index.py 文件源码

def main():
    df = pd.read_csv("dataset.csv")
    df = df.dropna()
    # print df
    x1 = df.copy()
    del x1['Customer']
    del x1['Effective To Date']
    x4 = pd.get_dummies(x1)
    # print x4
    n = 10
    clf = k_means(x4, n_clusters = n)
    centroids = clf[0] 
    # 10 clusters
    labels = clf[1] 
    # print x4[1]
    index_db_val = compute_DB_index(x4, labels, centroids, n)
    print "The value of Davies Bouldin index for a K-Means cluser of size " + str(n) + " is: " + str(index_db_val)