#Importing libraries
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error, r2_score
from sklearn.model_selection import train_test_split

#Getting the dataset
housing_data = pd.read_csv('/content/drive/MyDrive/11th Grade/Advanced Topics Comp. Sci./Machine Learning/Data/BostonHousing.csv')

housing_data.head()

	crim	zn	indus	chas	nox	rm	age	dis	rad	tax	ptratio	b	lstat	medv
0	0.00632	18.0	2.31	0	0.538	6.575	65.2	4.0900	1	296	15.3	396.90	4.98	24.0
1	0.02731	0.0	7.07	0	0.469	6.421	78.9	4.9671	2	242	17.8	396.90	9.14	21.6
2	0.02729	0.0	7.07	0	0.469	7.185	61.1	4.9671	2	242	17.8	392.83	4.03	34.7
3	0.03237	0.0	2.18	0	0.458	6.998	45.8	6.0622	3	222	18.7	394.63	2.94	33.4
4	0.06905	0.0	2.18	0	0.458	7.147	54.2	6.0622	3	222	18.7	396.90	5.33	36.2

#Data preprocessing
# Check for missing values
print("Missing values in each column:")
print(housing_data.isnull().sum())
print()

Missing values in each column:
crim       0
zn         0
indus      0
chas       0
nox        0
rm         0
age        0
dis        0
rad        0
tax        0
ptratio    0
b          0
lstat      0
medv       0
dtype: int64

#Assign feature and label vectors
X = housing_data.drop("medv", axis = "columns")
y = housing_data['medv']

#Split data
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)

#Create and fit the model
model = LinearRegression()
model.fit(X_train, y_train)

LinearRegression()

In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.

#Create predictions
y_pred = model.predict(X_test)

#Model evaluations
print('Coefficients', model.coef_)
print(X_train.columns)
print('Intercept', model.intercept_)
print('MSE: %.2f' % mean_squared_error(y_test, y_pred))
print('R^2: %.2f' % r2_score(y_test, y_pred))

Coefficients [-1.06372562e-01  4.60727522e-02  2.77431050e-02  4.42728626e+00
 -1.39081525e+01  3.72044846e+00 -2.50053593e-03 -1.24722721e+00
  2.92025350e-01 -1.23478432e-02 -8.80824406e-01  6.53167503e-03
 -5.45683176e-01]
Index(['crim', 'zn', 'indus', 'chas', 'nox', 'rm', 'age', 'dis', 'rad', 'tax',
       'ptratio', 'b', 'lstat'],
      dtype='object')
Intercept 33.97648697262077
MSE: 27.70
R^2: 0.70

#Create a scatter plot of the predicted values vs. actual values
plt.scatter(y_test, y_pred, alpha = 0.8, marker = "^", color = "red")
plt.xlabel("Actual values")
plt.ylabel("Predicted values")
plt.title("Actual vs Predicited Values")
plt.show()