Python for Data Science — Datasets
====================================================
Book 4 of the Data Science Foundations Series

This folder contains the datasets used throughout this book, exported as
plain CSV files.

SYNTHETIC / ILLUSTRATIVE DATASETS (used directly in the book's own examples):
- employees.csv     — small illustrative dataset used in early pandas/CSV
                       chapters (Chapter 10, Chapter 13)
- retail_sales.csv  — Chapter 16's final end-to-end mini-project dataset
                       (500 transactions). Deliberately "messy" on purpose:
                       contains missing values in product_category and
                       unit_price, and inconsistent text casing/spacing in
                       store_region (e.g. "West", "  West  ", "WEST", "west"
                       all appear) — exactly the realistic data-cleaning
                       challenge the chapter is built around. Clean this
                       column yourself (e.g. .str.strip().str.title()) as
                       the chapter's own cleaning stage demonstrates.

REAL DATASETS (built into scikit-learn, exported here as CSV, used in
various earlier chapters for pandas/NumPy practice):
- iris.csv           — sklearn.datasets.load_iris() (150 rows)
- wine.csv           — sklearn.datasets.load_wine() (178 rows)
- diabetes.csv       — sklearn.datasets.load_diabetes() (442 rows)
- breast_cancer.csv  — sklearn.datasets.load_breast_cancer() (569 rows)

More info and the latest version of this collection: www.waskeypress.com
