coolneng
/
locimend
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Create a validation set

This commit is contained in:
coolneng 2021-06-06 00:03:39 +02:00
parent 38903c5737
commit 2920db70b4
Signed by: coolneng
GPG Key ID: 9893DA236405AF57
1 changed files with 13 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
src/preprocessing.py
View File

@ -59,11 +59,15 @@ def create_dataset(data_file, label_file) -> None:
Create a training and test dataset with a 70/30 split respectively
"""
data = read_fastq(data_file, label_file)
train_test_split = 0.7
with TFRecordWriter(TRAIN_DATASET) as train, TFRecordWriter(TEST_DATASET) as test:
train_eval_test_split = [0.8, 0.1, 0.1]
with TFRecordWriter(TRAIN_DATASET) as training, TFRecordWriter(
TEST_DATASET
) as test, TFRecordWriter(EVAL_DATASET) as evaluation:
for element in data:
if random() < train_test_split:
train.write(element)
if random() < train_eval_test_split[0]:
training.write(element)
elif random() < train_eval_test_split[0] + train_eval_test_split[1]:
evaluation.write(element)
else:
test.write(element)
@ -94,8 +98,11 @@ def read_dataset(filepath) -> TFRecordDataset:
return batched_dataset
def dataset_creation(data_file, label_file) -> Tuple[TFRecordDataset, TFRecordDataset]:
def dataset_creation(
data_file, label_file
) -> Tuple[TFRecordDataset, TFRecordDataset, TFRecordDataset]:
create_dataset(data_file, label_file)
train_data = read_dataset(TRAIN_DATASET)
eval_data = read_dataset(EVAL_DATASET)
test_data = read_dataset(TEST_DATASET)
return train_data, test_data
return train_data, eval_data, test_data