# PLAsTiCC Astronomical Classification — Data

来源：https://www.kaggle.com/competitions/PLAsTiCC-2018/data

采集时间：2026-10-24T02:05:41Z

### File Descriptions
- `data_note`: Start here for a more extensive context than we can provide in this space. You'll get helpful background on both this dataset and the relevant astronomy. This is also available on [arxiv.org][1]. We've also posted kernels with additional [context about the relevant astronomy][2] and [the approaches astronomers have taken in the past][3].
- `[training/test]_set_metadata`: Information about objects in the that doesn't change over time, like the coordinates of the object.
- `[training/test]_set`: Time series of observations of the objects. Maps to the metadata via `object_id`.
- `test_set_sample`: The first million rows of the test set.
- `sample_submission`: A valid submission file. You can submit probabilities of precision float64, but we highly recommend sticking to float16 for your initial iterations to minimize upload time.

### Metadata File Column Descriptions
- `object_id`: unique object identifier. Int32
- `ra`: right ascension, sky coordinate: co-longitude in degrees. Float32
- `decl`: declination, sky coordinate: co-latitude in degrees. Float32
- `gal_l`: galactic longitude in degrees. Float32
- `gal_b`: galactic latitude in degrees. Float32
- `ddf`: A flag to identify the object as coming from the DDF survey
area (with value DDF = 1 for the DDF, DDF = 0 for the WFD survey). Note that while the DDF fields are
contained within the full WFD survey area, the DDF fluxes have significantly smaller
uncertainties. Boolean
- `hostgal_specz`: the spectroscopic redshift of the source. This is an extremely accurate
measure of redshift, available for the training set and a small fraction of the
test set. Float32
- `hostgal_photoz`: The photometric redshift of the host galaxy of the astronomical
source. While this is meant to be a proxy for hostgal_specz, there can be large
differences between the two and should be regarded as a far less accurate version
of hostgal_specz. Float32
- `hostgal_photoz_err`: The uncertainty on the hostgal_photoz based on LSST survey
projections. Float32
- `distmod`: The distance to the source calculated from hostgal_photoz
 and using general relativity. Float32
- `mwebv`:  MW E(B-V). this ‘extinction’ of light is a property of the Milky Way (MW)
dust along the line of sight to the astronomical source, and is thus a function of
the sky coordinates of the source ra, decl. This is used to determine a passband
dependent dimming and redenning of light from astronomical sources as described
in subsection 2.1, and based on the [Schlafly et al. (2011)](http://adsabs.harvard.edu/abs/2011ApJ...737..103S) and [Schlegel et al. (1998)](http://adsabs.harvard.edu/abs/1998ApJ...500..525S) dust models. Float32
- `target`: The class of the astronomical source. This is provided in
the training data. Correctly determining the target (correctly assigning classification
probabilities to the objects) is the ‘goal’ of the classification challenge for the test
data. Note that there is one class in the test set that does not occur in the training set: `class_99`
serves as an "other" class for objects that don't belong in any of the 14 classes in the training set. Int8

### Data File Column Descriptions
- `object_id`: Foreign key with the metadata. Int32
- `mjd`: the time in Modified Julian Date (MJD) of the observation. Can be read as days since November 17, 1858. Can be converted to
Unix epoch time with the formula `unix_time = (MJD−40587)×86400`. Float64
- `passband`: The specific LSST passband integer, such that u, g, r, i, z, Y =
0, 1, 2, 3, 4, 5 in which it was viewed. Int8
- `flux`: the measured flux (brightness) in the passband of observation as listed in the
passband column. These values have already been corrected for dust extinction (mwebv), though heavily
extincted objects will have larger uncertainties (`flux_err`) in spite of the correction. Float32
- `flux_err`: the uncertainty on the measurement of the flux listed above. Float32
- `detected`: If 1, the object's brightness is significantly different at the 3-sigma level relative to the reference template.
Only objects with at least 2 detections are included in the dataset. Boolean

### Caveats
A few caveats about the light-curve data are as follows:

- Data gaps: Different passbands are taken at different times, sometimes many days
apart.
- Galactic vs extragalactic: The given redshift for objects in our own galaxy is given
as zero.
- Negative Flux: Due to statistical fluctuations (of e.g. the sky brightness) and the
way the brightness is estimated, the flux may be negative for dim sources, where
the true flux is close to zero. Second, if the pre-survey image actually contains a
flux brighter than its true ‘zero’, this can lead to a negative flux when the difference is
computed.


  [1]: https://arxiv.org/abs/1810.00001
  [2]: https://www.kaggle.com/michaelapers/the-plasticc-astronomy-starter-kit
  [3]: https://www.kaggle.com/michaelapers/the-plasticc-astronomy-classification-demo