def train(data: utils.URLPath, output: utils.URLPath):
"""Train a new classifier using SOM data."""
groups = GROUPS
tubes = ("1", "2", "3")
balance = {
"CLL": 4000,
"MBL": 2000,
"MCL": 1000,
"PL": 1000,
"LPL": 1000,
"MZL": 1000,
"FL": 1000,
"HCL": 1000,
"normal": 6000,
}
mapping = None
dataset = som_dataset.SOMDataset.from_path(data)
train_dataset, validate_dataset = prepare_classifier_train_dataset(
dataset, groups=groups, mapping=mapping, balance=balance)
config = classifier.SOMClassifierConfig(
**{
"tubes": {tube: dataset.config[tube]
for tube in tubes},
"groups": groups,
"pad_width": 2,
"mapping": mapping,
"cost_matrix": None,
})
model = train_som_classifier(train_dataset, validate_dataset, config)
model.save(output)
model.save_information(output)
def main(args):
dataset = som_dataset.SOMDataset.from_path(args.input)
val = args.val
train = args.train
OUTPUT = args.output
PANEL = args.panel
bal = args.bal
# set the groups according to the panel
if PANEL == "MLL":
groups = GROUPS
elif PANEL == "ERLANGEN":
groups = ["CLL", "MBL", "MCL", "LPL", "MZL", "FL", "HCL", "normal"]
else:
groups = ["CLL", "MCL", "LPL", "MZL", "FL", "HCL", "normal"]
tubes = ("1")
mapping = None
balance = dict((key, bal) for key in groups)
config = classifier.SOMClassifierConfig(
**{
"tubes": {tube: dataset.config[tube]
for tube in tubes},
"groups": groups,
"pad_width": 2,
"mapping": mapping,
"cost_matrix": None,
"train_epochs": 20,
})
val = io_functions.load_json(val)
validate_dataset = dataset.filter(labels=val)
labels = io_functions.load_json(train)
train_dataset = dataset.filter(labels=labels)
train_dataset, validate_dataset = fc_api.prepare_classifier_train_dataset(
train_dataset,
split_ratio=0.9,
groups=groups,
mapping=mapping,
balance=balance,
val_dataset=validate_dataset)
print(train_dataset.group_count)
print(validate_dataset.group_count)
model = fc_api.train_som_classifier(train_dataset, validate_dataset,
config)
model.save(OUTPUT)
model.save_information(OUTPUT)
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
#tubes = ("1", "2")
mapping = None
dataset = som_dataset.SOMDataset.from_path(SOM_DATASET)
train_dataset, validate_dataset = fc_api.prepare_classifier_train_dataset(
dataset, split_ratio=0.3, groups=groups, mapping=mapping, balance=None)
labels_dict = train_dataset.group_count
config = classifier.SOMClassifierConfig(
**{
"tubes": {tube: dataset.config[tube]
for tube in tubes},
"groups": groups,
"pad_width": 2,
"mapping": mapping,
"cost_matrix": None,
})
class_weight = create_class_weight(labels_dict)
#class_weight = utils.classification_utils.calculate_group_weights(labels_dict)
class_weight = {i: class_weight.get(g, 1.0) for i, g in enumerate(groups)}
print(class_weight)
model = fc_api.train_som_classifier(train_dataset,
validate_dataset,
config,
class_weights=class_weight)
model.save(OUTPUT)
model.save_information(OUTPUT)
from flowcat.classifier import som_dataset
from flowcat.classifier.models import create_model_multi_input
#MARKERS = io_functions.load_json(utils.URLPath("/data/flowcat-data/2020-04_merged_train/MLL9F/markers.json"))
SOM_DATASET = utils.URLPath("/data/flowcat-data/2020-04_merged_train/MLL9F")
OUTPUT = utils.URLPath("/data/flowcat-data/2020-04_merged_train/MLL9F/Exp1")
LOGGER = utils.logs.setup_logging(None, "classify")
groups = ["MCL", "PL", "LPL", "MZL", "FL", "HCL"]
tubes = ("1")
mapping = None
dataset = som_dataset.SOMDataset.from_path(SOM_DATASET)
train_dataset, validate_dataset = fc_api.prepare_classifier_train_dataset(
dataset, split_ratio=0.9, groups=groups, mapping=mapping, balance=None)
config = classifier.SOMClassifierConfig(
**{
"tubes": {tube: dataset.config[tube]
for tube in tubes},
"groups": groups,
"pad_width": 2,
"mapping": mapping,
"cost_matrix": None,
})
model = fc_api.train_som_classifier(train_dataset, validate_dataset, config)
model.save(OUTPUT)
model.save_information(OUTPUT)
