-
Notifications
You must be signed in to change notification settings - Fork 0
/
case_study2.py
47 lines (37 loc) · 1.06 KB
/
case_study2.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
import numpy as np
from sklearn import linear_model
from sklearn.metrics import mean_squared_error, r2_score
import random
def main():
array = np.loadtxt('case_study2_data/data.txt') #loading data
list1 = array.tolist()
x_train = []
y_train = []
x_test = []
y_test = []
#splitting into training and testing datasets
for row in list1:
label = row.pop()
if random.random() <= 0.5:
x_train.append(row)
y_train.append(label)
else:
x_test.append(row)
y_test.append(label)
x_train = np.array(x_train)
y_train = np.array(y_train)
x_test = np.array(x_test)
y_test = np.array(y_test)
#creating model
regr = linear_model.LinearRegression(normalize=True)
regr.fit(x_train, y_train)
pred = regr.predict(x_test)
# coefficients
print('Coefficients: \n', regr.coef_)
#error
print('Mean squared error: %.2f'
% mean_squared_error(y_test, pred))
# The coefficient of determination: 1 is perfect prediction
print('Coefficient of determination: %.2f'
% r2_score(y_test, pred))
main()