#importing necessary libraries
import numpy as np
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
import sklearn as sk
loan = pd.read_csv('train_ctrUa4K.csv')
loan.head()
Loan_IDobject
Genderobject
0
LP001002
Male
1
LP001003
Male
2
LP001005
Male
3
LP001006
Male
4
LP001008
Male
loan.describe()
ApplicantIncomefloat64
CoapplicantIncomefloat64
count
614
614
mean
5403.459283
1621.245798
std
6109.041673
2926.248369
min
150
0
25%
2877.5
0
50%
3812.5
1188.5
75%
5795
2297.25
max
81000
41667
loan["LoanAmount"]= loan["LoanAmount"].fillna(value=loan["LoanAmount"].median())
data = loan.iloc[:, [6, 8]].values
from sklearn.cluster import KMeans
wcss = []
for i in range(1, 11): #Test 1 to 10 differnt clusters
#Loop over the indented statements 10 times to see how distance reduces till it becomes steady
kmeans = KMeans(n_clusters = i, init = 'k-means++', random_state = 42)
kmeans.fit(data)
wcss.append(kmeans.inertia_)
plt.plot(range(1, 11), wcss) # plot the ten different wcss against the number of clusters
plt.title('The Elbow Method')
plt.xlabel('Number of clusters')
plt.ylabel('WCSS')
plt.show()
kmeans = KMeans(n_clusters = 3, init = 'k-means++', random_state = 42)
y_kmeans = kmeans.fit_predict(data)
plt.scatter(data[y_kmeans == 0, 0], data[y_kmeans == 0, 1], s = 100, c = 'red', label = 'Cluster 1')
plt.scatter(data[y_kmeans == 1, 0], data[y_kmeans == 1, 1], s = 100, c = 'blue', label = 'Cluster 2')
plt.scatter(data[y_kmeans == 2, 0], data[y_kmeans == 2, 1], s = 100, c = 'green', label = 'Cluster 3')
plt.scatter(kmeans.cluster_centers_[:, 0], kmeans.cluster_centers_[:, 1], s = 300, c = 'yellow', label = 'Centroids')
plt.title('Clusters of customers')
plt.xlabel('Annual Income (k$)')
plt.ylabel('Spending Score (1-100)')
plt.legend()
plt.show()