Logo ROOT  

Reference Guide
 
Loading...
Searching...
No Matches
Namespaces
RBatchGenerator_NumPy.py File Reference
Tutorials » Machine Learning tutorials

Detailed Description

View in nbviewer Open in SWAN
Example of getting batches of events from a ROOT dataset as Python generators of numpy arrays.

import ROOT
tree_name = "sig_tree"
file_name = str(ROOT.gROOT.GetTutorialDir()) + "/machine_learning/data/Higgs_data.root"
batch_size = 128
chunk_size = 5000
block_size = 400
rdataframe = ROOT.RDataFrame(tree_name, file_name)
target = "Type"
num_of_epochs = 2
gen_train, gen_validation = ROOT.TMVA.Experimental.CreateNumPyGenerators(
rdataframe,
batch_size,
chunk_size,
block_size,
target = target,
validation_split = 0.3,
shuffle = True,
drop_remainder = True
)
for i in range(num_of_epochs):
# Loop through training set
for i, (x_train, y_train) in enumerate(gen_train):
print(f"Training batch {i + 1} => x: {x_train.shape}, y: {y_train.shape}")
# Loop through Validation set
for i, (x_validation, y_validation) in enumerate(gen_validation):
print(f"Validation batch {i + 1} => x: {x_validation.shape}, y: {y_validation.shape}")
TRangeDynCast
ROOT::Detail::TRangeCast< T, true > TRangeDynCast
TRangeDynCast is an adapter class that allows the typed iteration through a TCollection.
Definition TCollection.h:358
ROOT::RDataFrame
ROOT's RDataFrame offers a modern, high-level interface for analysis of data stored in TTree ,...
Definition RDataFrame.hxx:44
Training batch 1 => x: (128, 28), y: (128, 1)
Training batch 2 => x: (128, 28), y: (128, 1)
Training batch 3 => x: (128, 28), y: (128, 1)
Training batch 4 => x: (128, 28), y: (128, 1)
Training batch 5 => x: (128, 28), y: (128, 1)
Training batch 6 => x: (128, 28), y: (128, 1)
Training batch 7 => x: (128, 28), y: (128, 1)
Training batch 8 => x: (128, 28), y: (128, 1)
Training batch 9 => x: (128, 28), y: (128, 1)
Training batch 10 => x: (128, 28), y: (128, 1)
Training batch 11 => x: (128, 28), y: (128, 1)
Training batch 12 => x: (128, 28), y: (128, 1)
Training batch 13 => x: (128, 28), y: (128, 1)
Training batch 14 => x: (128, 28), y: (128, 1)
Training batch 15 => x: (128, 28), y: (128, 1)
Training batch 16 => x: (128, 28), y: (128, 1)
Training batch 17 => x: (128, 28), y: (128, 1)
Training batch 18 => x: (128, 28), y: (128, 1)
Training batch 19 => x: (128, 28), y: (128, 1)
Training batch 20 => x: (128, 28), y: (128, 1)
Training batch 21 => x: (128, 28), y: (128, 1)
Training batch 22 => x: (128, 28), y: (128, 1)
Training batch 23 => x: (128, 28), y: (128, 1)
Training batch 24 => x: (128, 28), y: (128, 1)
Training batch 25 => x: (128, 28), y: (128, 1)
Training batch 26 => x: (128, 28), y: (128, 1)
Training batch 27 => x: (128, 28), y: (128, 1)
Training batch 28 => x: (128, 28), y: (128, 1)
Training batch 29 => x: (128, 28), y: (128, 1)
Training batch 30 => x: (128, 28), y: (128, 1)
Training batch 31 => x: (128, 28), y: (128, 1)
Training batch 32 => x: (128, 28), y: (128, 1)
Training batch 33 => x: (128, 28), y: (128, 1)
Training batch 34 => x: (128, 28), y: (128, 1)
Training batch 35 => x: (128, 28), y: (128, 1)
Training batch 36 => x: (128, 28), y: (128, 1)
Training batch 37 => x: (128, 28), y: (128, 1)
Training batch 38 => x: (128, 28), y: (128, 1)
Training batch 39 => x: (128, 28), y: (128, 1)
Training batch 40 => x: (128, 28), y: (128, 1)
Training batch 41 => x: (128, 28), y: (128, 1)
Training batch 42 => x: (128, 28), y: (128, 1)
Training batch 43 => x: (128, 28), y: (128, 1)
Training batch 44 => x: (128, 28), y: (128, 1)
Training batch 45 => x: (128, 28), y: (128, 1)
Training batch 46 => x: (128, 28), y: (128, 1)
Training batch 47 => x: (128, 28), y: (128, 1)
Training batch 48 => x: (128, 28), y: (128, 1)
Training batch 49 => x: (128, 28), y: (128, 1)
Training batch 50 => x: (128, 28), y: (128, 1)
Training batch 51 => x: (128, 28), y: (128, 1)
Training batch 52 => x: (128, 28), y: (128, 1)
Training batch 53 => x: (128, 28), y: (128, 1)
Training batch 54 => x: (128, 28), y: (128, 1)
Validation batch 1 => x: (128, 28), y: (128, 1)
Validation batch 2 => x: (128, 28), y: (128, 1)
Validation batch 3 => x: (128, 28), y: (128, 1)
Validation batch 4 => x: (128, 28), y: (128, 1)
Validation batch 5 => x: (128, 28), y: (128, 1)
Validation batch 6 => x: (128, 28), y: (128, 1)
Validation batch 7 => x: (128, 28), y: (128, 1)
Validation batch 8 => x: (128, 28), y: (128, 1)
Validation batch 9 => x: (128, 28), y: (128, 1)
Validation batch 10 => x: (128, 28), y: (128, 1)
Validation batch 11 => x: (128, 28), y: (128, 1)
Validation batch 12 => x: (128, 28), y: (128, 1)
Validation batch 13 => x: (128, 28), y: (128, 1)
Validation batch 14 => x: (128, 28), y: (128, 1)
Validation batch 15 => x: (128, 28), y: (128, 1)
Validation batch 16 => x: (128, 28), y: (128, 1)
Validation batch 17 => x: (128, 28), y: (128, 1)
Validation batch 18 => x: (128, 28), y: (128, 1)
Validation batch 19 => x: (128, 28), y: (128, 1)
Validation batch 20 => x: (128, 28), y: (128, 1)
Validation batch 21 => x: (128, 28), y: (128, 1)
Validation batch 22 => x: (128, 28), y: (128, 1)
Validation batch 23 => x: (128, 28), y: (128, 1)
Training batch 1 => x: (128, 28), y: (128, 1)
Training batch 2 => x: (128, 28), y: (128, 1)
Training batch 3 => x: (128, 28), y: (128, 1)
Training batch 4 => x: (128, 28), y: (128, 1)
Training batch 5 => x: (128, 28), y: (128, 1)
Training batch 6 => x: (128, 28), y: (128, 1)
Training batch 7 => x: (128, 28), y: (128, 1)
Training batch 8 => x: (128, 28), y: (128, 1)
Training batch 9 => x: (128, 28), y: (128, 1)
Training batch 10 => x: (128, 28), y: (128, 1)
Training batch 11 => x: (128, 28), y: (128, 1)
Training batch 12 => x: (128, 28), y: (128, 1)
Training batch 13 => x: (128, 28), y: (128, 1)
Training batch 14 => x: (128, 28), y: (128, 1)
Training batch 15 => x: (128, 28), y: (128, 1)
Training batch 16 => x: (128, 28), y: (128, 1)
Training batch 17 => x: (128, 28), y: (128, 1)
Training batch 18 => x: (128, 28), y: (128, 1)
Training batch 19 => x: (128, 28), y: (128, 1)
Training batch 20 => x: (128, 28), y: (128, 1)
Training batch 21 => x: (128, 28), y: (128, 1)
Training batch 22 => x: (128, 28), y: (128, 1)
Training batch 23 => x: (128, 28), y: (128, 1)
Training batch 24 => x: (128, 28), y: (128, 1)
Training batch 25 => x: (128, 28), y: (128, 1)
Training batch 26 => x: (128, 28), y: (128, 1)
Training batch 27 => x: (128, 28), y: (128, 1)
Training batch 28 => x: (128, 28), y: (128, 1)
Training batch 29 => x: (128, 28), y: (128, 1)
Training batch 30 => x: (128, 28), y: (128, 1)
Training batch 31 => x: (128, 28), y: (128, 1)
Training batch 32 => x: (128, 28), y: (128, 1)
Training batch 33 => x: (128, 28), y: (128, 1)
Training batch 34 => x: (128, 28), y: (128, 1)
Training batch 35 => x: (128, 28), y: (128, 1)
Training batch 36 => x: (128, 28), y: (128, 1)
Training batch 37 => x: (128, 28), y: (128, 1)
Training batch 38 => x: (128, 28), y: (128, 1)
Training batch 39 => x: (128, 28), y: (128, 1)
Training batch 40 => x: (128, 28), y: (128, 1)
Training batch 41 => x: (128, 28), y: (128, 1)
Training batch 42 => x: (128, 28), y: (128, 1)
Training batch 43 => x: (128, 28), y: (128, 1)
Training batch 44 => x: (128, 28), y: (128, 1)
Training batch 45 => x: (128, 28), y: (128, 1)
Training batch 46 => x: (128, 28), y: (128, 1)
Training batch 47 => x: (128, 28), y: (128, 1)
Training batch 48 => x: (128, 28), y: (128, 1)
Training batch 49 => x: (128, 28), y: (128, 1)
Training batch 50 => x: (128, 28), y: (128, 1)
Training batch 51 => x: (128, 28), y: (128, 1)
Training batch 52 => x: (128, 28), y: (128, 1)
Training batch 53 => x: (128, 28), y: (128, 1)
Training batch 54 => x: (128, 28), y: (128, 1)
Validation batch 1 => x: (128, 28), y: (128, 1)
Validation batch 2 => x: (128, 28), y: (128, 1)
Validation batch 3 => x: (128, 28), y: (128, 1)
Validation batch 4 => x: (128, 28), y: (128, 1)
Validation batch 5 => x: (128, 28), y: (128, 1)
Validation batch 6 => x: (128, 28), y: (128, 1)
Validation batch 7 => x: (128, 28), y: (128, 1)
Validation batch 8 => x: (128, 28), y: (128, 1)
Validation batch 9 => x: (128, 28), y: (128, 1)
Validation batch 10 => x: (128, 28), y: (128, 1)
Validation batch 11 => x: (128, 28), y: (128, 1)
Validation batch 12 => x: (128, 28), y: (128, 1)
Validation batch 13 => x: (128, 28), y: (128, 1)
Validation batch 14 => x: (128, 28), y: (128, 1)
Validation batch 15 => x: (128, 28), y: (128, 1)
Validation batch 16 => x: (128, 28), y: (128, 1)
Validation batch 17 => x: (128, 28), y: (128, 1)
Validation batch 18 => x: (128, 28), y: (128, 1)
Validation batch 19 => x: (128, 28), y: (128, 1)
Validation batch 20 => x: (128, 28), y: (128, 1)
Validation batch 21 => x: (128, 28), y: (128, 1)
Validation batch 22 => x: (128, 28), y: (128, 1)
Validation batch 23 => x: (128, 28), y: (128, 1)
Author
Dante Niewenhuis

Definition in file RBatchGenerator_NumPy.py.