Applied Data Science & Generative AI Hub
This curriculum bridges classical data science (wrangling, exploration, predictive modeling) with the new frontier of Generative AI. Designed by Amol Shukla, this course features code illustrations and interactive note pages designed to help students quickly understand data operations and agent-driven engineering.
Course Modules
Module 1: Foundations of Python & Ecosystem
Set up the local environment and master Python fundamentals optimized for large data manipulation.
1: The Python Data Science Ecosystem
Jupyter setup, virtual environments, variables, data structures, and list comprehensions.
Module 2: Vectorized Computing & Wrangling
Transform raw, unstructured datasets into clean, actionable insights using NumPy and Pandas.
2: NumPy Arrays & Pandas Wrangling
N-dimensional arrays, vectorized functions, DataFrame operations, grouping, and handling missing data.
Module 3: Visual Analytics
Design premium visual dashboards that communicate statistical patterns clearly.
3: Visualizing Patterns with Seaborn & Matplotlib
Building distribution charts, relational scatter plots, and correlation heatmaps.
Module 4: Machine Learning Foundations
Fit mathematical models to make predictions on unseen records.
4: Predictive Modeling with Scikit-Learn
Features vs Labels, train-test splitting, fitting Linear Regression, and checking MSE / R2.
Module 5: Agentic AI Pipelines
Deploy large language models in an agentic loop to write and execute code dynamically.
5: Developing Intelligent Agentic Data Pipelines
Tool-calling patterns, ReAct architecture, safety sandboxing, and orchestrating analytical agents.