# Observing Dark Worlds — Data

来源：https://www.kaggle.com/competitions/DarkWorlds/data

采集时间：2026-10-19T18:57:57Z

Training Data
The training data consists of 300 simulated skies similar to the final panel in Figure 2 of the
[description page](https://www.kaggle.com/c/DarkWorlds)
. Each sky contains between 300 and 740 galaxies. Each galaxy will have an x and y position ranging from 0 to 4200 (units are pixels), and a measure of ellipticity: e1 and e2 (see
[An Introduction to Ellipticity](https://www.kaggle.com/c/DarkWorlds/details/an-introduction-to-ellipticity)
).
Training galaxy data is provided in a series of 300 files, one file for each Sky (e.g, Training_Sky27.csv or Training_Sky123.csv). These files have 4 columns:
galaxy id
x-coordinate
y-coordinate
e1
e2
Dark matter halo locations in each sky are provided in the file
Training_halos.csv
. This file contains 10 columns, namely:
Sky Id
number of halos (1, 2 or 3)
reference x-coordinate (used for evalulation metric)
reference y-coordinate (used for evalulation metric)
x-coordinate halo 1
y-coordinate halo 1
x-coordinate halo 2
y-coordinate halo 2
x-coordinate halo 3
y-coordinate halo 3
In the case of only two or one halo present there will be zeros in the column.
Test Data
The test data is in a similar format to the training data. There are 120 simulated skies (see final panel in Figure 2 of the
[description](https://www.kaggle.com/competitions/wizard/(may%20or%20may%20not%20be%20present))
). Each sky contains 300 to 740 galaxies. Each galaxy will have an x and y position ranging from 0 to 4200, e1 and e2 values (totalling 4 columns per galaxy in the sky).
In each sky there are either 1, 2 or 3 dark matter halos. The halo counts in each sky are provided in the file
Test_haloCounts.csv
.
The challenge is to predict the center of each dark matter halo in each test sky based on the galaxy information provided.