DataScience/kmeansDBSCAN.py at master · an-hyojin/DataScience · 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
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
#!/usr/bin/env python
# coding: utf-8

# In[2]:


import numpy as np
import pandas as pd
import os
import matplotlib.pyplot as plt
import seaborn as sns
sns.set(context="notebook", palette="Spectral", style="darkgrid", font_scale=1.5, color_codes =True)


# In[3]:


dataset = pd.read_csv('input.csv', index_col='CustomerID')


# In[4]:


dataset.head()


# In[5]:


dataset.info()


# In[6]:


dataset.describe()


# In[7]:


dataset.isnull().sum()


# In[8]:


dataset.drop_duplicates(inplace=True)


# In[9]:


X = dataset.iloc[:,[2,3]].values


# In[10]:


from sklearn.cluster import KMeans
wcss = []

for i in range(1, 11):
    kmeans = KMeans(n_clusters= i, init = 'k-means++', random_state=42)
    kmeans.fit(X)
    wcss.append(kmeans.inertia_)


# In[11]:


plt.figure(figsize=(10,5))
sns.lineplot(range(1,11), wcss,marker='o', color='red')
plt.title('The Elbow Method')
plt.xlabel('Number of clusters')
plt.ylabel('WCSS')
plt.show()


# In[12]:


kmeans = KMeans(n_clusters = 5, init = 'k-means++', random_state = 42)
y_kmeans = kmeans.fit_predict(X)


# In[13]:


plt.figure(figsize=(15,7))
sns.scatterplot(X[y_kmeans==0,0], X[y_kmeans ==0,1], color = 'yellow', label='Cluster 1 ', s=50)
sns.scatterplot(X[y_kmeans==1,0], X[y_kmeans ==1,1], color = 'blue', label='Cluster 2 ', s=50)
sns.scatterplot(X[y_kmeans==2,0], X[y_kmeans ==2,1], color = 'green', label='Cluster 3 ', s=50)
sns.scatterplot(X[y_kmeans==3,0], X[y_kmeans ==3,1], color = 'grey', label='Cluster 4 ', s=50)
sns.scatterplot(X[y_kmeans==4,0], X[y_kmeans ==4,1], color = 'orange', label='Cluster 5 ', s=50)
sns.scatterplot(kmeans.cluster_centers_[:, 0], kmeans.cluster_centers_[:, 1], color = 'red',
                label = 'Centroids',s=300,marker=',')
plt.grid(False)
plt.title('Clusters of customers')
plt.xlabel('Annual Income (k$)')
plt.ylabel('Spending Score (1-100)')
plt.legend()
plt.show()


# In[42]:


from sklearn.cluster import DBSCAN
db = DBSCAN(eps=10, min_samples=8, metric='euclidean')
y_db = db.fit_predict(X)


plt.figure(figsize=(15,7))

sns.scatterplot(X[y_db==0,0], X[y_db ==0,1], color = 'yellow', label='Cluster 1 ', s=50)
sns.scatterplot(X[y_db==1,0], X[y_db ==1,1], color = 'blue', label='Cluster 2 ', s=50)
sns.scatterplot(X[y_db==2,0], X[y_db ==2,1], color = 'green', label='Cluster 3 ', s=50)
sns.scatterplot(X[y_db==3,0], X[y_db ==3,1], color = 'grey', label='Cluster 4 ', s=50)
sns.scatterplot(X[y_db==4,0], X[y_db ==4,1], color = 'orange', label='Cluster 5 ', s=50)

plt.grid(False)
plt.title('Clusters of customers')
plt.xlabel('Annual Income (k$)')
plt.ylabel('Spending Score (1-100)')
plt.legend()
plt.show()


# In[ ]: