Machine-Learning/Hierarchical Clustering.py at master · BlueTeamQQ1/Machine-Learning · GitHub

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
#!/usr/bin/env python
# coding: utf-8

# In[5]:


import pandas as pd
import matplotlib.pyplot as plt


# In[2]:


dataset= pd.read_csv("Mall_Customers.csv")


# In[3]:


X = dataset.iloc[:, [3,4]].values


# In[6]:


import scipy.cluster.hierarchy as sch
dendrogram = sch.dendrogram(sch.linkage(X, method="ward"))
plt.show()


# In[7]:


from sklearn.cluster import AgglomerativeClustering
hc = AgglomerativeClustering(n_clusters=5, affinity= "euclidean", linkage= "ward")
y_hc = hc.fit_predict(X)


# In[8]:


plt.scatter(X[y_hc == 0, 0], X[y_hc == 0, 1], s = 100, c = 'red', label = 'Cluster 1')
plt.scatter(X[y_hc == 1, 0], X[y_hc == 1, 1], s = 100, c = 'blue', label = 'Cluster 2')
plt.scatter(X[y_hc == 2, 0], X[y_hc == 2, 1], s = 100, c = 'green', label = 'Cluster 3')
plt.scatter(X[y_hc == 3, 0], X[y_hc == 3, 1], s = 100, c = 'cyan', label = 'Cluster 4')
plt.scatter(X[y_hc == 4, 0], X[y_hc == 4, 1], s = 100, c = 'magenta', label = 'Cluster 5')
plt.title('Clusters of customers')
plt.xlabel('Annual Income (k$)')
plt.ylabel('Spending Score (1-100)')
plt.legend()
plt.show()


# In[ ]: