M05-03 · AI + Data & Decision Science

Python for Data Analysis

Teaches Python as the primary programming language for data analysis work. Covers pandas for data manipulation, numpy for numerical operations, matplotlib/seaborn/plotly for visualization, and Jupyter notebook practices for reproducible analysis. Students write real code with AI assistance, learning to verify AI-generated code against known values and understand what it does — not just accept output blindly.

30 Hours

7 Learning objectives

Create Bloom's ceiling (?)

5 Competencies

What You'll Be Able To Do

Learning Objectives

Objectives

Depth

Write pandas code for the complete data analysis workflow: loading data (read_sql, read_csv), profiling (info, describe, isnull, duplicated), cleaning (str methods, to_numeric, to_datetime, drop_duplicates), and analysis (groupby, pivot_table, merge) Apply
Create publication-quality data visualizations using matplotlib and seaborn: line charts for trends, bar charts for comparisons, heatmaps for correlations, with proper labels, legends, and error bars Create
Set up and manage Python environments: virtual environments (venv/conda), package installation, requirements files, and reproducible environment configurations Apply
Use Jupyter notebooks with professional discipline: meaningful filenames, markdown header cells (question, sources, date, status), stripped outputs for version control, clear execution order Apply
Evaluate AI-generated Python code by running it against known values, checking join types, verifying aggregation levels, and testing edge cases before trusting results Evaluate
Analyze dataset size constraints and select appropriate tools: pandas for datasets under 5M rows, SQL/warehouse for larger datasets, chunked processing for memory-constrained operations Analyze
Build reusable analysis functions and scripts that accept parameters, handle errors gracefully, and produce consistent output formats across analyses Create

Levels: Remember · Understand · Apply · Analyze · Evaluate · Create — highest demands most original thinking.

Core Competencies

What You'll Master

pandas Proficiency

Loading, profiling, cleaning, transforming, and analyzing tabular data fluently in pandas.

Data Visualization

Creating clear, labeled, context-rich charts using matplotlib, seaborn, and plotly that communicate insights to technical and non-technical audiences.

Notebook Discipline

Maintaining professional Jupyter notebooks with documentation, reproducible execution, version control compatibility, and clear narrative flow.

AI-Assisted Coding

Using Claude/Copilot to generate analysis code, then systematically verifying correctness against known values and edge cases.

Environment Management

Setting up reproducible Python environments, managing dependencies, and ensuring analysis can run on any team member's machine.

Portfolio Artifact

What You'll Build

Analysis Notebook Portfolio — Student produces 3 polished Jupyter notebooks covering distinct analysis types: (1) an exploratory data analysis with profiling and visualization, (2) a group-by/pivot analysis answering a business question with charts, and (3) a data cleaning pipeline with before/after comparisons. Each notebook includes a markdown header (question, data sources, date, author), commented code, AI-assisted sections with annotations on what was verified, and exported visualizations. All notebooks are version-controlled with outputs stripped.

Tools You'll Use

Industry Tools, Not Toy Projects

Python (pandas, numpy)

Core data manipulation and numerical computation libraries for professional data analysis.

matplotlib / seaborn / plotly

Visualization libraries for creating publication-quality charts, from static reports to interactive dashboards.

Jupyter / JupyterLab

Interactive notebook environment for combining code, visualizations, and narrative in reproducible analyses.

VS Code

Code editor with Python extensions for script development and notebook editing.

Git / GitHub

Version control with nbstripout for managing notebook files in collaborative environments.

Claude

AI assistant for code generation, debugging, and learning new pandas patterns with verification workflows.