In [57]: import pandas as pd
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
data=pd.read_csv("C:\\Users\\Liki\\Onedrive\\Documents\\Mall_Customers.csv")
display(data)
data.tail()
data.head()
x=data.iloc[:,[3,4]]
display(x)
sns.scatterplot(x="Annual Income (k$)",y="Spending Score (1-100)",data=data)
from sklearn.cluster import KMeans
cs=[]
for i in range(1,11):
kmeans=KMeans(n_clusters=i,init='k-means++',random_state=42)
kmeans.fit(x)
cs.append(kmeans.inertia_)
plt.plot(range(1,11),cs,marker='o')
plt.title("The Elbow method\n")
plt.xlabel("Number of clusters")
plt.ylabel("cs")
CustomerID Genre Age Annual Income (k$) 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
... ... ... ... ... ...
195 196 Female 35 120 79
196 197 Female 45 126 28
197 198 Male 32 126 74
198 199 Male 32 137 18
199 200 Male 30 137 83
In [ ]: