Spaces:
Runtime error
Runtime error
| from transformers import T5Tokenizer, T5Model, T5ForConditionalGeneration, MarianMTModel, MarianTokenizer, pipeline | |
| import nltk.data | |
| import pandas as pd | |
| import matplotlib.pyplot as plt | |
| nltk.download('punkt') | |
| import gradio as gr | |
| from gradio.mix import Parallel | |
| tokenizer_t5 = T5Tokenizer.from_pretrained("panggi/t5-base-indonesian-summarization-cased") | |
| model_t5 = T5ForConditionalGeneration.from_pretrained("panggi/t5-base-indonesian-summarization-cased") | |
| pretrained_sentiment = "ProsusAI/finbert" | |
| pretrained_ner = "51la5/roberta-large-NER" | |
| sentence_tokenizer = nltk.data.load('tokenizers/punkt/english.pickle') | |
| tokenizer_translate = MarianTokenizer.from_pretrained("Helsinki-NLP/opus-mt-id-en") | |
| model_translate = MarianMTModel.from_pretrained( | |
| "Helsinki-NLP/opus-mt-id-en") | |
| #finetuned_model = MarianMTModel.from_pretrained( | |
| # "wolfrage89/annual_report_translation_id_en") | |
| sentiment_pipeline = pipeline( | |
| "sentiment-analysis", | |
| model=pretrained_sentiment, | |
| tokenizer=pretrained_sentiment, | |
| return_all_scores=True | |
| ) | |
| ner_pipeline = pipeline( | |
| "ner", | |
| model=pretrained_ner, | |
| tokenizer=pretrained_ner, | |
| grouped_entities=True | |
| ) | |
| examples = [ | |
| "Perusahaan industri e-commerce Indonesia, Bukalapak telah memberhentikan puluhan karyawan dari beberapa function; Berlawanan dengan PHK sebelumnya, perusahaan mengontrak jajaran pekerja kantornya, harian Kompas melaporkan.", | |
| "Dengan pabrik produksi baru, perusahaan akan meningkatkan kapasitasnya untuk memenuhi peningkatan permintaan yang diharapkan dan akan meningkatkan penggunaan bahan baku dan oleh karena itu meningkatkan profitabilitas produksi.", | |
| "Lifetree didirikan pada tahun 2000, dan pendapatannya meningkat rata-rata 40% dengan margin di akhir 30-an." | |
| ] | |
| def get_translation(text): | |
| translated_tokens = model_translate.generate( | |
| **tokenizer_translate([text], return_tensors='pt', max_length=104, truncation=True))[0] | |
| translated_sentence = tokenizer_translate.decode( | |
| translated_tokens, skip_special_tokens=True) | |
| return translated_sentence | |
| def summ_t5(text): | |
| input_ids = tokenizer_t5.encode(text, return_tensors='pt') | |
| summary_ids = model_t5.generate(input_ids, | |
| max_length=100, | |
| num_beams=2, | |
| repetition_penalty=2.5, | |
| length_penalty=1.0, | |
| early_stopping=True, | |
| no_repeat_ngram_size=2, | |
| use_cache=True) | |
| summary_text = tokenizer_t5.decode(summary_ids[0], skip_special_tokens=True) | |
| return summary_text | |
| def sentiment_analysis(text): | |
| output = sentiment_pipeline(text) | |
| return {elm["label"]: elm["score"] for elm in output[0]} | |
| def ner(text): | |
| output = ner_pipeline(text) | |
| for elm in output: | |
| elm['entity'] = elm['entity_group'] | |
| return {"text": text, "entities": output} | |
| def sentiment_df(text): | |
| df = pd.DataFrame(columns=['Text', 'Eng', 'Label', 'Score']) | |
| text_list = sentence_tokenizer.tokenize(text) | |
| eng_text = [get_translation(text) for text in text_list] | |
| result = [sentiment_analysis(text) for text in eng_text] | |
| labels = [] | |
| scores = [] | |
| for pred in result: | |
| idx = list(pred.values()).index(max(list(pred.values()))) | |
| labels.append(list(pred.keys())[idx]) | |
| scores.append(round(list(pred.values())[idx], 3)) | |
| df['Text'] = text_list | |
| df['Eng'] = eng_text | |
| df['Label'] = labels | |
| df['Score'] = scores | |
| return df | |
| def run(text): | |
| summ_ = summ_t5(text) | |
| summ_translated = get_translation(summ_) | |
| sent_ = sentiment_analysis(summ_translated ) | |
| ner_ = ner(summ_) | |
| df_sentiment = sentiment_df(text) | |
| return summ_, sent_, ner_, df_sentiment | |
| if __name__ == "__main__": | |
| with gr.Blocks() as demo: | |
| gr.Markdown("""<h1 style="text-align:center">Financial Statement Analysis - Indonesia</h1>""") | |
| gr.Markdown( | |
| """ | |
| Creator: Wira Indra Kusuma | |
| """ | |
| ) | |
| with gr.Row(): | |
| with gr.Column(): | |
| input_text = gr.Textbox(label="Input Text") | |
| analyze_button = gr.Button(label="Analyze") | |
| examples_bar = gr.Examples(examples=examples, inputs=input_text) | |
| with gr.Column(): | |
| summ_output = gr.Textbox(label="Article Summary") | |
| ner_output = gr.HighlightedText(label="NER of Summary") | |
| sent_output = gr.Label(label="Sentiment of Summary") | |
| dataframe_component = gr.DataFrame(type="pandas", | |
| label="Dataframe", | |
| max_rows=(20,'fixed'), | |
| overflow_row_behaviour='paginate', | |
| wrap=True) | |
| analyze_button.click(run, inputs=input_text, outputs=[summ_output, sent_output, ner_output, dataframe_component ]) | |
| demo.launch() |