Hands-On Python Deep Learning for the Web

Step 2 – Loading the dataset and observing

Let's load the dataset, assuming it to be stored in a folder named data that is on the same directory level as that of the directory containing our Jupyter notebook:

df = pd.read_csv("data/heart.csv")

We'll quickly observe the DataFrame to see whether all the columns have been imported correctly:

df.head(5)

This produces the following output in the Jupyter notebook:

We can observe the 14 columns and see that they have been imported correctly. A basic Exploratory Data Analysis (EDA) would reveal that the dataset does not contain any missing values. However, the raw UCI Cleveland dataset does contain ...