Update app.py

app.py

@@ -27,21 +27,23 @@ def process_data(input_data,columnname = 'text', num_data = 100):
     processed_data = [i for i in input_data[columnname]]
     random_selection = random.sample(processed_data, num_data)
     filtered_data = filter_similar_items(random_selection, similarity_threshold = 0.5)
-    st.write('The Number of Data You Input: ',len(random_selection))
-    st.write('After Removing Duplicates: ',len(filtered_data))
+    st.write('Number of data input: ',len(random_selection))
+    st.write('After removing duplicates: ',len(filtered_data))
     return filtered_data
 
 def chi2eng(filtered_data):
-    trans_pipe = pipeline("translation", model="Helsinki-NLP/opus-mt-zh-en")
     translated_data = []
     language_Classification = langid.classify(filtered_data[0])[0]
     if language_Classification == "zh":
-      st.write("Your input is Chinese, Translating to English")
+      st.write("Your input is Chinese, translating to English")
+      st.write('▶️ Translation model start downing, loading model may takes time, please wait...')
+      trans_pipe = pipeline("translation", model="Helsinki-NLP/opus-mt-zh-en")
+      st.write('⏺️ Translation model successfully loaded')
       for i in filtered_data:
         st.write(trans_pipe(i)[0]['translation_text'])
         translated_data.append(trans_pipe(i)[0]['translation_text'])
     elif language_Classification == 'en':
-        st.write("Your input is English, Moving to Next Stage")
+        st.write("Your input is English, moving to next stage...")
         translated_data = [i for i in filtered_data]
     else:
         st.write('The anguage you input is: ',langid.classify(filtered_data[0])[0],'the program cannot process')
@@ -49,7 +51,9 @@ def chi2eng(filtered_data):
 
 # Text Classification：Negative/Neutral/Positive
 def emotion_classification(translated_data):
+    st.write('▶️ Classification model start downing, loading model may takes time, please wait...')
     emo_pipe = pipeline("text-classification", model="deeplearningwithpython5240/twitter_roberta_base_sentiment_fintune_with_app_reviews")
+    st.write('⏺️ Classification model successfully loaded')
     negative_count, neutral_count, positive_count = 0,0,0
     negative_dict = {}
     for i in translated_data:
@@ -91,7 +95,9 @@ def emotion_classification(translated_data):
 
 # Summarization
 def summarization(top10_negative_str):
+    st.write('▶️ Summarizatio model start downing, loading model may takes time, please wait...')
     summarize_pipe = pipeline("text2text-generation", model="deeplearningwithpython5240/summarisation-t5-finetuned-model", max_new_tokens =512)
+    st.write('⏺️ Summarization model successfully loaded')
     summarized_text = summarize_pipe(top10_negative_str)
     return summarized_text
 
@@ -122,9 +128,9 @@ def main():
         st.text('️️ ')
 
         #stage 3：emotion Classification
-        st.text('️️🔶 Processing Emotion Calssification 🔶')
+        st.text('️️🔶 Processing Emotion Classification 🔶')
         top10_negative_str = emotion_classification(translated_data)
-        st.text('️️🟢 Emotion Calssification Finished 🟢')
+        st.text('️️🟢 Emotion Classification Finished 🟢')
         st.text('️️ ')
 
         #stage 4：Summarization
@@ -133,7 +139,7 @@ def main():
         st.write(summarized_text)
         st.text('️️🟢 Summarization Finished 🟢')
     except:
-        st.write("Please load a file to continue...")
+        st.write("")
         
 if __name__ == "__main__":
     main()