Data Analysis with Python and pandas

32 free written lectures. Start with README.txt for setup, and keep the raw fictional data unchanged.

1. Define the Question, Row Grain, and Metric Contract
2. Install Python and Build a Reproducible Analysis Project
3. NumPy Arrays, Vectorization, and Monetary Arithmetic
4. Series, DataFrames, Indexes, and Explicit Schemas
5. Read CSV and JSON Without Losing Identifiers
6. Select, Filter, Sort, and Assign with loc and iloc
7. Nullable Dtypes, Type Conversion, and pandas 3 Copy-on-Write
8. Profile a Dataset and Build a Data Quality Audit
9. Handle Missing Data Without Inventing Facts
10. Resolve Duplicate Rows and Conflicting Business Keys
11. Normalize Text and Work with Categorical Domains
12. Parse Dates, Convert Timezones, and Define Reporting Windows
13. Build Derived Columns and Reusable Transformations
14. Join Tables Safely with Cardinality and Reconciliation Checks
15. GroupBy, Weighted Ratios, and Reliable KPI Tables
16. Reshape Tables with Pivot, Melt, and Explicit Aggregation
17. Resample Time Series and Calculate Rolling Measures
18. Explore Distributions and Investigate Outliers
19. Create Clear Charts with Matplotlib
20. Analyze Customer Cohorts and Retention Denominators
21. Sampling, Selection Bias, and the Unit of Analysis
22. Bootstrap Confidence Intervals with Explicit Assumptions
23. Analyze a Randomized A/B Test and Avoid Peeking
24. Correlation, Confounding, and Interpretable Regression
25. Use SQLite and Reconcile SQL Results with pandas
26. Reduce Memory Use and Aggregate Files in Chunks
27. Build a Command-Line Analysis Pipeline with Audit Outputs
28. Test Data Contracts, Reconciliation, and Failure Paths
29. Write Decision Memos and Share Analysis Safely
30. Capstone Part 1: Define the Brief and Audit the Source
31. Capstone Part 2: Reconcile Channels, Months, and Customer Segments
32. Capstone Part 3: Deliver the Report, Tests, and Decision Memo

The public course is at Programming Line.