dataaspirant-regularization-load-house-price-data.py

## import the required libraries
import pandas as pd 
import numpy as np 
import matplotlib.pyplot as plt
from statistics import mean 
from sklearn.linear_model import LinearRegression, Ridge, Lasso 
from sklearn.model_selection import train_test_split, cross_val_score 

## load the dataset
df = pd.read_csv("kc_house_data.csv")
## dropping unnecessary columns
df = df.drop(['id', 'date', 'zipcode'], axis=1) 

## separating the target variable
X = df.drop('price', axis=1)
y = df['price']
## splitting the data into train and test (70-30 ratio)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.30)