#!/usr/bin/env python # coding: utf-8 # #

Introduction to Kaggle

# # In[ ]: # This Python 3 environment comes with many helpful analytics libraries installed # It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python # For example, here's several helpful packages to load import numpy as np # linear algebra import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv) # Input data files are available in the read-only "../input/" directory # For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory import os for dirname, _, filenames in os.walk('/kaggle/input'): for filename in filenames: print(os.path.join(dirname, filename)) # You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using "Save & Run All" # You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session data = pd.read_csv('https://www.kaggle.com/housing-prices-dataset/Housing.csv') X = data[['price', 'area', 'bedrooms', 'bathrooms', 'stories']].to_numpy() from sklearn.preprocessing import StandardScaler from sklearn.linear_model import LinearRegression from sklearn.metrics import mean_squared_error Xscaled = StandardScaler().fit_transform(X) from sklearn.model_selection import train_test_split Xtrain, Xtest, ytrain, ytest = train_test_split(Xscaled[:, 1:],Xscaled[:,0]) numXP = 100 MSE = np.zeros((4,numXP)) for xp in np.arange(numXP): for k in np.arange(1,5): reg = LinearRegression().fit(Xtrain[:,0:k], ytrain) prediction = reg.predict(Xtest[:,0:k]) MSE[k-1,xp] = mean_squared_error(ytest, prediction) import matplotlib.pyplot as plt plt.plot(np.mean(MSE, axis=1)) plt.show()