In [9]:
import matplotlib.pyplot as plt  
import pandas as pd  
%matplotlib inline
import numpy as np
In [10]:
customer_data = pd.read_csv('shopping_data.csv')
In [11]:
customer_data.shape
Out[11]:
(200, 5)
In [12]:
customer_data.head()
Out[12]:
CustomerID Genre Age Annual Income (k$) Spending Score (1-100)
0 1 Male 19 15 39
1 2 Male 21 15 81
2 3 Female 20 16 6
3 4 Female 23 16 77
4 5 Female 31 17 40
In [13]:
data = customer_data.iloc[:, 3:5].values
In [14]:
import scipy.cluster.hierarchy as shc

plt.figure(figsize=(20, 10))  
plt.title("Customer Dendograms")  
dend = shc.dendrogram(shc.linkage(data, method='ward'))
In [15]:
from sklearn.cluster import AgglomerativeClustering

cluster = AgglomerativeClustering(n_clusters=5, affinity='euclidean', linkage='ward')  
cluster.fit_predict(data)
Out[15]:
array([4, 3, 4, 3, 4, 3, 4, 3, 4, 3, 4, 3, 4, 3, 4, 3, 4, 3, 4, 3, 4, 3,
       4, 3, 4, 3, 4, 3, 4, 3, 4, 3, 4, 3, 4, 3, 4, 3, 4, 3, 4, 3, 4, 1,
       4, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 1, 2, 1, 2, 0, 2, 0, 2,
       1, 2, 0, 2, 0, 2, 0, 2, 0, 2, 1, 2, 0, 2, 1, 2, 0, 2, 0, 2, 0, 2,
       0, 2, 0, 2, 0, 2, 1, 2, 0, 2, 0, 2, 0, 2, 0, 2, 0, 2, 0, 2, 0, 2,
       0, 2, 0, 2, 0, 2, 0, 2, 0, 2, 0, 2, 0, 2, 0, 2, 0, 2, 0, 2, 0, 2,
       0, 2])
In [16]:
plt.figure(figsize=(10, 7))  
plt.scatter(data[:,0], data[:,1], c=cluster.labels_, cmap='rainbow')
Out[16]:
<matplotlib.collections.PathCollection at 0x7f2d8d002490>
In [ ]:
In [ ]: