Machine Learning Resources for Python [Basic]
There are lots of github repositories and blogs that have more exhaustive resources than what I’ve put down here that covers a whole lot. But these would be good to start off, I’ll put together an intermediate list in the next post.
Understanding Anaconda distribution & using it for Machine Learning(ML)
As someone starting off with ML & using Python to do it, you will have to understand that ML or Data Science is more of sharing, collaboration and involves you having to share all your findings/research/outcomes to the stake-holders or engineering folks that would use it. Anaconda distribution is one such means through which you will keep yourself sane as well as keep others sane.
Right from the start, try using Jupyter notebooks rather than an IDE, this will help you to explore more and document your findings/issues/quirks without leaving the notebook.
- Installation
- NOTE: If you have Windows, just download the conda installer for Windows and install .exe file
- NOTE: If you have Ubuntu/Mac, use
wget <url link>
- Miniconda installation -alternate space saver for Anaconda, I’ll suggest this
- Miniconda .exe files
- Understanding to use Jupyter notebooks
- Conda myths and misconceptions - Must read
Basics of Python:
- JM Portilla course notebooks
- Python Programming - MUST READ
- Python Programming - sentdex videos MUST WATCH
Extra Resources:
- Learning how to write Markdown Documents - Essential
- Awesome Python - github
- Code Handbook for Python
Statistics & Machine Learning basics
- Brandon Foltz’s Stats videos - MUST WATCH
- What is Machine Learning
- Analytics Vidhya ML path using Python
- NOTE: Please do not attempt Kaggle competitions now, it would hinder your progress. Go through the basics first and then attempt Kaggle competitions.
- Coursera Andrew NG videos - Watch these after you are done with all the courses
Python for Data Science
You have to learn about a few libraries that are core pillars of Python:
NOTE: Click here for an umbrella source for Data Science using Python
- Numpy
- Pandas
- Matplotlib
- Seaborn
- Scikit-Learn
- NOTE: You’ll be able to appreciate Scikit learn after you know the theory of Machine Learning (ML)
- Scikit learn basics by Data Camp
- ML Mastery by Jason Bronwlee - Basics SKLearn
A few blogs that regularly you will need to refer regularly
- Analytics Vidhya - They have decent ML/Data Science related articles for theory and handson
- DataCamp
- Dataquest
- yHat blog
- Chris Albon - Whenever you get stuck,don’t know a syntax
Generic Reading
Regular Reading
- You’ll need to make sure you read at least one article related to ML/DL/Data Science EVERYDAY. You understand it or not is a different thing, but it would help you to think about why/what/how. If you understand, it would add more to your understanding, if not then you can read more about it. Few reading feeds you can follow are:
Books that would help
Do let me know if this a good list for a beginner or would have to add/remove anything. Enjoy & learn!