Update app.py

app.py

@@ -2,7 +2,6 @@ from transformers import T5Tokenizer, T5Model, T5ForConditionalGeneration, pipel
 import nltk.data
 import pandas as pd
 import matplotlib.pyplot as plt
-from googletrans import Translator
 from google_trans_new import google_translator  
 
 nltk.download('punkt')
@@ -59,8 +58,9 @@ def ner(text):
     return {"text": text, "entities": output}
     
 def sentiment_df(text):
-    df = pd.DataFrame(columns=['Text', 'Label', 'Score'])
+    df = pd.DataFrame(columns=['Text', 'Eng', 'Label', 'Score'])
     text_list = sentence_tokenizer.tokenize(text)
+    eng_text = [translator.transalate(text, lang_src='id',lang_tgt='en') for text in text_list]
     result = [sentiment_analysis(text) for text in text_list]
     labels = []
     scores = []
@@ -69,6 +69,7 @@ def sentiment_df(text):
         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
@@ -78,7 +79,8 @@ def run(text):
     summ_translated = translator.transalate(summ_, lang_src='id',lang_tgt='en')
     sent_ = sentiment_analysis(summ_translated )
     ner_ = ner(summ_)
-    return summ_, sent_, ner_
+    df_sentiment = sentiment_df(text)
+    return summ_, sent_, ner_, df_sentiment
 
 if __name__ == "__main__":
     with gr.Blocks() as demo:
@@ -99,6 +101,12 @@ if __name__ == "__main__":
                 ner_output = gr.HighlightedText(label="NER Summary")
                 sent_output = gr.Label(label="Sentiment 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])
     demo.launch()