# 091. Recorded fire seasonality

**Question:** Which months contain the most fire records and recorded burned area?

## Result

The largest computed metric is 184 for aug; the smallest is 1 for nov. Metric: records (Recorded observations).

The denominator is not days or land area at risk. More records do not alone establish a higher ignition probability.

![Recorded fire seasonality](outputs/chart.png)

| month | records | recorded_hectares | median_hectares |
| --- | --- | --- | --- |
| apr | 9 | 80.02 | 0 |
| aug | 184 | 2,298 | 0.545 |
| dec | 9 | 120 | 10.73 |
| feb | 20 | 125.5 | 0.55 |
| jan | 2 | 0 | 0 |
| jul | 32 | 459.8 | 1.035 |
| jun | 17 | 99.3 | 0 |
| mar | 54 | 235.3 | 0 |
| may | 2 | 38.48 | 19.24 |
| nov | 1 | 0 | 0 |
| oct | 15 | 99.57 | 0 |
| sep | 172 | 3,086 | 1.36 |

The chart shows 12 of 12 result rows; the table previews the first 12 in the analysis-defined order. [Download the full result table](outputs/results.csv). Numerical values are computed from the source; missing results stay unavailable.

## Method

Monthly counts, area totals and medians among the supplied fire observations.

The study uses shared source preparation and reusable statistical routines. Its specific transformations are in [analysis.py](analysis.py), and common model/evaluation code is in [portfolio/methods.py](../../portfolio/methods.py). The [notebook](analysis.ipynb) executes the study and displays the saved results.

## Decision and limitations

Use exposure and incident definitions before interpreting seasonal risk.

The sample consists of recorded fire observations, not all places and times at risk. Zero recorded area is not evidence of no ignition. No precise dates or event identifiers are supplied. This is not an emergency forecasting system. 

Related studies may share observations or holdouts. These are focused analytical studies, not independent replications or deployed business systems. Any model refinements informed by these results need new untouched evaluation data. No commercial impact is inferred from an association or backtest.

## Reproduce

From the repository root, after installing `requirements.txt`:

```powershell
python projects/091-recorded-fire-seasonality/analysis.py
```

Source data are downloaded automatically if absent. Original archives are retained unchanged and checked by SHA-256. The cleaned cache normalizes column names; field-specific changes are visible in [data preparation](../../portfolio/data.py). Runtime evidence is in [receipt.json](outputs/receipt.json).

## Source

[Forest Fires](https://archive.ics.uci.edu/dataset/162/forest+fires), Cortez and Morais (2007). [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/). Source data are transformed and aggregated in this study. [Source provenance](../../data/provenance/fires.json) and [prepared-data audit](../../data/provenance/fires_prepared.json) record the downloaded files, field coverage and hashes.