diff --git a/main.py b/main.py index 05d739c..484d5e5 100644 --- a/main.py +++ b/main.py @@ -2,6 +2,16 @@ import csv import numpy as np import pandas as pd from sklearn.model_selection import train_test_split +import kaggle +import os + +kaggle.api.authenticate() + +c_directory = os.getcwd() + +kaggle.api.dataset_download_files('kamilpytlak/personal-key-indicators-of-heart-disease', path=f"{c_directory}", unzip=True) + + dataset = pd.read_csv("heart_2020_cleaned.csv") print(dataset.describe(include='all'))