The aim of this textbook is to introduce machine learning, and the algorithmic paradigms it offers, in a principled way. The book provides a theoretical account of the fundamentals underlying machine learning and the mathematical derivations that transform these principles into practical algorithms. 

Python Basics: cheat sheet!🤓

Self Paced Videos and Slides

Module 1 - Introduction to Data Science
https://t.me/Machine_Learning_Deep_Learning/436

Module 2 - Introduction to Python
https://t.me/Machine_Learning_Deep_Learning/458

Module 3 - Pandas
Module 4 - Merging Data Frames with Pandas

Module 5 - Introduction to Data Visualisation Using Matplotlib
https://t.me/c/1454674396/8
Part- 1,2,3,4

Module 6 - Data Visualization with Seaborn
https://t.me/c/1454674396/61
Part - 1,2

Module 7 - Descriptive Statistics with Python
https://t.me/c/1454674396/106

Module 8 - Inferential Statistics with Python
https://t.me/c/1454674396/129

Module 9 - Feature Engineering
https://t.me/c/1454674396/155
Part- 1,2,3,4

Module 9.5 - Exploratory Data Analysis

Module 10 - Machine Learning for Everyone
https://t.me/Machine_Learning_Deep_Learning/225

Module 11 - Supervised Learning with scikit-learn
https://t.me/Machine_Learning_Deep_Learning/241
Part - 1,2,3,4

Module 12 - Machine Learning with Tree-Based Models in Python
https://t.me/Machine_Learning_Deep_Learning/347

Module 12.5 - Extreme Gradient Boosting with XGBoost
(No videos. Only ecercise)

Module 13 - Dimensionality Reduction and Unsupervised Learning
https://t.me/Machine_Learning_Deep_Learning/361

Module 14 - Machine Learning for Time Series Data
(No videos. Only exercise)

How to avoid machine learning pitfalls

Algorithms

GitHub basic commands

Three Levels of ML Software
https://ml-ops.org/content/three-levels-of-ml-software

Gist of the above article:

Building successful ML-based software projects is still difficult because every ML-based software needs to manage three main assets: Data, Model, and Code
—————————————
Machine Learning Operations(= MLOps) --> processes around designing, building, and deploying ML models into production.

Mainly 3 Steps:
1.Data —> Data Engineering Pipelines
2.Model —> Machine Learning Pipelines
3.Code —> Deployment Pipelines
———————————-
1.Data: Data Engineering Pipelines

1A: Data Ingestion
-Collecting data by using various systems

1B:Exploration and Validation
-Understanding the data
-obtain information about the content and structure of the data.

1C:Data Wrangling (Cleaning)

1D:Data Splitting
-Splitting the data into training (80 %), validation, and test datasets
————————————
2.Model: Machine Learning Pipelines

2A: Model Training
2B: Model Evaluation
2C: Model Testing
2D: Model Packaging
———————————-
3.Code: Deployment Pipelines

3A:Model Serving -
Deploying the ML model in a production environment.

3B: Model Performance Monitoring - The process of observing the ML model performance based on live and previously unseen data, such as prediction or recommendation.

3C:Model Performance Logging - Every inference request results in a log-record.

At Last:
Deploying ML Models as Docker Containers

(Please read main article, I have not covered all things.It is very extensive. You will find this article useful when you will start hand-on-experience)

Internship Alert:

If you have basic knowledge of computer vision, I'm looking for interns at Doctor on Click Pvt Ltd.
(Image manipulation/ Images masking/ Image segmentation/ Image classifications. Anything)

Check out this job at Doctor On Click: https://www.linkedin.com/jobs/view/2721296401

Machine learning Crash course By Google
https://developers.google.com/machine-learning/crash-course

👆It is free. Open for all.

One of the most requested Book for Machine learning. Save for the future reference and doubt solving.

You don't need to master all to START.

Also includes list of Verbs and samples