ML BOOTCAMP

Un-Supervised Learning

2020-10-20T15:31:50+00:00

www.bharathkreddy.com

MATERIAL FOR UN-SUPERVISED LEARNING

SLIDE DECK UNSUPERVISED LEARNING

VIDEOS

1.

INTRODUCTION TO UN-SUPERVISED LEARNING

2.

INTUTION FOR VARIOUS CLUSTERING METHODS

3.

HANDS-ON: K-MEANS CLUSTERING

4.

HANDS-ON: HEIRARCHICAL CLUSTERING

A lot of effort and time goes into making this material and videos. One of the ways you can help and support me is by sharing your thoughts on twitter, subscibing my channel on youtube, liking the videos.

www.bharathkreddy.com

Week 11 : 31th October 2020

2020-10-15T18:20:50+00:00

www.bharathkreddy.com

Material for Week 11 of ML boot camp.

Prerequisites - you should be familiar and should at least be able to understand below, if not please refer to previous vidoes and course material.

You should be clear on CART and Decision trees.

YOUR CHECKLIST FOR SESSION ON 31th OCT @ 13:30 PM IST

Day1: Watch all the Videos below.
Day2: Recreate the notebook I discussed in videos. You can find Iris notebook here. Work out Titanic, Pima Indian, Car, Iris, Glass and credit card datasets on all the algorithms you have learnt. Compare the accuracy scores.
Day3: PROJECT 1: This would be your first project. Apply everything you have learnt so far. Find details about your project here, the dataset here.
Day4: Work on your PROJECT.
Day5: SUBMIT PROJECT.

SLIDE DECK ENSEMBLE METHODS

VIDEOS

1.

INTUTION FOR ENSEMBLE METHODS

2.

INTUTION FOR RANDOM FORESTS

3.

INTUITION FOR BAGGING TECHINIQUES

4.

INTUITION FOR BOOSTING TECHNIQUES

5.

HANDS ON EXCERCISE

www.bharathkreddy.com

Week 10 : 24th October 2020

2020-10-12T18:20:50+00:00

www.bharathkreddy.com

Material for Week 10 of ML boot camp.

Prerequisites - you should be familiar and should at least be able to understand below, if not please refer to previous vidoes and course material.

Data wrangling with numpy and pandas, Data viz with matplotlib and seaborn.

Able to handle missing values, categorical data, create pipelines.

Understand Linear regression, Logistic regression, KNN, Naive Bayes. Deploy these algorithms and measure their performance.

YOUR CHECKLIST FOR SESSION ON 24th OCT @ 13:30 PM IST

Day1: Watch all the Videos below.
Day2: Recreate the notebook I discussed in videos. You can find Iris notebook here and Glass notebook here. Work out Titanic, Pima Indian, Car , Iris and credit card datasets on all the algorithms you have learnt. Compare the accuracy scores.
Day3: Do an end to end project - Read data, clean data, use pipelines, measure accuracy for all the algorithms you have learnt so far.
Day4: Read material on Decision trees from internet.
Day5: PRACTICE NOTEBOOKS

SLIDE DECK CART

VIDEOS

1.

INTUTION FOR CART AND DECISION TREES

2.

INTUTION ON GINI IMPURITY

3.

WHY DECISION TREES OVERFIT AND HOW TO FIX IT

4.

HANDS ON EXAMPLE ON JUPYTER NOTEBOOK

www.bharathkreddy.com

Week9 17th October 2020

2020-09-28T18:20:50+00:00

www.bharathkreddy.com

Material for Week 9 of ML boot camp.

Prerequisites - you should be familiar and should at least be able to understand below, if not please refer to previous vidoes and course material.

Data wrangling with numpy and pandas, Data viz with matplotlib and seaborn.

Able to handle missing values, categorical data, create pipelines.

Understand Linear regression, Logistic regression, KNN, Naive Bayes. Deploy these algorithms and measure their performance.

YOUR CHECKLIST FOR SESSION ON 17th OCT @ 13:30 PM IST

Day1: Go through the Video on Support Vector Machines. Understand the concepts explained in the slide deck for Support Vector Machine.
Day2: Replicate this Notebook, If you are note able to - see the video on SVM hands-on.
Day3: Take a dataset with missing values and categrical data in it. Ensure it is a classification problem. Apply all the skills you have learnt so far on that dataset. Try clearning the dataset, encoding the labels, use pipelines, then fit these models - Logistic Regression, KNN, Naive Bayes and SVM.
Day4: Practice on a few more datasets end to end. You can pick these datasets from previous practice notebooks I have shared.
Day5: Read about Gamma and C - hyperparameters for SVM algorithm.

SLIDE DECK SUPPORT VECTOR MACHINES.

VIDEOS

SUPPORT VECTOR MACHINES INTUITION.

SUPPORT VECTOR MACHINES HANDS-ON.

www.bharathkreddy.com

Week8 09th October 2020

2020-09-28T15:31:50+00:00

www.bharathkreddy.com

Material for Week 8 of ML boot camp.

Prerequisites - you should be familiar and should at least be able to understand below, if not please refer to previous vidoes and course material.

Python programming

Numpy & Pandas

Visualization using Matplotlib & Seaborn

Able to work with missing data and categorical data using sklearn pipelines or transformers.

Be clear with Theory of Linear Regression and Logistic Regression

YOUR CHECKLIST FOR SESSION ON 10th OCT @ 13:30 PM IST

Items ticked are highly recomended to be completed before session, unticked ones are for the more adventerous of you :)

Day1: Go through the KNN slide deck and practice this notebook.
Day2: Recreate this notebook and this notebook
Day3: Go through the Naive Bayes slide deck, I have explained conditional probability here and practice this notebook and this notebook. Go through the deck on probability if you are not comfortable with probability theory. Watch the vidoes in this order : First Probability theory and then Naive bayes video.
Day4: Run Logisitic Regression, KNN and Naive Bayes algorithms on Titanic and Pima India diabetes dataset. Compare the accuracy reports, Let’s have a discussion next week on your observations.
Day5: I have saved over hundred datasets here, try picking a few datasets and see if you can try everything that you have learnt so far on these - missing values , categorical values and then model.

Check out the KNN app i have deployed here

SLIDE DECK PROBABILITY THEORY

SLIDE DECK NAIVE BAYES

SLIDE DECK KNN CLASSIFIER

VIDEOS

PROBABILITY THEORY

NAIVE BAYES

KNN CLASSIFIER

CLASS ROOM RECORDING

Hoping to see you soon in the session.

www.bharathkreddy.com

Week7 03rd October 2020

2020-09-27T14:01:56+00:00

www.bharathkreddy.com

Material for Week 7 of ML boot camp.

Prerequisites - you should be familiar and should at least be able to understand below

Numpy

Pandas

Matplotlib

Able to use sklearn to split the dataset in test and train datasets

Able to use sklearn to pre-preocess the data and use sklearn pipelines

Be clear with Theory of Linear Regression and be able to Use Linear Regression

YOUR CHECKLIST FOR SESSION ON 03rd OCT @ 13:30 PM IST

Items ticked are highly recomended to be completed before session, unticked ones are for the more adventerous of you :)

Day1: Understand working with missing data AND Practice working on missing data
Day2: Working with categorical data and Three practice datasets
Day3: Use Pipelines to manage Missing values & categorical encoding at one go using SKLEARN PIPELINES, I am not adding any separate practice datasets as you can practice these concepts on same notebooks which i have provided for Linear Regression and Logistic Regression.
Day4: Linear Regression: First go through this notebook. Then go through 2 notebooks I provided in week5. You can use Ames housing & Boston housing datasets to predict Prices.These datasets are from Missing value day1 link. You can use Automobile import dataset from day2 link to predict Prices of automobiles.
Day5: Logistic Regression revise week6, Practice you skills on Titanic dataset to predict survival, Pima-Indian dataset to predict diabites.

SLIDE DECK

VIDEOS

Logistic Regression THEORY

Linear Regression Part 2

Linear Regression Part 1

Hoping to see you soon in the session.

www.bharathkreddy.com

Week6 26th September 2020

2020-09-20T14:01:56+00:00

www.bharathkreddy.com

Material for Week 6 of ML boot camp.

Prerequisites - you should be familiar and should at least be able to understand below

Numpy

Pandas

Matplotlib

Able to use sklearn to split the dataset in test and train datasets

Able to use sklearn to pre-preocess the data and use sklearn pipelines

YOUR CHECKLIST FOR SESSION ON 26th SEPT @ 13:30 PM IST

Items ticked are highly recomended to be completed before session, unticked ones are for the more adventerous of you :)

Day1: Read the theory on Logistic regression from my Github Repositary, see the readme file in repo.
Day2: Practice - Using sklearn pre-processing pipelines until you are comfortable using them. You would see i have used them again in the notebook in my github repo.
Day3: Try recreate the steps in the notebook in my github repo on titanic dataset
Day4: Revise Logistic regression week 4 & week 5 Material.
Day5: If you are done with all above - check the week 7 material metioned in my github repo

SLIDE DECK)

VIDEOS

Linear Regression Part 2

Linear Regression Part 1

Hoping to see you soon in the session.

www.bharathkreddy.com

Week5 19th September 2020

2020-09-13T14:01:56+00:00

www.bharathkreddy.com

Material for Week 5 of ML boot camp.

Prerequisites - you should be familiar and should at least be able to understand below

Numpy

Pandas

Matplotlib

I am going to follow this book

Hands-on Machine Learning with Scikit-Learn, Keras and TensorFlow

which you can download from here

YOUR CHECKLIST FOR SESSION ON 19th SEPT @ 13:30 PM IST

Items ticked are highly recomended to be completed before session, unticked ones are for the more adventerous of you :)

Day1: Download this notebook and csv file. Try to recreate this notebook. It is very very important you follow all the steps in the notebook
Day2: Go through the notebook again - google all the things that you are not comfortable with.
Day3: Test your knowledge by completing this notebook, you can find the requried data for this notebook here.. Give this an honest attempt and compare your resutls with solutions here
Day4: Go through the slide deck below and relate to your understanding of Machine Learning and practice the same file as given under Day1
Day5: You should know every line of code in Day1 notebook. Any doubts please email/text me any time, but it is important you understand all these things.

SLIDE DECK

VIDEOS

Linear Regression Part 1

Hoping to see you soon in the session.

www.bharathkreddy.com

Week4 12th September 2020

2020-09-04T15:27:56+00:00

www.bharathkreddy.com

You will find here all the material for Week 4 of our ML boot camp.

You now should be comfortable with numpy and more iportantly pandas.

YOUR CHECKLIST FOR SESSION ON 12th SEPT @ 13:30 PM IST

Items ticked are highly recomended to be completed before session, this is how i recomend you plan your week.

Some Good resources to learn:

PANDAS by Hernan rojas

PANDAS by kaggle - highly recomended

DATA VISUALIZTION Kaggle

DATA CLEANING Kaggle

SLIDE DECK

VIDEOS

Introduction to Jupter Notebook

Numpy & Pandas

Matplotlib & Seaborn

Hoping to see you soon in the session.

Week3 05th September 2020

2020-09-04T13:27:56+00:00

www.bharathkreddy.com

You will find here all the material for Week 3 of our ML boot camp.

You now should be comfortable using Jupyter notebooks and have understanding of basic datatypes in python.

YOUR CHECKLIST FOR SESSION ON 5th SEPT @ 13:30 PM IST

Items ticked are highly recomended to be completed before session, unticked ones are for the more adventerous of you :)

Installed Anaconda.
You are able to lauch Jupyter notebooks.
You are able to open files saved in Last weeks material on your jupyter notebooks and pacticed
Download all the e-books i have provided.
Read first 10 chapters from the ebook
Download NUMPY NOTEBOOK and go through it fully.
Download PANDAS NOTEBOOK and go throug it fully.
Try to recreate this notebook

Instructions to download jupyter notebooks I have provided above

Click on link - it should open up the page
Click on "RAW" and you should see some garbled messy code
Right-click and save as >> NOTE >> DO NOT FORGET to change the file type to All files else the file would save as .txt file.

complete working on this csv file , and this csv file for the second csv file, you will have to match the file name to the code in pandas jupter notebook. You would use this csv when you work on pandas notebook i have added above.

ML BOOTCAMP

Un-Supervised Learning

MATERIAL FOR UN-SUPERVISED LEARNING

SLIDE DECK UNSUPERVISED LEARNING

VIDEOS

1.

INTRODUCTION TO UN-SUPERVISED LEARNING

2.

INTUTION FOR VARIOUS CLUSTERING METHODS

3.

HANDS-ON: K-MEANS CLUSTERING

4.

HANDS-ON: HEIRARCHICAL CLUSTERING

Week 11 : 31th October 2020

Material for Week 11 of ML boot camp.

YOUR CHECKLIST FOR SESSION ON 31th OCT @ 13:30 PM IST

SLIDE DECK ENSEMBLE METHODS

VIDEOS

1.

INTUTION FOR ENSEMBLE METHODS

2.

INTUTION FOR RANDOM FORESTS

3.

INTUITION FOR BAGGING TECHINIQUES

4.

INTUITION FOR BOOSTING TECHNIQUES

5.

HANDS ON EXCERCISE

Week 10 : 24th October 2020

Material for Week 10 of ML boot camp.

YOUR CHECKLIST FOR SESSION ON 24th OCT @ 13:30 PM IST

SLIDE DECK CART

VIDEOS

1.

INTUTION FOR CART AND DECISION TREES

2.

INTUTION ON GINI IMPURITY

3.

WHY DECISION TREES OVERFIT AND HOW TO FIX IT

4.

HANDS ON EXAMPLE ON JUPYTER NOTEBOOK

Week9 17th October 2020

Material for Week 9 of ML boot camp.

YOUR CHECKLIST FOR SESSION ON 17th OCT @ 13:30 PM IST

SLIDE DECK SUPPORT VECTOR MACHINES.

VIDEOS

SUPPORT VECTOR MACHINES INTUITION.

SUPPORT VECTOR MACHINES HANDS-ON.

Week8 09th October 2020

Material for Week 8 of ML boot camp.

YOUR CHECKLIST FOR SESSION ON 10th OCT @ 13:30 PM IST

SLIDE DECK PROBABILITY THEORY

SLIDE DECK NAIVE BAYES

SLIDE DECK KNN CLASSIFIER

VIDEOS

PROBABILITY THEORY

NAIVE BAYES

KNN CLASSIFIER

CLASS ROOM RECORDING

Hoping to see you soon in the session.

Week7 03rd October 2020

Material for Week 7 of ML boot camp.

YOUR CHECKLIST FOR SESSION ON 03rd OCT @ 13:30 PM IST

SUGGESTED READING

SLIDE DECK

VIDEOS

Logistic Regression THEORY

Linear Regression Part 2

Linear Regression Part 1

Hoping to see you soon in the session.

Week6 26th September 2020

Material for Week 6 of ML boot camp.

YOUR CHECKLIST FOR SESSION ON 26th SEPT @ 13:30 PM IST

SLIDE DECK)

VIDEOS

Linear Regression Part 2

Linear Regression Part 1

Hoping to see you soon in the session.

Week5 19th September 2020

Material for Week 5 of ML boot camp.