PyStatsV1 Workbook

Getting started

• Quickstart (all platforms)
  • Prerequisites
  • 1) Install PyStatsV1
  • 2) Initialize the Workbook
  • 3) Run → Inspect → Check (Chapter 10 example)
  • Next steps
• Windows 11 setup (students)
  • What you need
  • 1) Install Python (3.10+)
  • 2) Install Git Bash
  • 3) Optional: Install make
  • 4) Create a workbook folder + virtual environment
  • 5) Initialize and run the Workbook
  • Keeping PyStatsV1 up to date
  • If something goes wrong
  • Understanding the setup commands (Windows + Git Bash)
  • 1) Create a virtual environment
  • 2) Activate the virtual environment
  • 3) Upgrade pip (inside the environment)
  • 4) Install PyStatsV1 + Workbook dependencies
  • 5) Check your environment
  • 6) Create your workbook starter folder
  • Chapter 11 note (Windows + Git Bash): missing helper file + PYTHONPATH
  • How to do the Study Habits Case Study Pack (TA instructions)
  • Quick checklist (use this for every chapter)
  • Where did my outputs go?
  • Study Habits case study: what to write down
  • “My Own Data” mini-guide (TA instructions)
  • Try “My Own Data” with Notepad (copy/paste example + expected results)
• Workflow: Run → Inspect → Check
  • Run
  • Inspect
  • Check
  • Next: Try your own data
  • Optional: Make targets (if you already have make)
• Study Habits Case Study Pack
  • The story
  • What you get
  • Run → Inspect → Check
  • How this becomes a mini-course
• Case Study Pack: Intro Stats
  • The story
  • What you get
  • Read the mini-textbook pages (recommended)
  • Run → Inspect → Check
  • Inspect your outputs
  • Then (optional) write up your interpretation
  • What you should see
  • Notes
• My Own Data: a mini-guide
  • 1) Put your data in the template
  • 2) Run the scaffold script
  • 3) Inspect what was created
  • 4) Check (tests)
  • 5) Customize for your dataset
• Troubleshooting
  • “pystatsv1” is not recognized / command not found
  • Pytest not installed
  • I ran a script but don’t see anything
  • Windows PowerShell activation blocked
• Track C: Psychology / Education
  • Available chapters
  • Run a chapter (example)
  • Check your work (example)
• Track D Student Edition (Workbook Landing)
  • Where to start (PyPI-only)
  • Helpful pages in the Workbook docs
  • What you are building (the pipeline)
  • Why Track D makes you a better analyst
  • Skill map (D00–D23)
  • How to use Track D week-to-week
  • Common “student mistakes” and what to do
  • What “good” looks like by the end
  • Next page
• Track D chapter index (PyPI)
  • D00PEEKDATA — peek at the (canonical) datasets.
  • D00SETUPDATA — (re)generate the synthetic datasets.
  • D01 — Accounting as a measurement system.
  • D02 — Double-entry and the general ledger as a database.
  • D03 — Financial statements as summary statistics.
  • D04 — Assets: inventory, fixed assets, depreciation (and leases, conceptual).
  • D05 — Liabilities, payroll, taxes, and equity: obligations and structure.
  • D06 — Reconciliations as quality control.
  • D07 — Preparing accounting data for analysis.
  • D08 — Descriptive statistics for financial performance.
  • D09 — Plotting/reporting style contract + example outputs.
  • D10 — Probability and Risk in Business Terms.
  • D11 — Sampling and Estimation (Audit and Controls Lens).
  • D12 — Hypothesis Testing for Decisions (Practical, Not Math-Heavy).
  • D13 — Correlation, Causation, and Controlled Comparisons (NSO running case).
  • D14 — Regression Driver Analysis (NSO).
  • D15 — Forecasting foundations (NSO).
  • D16 — Seasonality and baseline forecasts (NSO).
  • D17 — Revenue forecasting via segmentation + drivers (NSO v1).
  • D18 — Expense forecasting (NSO running case).
  • D19 — Cash flow forecasting (direct method, 13-week).
  • D20 — Integrated forecasting (P&L + balance sheet + cash tie-out).
  • D21 — scenario planning, sensitivity, and stress testing.
  • D22 — Financial statement analysis toolkit.
  • D23 — Communicating results (memos, dashboards, governance).
• Track D Workbook: Business Statistics for Accounting Data
  • Start here (students)
  • What you get
  • Quickstart (PyPI-only)
  • What data you are working with
  • Resetting (or regenerating) the datasets
  • Where your results go
  • How Track D helps you become a better accounting-data analyst
  • Suggested workflow by week
  • Troubleshooting
• Track D Dataset Map
  • Where the datasets live
  • Two dataset families
  • Two dataset families
  • LedgerLab (Ch01): COA → GL → TB → Statements
  • NSO v1 running case
  • Keys and joins cheat sheet
  • Intentional QC issues (the “warts”)
  • How to use this map in a lab
• Track D Outputs Guide
  • Why outputs matter
  • Where outputs go
  • What kinds of files you get
  • The Track D output folder layout
  • Interpreting the console output
  • Fast workflow: from outputs to a write-up
  • Optional: changing the output location
  • Common gotchas
  • Appendix: reading a JSON summary in Python
• Track D: Apply what you learned to your data
  • Two paths
  • Setup once (recommended)
  • Path A: exports only (bank + invoices/bills)
  • Path B: GL export (journal / general ledger detail)
  • Common pitfalls (and what to do)
  • Template header pack (copy/paste)
  • Next steps
• Track D BYOD: Bring Your Own Data
  • What “BYOD” means in Track D
  • Quick start (template)
  • PyPI-only setup (no Git required)
  • Next: choose a tutorial
  • Where this fits in the workbook
• Track D BYOD with GnuCash (core_gl profile)
  • What you’ll do
  • Downloads (demo pack)
  • Step 1 — Create a tiny GnuCash book
  • Step 2 — Enter the demo transactions
  • Step 3 — Export from GnuCash (complex layout)
  • Step 4 — Initialize a Track D BYOD project
  • Step 5 — Point the project at the GnuCash adapter
  • Step 6 — Place your export in the expected location
  • Step 7 — Normalize
  • Step 8 — Validate the normalized tables
  • Step 9 — Do a first analysis
  • Troubleshooting
• GnuCash demo: daily totals + first analysis
  • What we’ll build
  • Download (prebuilt)
  • Option A — Build daily totals from your normalized tables
  • Option B — Quick first analysis (no repo clone required)
• Track D assignments: labs + rubric (TA)
  • Prerequisites (students)
  • Submission format
  • Lab 1 — Run + interpret outputs
  • Lab 2 — QC detective: duplicate bank transaction IDs
  • Lab 3 — Executive summary memo
  • Rubric (100 points)
  • Extensions (optional)
• Track D Lab 0/1 (PyPI-only)
  • TA Notes + Script for Explaining the Lab and the Outputs
  • Recommended pre-reading (TA)
  • How to use the assignments page
• 1. Learning goals
  • TA framing line
• 2. Lab structure
• 3. Environment setup talk track
  • 3.1 Why virtual environments matter (30 seconds)
  • 3.2 Commands
  • What students should notice
• 4. Initialize the Track D workbook
  • 4.1 What init does
  • 4.2 Why seed=123 matters
• 5. List the available Track D runs
  • Explain the list
• 6. Run d00_peek_data (data tour)
  • 6.1 What d00_peek_data is doing
  • 6.2 Two datasets: LedgerLab vs NSO
  • 6.3 Key columns to explain
• 7. Run d01 (Chapter 1 checks + key metrics)
  • 7.1 Checks (what they mean)
  • 7.2 Key metrics (how to interpret)
• 8. Outputs (what to open)
• 9. Run the smoke tests (business_smoke)
  • Explain plainly
• 10. Common issues and quick fixes
  • Command not found
  • Wrong folder
  • Reset everything
  • Confusion about negative income
• 11. Discussion prompts (if time)
• 12. Closing script (30 seconds)
• Track D Lab + TA Notes (PyPI-only)
• Appendix A: Command block (TA slide)