Objectives
Equip students with the skills to collect, clean, analyze, and model data using Python and machine learning techniques to build intelligent systems and generate predictive insights.
Eligibility
- No prior experience required, but basic understanding of math/statistics is helpful.
- Ideal for those interested in AI, machine learning, and data modeling.
- Perfect for aspiring data scientists, engineers, and AI enthusiasts.
- Device: You'll need a desktop/laptop (Mac, Windows or Linux).
Technologies
Python
NumPy
Pandas
Scikit-learn
Matplotlib
Prophet
Pytorch
Jupyter
Seaborn
Streamlit
Github
Program Outline
Module 1 (Wk 1-2): Python for Data Science
Python Topics
- Python Basics: Variables, Data Types, and Operators
- Control Flow: if, loops, functions
- Data Structures: Lists, Tuples, Dictionaries, Sets
- File Handling: Reading/Writing CSV, JSON
- Introduction to Git & GitHub (version control, commits, pushes, pull requests)
Module 2 (Wk 3): Data Cleaning & Manipulation
NumPy and Pandas
- Creating and Manipulating Arrays
- DataFrames: indexing, filtering, merging
- Handling missing data
- Data aggregation and grouping
- Feature engineering basics
Module 3 (Wk 4-5): Data Visualization
Matplotlib & Seaborn
- Line, Bar, Scatter, and Histogram Plots
- Heatmaps and Pairplots
- Customizing charts and styles
- Exploratory Data Analysis (EDA) projects
Module 4 (wk 6-7): Introduction to Machine Learning
Machine Learning with Scikit-learn
- Supervised vs Unsupervised Learning
- Regression: Linear and Logistic
- Classification: Decision Trees and Random Forests
- Clustering: KMeans
- Model Evaluation & cross validation
- Basic pipelines
Module 5 (Wk 8): Time Series & Forecasting
Prophet
- Introduction to time series concepts
- Trend, seasonality, and noise
- Forecasting using Prophet
- Evaluating forecast models
Module 6 (Wk 9-10): Deep Learning & Neural Networks
Pytorch
- Introduction to neural networks
- Feedforward networks, activation functions
- Training, loss functions, optimization
- Simple image/text projects
Module 7 (Wk 11): Deployment & Dashboards
Streamlit
- Building simple web apps to display ML models
- Data visualization dashboards
- Integrating model predictions with interactive UI
Capstone Project & Presentation (Wk 12-13)
Real-world dataset project
- Apply Python, Pandas, visualization, ML, Deep Learning
- Version control via GitHub
- Presentation and peer/project review
- Earn a certificate
