def __k_mean(cls, df, k_clusters, xnorm, label_name):
from sklearn.cluster import KMeans
kmeans_cat = label_name
if xnorm.shape[1] > 0:
#n_clusters = elbow point
start_time = time.time()
estimator = KMeans(n_clusters=k_clusters)
estimator.fit(xnorm)
y_pred = estimator.predict(xnorm)
res=estimator.__dict__
#print(res['cluster_centers_'])
cluster_center = res['cluster_centers_']
print("training time: ", time.time()-start_time, "(sec)")
else:
#no split
y_pred = 0
cluster_center = []
print("no kmeans split")
df[kmeans_cat] = y_pred + 1
return df, kmeans_cat, cluster_center
# ss.to_csv("../feature/cf_clustering_20.txt",index=False)
print("saddddddd")
userFactors=model.userFactors.withColumn("features",array2Vec("features"))#
userFactors.show()
############################################
# data = pd.read_csv("../feature/cf_clustering_20.txt")
data = ss
y = data['id']
x = data[[x for x in data.columns if x != 'id']]
from sklearn.cluster import KMeans
kmeans = KMeans(n_clusters=30,max_iter=200)
kmeans = kmeans.fit(x)
lables = kmeans.predict(x)
data['culster30'] = lables
print("##################")
print(data.head())
print(kmeans.cluster_centers_)
# data = data[[x for x in data.columns if x in ('id','lable')]]
data.to_csv("../feature/cf_clustering_app30.txt",index=False)
# kmeans = KMeans(n_clusters=100,max_iter=300)
# kmeans = kmeans.fit(x)
#
# lables = kmeans.predict(x)
# data['culster100'] = lables
# print("##################")
