def label_chunk_file(file_to_label: Path, output_file: Path):
r""" Perform NER on file \p file_to_label and write to \p output_file """
label_corpus = Corpus(file_to_label)
label_corpus.fit_features()
data_path = file_to_label.with_suffix(".dat_chunk")
label_corpus.export(data_path)
output_file.parent.mkdir(parents=True, exist_ok=True)
label_with_maxent(data_path=data_path, model_path=MODEL_PATH, output_file=output_file)
def build_model(train_path: Path):
r""" Construct the learner model """
train_corpus = Corpus(train_path)
train_corpus.fit_features()
data_path = train_path.with_suffix(".dat_name")
train_corpus.export(data_path)
if MODEL_PATH.exists(): MODEL_PATH.unlink() # Delete the existing model
MODEL_PATH.parent.mkdir(exist_ok=True, parents=True)
train_maxent_model(data_path=data_path, model_path=MODEL_PATH)