ml_dataloader_filters_vectors.py File Reference

Detailed Description

 
##################################################
# This tutorial shows the usage of filters and vectors
# when using the ROOT ML dataloader
##################################################
 
import ROOT
 
tree_name = "test_tree"
file_name = ROOT.gROOT.GetTutorialDir().Data() + "/machine_learning/ml_dataloader_filters_vectors_hvector.root"
 
chunk_size = 50  # Defines the size of the chunks
batch_size = 5  # Defines the size of the returned batches
block_size = 10  # Defines the size of the blocks that builds up a chunk
 
rdataframe = ROOT.RDataFrame(tree_name, file_name)
 
# Define filters, filters must be named
filteredrdf = (
    rdataframe.Filter("f1 > 30", "first_filter").Filter("f2 < 70", "second_filter").Filter("f3==true", "third_filter")
)
 
max_vec_sizes = {"f4": 3, "f5": 2, "f6": 1}
 
ds_train, ds_validation = ROOT.Experimental.ML.CreateNumPyGenerators(
    filteredrdf,
    batch_size,
    chunk_size,
    block_size,
    validation_split=0.3,
    max_vec_sizes=max_vec_sizes,
    shuffle=False,
)
 
print(f"Columns: {ds_train.columns}")
 
for i, b in enumerate(ds_train):
    print(f"Training batch {i} => {b.shape}")
 
for i, b in enumerate(ds_validation):
    print(f"Validation batch {i} => {b.shape}")

Columns: ['f1', 'f2', 'f3', 'f4_0', 'f4_1', 'f4_2', 'f5_0', 'f5_1', 'f6_0']
Training batch 0 => (5, 9)
Training batch 1 => (5, 9)
Validation batch 0 => (5, 9)

Author

Dante Niewenhuis

Definition in file ml_dataloader_filters_vectors.py.