# 1000 Genomes Ancestry — Data

来源：https://www.kaggle.com/competitions/1000-genomes-ancestry/data

采集时间：2026-10-20T02:00:11Z

The majority of the columns in the data represent alleles -- pairs of letters that identify the nucleotides at that position in an individual's genome. The alleles can be any two-letter permutation of letters A,T,C,G. The "rs*" identifier in the column name is an identifier that can be used to find more information about the allele variation at that location in the genome. The data from this competition was collected using the [ezancestry](https://github.com/arvkevi/ezancestry) Python library.

There is also a gender field included in these data.

There are 55 AISNPs in `kidd_train.csv` and 128 AISNPs in `seldin_train.csv`. Both files have the same individuals.

The test dataset has missing data for some of the AISNPs.

You are predicting the superpopulation column.

## Files

*   **kidd_train.csv** - the training set with Kidd AISNPs
*   **seldin_train.csv** - the training set with Seldin AISNPs
*   **kidd_test.csv** - the test set with Kidd AISNPs
*   **seldin_test.csv** - the test set with Seldin AISNPs
*   **sample_submission.csv** - a sample submission file in the correct format

## Columns

*   `id` - A unique identifier for each individual in the 1000 Genomes Project.
*   `rs*` - The alleles for each AISNP.
*   `gender` - The reported gender of the individual in the 1000 Genomes Project.
*   `superpopulation` - The reported superpopulation of the individual in the 1000 Genomes Project.

superpopulation codes:
AFR: Africa
EAS: East Asia
EUR: Europe
SAS: South Asia
AMR: Americas