kmeans2

import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
import seaborn as sns
df_cust=pd.read_csv("Customers.csv")
df_cust.head()
df_cust.corr()
df_cust.columns
df_cust.drop(["CustomerID"],axis=1,inplace=True)
df_cust.plot.scatter(x='Age',y='Spending Score (1-100)')
sns.countplot(x='Genre',data=df_cust)
plt.figure(figsize=(12,10))
sns.countplot(x='Age',data=df_cust)
from sklearn.cluster import KMeans
X=df_cust[["Annual Income (k$)","Spending Score (1-100)"]] wcss=[] for i in range(1,11): (-give-space-)km=KMeans(n_clusters=i) (-give-space-)km.fit(X) (-give-space-)wcss.append(km.inertia_) km1=KMeans(n_clusters=5) km1.fit(X) y=km1.predict(X) df_cust["label"] = y df_cust.head() plt.figure(figsize=(10,6)) sns.scatterplot(x = 'Annual Income (k$)',y = 'Spending Score (1-100)',hue="label",
palette=['green','orange','brown','dodgerblue','red'], legend='full',data = df_cust ,s = 60 )
plt.xlabel('Annual Income (k$)') plt.ylabel('Spending Score (1-100)') plt.title('Spending Score (1-100) vs Annual Income (k$)')
plt.show();