Parton-Level Cross Section Interpolation
Interpolate the relationship between a (parametrised) underlying distribution of particles and the probability of such an event occurring in a collider.
Hosted by
CERN
Posted
Which is the test file for submission?
Hi,
I followed the instructions in Docs to set it up. I see there are two event files.
- events-validation.hdf5
- events.hdf5
I see both these files have events data with the differential cross-section column having a value. Which file contains the data that needs to be predicted for submission?
I'm using the functions in introduction.ipynb to inspect. This is my code.
print("Train files")
file_train_path = Path("../.aqora/data/data/events.hdf5")
abs_file_train_path = file_train_path.resolve()
print("Inspect file")
inspect_hdf5(abs_file_train_path)
print("Inspect events")
inspect_events_hdf5(abs_file_train_path)
print("Inspect random number")
inspect_random_numbers(abs_file_train_path)
print("\n")
print("Test files")
file_test_path = Path("../.aqora/data/data/events-validation.hdf5")
abs_file_test_path = file_test_path.resolve()
print("Inspect file")
inspect_hdf5(abs_file_test_path)
print("Inspect events")
inspect_events_hdf5(abs_file_test_path)
print("Inspect random number")
inspect_random_numbers(abs_file_test_path)Thank you.
Order by:
Posted by eno •
Hi @jag, the events.hdf5 file is the training data set. The events-validation.hdf5 is data that should not be used for training. It can be used to check how well the trained model predicts unknown points.
Posted by jag •
Hi @eno, the events-validation.hdf5 file is the one that needs to be predicted and submitted as a solution?
Posted by eno •
Yes. With the cross sections predicted by your model, which should only be trained using events.hdf5.
Posted by jag •
Thank you.
Posted by jag •
@eno One small question, in the task description, it is stated
- randomNumbers, the parametrised phase space points (differing in dimensionality with n).
But, I checked that all the rows of randomNumbers have 5 columns. Am I missing something?
Posted by eno •
Initially the idea was to provide data for different final-state particle multiplicities. In that case, each file would have a different n (but it would be constant in each data file). So the statement about the differing dimensionality is a bit misleading, given that you are in the final form of the project only provided a single file for a single multiplicity. Sorry about that.