Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- from sklearn.cluster import KMeans
- import pandas as pd
- from sklearn.preprocessing import MinMaxScaler
- from matplotlib import pyplot as plt
- url='https://raw.githubusercontent.com/codebasics/py/master/ML/13_kmeans/i
- ncome.csv'
- df = pd.read_csv(url)
- df.head()
- plt.scatter(df.Age,df['Income($)'])
- plt.xlabel('Age')
- plt.ylabel('Income($)')
- ------------------------------------------------------------------------------------------------------------------------------------------
- km = KMeans(n_clusters=3)
- y_predicted = km.fit_predict(df[['Age','Income($)']])
- y_predicted
- df['cluster']=y_predicted
- df.head()
- km.cluster_centers_
- df1 = df[df.cluster==0]
- df2 = df[df.cluster==1]
- df3 = df[df.cluster==2]
- plt.scatter(df1.Age,df1['Income($)'],color='green')
- plt.scatter(df2.Age,df2['Income($)'],color='red')
- plt.scatter(df3.Age,df3['Income($)'],color='black')
- plt.scatter(km.cluster_centers_[:,0],km.cluster_centers_[:,1],color='purpl
- e',marker='*',label=
- 'centroid')
- plt.xlabel('Age')
- plt.ylabel('Income ($)')
- plt.legend()
- scaler = MinMaxScaler()
- scaler.fit(df[['Income($)']])
- df['Income($)'] = scaler.transform(df[['Income($)']])
- scaler.fit(df[['Age']])
- df['Age'] = scaler.transform(df[['Age']])
- df.head()
- plt.scatter(df.Age,df['Income($)'])
- km = KMeans(n_clusters=3)
- y_predicted = km.fit_predict(df[['Age','Income($)']])
- y_predicted
- df['cluster']=y_predicted
- df.head()
- km.cluster_centers_
- df1 = df[df.cluster==0]
- df2 = df[df.cluster==1]
- df3 = df[df.cluster==2]
- plt.scatter(df1.Age,df1['Income($)'],color='green')
- plt.scatter(df2.Age,df2['Income($)'],color='red')
- plt.scatter(df3.Age,df3['Income($)'],color='black')
- plt.scatter(km.cluster_centers_[:,0],km.cluster_centers_[:,1],color='purpl
- e',marker='*',label=
- 'centroid')
- plt.legend()
Add Comment
Please, Sign In to add comment
