def run_transfer(options, train_dataset, validate_dataset):
config = options["config"]
base_model = models.load_model(options["base_model_path"])
tl_model = create_tl_model(base_model, config)
model = SOMClassifier(config, tl_model)
train = model.create_sequence(train_dataset, config.train_batch_size)
if validate_dataset is not None:
validate = model.create_sequence(validate_dataset, config.valid_batch_size)
else:
validate = None
model.train_generator(train, validate, epochs=config.train_epochs, class_weight=None)
output = utils.URLPath(options["output_path"])
if validate:
pred_arr, pred_labels = model.predict_generator(validate)
true_labels = validate.true_labels
pred_df = pd.DataFrame(pred_arr, columns=validate.binarizer.classes_, index=validate.dataset.labels)
io_functions.save_csv(pred_df, output / "preds.csv")
io_functions.save_json({"true": list(true_labels), "pred": list(pred_labels)}, output / "preds_labels.json")
generate_all_metrics(true_labels, pred_labels, config.mapping, output)
model.save(output)
model.save_information(output)
keras.backend.clear_session()
del model
def generate_confusion(true_labels, pred_labels, groups, output):
"""Calculate confusion matrix metrics and also create plots."""
confusion = metrics.confusion_matrix(true_labels, pred_labels, labels=groups)
confusion = pd.DataFrame(confusion, index=groups, columns=groups)
print(confusion)
io_functions.save_csv(confusion, output / "validation_confusion.csv")
plot_confusion.plot_confusion_matrix(
confusion, normalize=False).savefig(str(output / "confusion_abs.png"), dpi=300)
plot_confusion.plot_confusion_matrix(
confusion, normalize=True).savefig(str(output / "confusion_norm.png"), dpi=300)
return confusion
def run_denovo(options, train_dataset, validate_dataset):
config = options["config"]
model = train_som_classifier(train_dataset, validate_dataset, config)
output = utils.URLPath(options["output_path"])
if validate_dataset:
validate = model.create_sequence(validate_dataset, config.valid_batch_size)
pred_arr, pred_labels = model.predict_generator(validate)
true_labels = validate.true_labels
pred_df = pd.DataFrame(pred_arr, columns=validate.binarizer.classes_, index=validate.dataset.labels)
io_functions.save_csv(pred_df, output / "preds.csv")
io_functions.save_json({"true": list(true_labels), "pred": list(pred_labels)}, output / "preds_labels.json")
generate_all_metrics(true_labels, pred_labels, config.mapping, output)
model.save(output)
model.save_information(output)
keras.backend.clear_session()
del model
io_functions.save_som(somsample.data, sompath, save_config=False)
somsample.data = None
somsample.path = sompath
casesamples[case.id].append(somsample)
somcases = []
for case in dataset:
somcases.append(case.copy(samples=casesamples[case.id]))
somcollection = case_dataset.CaseCollection(somcases)
io_functions.save_json(somcollection, output + ".json")
labels = [{"label": case.id, "randnum": 0, "group": case.group} for case in dataset]
# Save metadata into an additional csv file with the same name
metadata = pd.DataFrame(labels)
io_functions.save_csv(metadata, output + ".csv")
io_functions.save_json(
{
tube: {
"dims": m.model.dims,
"channels": m.model.markers,
} for tube, m in model.models.items()
}, output + "_config.json")
def main(args):
"""Load a model with given transforming arguments and transform individual
cases."""
cases = io_functions.load_case_collection(args.data, args.meta)
# cases = cases.sample(1, groups=["CLL", "normal"])
selected_markers = cases.selected_markers
