0% found this document useful (0 votes)
32 views

Data Science

This document provides an overview of a full-stack roadmap for data science, machine learning, generative AI, and MLOps. It outlines 15 modules that will be covered over 12 weeks, including topics like Python, data structures and algorithms, Git/GitHub, data visualization, natural language processing, computer vision, and SQL. The goal is to help professionals and leaders build a strong portfolio in these fields in a short period of time through curated content and projects.

Uploaded by

Muhammad Khalid
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
32 views

Data Science

This document provides an overview of a full-stack roadmap for data science, machine learning, generative AI, and MLOps. It outlines 15 modules that will be covered over 12 weeks, including topics like Python, data structures and algorithms, Git/GitHub, data visualization, natural language processing, computer vision, and SQL. The goal is to help professionals and leaders build a strong portfolio in these fields in a short period of time through curated content and projects.

Uploaded by

Muhammad Khalid
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 37

2024 🚀

Data Science
Machine Learning
GenerativeAI | MLOps
Full-Stack Roadmap for Leaders & Professionals

Curated content for Decision Makers

Build Your Strong Data Science ML Gen AI Portfolio/Personal


Brand in 12 weeks🚀

Himanshu Ramchandani

https://www.linkedin.com/in/hemansnation/
Subscribe and Get the Roadmap in Your Email Inbox

https://embeds.beehiiv.com/efdd81cb-9fca-427d-b60d-d8c2fabb13
25

Modules→
1 → Python for Machine Learning 🚀
2 → Data Structures & Algorithms

3 → Git & GitHub Make Recruiters reach You, Build your stunning
profile

4 → Data Science X NumPy, Pandas, Matplotlib, Seaborn

5 → Mathematics in Machine Learning

6 → Machine‌‌Learning‌Algorithms X Data Processing

7 → Natural Language Processing X Deep Learning

8 → Generative AI - GANs, VAEs, LLMs

9 → Computer Vision X Deep Learning

10 → MLOps | Machine Learning Operations

11 → Machine Learning System Design

12 → SQL - Structured Query Language

13 → Major Capstone Projects

14 → Data Science, ML, GenAI Interview

15 → Personal Branding & Portfolio

16 → Others
Technology‌‌Stack‌

● Python‌
● Data‌‌Structures‌
● NumPy‌
● Pandas‌
● Matplotlib‌
● Seaborn‌
● Scikit-Learn‌
● Statsmodels‌
● Natural‌‌Language‌‌Toolkit‌‌(‌‌NLTK‌‌)‌
● PyTorch‌
● Structure‌‌Query‌‌Language‌‌(‌‌SQL‌‌)‌
● Docker
● Jupyter
● VScode
● TensorFlow
● 5‌‌Major‌‌Projects‌
● Git‌‌and‌‌GitHub‌‌
● AWS
● GCP
● Azure
1 | Python Programming and Logic
Building
I prefer Python Programming Language. Python is the best for
starting your programming journey.

1 | Introduction and Basics

● Installation
● Python Org, Python 3
● Variables
● Print function
● Input from user
● Data Types
● Type Conversion
● First Program

2 | Operators

● Arithmetic Operators
● Relational Operators
● Bitwise Operators
● Logical Operators
● Assignment Operators
● Compound Operators
● Membership Operators
● Identity Operators

3 | Conditional Statements

● If Else
● If
● Else
● El If (else if)
● If Else Ternary Expression
4 | While Loop

● While loop logic building


● Series based Questions
● Break
● Continue
● Nested While Loops
● Pattern-Based Questions
● pass
● Loop else

5 | Lists

● List Basics
● List Operations
● List Comprehensions / Slicing
● List Methods

6 | Strings

● String Basics
● String Literals
● String Operations
● String Comprehensions / Slicing
● String Methods

7 | For Loops

● Range function
● For loop
● Nested For Loops
● Pattern-Based Questions
● Break
● Continue
● Pass
● Loop else
8 | Functions

● Definition
● Call
● Function Arguments
● Default Arguments
● Docstrings
● Scope
● Special functions Lambda, Map, and Filter
● Recursion
● Functional Programming and Reference Functions

9 | Dictionary

● Dictionaries Basics
● Operations
● Comprehensions
● Dictionaries Methods

10 | Tuple

● Tuples Basics
● Tuples Comprehensions / Slicing
● Tuple Functions
● Tuple Methods

11 | Set

● Sets Basics
● Sets Operations
● Union
● Intersection
● Difference and Symmetric Difference
12 | Object-Oriented Programming

● Classes
● Objects
● Method Calls
● Inheritance and Its Types
● Overloading
● Overriding
● Data Hiding
● Operator Overloading

13 | File Handling

● File Basics
● Opening Files
● Reading Files
● Writing Files
● Editing Files
● Working with different extensions of file
● With Statements

14 | Exception Handling

● Common Exceptions
● Exception Handling
● Try
● Except
● Try except else
● Finally
● Raising exceptions
● Assertion
15 | Regular Expression

● Basic RE functions
● Patterns
● Meta Characters
● Character Classes

16 | Modules & Packages

● Different types of modules


● Inbuilt modules
● OS
● Sys
● Statistics
● Math
● String
● Random
● Create your own module
● Building Packages
● Build your own python module and deploy it on pip

17 | Data Structures

● Stack
● Queue
● Linked Lists
● Sorting
● Searching
● Linear Search
● Binary Search
18 | Higher-Order Functions

● Function as a parameter
● Function as a return value
● Closures
● Decorators
● Map, Filter, Reduce Functions

19 | Python Web Scrapping

● Understanding BeautifulSoup
● Extracting Data from websites
● Extracting Tables
● Data in JSON format

20 | Virtual Environment

● Virtual Environment Setup

21 | Web Application Project

● Flask
● Project Structure
● Routes
● Templates
● Navigations

22 | Git and GitHub

● Git - Version Control System


● GitHub Profile building
● Manage your work on GitHub
23 | Deployment

● Heroku Deployment
● Flask Integration

24 | Python Package Manager

● What is PIP?
● Installation
● PIP Freeze
● Creating Your Own Package
● Upload it on PIP

25 | Python with MongoDB Database

● SQL and NoSQL


● Connecting to MongoDB URI
● Flask application and MongoDB integration
● CRUD Operations
● Find
● Delete
● Drop

26 | Building API

● API (Application Programming Interface)


● Building API
● Structure of an API
● PUT
● POST
● DELETE
● Using Postman
27 | Statistics with NumPy

● Statistics
● NumPy basics
● Working with Matrix
● Linear Algebra operations
● Descriptive Statistics

28 | Data Analysis with Pandas

● Data Analysis basics


● Dataframe operations
● Working with 2-dimensional data
● Data Cleaning
● Data Grouping

29 | Data Visualization with Matplotlib

● Matplotlib Basics
● Working with plots
● Plot
● Pie Chart
● Histogram

30 | What to do Now?

● Discussions on how to process further with this knowledge.


2 | Data Structure & Algorithms
Data Structure is the most important thing to learn not only for
data scientists but for all the people working in computer
science.

0 | Data Structures & Algorithms Starting Point

● Getting Started
● Variables
● Data Types
● Data Structures
● Algorithms
● Analysis of Algorithm
● Time Complexity
● Space Complexity
● Types of Analysis
● Worst
● Best
● Average
● Asymptotic Notations
● Big-O
● Omega
● Theta
Data Structures - Phase 1

1 | Stack

2 | Queue

3 | Linked List

4 | Tree

5 | Graph

Algorithms - Phase 2

6 | List and Array

7 | Swapping and Sorting

8 | Searching

9 | Recursion

10 | Hashing

11 | Strings
3 | Git and GitHub

Steal My GitHub Profile - https://github.com/hemansnation

● Understanding Git
● Commands and How to commit your first code?
● How to use GitHub?
● How to work with a team?
● How to make your first open-source contribution?
● How to create your stunning GitHub profile?
● How to build your own viral repository?
● Building a personal landing page for your Portfolio for
FREE
● How to grow followers on GitHub?
● How to work with a team?

Git Resources
Git - Version Control System

Resources and Cheatsheets

Personal Profile

GitHub Resources
Resources and Tools

Interview Questions

Portfolio of Projects

Repo Description
4 | Data Science X Pandas Numpy
Matplotlib Seaborn
Numpy

● Vectors, Matrix
● Operations on Matrix
● Mean, Variance, and Standard Deviation
● Reshaping Arrays
● Transpose and Determinant of Matrix
● Diagonal Operations, Trace
● Add, Subtract, Multiply, Dot, and Cross Product.

Pandas

● Series and DataFrames


● Slicing, Rows, and Columns
● Operations on DataFrame
● Different ways to create DataFrame
● Read, Write Operations with CSV files
● Handling Missing values, replacing values, and Regular
Expression
● GroupBy and Concatenation

Matplotlib

● Graph Basics
● Format Strings in Plots
● Label Parameters, Legend
● Bar Chart, Pie Chart, Histogram, Scatter Plot
5 | Mathematics for Machine Learning
Algebra, Topology, Differential Calculus, and Optimization Theory
For Computer Science and Machine Learning

All math topics for Machine Learning by Stanford

Stanford CS229: Machine Learning Course | Summer 2019 (Anand


Avati)
Chapter 1 - Linear Algebra

Learn for FREE - Mathematics for ML - Linear


Algebra
Mathematics for Machine Learning - Linear Algebra

1 | Vectors

2 | Matrix

3 | Eigenvalues and Eigenvectors

3 | Factorization

4 | Singular Value Decomposition (SVD)

5 | Gradient

6 | Tensors

7 | Jacobian Matrix

8 | Curse of Dimensionality

Chapter 2 - Statistics
Elements of Statistical Learning: data mining, inference, and
prediction. 2nd Edition.

Statistics give us 2 tools descriptive and inferential


1 | Descriptive Statistics

1 | Variables

2 | Mean

3 | Median

4 | Mode

5 | Standard Deviation

6 | Variance

7 | Range

8 | Percentile

9 | Skewness

10 | Kurtosis

2 | Inferential Statistics

1 | Sampling Distributions

2 | Central Limit Theorem

3 | Hypothesis Testing

4 | Confidence Intervals

5 | T-Tests

6 | Analysis of Variance (ANOVA)

7 | Chi-Square Test

8 | Regression Analysis
9 | Bayesian Inference

10 | Maximum Likelihood Estimation (MLE)

Chapter 3 - Probability
Probability Theory: The Logic of Science

https://bayes.wustl.edu/etj/prob/book.pdf

1 | Probability Distribution

2 | Conditional Probability

3 | Bayes' Theorem

4 | Joint and Marginal Probabilities

5 | Independence and Conditional Independence

Chapter 4 - Objective Functions

1 | Mean Squared Error (MSE)

2 | Mean Absolute Error (MAE)

3 | Binary Cross-Entropy (Log Loss)

4 | Maximum Likelihood Estimation (MLE)

5 | Gini Impurity
Chapter 5 - Regularization

1 | L1 Regularization (Lasso Regression)

2 | L2 Regularization (Ridge Regression)

3 | Elastic Net Regularization

4 | Dropout Regularization

5 | Max-Norm Regularization

6 | Batch Normalization

Chapter 6 - Information Theory


Information Theory, Inference and Learning Algorithms

David MacKay: Information Theory, Pattern Recognition and Neural


Networks: The Book

1 | Entropy

2 | Conditional Entropy

3 | Joint Entropy

4 | Cross-Entropy

5 | Information Gain

6 | Data Entropy
Chapter 7 - Optimization

1 | Gradient Descent

2 | Stochastic Gradient Descent (SGD)

3 | Adagrad (Adaptive Gradient Algorithm)

4 | Adam (Adaptive Moment Estimation)

Chapter 8 - Distribution

1 | Bernoulli Distribution

2 | Binomial Distribution

3 | Multinomial Distribution

4 | Normal (Gaussian) Distribution

Calculus

Calculus 1 | Math | Khan Academy


6 | Machine‌‌Learning‌Algorithms X
Data Processing

Chapter 1 - Categories of Machine Learning


1 | Supervised

2 | Unsupervised

3 | Reinforcement

Algorithms

● Linear Regression
● Logistic Regression
● Decision Tree
● Gradient Descent
● Random Forest
● Ridge and Lasso Regression
● Naive Bayes
● Support Vector Machine
● KMeans Clustering

Chapter 2 - Types of Machine Learning


1 | Regression

2 | Classification

3 | Clustering

4 | Dimensionality Reduction
5 | Density Estimation

Chapter 3 - Parameter Tuning


1 | Hyperparameter

2 | Cross-validation

3 | Regularization

4 | Overfitting

5 | Underfitting

Chapter 4 - Ensemble Methods


1 | Bagging

2 | Boosting

Chapter 5 - Performance Analysis


1 | Confusion Matrix

2 | Accuracy

3 | Precision, Recall and F1 score

4 | ROC and AUC curve

5 | Mean Squared Error (MSE)

6 | Mean Absolute Error (MAE)

7 | R-squared

8 | Bias-Variance Tradeoff
Chapter 6 - Libraries and Framework
1 | NumPy

2 | Pandas

3 | Scikit-Learn

4 | TensorFlow

5 | PyTorch

6 | Keras
7 | Natural Language Processing X
Deep Learning

Understanding Models and Hands-On implementation

1 | NLP Fundamentals

2 | PyTorch x NLP

3 | The model building API - Keras

4 | Word to Vector Representation

5 | Convolutional Neural Network

6 | Named Entity Recognition using Recurrent Neural


Network(RNN)

7 | Long Short Term Memory (LSTM)

8 | Generating Text using LSTM

9 | Transformers Basics

Others

● Sentiment analysis
● POS Tagging, Parsing,
● Text preprocessing
● Stemming and Lemmatization
● Sentiment classification using Naive Bayes
● TF-IDF, N-gram,
● Machine Translation, BLEU Score
● Text Generation, Summarization, ROUGE Score
● Language Modeling, Perplexity
● Building a text classifier
8 | Generative AI - GANs, VAEs, LLMs

1 | Foundational Understanding of Large Language Models (LLMs)

2 | TensorFlow Revision

3 | Environment Setup

4 | Understanding Docker, Kubernetes, and Kubeflow

5 | Deep Learning Fundamentals

6 | Understanding Variational Autoencoders (VAEs)

7 | GANs (Generative Adversarial Networks)

8 | LSTM (Long Short-Term Memory networks) Revision

9 | GPTs (Generative Pre-trained Transformers)

10 | Generative AI

11 | Prompt Engineering
9 | Computer Vision X Deep Learning

1 | Image Classification

2 | Transfer Learning

3 | Autoencoders Noise Reduction

4 | Image Captioning

5 | Segmentation & Object Detection

6 | In-Depth DeepFakes

Others

● PyTorch Tensors
● Understanding Pretrained models like AlexNet,
ImageNet, and ResNet.
● Neural Networks
● Building a perceptron
● Building a single-layer neural network
● Building a deep neural network
● Recurrent neural network for sequential data analysis
10 | MLOps | Machine Learning
Operations

Deploy your models in production and let the


world see your portfolio
Not knowing any of the cloud platform for production AWS, GCP
or Azure is a concern.

Chapter 1 - Fundamentals
1 | Basics of ML Operations

2 | ML Model, Data and Code


Chapter 2 - Pipeline
3 | Building Machine Learning Pipeline

4 | Deployment

5 | CI/CD Pipeline and APIs

6 | Monitoring

7 | Orchestration

Chapter 3 - AWS
1 | MLOps Fundamentals on AWS

2 | Containers

3 | Analytics using Amazon RedShift Serverless

4 | SageMaker

Chapter 4 - Project Deployment and


end-to-end Pipeline
1 | Amazon EKS and KubeFlow
Resources
https://github.com/GokuMohandas/mlops-course

https://github.com/DataTalksClub/mlops-zoomcamp

● Deploy ML models using Flask


● Amazon Lex — Natural Language Understanding
● AWS Polly — Voice Analysis
● Amazon Transcribe — Speech to Text
● Amazon Textract — Extract Text
● Amazon Rekognition — Image Applications
● Amazon SageMaker — Building and deploying models
● Working with Deep Learning on AWS
11 | Machine Learning System Design

Create Your ML Design

Understanding the whole Machine Learning architecture from a


birds-eye view, so that you will not end up knowing anything.

Resources
https://github.com/CathyQian/Machine-Learning-System-Design

https://github.com/ifding/ml-system-design

Chapter 1
1 | Fundamentals

2 | Pinterest → Visual Search ML System

3 | YouTube → Video Search ML System

4 | Video Recommendation System


12 | Structured Query Language (SQL)

1 | Fundamentals to SQL and Installation

2 | Creating Tables - modifiers, altering table, Insert, Update,


Delete

3 | Retrieving Data - SELECT

4 | Aggregating Data using Functions

5 | Subqueries - retrieving data with conditions

6 | JOINS

Others

● Fundamental to SQL syntax and Installation


● Creating Tables, Modifiers
● Inserting and Retrieving Data, SELECT INSERT UPDATE
DELETE
● Aggregating Data using Functions, Filtering, and RegEX
● Subqueries, retrieve data based on conditions, grouping of
Data.
● Practice Questions
● JOINs
● Advanced SQL concepts such as transactions, views, stored
procedures, and functions.
● Database Design principles, normalization, and ER diagrams.
● Practice, Practice, Practice: Practice writing SQL queries on
real-world datasets, and work on projects to apply your
knowledge.
13 | Major Capstone Project
Check the following list of 600 ML Projects
https://github.com/hemansnation/God-Level-Data-Science-ML-Fu
ll-Stack/tree/master/projects

Projects

Here is the list of project ideas

14 | Data Science, ML, GenAI Interview


Interview Questions

LLMs Interview Questions

Machine Learning Interview Questions

Resume Checklist
15 | Personal Branding & Portfolio

Portfolio
Work on your craft.

1. Technical blogs (Posts on social media) -


Newsletter(LinkedIn, BeeHiive, CovertKit, Medium)
2. Projects - Live (Proof of Work) - read.cv
3. Certification - Google Cloud (ACE)
4. Soft skills - Leadership, Talk, Session, NGO
5. Story - Your Story
6. Research Paper

Personal Branding
1. Profile Page as Landing Page
2. How to Post
3. Who to connect with
4. Tools to use to make it better
Data Science ML Generative AI
Roadmap, Resources 2024 🚀
For Leaders and Data Professionals

Click Here to Subscribe and Get the Roadmap in Your


Email Inbox

https://embeds.beehiiv.com/efdd81cb-9fca-427d-b60d-
d8c2fabb1325

Community of 35k Data Professionals


Join them 👉
LinkedIn (25,000+), Telegram (5,500+), Discord (1000+),

Instagram (4,100+), GitHub (1.9k)


About Your Mentor

Himanshu Ramchandani
AI Advisor - I help Industry Leaders 10x their AI expertise.
Building AI & Data Teams
Modern Data Architecture & Engineering Consulting

Join Telegram:
https://t.me/+sREuRiFssMo4YWJl

Join the Discord Community:

https://discord.gg/q3svy4VEEs

You might also like