Machine Learning with scikit-learn Quick Start Guide

Creating the base k-means model

In order to load the dataset into our workspace and drop the target feature with the labels, we use the following code:

import pandas as pd#Reading in the datasetdf = pd.read_csv('fraud_prediction.csv')#Dropping the target feature & the indexdf = df.drop(['Unnamed: 0', 'isFraud'], axis = 1)

Next, we can implement the k-means algorithm with two cluster means. The choice of using two cluster means is arbitrary in nature, since we know that there should be two distinct clusters as a result of two labels: fraud and not fraud transactions. We can do this by using the following code:

from sklearn.cluster import KMeans#Initializing K-means with 2 clustersk_means = KMeans(n_clusters = 2)#Fitting the model on the data ...