The most common question I get asked about Machine Learning on Twitter is :

" Which machine learning frameworks do I need to learn at the start? "

Let's find out

It can be overwhelming seeing all the machine learning frameworks at once and not even knowing what they do.

I made this thread so that your machine learning journey becomes just a little bit easier.

(2 / 11)

This thread will only focus on Python frameworks.

Why?
Because Python is the most common path into machine learning.

( If you have experience with any other language then learning Python will not be difficult at all. )

(3 / 11)

Here's the entire list:

- Pandas
- Numpy
- Matplotlib
- TensorFlow
- PyTorch
- Keras
- Scikit Learn

Let's see what they do.

(4 / 11)

You'll have to interact with csv files or databases on a regular basis to access data in machine learning, pandas helps you do just that.

The cool thing about Pandas is that it actually doesn't change the original data...

(5 / 11)

.. and instead creates a copy of the csv or database as a python array in the RAM.

We use Numpy in order to change the shape of the data we just pulled using Pandas, the arrays are converted to special numpy arrays which are much faster than Python's default ones.

(6 / 11)

Matplotlib is used to visualize data, bar graphs, line plots, pie charts... you get the point.

These are the frameworks that you will have to use extensively throughout your machine learning journey.

(7 / 11)

Now comes the tougher part, TensorFlow, Pytorch, Keras or Scikit learn? Or all? or neither?....

It depends on personal preference.

(8 / 11)

TensorFlow, Keras and Pytorch generally do the same thing in different syntax.

SciKit learn has a bunch of scientific tools which you might need here and there.

(9 / 11)

Here's what I suggest, try making a convolutionary neural network for the MNIST dataset with all of these and then decide which one is right for you.

I personally use TensorFlow + ScikitLearn, it might not work for you.

(10 / 11)

That's it! It really wasn't that complex and now you know which frameworks you need to get started with machine learning.

Cheers!

(11 / 11)