# Miniproject #1 2021 — Data

来源：https://www.kaggle.com/competitions/caltech-cs-155-2021-mp1-part-1/data

采集时间：2026-10-19T15:36:53Z

## File descriptions
* WILDFIRE_TRAIN.csv - the training set, including labels
* WILDFIRE_TEST.csv - the test set, excluding labels
* WIDFIRE_SAMPLE_SUBMISSION.csv - a sample submission file in the correct format.  There should be 5 columns: an ID column, and four columns (P1, P2, P3, P4). For example, for row **i**, columns P2 will contain the probability of sample **i** being from class 2. The four columns should sum up to 1 for each row.

## Data Fields

* `LATITUDE` = Latitude (NAD83) for point location of the fire (decimal degrees).
* `LONGITUDE` = Longitude (NAD83) for point location of the fire (decimal degrees).
* `STATE` = Two-letter alphabetic code for the state in which the fire burned (or originated), based on the nominal designation in the fire report.
* `DISCOVERY_TIME` = Time of day that the fire was discovered or confirmed to exist.
* `FIRE_SIZE` = Estimate of acres within the final perimeter of the fire.
* `FIPS_NAME` = County name from the FIPS publication 6-4 for representation of counties and equivalent entities.
* `FIPS_CODE` = Three-digit code from the Federal Information Process Standards (FIPS) publication 6-4 for representation of counties and equivalent entities.
* `SOURCE_REPORTING_UNIT_NAME` = Name of reporting agency unit preparing the fire report, based on code/name in the source dataset.
* `DATE` = Date that the fire was first discovered, in YYYY-MM-DD format
* `LABEL` = Description of the (statistical) cause of the fire.
    * `1` = Natural cause (Lightning)
    * `2` = Accidental cause (in order of decreasing frequency: Debris Burning, Equipment Use, Children, Campfire, Smoking, Railroad, Powerline, Fireworks, Structure)
    * `3` = Malicious cause (Arson)
    * `4` = Other (Miscellaneous, or Missing/Undefined)

## Task
Your task is to predict the target in `WILDFIRES_TEST.csv` to the best of your ability. It is generally encouraged to submit probabilities from your models instead of 0/1 predictions, as you get rewarded for having a non-zero probability of the correct class even if it is not the highest probability for that sample. This also represents real world conditions, where you would like to know the relative likelihoods of each class being the right one.