In [1]:
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn.cluster import KMeans
import seaborn as sns
# To ignore warnings
import warnings
warnings.filterwarnings("ignore")
In [2]:
customer_data = pd.read_csv("Mall_Customers.csv")
In [3]:
customer_data.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 200 entries, 0 to 199
Data columns (total 5 columns):
 #   Column                  Non-Null Count  Dtype 
---  ------                  --------------  ----- 
 0   CustomerID              200 non-null    int64 
 1   Gender                  200 non-null    object
 2   Age                     200 non-null    int64 
 3   Annual Income (k$)      200 non-null    int64 
 4   Spending Score (1-100)  200 non-null    int64 
dtypes: int64(4), object(1)
memory usage: 7.9+ KB
In [4]:
customer_data.head()
Out[4]:
CustomerID Gender Age Annual Income (k$) 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 [5]:
plt.scatter(customer_data['Age'],customer_data['Spending Score (1-100)'])
plt.xlabel('Age')
plt.ylabel('Spending Score')
plt.show()
In [6]:
km_sample = KMeans(n_clusters=3)
km_sample.fit(customer_data[['Age','Spending Score (1-100)']])
Out[6]:
KMeans(n_clusters=3)
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
KMeans(n_clusters=3)
In [7]:
labels_sample = km_sample.labels_
customer_data['label'] = labels_sample
sns.scatterplot(x=customer_data['Age'],y=customer_data['Spending Score (1-100)'],hue=customer_data['label'],palette='Set1')
Out[7]:
<Axes: xlabel='Age', ylabel='Spending Score (1-100)'>

Observation¶

Cluster 0 - Young adults - Spenders¶

Cluster 1 - Average spenders - all age group¶

Cluster 2 - Savers ( spend wisely~) - Age group average to high¶

In [8]:
km_sample1 = KMeans(n_clusters=3)
km_sample1.fit(customer_data[['Annual Income (k$)','Spending Score (1-100)']])
Out[8]:
KMeans(n_clusters=3)
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
KMeans(n_clusters=3)
In [9]:
labels_sample1 = km_sample1.labels_
customer_data['label'] = labels_sample1
sns.scatterplot(x=customer_data['Annual Income (k$)'],y=customer_data['Spending Score (1-100)'],hue=customer_data['label'],palette='Set1')
Out[9]:
<Axes: xlabel='Annual Income (k$)', ylabel='Spending Score (1-100)'>

Observation ? in terms of Spending habit, income and age¶

Cluster 0 - ?¶

Cluster 1 - ?¶

Cluster 2 - ?¶

In [10]:
WCSS= []
K = range(1,9)
for i in K:
    Kmeanmodel=KMeans(n_clusters=i, init='k-means++', max_iter=300, n_init=10, random_state=42)
    Kmeanmodel.fit(customer_data[['Age','Spending Score (1-100)']])
    WCSS.append(Kmeanmodel.inertia_)
In [11]:
plt.plot(range(1,9),WCSS)
plt.xlabel('Number of clusters')
plt.ylabel('WCSS')
plt.show()

What is the recommended cluster count ?¶

In [ ]: