Share this page!

Enter URL or ID to Unroll

You can paste full URL like: https://x.com/threadreaderapp/status/1644127596119195649
or just the ID like: 1644127596119195649

How to get URL link on X (Twitter) App

  1. On the Twitter thread, click on or icon on the bottom
  2. Click again on or Share Via icon
  3. Click on Copy Link to Tweet
  4. Paste it above and click "Unroll Thread"!
  5. More info at Twitter Help
Tom Mitchell Profile picture
@imtommitchell
Aug 5, 2023 • 7 tweets • 3 min read • Read on X
Scrolly
GitHub offers the best free Data Science education on the internet.

But there are more than 372 million repositories to choose from.

How do you find the best ones?

Bookmark these 5 repositories and start learning fast:
1. Free Programming Books

Books are still an important source of knowledge for any field — and Data Science is no exception.

This GitHub repository contains a huge list of freely available books to learn anything related to programming.

🔗 https://t.co/VnC2HXnKAqgithub.com/EbookFoundatio…
Image
2. Data Science Roadmap

This repo covers everything from fundamentals to statistics and programming, and then on to machine learning, data visualization and beyond!

🔗 https://t.co/G0DTtEMCOzgithub.com/Moataz-Elmesma…
Image
3. Awesome Repo

The Awesome Github repository provides an organized list of machine learning libraries, frameworks and tools in many different languages.

🔗 https://t.co/nARAZNZgJAgithub.com/sindresorhus/a…
Image
4. Public APIs for Data

Finding datasets to practice on can be a challenge.

This repo contains a collective list of free APIs to use for data work

🔗 https://t.co/QSnYHkkAMLgithub.com/public-apis/pu…
Image
5. Project-Based Learning

A list of programming tutorials divided into primary programming languages like R and Python.

🔗 https://t.co/epotI5RLRxgithub.com/practical-tuto…
Image
And there you have it!

5 elite Github repos to get you started on your Data Science journey.

If you found this thread helpful, consider following me: @tommitchelldata

I post data-related content every day.

• • •

Missing some Tweet in this thread? You can try to force a refresh
　

Keep Current with Tom Mitchell

Tom Mitchell Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @imtommitchell

Tom Mitchell Profile picture
Apr 30
A Data Analyst who understands segmentation will never be short of work.

Problem is, it's not covered often in courses.

Here's everything I know about customer segmentation condensed:
Customer segmentation helps businesses understand their customers better.

It allows them to tailor marketing strategies, product offerings, and customer experiences to meet the specific needs of each segment.

A segment is a group of customers that share characteristics.

You can segment based on factors like age, gender, location, income, and interests.

Here are some examples of different types of segmentation:
Demographic Segmentation divides customers based on characteristics like age, gender, education, and income.

Behavioural Segmentation categorises customers based on their interactions with your products or services.

Are they loyal, occasional buyers, or inactive customers?

Psychographic Segmentation looks at customer attitudes, values, and lifestyles.
Read 7 tweets
Tom Mitchell Profile picture
Mar 31
Learn SQL in 10 steps (the simple way):
1. The basics are your best mates.

From SELECT to WHERE, get familiar with them.

They’ll make the advanced stuff much easier to grasp.

Don't go too deep into windows functions etc yet. Plenty of time for that later.
2. Coding is an art.

It takes time and consistency to create masterpieces.

Don't rush it.

Look at how other professionals structure their code.

Readability, maintainability, efficiency is the aim of the game.
Read 12 tweets
Tom Mitchell Profile picture
Mar 26
To do Data Analysis using Python you must master Pandas.

But this library contains a lot.

Here is what you need to focus on from day 1 👇
Pandas is an open-source Python library built on top of a Python core packages called NumPy (Numerical Python).

Pandas offers Data Analysts an easy way to work with data and provides many tools for extracting maximum value.

Let's get into it...
There are two main concepts in Pandas:

A series and a dataframe.

A Series is a Pandas array that can hold any type of data.

It is a one-dimensional array or a single column of a matrix.

A series is a set of data values that are associated with a specific label, with specific index values attached to each row.
Read 12 tweets
Tom Mitchell Profile picture
Jan 30
Nobody showed me how to create a data analysis portfolio.

I was lucky to land my first job.

If I were to start again, I'd create one using this 5-step plan: 👇
Step 1: Pick a subject that you are passionate about and enjoy.

You must have a genuine interest in the topic you are researching.

This will allow your mind to wander and be inquisitive, a key element in data analysis.
Step 2: Find some data and come up with questions to answer.

There are many amazing resources for finding data on the internet.

Two of my favourites are:

- Kaggle
- Google Datasets

Start to explore the data and come up with some questions.

If you struggle, ask ChatGPT.
Read 8 tweets
Tom Mitchell Profile picture
Jan 19
Pivot tables explained in simple terms:
Pivot tables are a way to interactively group, filter, and interrogate large amounts of data.

You might be thinking:

"But Tom. I can do all this in Excel anyway?"

But here's why they're so powerful...
Excel has a maximum row limit of 1.05m.

That means any dataset larger than that will have parts cut off.

A big problem if you're looking to produce accurate and reliable data insights.
Read 12 tweets
Tom Mitchell Profile picture
Nov 1, 2024
When I first started as a data analyst, I was dashboard crazy.

I quickly learnt the consequences of not validating my work properly during development.

Don't make the same mistake I did.

Instead, use this 4-step framework to bulletproof your work:
1. Verify data accuracy.

Ensure up-to-date data sources, accurate calculations, aggregations, and transformations in your visualisation tool.

Cross-check with original sources or validate samples to confirm accuracy.

This doesn't need to be complicated...

Do totals match up?

When you group by particular categories, does the segmentation work as expected?

Etc
2. Review visuals for accuracy and visual appeal.

Check data labels, legends, and axis scaling.

Does each visual give you enough info to extract insight?

Remember, you've probably looked at this for a while and got it; others will be seeing it for the first time.
Read 6 tweets

Did Thread Reader help you today?

Support us! We are indie developers!

This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Don't want to be a Premium member but still want to support us?

Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal

Or Donate anonymously using crypto!

Ethereum

0xfe58350B80634f60Fa6Dc149a72b4DFbc17D341E copy

Bitcoin

3ATGMxNzCUFzxpMCHL5sWSt4DVtS8UqXpi copy

Thank you for your support!

Follow Us!

Send Email!

:(