Exercise

Exploring credit card fraud dataset

In this exercise, you will do some data exploration on a sample of the credit card fraud detection dataset from Kaggle. For any problem, starting with some data exploration is a good practice and helps us better understand the characteristics of the data.

The credit card fraud dataset is already loaded in the environment as a data table with the name creditcard. As you saw in the video, it consists of 30 numerical variables. The Class column indicates if the transaction is fraudulent.

The ggplot2 package has been loaded for you.

Instructions

100 XP

Have a look at the dimensions of creditcard.
Explore the structure of the creditcard object.
Generate a summary of the dataset.
Plot a histogram of the transaction time using ggplot().

Take Hint (-30 XP)