pickle.dump(pad_token_dict, open(fine_label_path + "/pad_token_dict.pkl", "wb"))
print("Pad token dict Dumped")
temp_df = df[df.label.isin(children)].reset_index(drop=True)
temp_coarse_lbls = [p] * len(temp_df.text.values)
temp_coarse_label_to_index = {p: 0}
coarse_input_ids, coarse_attention_masks, _ = gpt2_tokenize(coarse_tokenizer, temp_df.text.values,
temp_coarse_lbls, pad_token_dict,
temp_coarse_label_to_index)
fine_input_ids, fine_attention_masks = gpt2_fine_tokenize(fine_tokenizer, temp_df, index_to_label,
pad_token_dict)
dataset = TensorDataset(coarse_input_ids, coarse_attention_masks, fine_input_ids, fine_attention_masks)
train_dataloader, validation_dataloader = create_data_loaders(dataset, batch_size=1)
label_to_exclusive_dataloader = {}
for ch in children:
child_df = pickle.load(open(pkl_dump_dir + "exclusive_" + str(iteration) + "it/" + ch + ".pkl", "rb"))
# for i in range(1, iteration + 1):
# temp_child_df = pickle.load(open(pkl_dump_dir + "exclusive_" + str(i) + "it/" + ch + ".pkl", "rb"))
# if i == 1:
# child_df = temp_child_df
# else:
# child_df = pd.concat([child_df, temp_child_df])
temp_child_lbls = [ch] * len(child_df.text.values)
child_exc_input_ids, child_exc_attention_masks = basic_gpt2_tokenize(fine_tokenizer, child_df.text.values,
temp_child_lbls, pad_token_dict)
child_exc_dataset = TensorDataset(child_exc_input_ids, child_exc_attention_masks)
dataloader = DataLoader(
for ch in parent_to_child[p]:
temp_df = pickle.load(
open(
pkl_dump_dir + "exclusive/" + algo + "/" + str(iteration) +
"it/" + ch + ".pkl", "rb"))
temp_df["label"] = [ch] * len(temp_df)
if df_weaksup is None:
df_weaksup = temp_df
else:
df_weaksup = pd.concat([df_weaksup, temp_df])
df = pd.concat([df, df_weaksup])
coarse_input_ids, coarse_attention_masks = basic_gpt2_tokenize(
tokenizer, df.text.values, df.label.values, pad_token_dict)
# Combine the training inputs into a TensorDataset.
dataset = TensorDataset(coarse_input_ids, coarse_attention_masks)
# Create a 90-10 train-validation split.
coarse_train_dataloader, coarse_validation_dataloader = create_data_loaders(
dataset, batch_size=4)
model = train(model, tokenizer, coarse_train_dataloader,
coarse_validation_dataloader, doc_start_ind, all_labels,
device, pad_token_dict)
test_generate(model, tokenizer, all_labels, pad_token_dict, device)
tokenizer.save_pretrained(tok_path)
torch.save(model, model_path + model_name)
pickle.dump(pad_token_dict, open(pkl_dump_dir + "pad_token_dict.pkl",
"wb"))
