Spaces:
Sleeping
Sleeping
| import gradio as gr | |
| import json | |
| from datetime import datetime | |
| import demoji | |
| from huggingface_hub import CommitScheduler | |
| from pathlib import Path | |
| import re | |
| from transformers import pipeline | |
| from uuid import uuid4 | |
| #based on https://huggingface.co/spaces/Wauplin/space_to_dataset_saver/blob/main/app_json.py | |
| #data is saved at https://huggingface.co/datasets/MR17u/tweeteval-irony-mcc/tree/main | |
| JSON_DATASET_DIR = Path("json_dataset") | |
| JSON_DATASET_DIR.mkdir(parents=True, exist_ok=True) | |
| JSON_DATASET_PATH = JSON_DATASET_DIR / f"data-{uuid4()}.json" | |
| CLS_MODEL_NAME = "PierreEpron/tweeteval-irony-mcc" | |
| scheduler = CommitScheduler( | |
| repo_id="tweeteval-irony-mcc", | |
| repo_type="dataset", | |
| folder_path=JSON_DATASET_DIR, | |
| path_in_repo="data", | |
| ) | |
| classifier = pipeline(model = CLS_MODEL_NAME, tokenizer = 'cardiffnlp/twitter-roberta-large-2022-154m') | |
| def clean_brackets(text): | |
| return text.replace('{', '(').replace('}', ')') | |
| def clean_emojis(text, type:str = ''): | |
| if type=='rem': | |
| return demoji.replace(text, '') | |
| elif type!='keep': | |
| return demoji.replace_with_desc(text, type) | |
| else: | |
| return text | |
| def clean_hashtags(text, hashtags=['#irony', '#sarcasm','#not']): | |
| for hashtag in hashtags: | |
| text = re.sub(hashtag, '', text, flags=re.I) | |
| return re.sub(r' +', r' ', text) | |
| def clean_text(text): | |
| return re.sub(' {2,}', ' ',clean_emojis(clean_hashtags(clean_brackets(text)))).strip() | |
| def save_json(entry: str, result) -> None: | |
| with scheduler.lock: | |
| with JSON_DATASET_PATH.open("a") as f: | |
| result = json.loads(result.replace("'",'"'))[0] | |
| json.dump({"entry": entry, "label": result['label'], "score": result['score'], "datetime": datetime.now().isoformat()}, f) | |
| f.write("\n") | |
| def classif(text: str): | |
| return classifier(clean_text(text)) | |
| with gr.Blocks() as demo: | |
| with gr.Row(): | |
| entry = gr.Textbox(label="Input") | |
| result = gr.Textbox(label="Classification") | |
| input_btn = gr.Button("Submit") | |
| input_btn.click(fn=classif, inputs=entry, outputs=result).success( | |
| fn=save_json, | |
| inputs=[entry, result], | |
| outputs=None | |
| ) | |
| demo.launch() |