
import pandas as pd

import numpy as np

import matplotlib.pyplot as plt

%matplotlib inline

import seaborn as sns


raw_data = pd.read_csv('Housing_Data.csv')


raw_data


sns.pairplot(raw_data)

<seaborn.axisgrid.PairGrid at 0x2a9c0f8f250>


x = raw_data[['Avg. Area Income', 'Avg. Area House Age', 'Avg. Area Number of Rooms',

       'Avg. Area Number of Bedrooms', 'Area Population']]


y = raw_data['Price']


from sklearn.model_selection import train_test_split


x_train, x_test, y_train, y_test = train_test_split(x, y, test_size = 0.3)


from sklearn.linear_model import LinearRegression


model = LinearRegression()


model.fit(x_train, y_train)

LinearRegression()


print(model.coef_)

[2.16439168e+01 1.63855631e+05 1.19945424e+05 2.20796129e+03
 1.52027854e+01]


print(model.intercept_)

-2627798.9504352147


pd.DataFrame(model.coef_, x.columns, columns = ['Coeff'])


predictions = model.predict(x_test)


plt.scatter(y_test, predictions)

<matplotlib.collections.PathCollection at 0x2a9c8f42e20>


plt.hist(y_test - predictions)

(array([  4.,  26., 104., 222., 282., 355., 271., 158.,  65.,  13.]),
 array([-327857.18771484, -266217.02064656, -204576.85357828,
        -142936.68651   ,  -81296.51944171,  -19656.35237343,
          41983.81469485,  103623.98176313,  165264.14883141,
         226904.31589969,  288544.48296797]),
 <BarContainer object of 10 artists>)


from sklearn import metrics


metrics.mean_absolute_error(y_test, predictions)

82246.42443937554


metrics.mean_squared_error(y_test, predictions)

10366906621.779713


np.sqrt(metrics.mean_squared_error(y_test, predictions))

101818.00735518111

	Avg. Area Income	Avg. Area House Age	Avg. Area Number of Rooms	Avg. Area Number of Bedrooms	Area Population	Price	Address
0	79545.458574	5.682861	7.009188	4.09	23086.800503	1.059034e+06	208 Michael Ferry Apt. 674\nLaurabury, NE 3701...
1	79248.642455	6.002900	6.730821	3.09	40173.072174	1.505891e+06	188 Johnson Views Suite 079\nLake Kathleen, CA...
2	61287.067179	5.865890	8.512727	5.13	36882.159400	1.058988e+06	9127 Elizabeth Stravenue\nDanieltown, WI 06482...
3	63345.240046	7.188236	5.586729	3.26	34310.242831	1.260617e+06	USS Barnett\nFPO AP 44820
4	59982.197226	5.040555	7.839388	4.23	26354.109472	6.309435e+05	USNS Raymond\nFPO AE 09386
...	...	...	...	...	...	...	...
4995	60567.944140	7.830362	6.137356	3.46	22837.361035	1.060194e+06	USNS Williams\nFPO AP 30153-7653
4996	78491.275435	6.999135	6.576763	4.02	25616.115489	1.482618e+06	PSC 9258, Box 8489\nAPO AA 42991-3352
4997	63390.686886	7.250591	4.805081	2.13	33266.145490	1.030730e+06	4215 Tracy Garden Suite 076\nJoshualand, VA 01...
4998	68001.331235	5.534388	7.130144	5.44	42625.620156	1.198657e+06	USS Wallace\nFPO AE 73316
4999	65510.581804	5.992305	6.792336	4.07	46501.283803	1.298950e+06	37778 George Ridges Apt. 509\nEast Holly, NV 2...

	Coeff
Avg. Area Income	21.643917
Avg. Area House Age	163855.630531
Avg. Area Number of Rooms	119945.424082
Avg. Area Number of Bedrooms	2207.961291
Area Population	15.202785

LINEAR REGRESSION¶