SimpleLinearRegression/multipleLinearRegression.py at master · minaee/SimpleLinearRegression · GitHub

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
import numpy as np
import pandas as pd

df = pd.read_csv("FuelConsumption.csv")
cdf = df[
    ['ENGINESIZE', 'CYLINDERS', 'FUELCONSUMPTION_CITY', 'FUELCONSUMPTION_HWY', 'FUELCONSUMPTION_COMB', 'CO2EMISSIONS']]

msk = np.random.rand(len(df)) < 0.8
train = cdf[msk]
test = cdf[~msk]

from sklearn import linear_model

# regr = linear_model.LinearRegression()
# x = np.asanyarray(train[['ENGINESIZE','CYLINDERS','FUELCONSUMPTION_COMB']])
# y = np.asanyarray(train[['CO2EMISSIONS']])
# regr.fit (x, y)
# The coefficients
# print ('Coefficients: ', regr.coef_)

# y_hat= regr.predict(test[['ENGINESIZE','CYLINDERS','FUELCONSUMPTION_COMB']])
# x = np.asanyarray(test[['ENGINESIZE','CYLINDERS','FUELCONSUMPTION_COMB']])
# y = np.asanyarray(test[['CO2EMISSIONS']])
# print("Residual sum of squares: %.2f"
# % np.mean((y_hat - y) ** 2))

# Explained variance score: 1 is perfect prediction
# print('Variance score: %.2f' % regr.score(x, y))


regr = linear_model.LinearRegression()
x = np.asanyarray(train[['ENGINESIZE', 'CYLINDERS', 'FUELCONSUMPTION_CITY', 'FUELCONSUMPTION_HWY']])
y = np.asanyarray(train[['CO2EMISSIONS']])
regr.fit(x, y)
print('Coefficients: ', regr.coef_)

y_hat = regr.predict(test[['ENGINESIZE', 'CYLINDERS', 'FUELCONSUMPTION_CITY', 'FUELCONSUMPTION_HWY']])
x = np.asanyarray(test[['ENGINESIZE', 'CYLINDERS', 'FUELCONSUMPTION_CITY', 'FUELCONSUMPTION_HWY']])
y = np.asanyarray(test[['CO2EMISSIONS']])
print("Residual sum of squares: %.2f"
      % np.mean((y_hat - y) ** 2))
# Explained variance score: 1 is perfect prediction
print('Variance score: %.2f' % regr.score(x, y))