A hands-on repository documenting my journey from Python fundamentals to Artificial Intelligence and Machine Learning.
This repository contains my learning exercises, experiments, data analysis work, machine learning implementations, NLP applications, computer vision projects, and practical mini-projects.
The goal is not only to learn concepts theoretically, but to understand how and why they work by implementing them in code.
Learn → Understand → Implement → Build → Improve
I started by building a strong foundation in Python programming and logic building.
Topics practiced include:
- Variables and data types
- Conditional statements
- Loops
- Functions
- Lists
- Tuples
- Sets
- Dictionaries
- List and dictionary manipulation
- Exception handling
- File handling
- Modules and libraries
- Input/output
- Logic building
- Problem solving
Examples can be found in files such as:
atm.py
chatbot.py
RockPaperSissors.py
list_dictionary.py
tuples-in-list.py
file-handling.py
gen_password.py
urls.py
I practiced Object-Oriented Programming by building small practical applications.
Concepts include:
- Classes and objects
- Constructors
- Instance attributes
- Methods
- Encapsulation
- Object-oriented design
- Building applications using classes
Examples:
oop_contacts.py
electronics.py
Inventory_system.py
As I moved toward AI/ML, I started working with data programmatically.
Practiced:
- Arrays
- Array operations
- Indexing and slicing
- Mathematical operations
- Statistical operations
- Working with multidimensional data
Example:
numpylibrary.py
Practiced:
- Loading datasets
- DataFrames and Series
- Data inspection
- Data cleaning
- Handling missing values
- Duplicate detection
- Data manipulation
- Filtering
- Grouping
- Aggregation
- Feature selection
- Statistical summaries
I learned how to understand a dataset before applying machine learning.
Practiced:
- Descriptive statistics
- Data distributions
- Histograms
- Scatter plots
- Correlation analysis
- Correlation heatmaps
- Feature relationships
- Data visualization
Tools:
- Matplotlib
- Seaborn
- Pandas visualization
This repository also contains practical projects where multiple concepts are combined into complete workflows. These projects allow me to practice the complete process of turning individual concepts into working applications.
My current focus is moving from knowing ML concepts theoretically to implementing them confidently and understanding the decisions behind the code. Areas I am continuing to strengthen include:
- Unsupervised Machine Learning
- Model evaluation
- Hyperparameter tuning
- Regularization
- Transfer learning
- Batch normalization
- Deep Learning
- CNNs, RNNs
- LSTMs
- Transformers
- Model deployment
- FastAPI
- Docker
- MLflow
- ML Pipelines
I am following a practical learning approach rather than simply collecting theoretical knowledge. For each concept, the goal is to understand:
What is it?
↓
Why do we need it?
↓
How does it work?
↓
What is the mathematics behind it?
↓
How is it implemented?
↓
When should I use it?
↓
What can go wrong?
↓
How can I improve it?
This repository therefore represents an evolving learning process rather than a collection of finished tutorials.
The repository is organized to keep learning material, algorithms, and complete projects distinguishable.
Small scripts and implementations used to understand individual Python, data, and ML concepts.
Algorithm implementations and experiments organized according to the machine learning concept being studied.
Complete applications that combine multiple concepts into a practical workflow.
Python Fundamentals
↓
Problem Solving & Logic Building
↓
Object-Oriented Programming
↓
NumPy & Pandas
↓
Data Cleaning & Manipulation
↓
Exploratory Data Analysis
↓
Data Visualization
↓
Supervised Machine Learning
↓
Unsupervised Machine Learning
↓
Model Evaluation
↓
Natural Language Processing
↓
Computer Vision & OCR
↓
Deep Learning
↓
Convolutional Neural Networks
↓
Advanced Machine Learning & Deep Learning
↓
Deployment & MLOps
This repository is continuously updated as I learn, experiment, make mistakes, improve implementations, and build more practical projects.
The objective is not simply to say "I know Python" or "I know Machine Learning."
The objective is to reach the point where I can:
Understand the problem → choose the right approach → implement it → evaluate it → improve it → and build something useful with it.
Symbol Pamnani BS Computer Science | AI/ML Engineer