01-linear-regression.py

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

raw_data = pd.read_csv('Housing_Data.csv')
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)
print(model.coef_)
print(model.intercept_)

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

predictions = model.predict(x_test)

# plt.scatter(y_test, predictions)
plt.hist(y_test - predictions)

from sklearn import metrics

metrics.mean_absolute_error(y_test, predictions)

metrics.mean_squared_error(y_test, predictions)

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