Create app.py

app.py

@@ -0,0 +1,107 @@
+from transformers import T5Tokenizer, T5Model, T5ForConditionalGeneration, pipeline
+import nltk.data
+import pandas as pd
+import matplotlib.pyplot as plt
+from googletrans import Translator
+
+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 = "cahya/bert-base-indonesian-NER"
+
+sentence_tokenizer = nltk.data.load('tokenizers/punkt/english.pickle')
+
+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
+)
+
+translator = Translator()
+
+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', 'Label', 'Score'])
+    text_list = sentence_tokenizer.tokenize(text)
+    result = [sentiment_analysis(text) for text in text_list]
+    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['Label'] = labels
+    df['Score'] = scores
+    return df
+    
+def run(text):
+    summ_ = summ_t5(text)
+    text_translated = translator.translate(text, src='id', dest='en')
+    sent_ = sentiment_analysis(text_translated )
+    ner_ = ner(summ_)
+    return summ_, sent_, ner_
+
+if __name__ == "__main__":
+    with gr.Blocks() as demo:
+        gr.Markdown("""<h1 style="text-align:center">Stock 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")
+                
+                summ_output = gr.Textbox(label="Article Summary")
+                ner_output = gr.HighlightedText(label="NER Summary")
+                sent_output = gr.Label(label="Sentiment Summary")
+                
+            with gr.Column():
+                summ_output = gr.Textbox(label="Article Summary")
+                ner_output = gr.HighlightedText(label="NER Summary")
+                sent_output = gr.Label(label="Sentiment Summary")
+                
+                
+        analyze_button.click(run, inputs=input_text, outputs=[summ_output, sent_output, ner_output])
+    demo.launch()