Linear Regression

An example of how to construct a linear regression model using the housing dataset and view results.



In [4]:

    
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
%matplotlib inline



In [1]:

    
# load the housing dataset
data_url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/housing/housing.data'
colnames = ['CRIM', 'ZN', 'INDUS', 'CHAS', 'NOX', 'RM', 'AGE', 'DIS', 
            'RAD', 'TAX', 'PTRATIO', 'B', 'LSTAT', 'MEDV']
df = pd.read_csv(data_url, header=None, sep='\s+', names=colnames)



In [5]:

    
# Exploratory data analysis
sns.set(style='whitegrid', context='notebook')
cols = ['LSTAT', 'INDUS', 'NOX', 'RM', 'MEDV']
sns.pairplot(df[cols], size=2.5)









    Out[5]:





<seaborn.axisgrid.PairGrid at 0x1a0fda6080>



In [ ]:

	CRIM	ZN	INDUS	NOX	RM	AGE	DIS	RAD	TAX	PTRATIO	B	LSTAT	MEDV
0	0.00632	18.0	2.31	0.538	6.575	65.2	4.0900	1	296.0	15.3	396.90	4.98	24.0
1	0.02731	0.0	7.07	0.469	6.421	78.9	4.9671	2	242.0	17.8	396.90	9.14	21.6
2	0.02729	0.0	7.07	0.469	7.185	61.1	4.9671	2	242.0	17.8	392.83	4.03	34.7
3	0.03237	0.0	2.18	0.458	6.998	45.8	6.0622	3	222.0	18.7	394.63	2.94	33.4
4	0.06905	0.0	2.18	0.458	7.147	54.2	6.0622	3	222.0	18.7	396.90	5.33	36.2