Linear Regression and Regularisation

What you'll be able to do

• What is linear regression and where can it be used?
• Build regression model from scratch
• Perform the pre model build analysis
• Check if the model is overfitted and learn to check the assumptions of linear regression and rectify
• Find the influential points in the data
• Learn the advanced regression algorithms
• Evaluate the model using various evaluation metrics
• Implement linear regression in a project and solve it end to end

1. 01SECTION 1: Introduction to Linear Regression7 lessons · 31 min

   1. What is Linear RegressionPreview5:23
   2. How to Get Queries Resolved1:00
   3. Download Resources1:00
   4. Regression Equation and TerminologiesPreview9:30
   5. Time Series RegressionPreview4:55
   6. Formula for CoefficientsPreview4:22
   7. Coefficients Computation from Scratch4:38
2. 02SECTION 2: Regression Algorithm from scratch: Gradient Descent5 lessons · 43 min

   1. What is Gradient Descent8:46
   2. Math behind Gradient Descent6:24
   3. Stochastic and Minibatch7:40
   4. Gradient Descent from Scratch - Coding19:06
   5. Course Review1:00
3. 03SECTION 3: Model Building and Concepts Part- 19 lessons · 58 min

   1. Problem Description and Data4:53
   2. Describe the Data2:33
   3. EDA Part 1 Understanding Sales6:55
   4. EDA Part 2 Graphical Analysis3:30
   5. Missing Values and Outlier3:33
   6. Outliers and mahalanobis distance11:16
   7. Building and Interpreting Linear Regression12:08
   8. R-Squared Intuition5:04
   9. Adjusted R Squared and F Statistic8:07
4. 04SECTION 4: Model Building and Concepts Part- 210 lessons · 58 min

   1. Assumptions of OLS - Part 14:17
   2. Assumptions of OLS - Part 28:53
   3. Assumptions of OLS - Part 32:45
   4. VIF4:29
   5. Durbin Watson statistic and Condition Number9:14
   6. Multicollinearity5:46
   7. How to check and rectify Heteroscedasticity6:26
   8. BoxCox Transform6:06
   9. The Other Way2:25
   10. Model Improvement Tactic Demo- Cooks D7:30
5. 05SECTION 5: Model Selection Approaches8 lessons · 1 h 24 min

   1. Evaluating Regression Models12:10
   2. Cross Validation Approaches5:50
   3. Need for Holdout Sample7:24
   4. Tactic 1 - LR Model Building7:21
   5. Tactic 2 - Backward Building Workout22:45
   6. Stepwise and Best Subsets12:13
   7. RFE and Caveats9:06
   8. RFE Demo7:09
6. 06SECTION 6: Regularization Modelling Approaches7 lessons · 1 h 16 min

   1. Bias Variance Tradeoff7:16
   2. Ridge Regression16:18
   3. Grid Search2:29
   4. LASSO Regression5:47
   5. ElasticNet5:18
   6. Ridge Regularization Code Demo23:25
   7. Why weights of L1 regularization reach zero but not L215:03
7. 07SECTION 7: Outlier Resistant and Advanced Regression8 lessons · 1 h 23 min

   1. RANSAC for Outliers Resistant Models8:42
   2. Theil-Sen Regression10:09
   3. Time Series Regression21:19
   4. Retraining Models6:59
   5. How to Identify if Data Drift occurred8:25
   6. Quantile Regression20:36
   7. Robust Regression with Huber Loss5:22
   8. Advanced Regression Code1:00
8. 08SECTION 8: Maximum Estimation for Linear Regression2 lessons · 22 min

   1. Linear Regression with Maximum Likelihood Estimation20:49
   2. Assignment1:00

What you need

• Basic Maths and Logical Reasoning
• Basic Python, Pandas
• Intent to become good at Data Science
• Learning Mindset

Who this course is for

• Future Data Scientists
• ML Engineers
• People Managers, Product Managers
• Program Managers, Scrum Masters
• Software engineers working with ML/Data Science Project / Team and want to know how ML works.
• Students and researchers using ML for their projects

Your instructor

Prabhakaran S

Principal Data Scientist

My name is Selva, and I am super excited to mentor you on this course!

I head the Data Science team for a global Fortune 500 company and over the last 10 years of my data science experience I've deployed 20+ global products. I'm also the Founder and Chief Author of Machine Learning Plus, which has over 4M annual readers.

I specialize in covering the in-depth intuition and maths of any concept or algorithm. And based on my existing student requests, I've put up the series of courses and projects with detailed explanations, just like on-the-job experience. Hope you love it!

from 3,965 ratings

4.92

learners

57K+

courses

85