Machine Learning - Beginner to Advanced

fetch_data.py

import pandas as pd

def load_housing_data():
    return pd.read_csv('housing.csv')
    
housing = load_housing_data()
housing.head()

split_data.py

import numpy as np

# For illustration only. Sklearn has train_test_split()
def split_train_test(data, test_ratio):
    shuffled_indices = np.random.permutation(len(data))
    test_set_size = int(len(data) * test_ratio)
    test_indices = shuffled_indices[:test_set_size]
    train_indices = shuffled_indices[test_set_size:]
    return data.iloc[train_indices], data.iloc[test_indices]

# Using the function to split
train_set, test_set = split_train_test(housing, 0.2)