| |
| """code7_gpt2.ipynb |
| |
| Automatically generated by Colaboratory. |
| |
| Original file is located at |
| https://colab.research.google.com/drive/1LlzuHqU-HhK-u9FJmKMJKmwSUvksslQ8 |
| """ |
|
|
| !pip install transformers torch |
| !pip install accelerate -U |
|
|
| from google.colab import files |
| import zipfile |
| import os |
|
|
| uploaded = files.upload() |
|
|
| for fn in uploaded.keys(): |
| print('User uploaded file "{name}" with length {length} bytes'.format( |
| name=fn, length=len(uploaded[fn]))) |
|
|
| if fn.endswith('.zip'): |
| with zipfile.ZipFile(fn, 'r') as zip_ref: |
| zip_ref.extractall() |
|
|
| print(f"Files from '{fn}' unzipped in the current directory!") |
| else: |
| print(f"'{fn}' is not a zip file.") |
|
|
| os.listdir() |
|
|
| !pip install transformers |
| import json |
| from transformers import GPT2Tokenizer, GPT2LMHeadModel |
|
|
| |
| with open('surprise.data', 'r') as data_file: |
| data = [json.loads(line) for line in data_file] |
|
|
| with open('surprise.solution', 'r') as solution_file: |
| solutions = [json.loads(line) for line in solution_file] |
|
|
| intent_map = {item['indoml_id']: item['intent'] for item in solutions} |
| intents = [intent_map[item['indoml_id']] for item in data] |
| utt = [item['utt'] for item in data] |
|
|
| label_map = {intent: i for i, intent in enumerate(set(intents))} |
|
|
| |
| tokenizer = GPT2Tokenizer.from_pretrained("gpt2-medium") |
| model = GPT2LMHeadModel.from_pretrained("gpt2-medium").eval() |
|
|
| def get_intent(utterance): |
| input_text = f"Detect the intent of the following sentence:\n'{utterance}'\nThe possible intents are: {', '.join(label_map.keys())}." |
| input_ids = tokenizer.encode(input_text, return_tensors='pt') |
| output = model.generate(input_ids, max_length=200, num_return_sequences=1, temperature=0.8) |
| output_text = tokenizer.decode(output[0], skip_special_tokens=True) |
| |
| intent = output_text.split('\n')[-1].strip() |
| return intent |
|
|
| |
| with open('massive_test.data', 'r') as test_file: |
| test_data = [json.loads(line) for line in test_file] |
|
|
| test_utterances = [item['utt'] for item in test_data] |
| predicted_intents = [get_intent(utterance) for utterance in test_utterances] |
|
|
| |
| submission_data = [{"indoml_id": int(item["indoml_id"]), "intent": intent} for item, intent in zip(test_data, predicted_intents)] |
| submission_filename = 'massive_test_submission.predict' |
| with open(submission_filename, 'w') as submission_file: |
| for item in submission_data: |
| submission_file.write(json.dumps(item) + '\n') |
|
|
| |
| import zipfile |
|
|
| with zipfile.ZipFile("submission.zip", "w") as zipf: |
| zipf.write(submission_filename) |
