-
Notifications
You must be signed in to change notification settings - Fork 5
/
3_34.py
56 lines (39 loc) · 1.25 KB
/
3_34.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
import sklearn.decomposition
import sklearn.preprocessing
import sklearn.cluster
import numpy as np
import pandas as pd
import elice_utils
def main():
np.random.seed(108)
# 1
noisy_circles = pd.read_csv('noisy_circle.csv')
noisy_circles = noisy_circles.set_index('index')
blobs = pd.read_csv('blobs.csv')
blobs = blobs.set_index('index')
return draw_graph([noisy_circles, blobs])
def run_kmeans(X, num_clusters):
# 2
kmeans = sklearn.cluster.KMeans(n_clusters = num_clusters, n_init = 1)
kmeans.fit(X)
return kmeans
def run_DBScan(X, eps):
# 3
dbscan = sklearn.cluster.DBSCAN(eps=0.2)
dbscan.fit(X)
return dbscan
def draw_graph(datasets, n_clusters=2, eps=0.2, alg_name = ['KMeans', 'DBScan']):
plot_num = 1
elice_utils.draw_init()
for dataset in datasets:
# 4
X = np.vstack((dataset.ix[:,1],dataset.ix[:,2])).T
kmeans_result = run_kmeans(X, n_clusters)
dbscan_result = run_DBScan(X, eps)
for name, algorithm in zip(alg_name, [kmeans_result, dbscan_result]):
elice_utils.draw_graph(X, algorithm, name, plot_num)
plot_num += 1
print(elice_utils.show_graph())
return dbscan_result
if __name__ == '__main__':
main()