Task2-KMeans.py

# -*- coding: utf-8 -*-
"""
Created on Mon Dec 27 18:51:43 2021

@author: Beboo
"""
import pandas as pd
import matplotlib.pyplot as plt

#1.	Factorize the YearsExp feature and convert it to numbers in new col.
dataset = pd.read_csv("Wuzzuf_Jobs.csv")
dataset["YearsExp"] = dataset["YearsExp"].str.split(" ", n = 1, expand = True)
x=dataset.iloc[:, 5].values
dataset['fact'] = pd.factorize(x)[0]

#2.	Apply K-means for job title and companies.
#Convert data from string to numbers
x1=dataset.iloc[:, 0].values
dataset['fact1'] = pd.factorize(x1)[0]
x2=dataset.iloc[:, 1].values
dataset['fact2'] = pd.factorize(x2)[0]
#Make list of job title and companies 
X = dataset.iloc[:,[9,10]].values

#Applay K-means
from sklearn.cluster import KMeans
wcss = []
for i in range(1, 20):
    kmeans = KMeans(n_clusters = i, init = 'k-means++', random_state = 10)
    kmeans.fit(X)
    wcss.append(kmeans.inertia_)

#Choose the elbow point using curve
plt.plot(range(1, 20), wcss)
plt.title('The Elbow Method')
plt.xlabel('Number of clusters')
plt.ylabel('WCSS')
plt.show()

#Choose the elbow point using KneeLocator   
from kneed import KneeLocator
k1 = KneeLocator(range(1, 20), wcss, curve="convex", direction="decreasing")
print(k1.elbow)

kmeans = KMeans(n_clusters = 5, init = 'k-means++', random_state = 10)
y_kmeans = kmeans.fit_predict(X)
y_kmeans == 0

# Visualising the clusters
plt.scatter(X[y_kmeans == 0, 0], X[y_kmeans == 0, 1], s = 100, c = 'red', label = 'Cluster 1')
plt.scatter(X[y_kmeans == 1, 0], X[y_kmeans == 1, 1], s = 100, c = 'blue', label = 'Cluster 2')
plt.scatter(X[y_kmeans == 2, 0], X[y_kmeans == 2, 1], s = 100, c = 'green', label = 'Cluster 3')
plt.scatter(X[y_kmeans == 3, 0], X[y_kmeans == 3, 1], s = 100, c = 'cyan', label = 'Cluster 4')
plt.scatter(X[y_kmeans == 4, 0], X[y_kmeans == 4, 1], s = 100, c = 'magenta', label = 'Cluster 5')
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()