A data engineering and statistical analysis project designed to automatically aggregate, clean, and analyze historical climate records from the UK Met Office. The project builds an automated extraction pipeline that dynamically maps, sanitizes, and writes time-series data from 37 historic weather stations into an optimized local SQLite database database for advanced statistical modeling.

🏗️ Repository Structure

uk_historical_weather_met/
│
├── .gitignore               # Prevents tracking of local environments and databases
├── README.md                # Project documentation and notebook instructions
├── requirements.txt         # Project dependencies (Pandas, Scipy, Seaborn, etc.)
│
├── data/                    # Storage for localized data assets
│   └── met_office_weather.db # SQLite Database generated by the ingestion engine
│
├── src/                     # Core data engineering pipeline
│   ├── __init__.py          # Empty file marking directory as an importable package
│   └── ingest_data.py       # Scraper and data cleaning utility
│
└── notebooks/               # Analytical environments for statistical modeling
    ├── 01_data_cleaning_checks.ipynb
    ├── 02_descriptive_stats.ipynb
    └── 03_climate_trend_analysis.ipynb