README.md

<!-- Prepared by Molla Samser (RSK World) | hello@rskworld.in | support@rskworld.in | +91 93305 39277 | Nutanhat, Mongolkote, Purba Burdwan, West Bengal, India 713147 | https://rskworld.in -->

# Sales Forecasting Dataset

Complete sales dataset with historical sales data, product information, and time-based features for forecasting and trend analysis.

## What’s Inside
- Historical sales records with product and customer context
- Time-based features (seasonality, Fourier terms, lags 7/14/28, rolling 4w/12w)
- Price and inventory signals (price deltas, coverage days, promo flag)
- Beginner-friendly Pandas workflow and preprocessing script
- Sample CSV to illustrate expected schema

## Project Metadata
- ID: 2
- Category: Tabular Data
- Difficulty: Beginner
- Technologies: CSV, SQL, Pandas, Time Series
- Source link: `./sales-forecasting/sales-forecasting.zip`
- Demo link: `./sales-forecasting/`

## Structure
- `metadata.json` — canonical project metadata.
- `data/sample_sales.csv` — sample rows showing expected schema.
- `docs/dataset_description.md` — dataset fields, targets, usage notes.
- `scripts/preprocess.py` — loads CSV, builds time features, trains baseline model.
- `notebooks/analysis_plan.md` — suggested notebook flow for exploration/forecasting.

## Quick Start
1) Install deps: `pip install pandas scikit-learn matplotlib`
2) Run preprocessing: `python scripts/preprocess.py --input data/sample_sales.csv --output data/processed_sales.csv`
3) Open the planned steps in `notebooks/analysis_plan.md` and adapt in a notebook.

## Notes
- Replace `data/sample_sales.csv` with your full dataset, then re-run preprocessing.
- Add your generated assets (`sales-forecasting.png`, `sales-forecasting.zip`) to match metadata links.
- Extend features easily in `scripts/preprocess.py` (e.g., holiday flags, promo depth, price elasticity).

## License
- MIT License — see `LICENSE`.