Simple Linear Regression

About this Notebook

In this notebook, we learn how to use scikit-learn to implement simple linear regression. We
download a dataset that is related to fuel consumption and Carbon dioxide emission of cars.
Then, we split our data into training and test sets, create a model using training set, evaluate
your model using test set, and finally use model to predict unknown value.
Table of contents
<ol>
<li><a href="#understanding_data">Understanding the Data</a></li>
<li><a href="#reading_data">Reading the data in</a></li> <li><a
href="#data_exploration">Data Exploration</a></li>
<li><a href="#simple_regression">Simple Regression
Model</a></li> </ol>

0.0.1 Importing Needed packages

[1]: import matplotlib.pyplot as plt

import pandas as pd
import pylab as pl
import numpy as np
%matplotlib inline

0.0.2 Downloading Data

To download the data, we will use !wget to download it from IBM Object Storage.
[4]: !wget -O FuelConsumption.csv https://s3-api.us-geo.objectstorage.softlayer.net/ ,→cf-

courses-data/CognitiveClass/ML0101ENv3/labs/FuelConsumptionCo2.csv

--2019-10-18 15:00:56-- https://s3-api.us-geo.objectstorage.softlayer.net/cf-

courses-data/CognitiveClass/ML0101ENv3/labs/FuelConsumptionCo2.csv Resolving
s3-api.us-geo.objectstorage.softlayer.net (s3-api.us-
geo.objectstorage.softlayer.net)… 67.228.254.193
Connecting to s3-api.us-geo.objectstorage.softlayer.net (s3-
api.us-geo.objectstorage.softlayer.net)|67.228.254.193|:443…
connected. HTTP request sent, awaiting response… 200 OK

1
 Length: 72629 (71K) [text/csv]
Saving to: ‘FuelConsumption.csv’

FuelConsumption.csv 100%[===================>] 70.93K --.-KB/s in 0.06s

2019-10-18 15:00:56 (1.16 MB/s) - ‘FuelConsumption.csv’ saved [72629/72629]

Did you know? When it comes to Machine Learning, you will likely be working with large
datasets. As a business, where can you host your data? IBM is offering a unique opportunity for
businesses, with 10 Tb of IBM Cloud Object Storage: Sign up now for free
Understanding the Data

0.0.3 FuelConsumption.csv:

We have downloaded a fuel consumption dataset, FuelConsumption.csv, which contains

model-specific fuel consumption ratings and estimated carbon dioxide emissions for new light-
duty vehicles for retail sale in Canada. Dataset source
• MODELYEAR e.g. 2014
• MAKE e.g. Acura
• MODEL e.g. ILX
• VEHICLE CLASS e.g. SUV
• ENGINE SIZE e.g. 4.7
• CYLINDERS e.g 6
• TRANSMISSION e.g. A6
• FUEL CONSUMPTION in CITY(L/100 km) e.g. 9.9
• FUEL CONSUMPTION in HWY (L/100 km) e.g. 8.9
• FUEL CONSUMPTION COMB (L/100 km) e.g. 9.2
• CO2 EMISSIONS (g/km) e.g. 182 --> low --> 0
Reading the data in
[5]: df = pd.read_csv("FuelConsumption.csv")

# take a look at the

dataset df.head()

[5]: MODELYEAR MAKE MODEL VEHICLECLASS ENGINESIZE CYLINDERS \

0 2014 ACURA ILX COMPACT 2.0 4
1 2014 ACURA ILX COMPACT 2.4 4
2 2014 ACURA ILX HYBRID COMPACT 1.5 4
3 2014 ACURA MDX 4WD SUV - SMALL 3.5 6
4 2014 ACURA RDX AWD SUV - SMALL 3.5 6

TRANSMISSION FUELTYPE FUELCONSUMPTION_CITY FUELCONSUMPTION_HWY \

0 AS5 Z 9.9 6.7
1 M6 Z 11.2 7.7
2 AV7 Z 6.0 5.8

2
 3 AS6 Z 12.7 9.1
4 AS6 Z 12.1 8.7

FUELCONSUMPTION_COMB FUELCONSUMPTION_COMB_MPG CO2EMISSIONS

0 8.5 33 196
1 9.6 29 221
2 5.9 48 136
3 11.1 25 255
4 10.6 27 244

Data Exploration
Lets first have a descriptive exploration on our data.
[6]: # summarize the data
df.describe()

[6]: MODELYEAR ENGINESIZE CYLINDERS FUELCONSUMPTION_CITY \

count 1067.0 1067.000000 1067.000000 1067.000000
mean 2014.0 3.346298 5.794752 13.296532
std 0.0 1.415895 1.797447 4.101253
min 2014.0 1.000000 3.000000 4.600000
25% 2014.0 2.000000 4.000000 10.250000
50% 2014.0 3.400000 6.000000 12.600000
75% 2014.0 4.300000 8.000000 15.550000
max 2014.0 8.400000 12.000000 30.200000

FUELCONSUMPTION_HWY FUELCONSUMPTION_COMB FUELCONSUMPTION_COMB_MPG \

count 1067.000000 1067.000000 1067.000000
mean 9.474602 11.580881 26.441425
std 2.794510 3.485595 7.468702
min 4.900000 4.700000 11.000000
25% 7.500000 9.000000 21.000000
50% 8.800000 10.900000 26.000000
75% 10.850000 13.350000 31.000000
max 20.500000 25.800000 60.000000

CO2EMISSIONS
count 1067.000000
mean 256.228679
std 63.372304
min 108.000000
25% 207.000000
50% 251.000000
75% 294.000000
max 488.000000

Lets select some features to explore more.

3
[7]: cdf = df[['ENGINESIZE','CYLINDERS','FUELCONSUMPTION_COMB','CO2EMISSIONS']]
cdf.head(9)

[7]: ENGINESIZE CYLINDERS FUELCONSUMPTION_COMB CO2EMISSIONS

0 2.0 4 8.5 196
1 2.4 4 9.6 221
2 1.5 4 5.9 136
3 3.5 6 11.1 255
4 3.5 6 10.6 244
5 3.5 6 10.0 230
6 3.5 6 10.1 232
7 3.7 6 11.1 255
8 3.7 6 11.6 267

we can plot each of these features:

[8]: viz = cdf[['CYLINDERS','ENGINESIZE','CO2EMISSIONS','FUELCONSUMPTION_COMB']]
viz.hist()
plt.show()

Now, lets plot each of these features vs the Emission, to see how linear is their relation:
[9]: plt.scatter(cdf.FUELCONSUMPTION_COMB, cdf.CO2EMISSIONS,
color='blue')
plt.xlabel("FUELCONSUMPTION_COMB")
plt.ylabel("Emission")

4
 plt.show()

[10]: plt.scatter(cdf.ENGINESIZE, cdf.CO2EMISSIONS, color='blue')

plt.xlabel("Engine size")
plt.ylabel("Emission")
plt.show()

5
 0.1 Practice
plot CYLINDER vs the Emission, to see how linear is their relation:

[12]: # write your code here

plt.scatter(cdf.CYLINDERS, cdf.CO2EMISSIONS, color ='blue')
plt.xlabel("Cylinders")
plt.ylabel("Emissions")
plt.show()

6
 Creating train and test dataset Train/Test Split involves splitting the dataset into training and
testing sets respectively, which are mutually exclusive. After which, you train with the training
set and test with the testing set. This will provide a more accurate evaluation on out-of-sample
accuracy because the testing dataset is not part of the dataset that have been used to train the
data. It is more realistic for real world problems.
This means that we know the outcome of each data point in this dataset, making it great to test
with! And since this data has not been used to train the model, the model has no knowledge of
the outcome of these data points. So, in essence, it is truly an out-of-sample testing.
Lets split our dataset into train and test sets, 80% of the entire data for training, and the 20% for
testing. We create a mask to select random rows using np.random.rand() function:
[14]: msk = np.random.rand(len(df)) < 0.8
train = cdf[msk]
test = cdf[~msk]

Simple Regression Model

Linear Regression fits a linear model with coefficients θ = (θ1, ..., θn) to minimize the ’residual
sum of squares’ between the independent x in the dataset, and the dependent y by the linear
approximation.

Train data distribution

7
[15]: plt.scatter(train.ENGINESIZE, train.CO2EMISSIONS, color='blue')
plt.xlabel("Engine size")
plt.ylabel("Emission")
plt.show()

Modeling Using sklearn package to model data.

[16]: from sklearn import linear_model

regr = linear_model.LinearRegression()
train_x = np.asanyarray(train[['ENGINESIZE']])
train_y = np.asanyarray(train[['CO2EMISSIONS']])
regr.fit (train_x, train_y)
# The coefficients
print ('Coefficients: ', regr.coef_)
print ('Intercept: ',regr.intercept_)

Coefficients: [[38.70722175]]
Intercept: [125.83531187]
As mentioned before, Coefficient and Intercept in the simple linear regression, are the parameters
of the fit line. Given that it is a simple linear regression, with only 2 parameters, and knowing that the
parameters are the intercept and slope of the line, sklearn can estimate them directly from our data.
Notice that all of the data must be available to traverse and calculate the parameters.

Plot outputs we can plot the fit line over the data:

8
[17]: plt.scatter(train.ENGINESIZE, train.CO2EMISSIONS, color='blue')
plt.plot(train_x, regr.coef_[0][0]*train_x + regr.intercept_[0], '-r')
plt.xlabel("Engine size")
plt.ylabel("Emission")

[17]: Text(0, 0.5, 'Emission')

Evaluation we compare the actual values and predicted values to calculate the accuracy of a
regression model. Evaluation metrics provide a key role in the development of a model, as it
provides insight to areas that require improvement.
There are different model evaluation metrics, lets use MSE here to calculate the accuracy of our
model based on the test set:
<li> Mean absolute error: It is the mean of the absolute value of the errors. This is the easi
<li> Mean Squared Error (MSE): Mean Squared Error (MSE) is the mean of the squared error. It’s
<li> Root Mean Squared Error (RMSE): This is the square root of the Mean Square Error. </li>
<li> R-squared is not error, but is a popular metric for accuracy of your model. It represents

[18]: from sklearn.metrics import r2_score

test_x = np.asanyarray(test[['ENGINESIZE']])
test_y = np.asanyarray(test[['CO2EMISSIONS']])
test_y_hat = regr.predict(test_x)

9
print("Mean absolute error: %.2f" % np.mean(np.absolute(test_y_hat - test_y)))
print("Residual sum of squares (MSE): %.2f" % np.mean((test_y_hat -
test_y) **␣ ,→2))
print("R2-score: %.2f" % r2_score(test_y_hat , test_y) )

Mean absolute error: 24.08

Residual sum of squares (MSE): 997.79
R2-score: 0.64
https://pdf2doc.com/

10