.values
        intra_idx.remove(i)
        intra_min = intra_min + df_dist.iloc[intra_idx, i].min()
        inter_min = inter_min + df_dist.iloc[inter_idx, i].min()
        intra_idx.append(i)

    # tratar caso de inter_min == 0
    if inter_min == 0:
        inter_min = 1

    n2 = (1.0 * intra_min) / (1.0 * inter_min)

    return n2