Scribd
Upload
20 views2 pages

BITS - AIML-Cohort 10 - Regression - Assignment 1

This document provides an assignment on linear regression and its variants for a machine learning course. It contains 5 questions involving implementing linear regression, ridge regression, lasso regression and polynomial regression on provided and custom datasets. Students need to code the implementations, record observations, and submit a Jupyter notebook with code, images of working and a short explanatory video.

Uploaded by

kirtikarandikar1
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
20 views2 pages

BITS - AIML-Cohort 10 - Regression - Assignment 1

This document provides an assignment on linear regression and its variants for a machine learning course. It contains 5 questions involving implementing linear regression, ridge regression, lasso regression and polynomial regression on provided and custom datasets. Students need to code the implementations, record observations, and submit a Jupyter notebook with code, images of working and a short explanatory video.

Uploaded by

kirtikarandikar1
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

Birla Institute of Technology & Science, Pilani

Regression - Assignment 1
Course No. : AIML_Oct_2023_C1_PCAMZC211
Course Title : PG Program in AI & Machine Learning
Total Marks: 36
==================================

1) Two different mathematical formulations were discussed in class for closed form
solution of Linear regression. Python code implementation was shown in contact
hour session for method (b) below. Do a similar implementation for method (a)

Test the implementation for the below data points and highlight your
observations.

X = np.array([[1, 2], [3, 4], [5, 6]])


y = np.array([1, 3, 5])

[2+2 Marks = 4 Marks]

2) Implement closed form solution for Ridge regression.


X = np.array([[1, 2], [3, 4], [5, 6]])
Y = np.array([1, 3, 5])

What are values of betas (coefficients) observed with ridge regression.

[4 Marks]

3) Another alternative that is smoother than both MSE and MAE. It's defined as the
logarithm of the hyperbolic cosine of the prediction error.

Prove that the function is a convex function. [2 Marks]


4) Download the data set and do following. [16 Marks]
DATASET LINK
https://drive.google.com/file/d/1wpayvaCAAGeCKMMGLpsAKE9f7q7xrjKD/
view?usp=sharing

a. Split the data in train and test with test size = 20%
[0.25 Marks]

b. Perform a simple linear regression using Scikit-Learn library and compute.


i. MSE
ii. Estimated Model coefficients.
[3+0.5+0.5 Marks]

c. Perform Ridge regression using Scikit-Learn library and compute –


i. MSE
ii. Estimated Model coefficients.
[3+0.5+0.5 Marks]

d. Perform Lasso regression using Scikit-Learn library and compute –


i. MSE
ii. Estimated Model coefficients.
[3+0.5+0.5 Marks]

e. Perform Polynomial regression using Scikit-Learn library for various


degrees in range of 1-5 and compute following.
i. MSE for degree 1
ii. MSE for degree 2
iii. MSE for degree 5
[3+0.25+0.25+0.25 Marks]

5) Record a short video explaining you code and observations [10 Marks]

Required deliverables –
1) Clean code implementation in ipynb file
2) Any observations or mathematical solution can be presented on pen and paper
and a image can be shared in a word / pdf file.
3) A short video is required explaining you code and observations. A flat 10 Marks
will be deducted without the video.

You might also like