GitHunt
MH

mhmdkardosha/CAT-Reloaded-2025-Data-Science-Roadmap

Roadmap for Data Science circle associated with CAT Reloaded.

data-cleaningdata-sciencedata-visualizationdeep-learningmachine-learningneural-networkspythonweb-scraping-python

Data Science Roadmap 2025

This roadmap is maintained by Mohamed Kardosha.

1. Introduction

It's a multidisciplinary field that looks at raw and structured data sets and provides potentially actionable insights. The field of data science looks at ensuring that we are asking the right questions as opposed to finding exact answers. Data Scientists require skillsets centered on Computer Science, Mathematics, and Statistics. Data Scientists use several unique techniques to analyze data such as machine learning, trends, linear regressions, and predictive modeling. The tools that data scientists use to apply these techniques include Python and R.

  • These are small differences between each job title:

Data-Science-ezgif com-webp-to-jpg-converter

  • For more details about each job title, you can see this Arabic video or this other video.

2. Levels

The roadmap is divided into 4 main levels, each level will be divided into weeks and each week will have a set of tasks to be completed. We will try to provide task links one by one when it's finished. Each level is designed to be completed within 1-3 months on average, however, the time taken to complete the roadmap may vary depending on the individual.

  1. Entry: Good introduction to the field.
  2. Beginner: Data scientist toolkit and foundations.
  3. Intermediate: Dive deeper and solidly understand and work with data.
  4. Advanced A: Mathematics and Machine Learning.
  5. Advanced B: Deep Learning and specializing in a specific field.

2.1. Entry Level

It includes the following topics:

  • Data Literacy
  • Understanding Data Science
  • Introduction to Statistics
  • Python Basics
  • OOP in Python
πŸ“… Phase πŸ“š Topics πŸ“– Resources βœ… Tasks
Week 1
  1. πŸ“Š Data Literacy
  2. πŸ” Understanding Data Science
  1. πŸ† Complete the Data Literacy course.
  2. πŸ† Complete the Understanding Data Science course.
  3. πŸ“ MCQ Quiz.
Week 2
    πŸ“Š Introduction to Statistics
  1. πŸ† Complete the Introduction to Statistics course.
  2. πŸ“ MCQ Quiz.
Week 3 🐍 Python Basics
  1. πŸ† Complete the Introduction to Python Udacity course.
  2. πŸ’‘ Problem-solving exercises.
  3. πŸ“ Quiz.
Week 4 🐍 OOP in Python
  1. πŸ† Complete the OOP in Python course.
  2. πŸŽ“ Capstone Project and presentation.

2.2. Beginner Level

It includes the following topics:

  • NumPy
  • Pandas
  • Matplotlib
  • Seaborn
  • Power BI
  • Git & GitHub
πŸ“… Phase πŸ“š Topics πŸ“– Resources βœ… Tasks
Week 1 πŸ”’ NumPy
  1. πŸ† Complete Keith Galli's NumPy tutorial.
  2. πŸ“Solve task notebook.
Week 2 🐼 Pandas
  1. πŸ† Complete Corey Schafer's course.
  2. πŸ“Solve task notebook.
Week 3 〽️ Matplotlib
  1. πŸ† Complete Understanding Data Visualization course.
  2. πŸ† Complete Corey Schafer's course.
  3. πŸ’‘ Practice and document all that you learned in a notebook.
Week 4 🌊 Seaborn
  1. πŸ† Complete Kimberly Fessel's course.
  2. πŸ’‘ Practice and document all that you learned in a notebook.
  3. πŸ“ Solve task notebook (use this data in your visualizations).
Week 5 πŸ“Š Power BI
  1. πŸ† Complete Alex The Analyst course.
  2. πŸ’‘ Make a Power BI dashboard.
Week 6 πŸ”— Git & GitHub
  1. πŸ† Complete any course.
  2. πŸ“ Quiz.

2.3. Intermediate Level

It includes the following topics:

  • Regular Expressions (RegEx)
  • Data Cleaning
  • Feature Engineering
  • Exploratory Data Analysis
  • Web Scraping
  • Structured Query Language (SQL)
πŸ“… Phase πŸ“š Topics πŸ“– Resources βœ… Tasks
Week 1 πŸ”£ Regular Expressions (Regex)
  1. πŸ† Complete the Regular Expressions in Python DataCamp course.
  2. πŸ“ Solve task notebook (data included in the folder).
Week 2 🧹 Data Cleaning
  1. πŸ† Complete the Cleaning Data in Python course.
  2. πŸ“ Read the blog and extract your insights from it.
  3. πŸ’‘ Practice cleaning in the task notebook with Candy dataset (considered one of the best data cleaning practice datasets).
Week 3 πŸ›  Feature Engineering
  1. πŸ† Complete the Feature Engineering for Machine Learning in Python course.
  2. πŸ“ Read the blog and extract your insights from it.
Week 4 πŸ” Exploratory Data Analysis (EDA)
  1. πŸ† Complete the Exploratory Data Analysis in Python course.
  2. πŸ“ Read the blog and extract your insights from it.
  3. πŸ’‘ Practicing Feature Engineering and EDA in the task notebook (data included in the folder).
Week 5 πŸ•Έ Web Scraping
  1. πŸ† Complete DataCamp Web Scraping in Python course.
  2. πŸ† Complete freeCodeCamp Scrapy course.
  3. πŸ’‘ Practice and scrape any website.(eg. Oxylabs)
Week 6 πŸ—ƒ Structured Query Language (SQL)
  1. πŸ† Complete the skill track.
  2. πŸ’‘ Practice problems on HackerRank.

2.4. Advanced A Level

It includes the following topics:

  • Math required for Machine Learning:
    • Linear Algebra
    • Multi-variate Calculus
  • Machine Learning Algorithms:
    • Supervised Learning
    • Unsupervised Learning
    • Ensemble Learning
  • Model Evaluation and Selection
  • APIs
πŸ“… Phase πŸ“š Topics πŸ“– Resources βœ… Tasks
Week 1 πŸ”’ Linear Algebra
  1. πŸ† Complete the Imperial College London course.
  2. πŸ“ Solve the MCQ quiz.
  3. πŸ’‘ Solve the task notebook.
Week 2 πŸ“ˆ Multi-variate Calculus
  1. πŸ† Complete the Imperial College London course.
  2. πŸ“ Solve the MCQ quiz.
  3. πŸ’‘ Solve the task notebook.

In this stage you are ready to dive deep in the world of Machine Learning. The following resources are general and not divided into categories or weeks, you can follow them in parallel with the base resources in the weeks as a supplementary resource if you want.

Now we let's continue the roadmap into weeks.

πŸ“… Phase πŸ“š Topics πŸ“– Resources βœ… Tasks
Weeks 3 - 4 πŸ•΅οΈ Supervised Learning
  1. πŸ† Complete Andrew Ng's course.
  2. πŸ† Complete the DataCamp course.
  3. πŸ“ Solve the task notebook(consider this data).
  4. πŸ“ Solve (week 3) task notebook.
Weeks 5 - 14 πŸ“– Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow, 3rd Edition
    Every week, we will study a chapter from the book until we reach chapter 9, the end of the machine learning section in the book.
  1. πŸ† Study the chapter and summarize it.
  2. πŸ“ Solve the task, if you find it in this folder, for each chapter in the book and choose any data from CAT Reloaded Kaggle profile.
Weeks 15 - 16
  • πŸ€– Unsupervised Learning
  • ֎ Reinforcement Learning
  1. πŸ† Complete the DataCamp course.
  2. πŸ† Complete Andrew Ng's course.
  3. πŸ“ Quiz.
Weeks 17 - 18
  • 🌲 Ensemble Learning
  • βš› Neural Networks
  1. πŸ† Complete the DataCamp course.
  2. πŸ† Complete Andrew Ng's course.
  3. πŸ“ Quiz.
Week 20 🌐 APIs
  1. πŸ† Complete the DataCamp courses.
  2. πŸ’‘ Practice.

In this stage, you now have strong basics about machine learning algorithms and how it works. Also, you learned about APIs and how to use them. Now you are ready to train models, practice on datasets, and make some projects involving the algorithms you learned. You may also make a machine learning algorithm from scratch; it would be great practice to understand the algorithms more.

2.5. Advanced B Level

In this stage, you will enter the Deep Learning and NLP World. It's divided into three phases:

  • Phase 1: Basic concepts of Deep Learning (NN, CNN, RNN, Backpropagation, Optimizers, etc.)
  • Phase 2: Transformers and LLMs.
  • Phase 3: NLP fields.

2.5.1. Phase 1: Basic Concepts of Deep Learning

πŸ“… Phase πŸ“š Topics πŸ“– Resources βœ… Tasks
Weeks 1 - 3 🧠 Basic concepts of Deep Learning
  1. πŸ† Complete Andrew Ng's course.
  2. πŸ† Complete Andrej Karpathy's course.
  3. πŸ† Complete the DataCamp course.
  4. πŸ“ Practice on a dataset.
Weeks 3 - 4
  • πŸš€ Optimizers
  • πŸ”¦ PyTorch
  1. πŸ† Complete Andrew Ng's course.
  2. πŸ† Complete the PyTorch Tutorials.
  3. πŸ“ Practice in a notebook.
Weeks 5
  • πŸ› οΈ Structuring Machine Learning projects
  • πŸ” Transfer Learning
  1. πŸ† Complete Andrew Ng's course.
  2. πŸ† Complete the PyTorch Tutorials.
  3. πŸ“ Practice in a notebook.
Weeks 6 - 8 πŸŒ€ Convolutional Neural Networks (CNN)
  1. πŸ† Complete Andrew Ng's course.
  2. πŸ† Complete Khaled El-Hady videos.
  3. πŸ“ Choose one task, for example, segmentation, search for an online tutorial on how to implement it, and try writing code by hand.
Weeks 9 - 11 ⟳ Recurrent Neural Networks (RNN)
  1. πŸ† Complete Andrew Ng's course.
  2. πŸ† Complete DataCamp courses.
  3. πŸ“ Make any text classification project and try to implement as many things as you can.

2.5.2. Phase 2: Transformers and LLMs

πŸ“… Phase πŸ“š Topics πŸ“– Resources βœ… Tasks
Weeks 12 - 13 πŸ€– Transformers
  1. πŸ† Read the paper carefully and try to write down what you got from it.
  2. πŸ“ Make the transformer model from scratch and follow along with the video, you don't have to make it alone for the first time.
Weeks 14 - 15 ֎ Large Language Models (LLMs)
  1. πŸ† Complete StatQuest's video.
  2. πŸ† Complete the Coursera course.
  3. πŸ† Finish Hugging Face tutorial.
  4. πŸ“ Make the GPT model from scratch and follow along with the video.
  5. πŸ“ Use the libraries you learned and try to make an NLP project.

2.5.3. Phase 3: NLP fields

  • There are many sub-fields in this amazing field (NLP), one of them is RAG.
  • At first you need to learn LangChain and LangGraph.
  • Also we recommend to you Abu Bakr Soliman's course. In this course, you will learn a lot of concepts and tools to build a solid project like (fastapΩ‡, docker, MongoDB, and MVC Design pattern).

More to be added and we will try to update this roadmap with the latest resources.

If you need to ask any questions or clarifications for some topic, don't hesitate to ask us:

A special thanks goes out to all the contributors who supported the creation of this roadmap and the preparation of its tasks. Deep appreciation as well to the dedicated supervisors for their commitment and hard work throughout the year:

Contributors

MH
Created November 4, 2024
Updated February 16, 2026