import numpy as np
from sklearn.metrics import silhouette_score
from clustering.kmeans import k_means
from sklearn.cluster import KMeans
from sklearn.metrics import calinski_harabasz_score
from clustering.preprocess.pre_process import load_data
import time
from clustering.kmeans import k_means
raw_data, data_all, data_pca, data_respectively_pca = load_data('/Users/jackietien/Documents/ClassificationAndClustering/clustering/preprocess/data.csv')
data = data_respectively_pca
k = 6
start_time = time.time()
estimator = KMeans(n_clusters=k).fit(data)
# _, label, sse = k_means.k_means(data, k)
end_time = time.time()
consuming_time = end_time - start_time
print(consuming_time)
# cluster_centers = estimator.cluster_centers_
#
label = estimator.labels_
sse = estimator.inertia_
silhouette = silhouette_score(data, label)
calinski_harabasz = calinski_harabasz_score(data, label)
print("lib result: \t", " k: ", k, "\tsse: ", sse, "\tsilhouette: ", silhouette, "\tcalinski_harabaz_score: ", calinski_harabasz)
for i in range(k):
cluster_k = raw_data[label == i]
a = {}
# res[len(res) - 1].append(i)
continue
else:
res[full_list[i]].append(i)
return res
def get_sub_list(full_list, indexes):
res = []
for i in indexes:
res.append(full_list[i])
return res
if __name__ == '__main__':
raw_data, full_data, data_pca, data_respectively_pca = pre_process.load_data(
"../preprocess/data.csv")
db = DBSCAN(eps=0.75, min_samples=20).fit(data_respectively_pca)
labels = db.labels_
grouped = group(labels)
fig1 = plt.figure()
ax1 = Axes3D(fig1)
ax2 = plt.figure().add_subplot(111)
ax3 = plt.figure().add_subplot(111)
ax4 = plt.figure().add_subplot(111)
for i in grouped:
plot_data = np.array(get_sub_list(data_pca, i))
import time
import matplotlib.pyplot as plt
from sklearn.cluster import DBSCAN
from sklearn.metrics import calinski_harabasz_score
from sklearn.metrics import silhouette_score
from sklearn.neighbors import NearestNeighbors
from clustering.preprocess.pre_process import load_data
raw_data, data_all, data_pca, data_respectively_pca = load_data(
"../preprocess/data.csv")
data = data_all
lib_SSE = []
# 轮廓系数
# lib_silhouette = []
# lib_calinski_harabasz = []
#
# self_SSE = []
# self_silhouette = []
# self_calinski_harabasz = []
#
#
# lib_SSE.clear()
# lib_silhouette.clear()
# lib_calinski_harabasz.clear()
# self_SSE.clear()
# self_silhouette.clear()
# self_calinski_harabasz.clear()