def from_csv(cls, file_path: str):
data_df = pd.read_csv(file_path, usecols=['text'])
seq_vocab = TokenDictionary()
label_dict = Dictionary()
max_seq_len = 0
for i, row in data_df.iterrows():
tokens = row['text'].split(' ')
max_seq_len = max(max_seq_len, len(tokens))
seq_vocab.add_items(tokens)
labels = row['label'].split(' ')
label_dict.add_items(labels)
return cls(data_df, max_seq_len, seq_vocab, label_dict)
def get_label_dict(labels: List[str], delimiter=' '):
label_dict = Dictionary()
for label in labels:
label = label.replace('\n', '')
label_dict.add_items(label.split(delimiter))
return label_dict
