This 3-month roadmap covers everything you need, from basic Python to

machine learning, allowing you to learn steadily in just 2 hours a day.

Month 1: Python Basics & Intermediate Python Tick here

Day 1
Introduction to Python Syntax
g
What is Python? g
g
j
Installing Python & setting up your environment g
g
j
Writing your first Python program: print("Hello, World!") g
g
j
Understanding indentation and structure of a Python script g
g
j
Day 2 g
g
j
Data Types and Variables g
g
j
• Integer, float, string, boolean, lists, tuples, sets, dictionaries g
g
j
• Declaring and using variables g
g
j
• Type conversion: int( ), str( ), float( ) g
g
j
g
g
j
Day 3 g
g
j
Basic Input/Output g
g
j
• Using input ( ) to get user input g
g
j
• Outputting data with print ( ) g
g
j
• String formatting using f "{ }" and format ( ) g
g
j
g
gj
g
g
j
g
j
 Day 4
Operators g
• Arithmetic operators (+, -, *, /, //, %, **) g
g
j
• Comparison operators (==, !=, >, <, >=, <=) g
g
j
• Logical operators (and, or, not) g
g
j
• Assignment operators g
g
j
Day 5 g
g
j
Conditional Statements g
g
j
• Using if, elif, else g
g
j
• Nested conditionals g
g
j
• Example tasks: Create simple conditions like guessing games g
g
j
Day 6 g
g
j
Loops g
g
j
• for loops: iterating over lists, strings g
g
j
• while loops: creating loops that run until a condition is false g
g
j
• Breaking out of loops: break, continue g
g
j
Day 7 g
g
j
Functions (Part 1) g
g
j
• Defining functions using def g
g
j
• Passing arguments and returning values g
g
j
• Scope of variables (local vs. global) g
g
j
Week 2: Functions & Modules g
g
j
Day 8 g
g
j
Functions (Part 2) g
g
j
• Default arguments g
g
j
• Keyword arguments g
g
j
g
j
 • Recursive functions (calling a function within itself) g
Day 9 g
g
j
Understanding Modules g
g
j
• What are modules? g
g
j
• Importing built-in modules like math, random g
g
j
• Creating and using custom modules g
g
j
Day 10 g
g
j
Working with Files (Part 1) g
g
j
• Opening files with open ( ) g
g
j
• Reading file contents: read ( ), readline ( ), readlines ( ) g
g
j
Day 11 g
g
j
Working with Files (Part 2) g
g
j
• Writing to files using write ( ) , writelines ( ) g
g
j
• Closing files and using with for automatic closure g
g
j
Day 12 g
g
j
Error Handling (Part 1) g
g
j
• Using try, except, finally g
g
j
• Handling specific exceptions: ValueError, TypeError, etc. g
g
j
Day 13 g
g
j
Error Handling (Part 2) g
g
j
• Raising exceptions manually with raise g
g
j
• Writing custom error messages g
g
j
Day 14 g
g
j
List Comprehensions g
g
j
• Basic syntax of list comprehensions g
g
j
• Using list comprehensions to filter and modify lists g
g
j
g
g
j
g
j
 Week 3: Object-Oriented Programming (OOP ) g
Day 15 g
g
j
Introduction to OOP g
g
j
• Understanding the concept of objects and classes g
g
j
• Creating classes and objects g
g
j
Day 16 g
g
j
Class Attributes & Methods g
g
j
• Defining attributes inside a class g
g
j
g
• Defining methods (functions inside a class) gj
Day 17 g
g
j
Constructors & Destructors g
g
j
• Understanding the __init__( ) method (constructor) g
g
j
• Using __del__( ) for cleanup g
g
j
Day 18 g
g
j
Inheritance (Part 1) g
g
j
• What is inheritance? g
g
j
• Creating a subclass and inheriting properties from a parent class g
g
j
Day 19 g
g
j
Inheritance (Part 2) g
g
j
• Overriding methods in subclasses g
g
j
• Using super ( ) to call parent class methods g
g
j
Day 20 g
g
j
Encapsulation & Polymorphism g
g
j
• Hiding data with private and protected variables g
g
j
• Creating polymorphic methods g
g
j
g
g
j
g
g
j
g
j
 Day 21 g
Hands-on OOP Practice g
g
j
• Build a small project that uses classes, inheritance, and polymorphism g
g
j
(e.g., a simple game or library system) g
j
Week 4: Data Structures and Algorithms g
Day 22 g
g
j
Understanding Lists, Tuples, and Dictionaries g
g
j
• Accessing, modifying, and iterating over these data structures g
g
j
Day 23 g
g
j
Advanced List Operations g
g
j
• List slicing and list methods (append( ), pop( ), extend( )) g
g
j
Day 24 g
g
j
Tuples and Sets g
g
j
• Properties of tuples and sets g
g
j
• Using set operations : union ( ), intersection( ), difference( ) g
g
j
Day 25 g
g
j
Dictionaries (Part 1) g
g
j
• Creating and accessing dictionaries g
g
j
• Looping through dictionaries g
g
j
Day 26 g
g
j
Dictionaries (Part 2) g
g
j
• Dictionary methods: get ( ), keys ( ), values ( ), items ( ) g
g
j
• Nested dictionaries g
g
j
Day 27 g
g
j
Lambda Functions g
g
j
• Writing anonymous functions using lambda g
g
j
• Using map( ), filter( ), and reduce( ) with lambda functions g
g
j
g
j
 Day 28 g
Hands-on Practice (Project Day) g
g
j
• Build a small project that uses lists, dictionaries, and lambda functions g
g
j
g
g
j
Month 2: Data Manipulation, Visualization, and Statistics g
g
j
Week 5: Introduction to NumPy g
g
j
Day 29 g
g
j
Understanding NumPy Arrays g
g
j
• Creating arrays with numpy.array ( ) g
g
j
• Array operations (addition, subtraction, etc.) g
g
j
Day 30 g
g
j
Array Manipulation g
g
j
• Reshaping arrays: reshape( ), flatten( ) g
g
j
• Indexing and slicing arrays g
g
j
Day 31 g
g
j
Advanced Array Operations g
g
j
• Performing matrix operations: dot product, transpose g
g
j
• Using aggregation functions: sum(), mean(), std() g
g
j
Day 32 g
g
j
Broadcasting in NumPy g
g
j
• Understanding broadcasting rules g
g
j
• Performing operations on arrays of different shapes g
g
j
Day 33 g
g
j
NumPy Practice Day g
g
j
Solve exercises to manipulate and perform calculations on arrays g
g
j
g
g
j
Day 34 g
g
j
g
j
Data Handling with Pandas (Part 1) g
• Introduction to Data Frame and Series g
g
j
• Creating and modifying Data Frames g
g
j
Day 35 g
g
j
Data Handling with Pandas (Part 2) g
g
j
• Filtering, sorting, and indexing data g
g
j
• Handling missing data: isna ( ), dropna() g
g
j
Week 6: Pandas and Data Visualization g
g
j
Day 36 g
g
j
Advanced Pandas Operations g
g
j
• Merging, joining, and concatenating Data Frames g
g
j
• Grouping data using groupby ( ) g
g
j
Day 37 g
g
j
Introduction to Matplotlib (Part 1) g
g
j
• Creating basic line plots, bar plots, and scatter plots g
g
j
Day 38 g
g
j
Advanced Plot Customization g
g
j
• Customizing plots: titles, labels, legends, colors g
g
j
Day 39 g
g
j
Introduction to Seaborn (Part 1) g
g
j
• Creating statistical plots: histograms, box plots g
g
j
Day 40 g
g
j
Advanced Seaborn Visualizations g
g
j
• Heatmaps, pair plots, and joint plots g
g
j
g
g
j
g
g
j
Day 41 g
g
j
g
j
Hands-on Practice (Data Visualization Project) g
• Build a small project to visualize data using Pandas, Matplotlib, and g
g
j
Seaborn g
j
Day 42 g
Exploring Data with Pandas g
g
j
• Perform a small analysis using Pandas (e.g., analyzing sales or weather g
g
j
data) g
j
Week 7: Statistics and Math with Python g
Day 43 g
g
j
Introduction to Scipy g
g
j
• Overview of SciPy and its modules g
g
j
• Using basic statistical methods: mean, median, mode g
g
j
Day 44 g
g
j
Linear Algebra in Python g
g
j
• Matrix operations using NumPy g
g
j
• Solving linear equations g
g
j
Day 45 g
g
j
Probability Distributions g
g
j
• Understanding normal distribution, binomial distribution using SciPy g
g
j
Day 46 g
g
j
Statistical Testing g
g
j
• Performing hypothesis testing (t-test, chi-squared test) g
g
j
Day 47 g
g
j
Hands-on Practice (Statistics and Math) g
g
j
• Apply statistical methods to analyze a dataset g
g
j
Day 48 g
g
j
Recap and Practice g
g
j
g
j
 • Review and practice NumPy, Pandas, Matplotlib, and Scipy g
Day 49 g
g
j
Hands-on Project g
g
j
• Analyze a dataset and create visualizations using what you’ve learned g
g
j
Week 8: Advanced Python Concepts g
g
j
Day 50 g
g
j
Iterators & Generators g
g
j
• Understanding __iter__(), __next__() g
g
j
• Creating generators with yield g
g
j
Day 51 g
g
j
Decorators (Part 1) g
g
j
• Understanding function decorators g
g
j
• Using built-in decorators like @staticmethod, @classmethod g
g
j
Day 52 g
g
j
Decorators (Part 2) g
g
j
• Writing custom decorators g
g
j
• Chaining multiple decorators g
g
j
Day 53 g
g
j
Context Managers g
g
j
• Using with to manage resources g
g
j
• Writing custom context managers g
g
j
Day 54 g
g
j
Dask for Big Data g
g
j
• Introduction to Dask and its importance for handling large datasets g
g
j
g
g
j
g
g
j
Day 55 g
g
j
g
j
Working with Dask g
• Using Dask for parallel computing and working with large DataFrames g
g
j
Day 56 g
g
j
Hands-on Practice with Dask g
g
j
• Build a small project that processes large datasets using Dask g
g
j
g
g
j
Month 3: Machine Learning with Python g
g
j
Week 9: Introduction to Machine Learning Libraries g
g
j
Day 57 g
g
j
Introduction to Scikit-learn g
g
j
• Overview of Scikit-learn library and ML basics g
g
j
• Implementing simple linear regression g
g
j
Day 58 g
g
j
Classification Algorithms (Part 1) g
g
j
• Implementing K-Nearest Neighbors (KNN) using Scikit-learn g
g
j
Day 59 g
g
j
Classification Algorithms (Part 2) g
g
j
• Implementing Decision Trees and Random Forest g
g
j
Day 60 g
g
j
Regression Algorithms g
g
j
• Implementing Linear Regression, Polynomial Regression g
g
j
Day 61 g
g
j
Clustering Algorithms g
g
j
• Implementing K-Means Clustering g
g
j
g
g
j
g
j
Day 62
Model Evaluation (Part 1) g
g
j
 • Introduction to Cross-validation g
Day 63 g
g
j
Model Evaluation (Part 2) g
g
j
• Hyperparameter tuning using Grid Search g
g
j
Week 10: Neural Networks and TensorFlow g
g
j
Day 64 g
g
j
Introduction to TensorFlow g
g
j
• Overview of TensorFlow and neural networks g
g
j
Day 65 g
g
j
Building Simple Neural Networks g
g
j
• Creating basic neural networks with TensorFlow g
g
j
Day 66 g
g
j
Introduction to Keras g
g
j
• Using Keras to build neural networks more easily g
g
j
Day 67 g
g
j
Building Models with Keras (Part 1) g
g
j
• Building a simple feedforward network g
g
j
Day 68 g
g
j
Building Models with Keras (Part 2) g
g
j
• Implementing dropout and batch normalization g
g
j
Day 69 g
g
j
Hands-on Practice with TensorFlow g
g
j
• Train a simple model on a small dataset using TensorFlow g
g
j
g
g
j
g
j

Day 70
Model Evaluation and Tuning g
g
j
 • Fine-tune a neural network with hyperparameter tuning g
Week 11: Machine Learning Projects g
g
j
Day 71 g
g
j
ML Project (Part 1) g
g
j
• Start a hands-on project using Scikit-learn (e.g., predicting house prices) g
g
j
Day 72 g
g
j
ML Project (Part 2) g
g
j
• Continue working on the project: data preprocessing, model building g
g
j
Day 73 g
g
j
ML Project (Part 3) g
g
j
• Fine-tune the model, perform cross-validation, and evaluate performance g
g
j
Day 74 g
g
j
ML Project (Part 4) g
g
j
• Finalize the project and document your results g
g
j
Day 75 g
g
j
Neural Network Project (Part 1) g
g
j
• Build a small neural network project using TensorFlow or Keras (e.g., g
g
j
digit classification) g
j
Day 76 g
Neural Network Project (Part 2) g
g
j
• Continue building and training the neural network model g
g
j
Week 12: Final Projects and Review g
g
j
Day 78 g
g
j
Recap and Review g
g
j
• Go over the major concepts learned (from Python basics to ML) g
g
j
Day 79 g
g
j
Final Project (Part 1) g
g
j
g
j
 • Start a comprehensive project that combines all concepts (e.g., building an g
end-to-end ML model) g
j
Day 80 g
Final Project (Part 2) g
g
j
• Continue working on the final project g
g
j
Day 81 g
g
j
Final Project (Part 3) g
g
j
• Finalize the project, test, and deploy the model g
g
j
Day 82 g
g
j
Wrap-Up g
g
j
• Review your progress, practice any weak areas, and organize your projects bgg
j
g
g
j
g
g
j
g
g
j
g
g
j
g
g
j
g
g
j
g
j