Update app.py

app.py

@@ -26,7 +26,7 @@ def process_data(input_data,columnname = 'text', num_data = 100):
     random.seed(20979738)
     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)
+    filtered_data = filter_similar_items(random_selection, similarity_threshold = 0.9)
     st.write('Number of data input: ',len(random_selection))
     st.write('After removing duplicates: ',len(filtered_data))
     return filtered_data
@@ -90,7 +90,7 @@ def emotion_classification(translated_data):
     negative_dict_sorted = dict(sorted(negative_dict.items(), key=lambda x: x[1], reverse=True))
     top10_negative_str = ""
     if len(negative_dict_sorted) < 10:
-        st.write("Totall Number of Negative Comments: ",len(negative_dict_sorted))
+        st.write("Total Number of Negative Comments: ",len(negative_dict_sorted))
         for k,v in negative_dict_sorted.items():
           st.write(k)
           top10_negative_str += f"{k}."
@@ -118,11 +118,12 @@ def main():
     st.set_option('deprecation.showPyplotGlobalUse', False)
     st.set_page_config(page_title="Review Sentiment Analysis and Improvement Summarisation Report for Business Product", page_icon="🦜")
     st.header("Review Sentiment Analysis and Improvement Summarisation Report for Business Product")
+    st.write(f"Welcome to the user guide for our product feedback analysis application. Our application is designed to help companies review their product feedback and summarise areas for improvement. Here are the steps to get started:\n1. Upload reviews in CSV file format\n2. Input column name and number of data to be analysed\n3. Automatically removes duplicate reviews\n4. Translate data into English (if the dataset is Chinese)\n5. Analyse reviews sentiment\n6. Summarize top negative reveiws")
     try:
       uploaded_file = st.file_uploader("🔶 Upload CSV file for analysis 🔶", type={"csv"})
       if uploaded_file is not None:
         columnname = st.text_input("🔶 Please enter the column name in CSV file you want to analyze 🔶")
-        num_data = st.number_input("🔶 Please enter the number of rows you want to process 🔶",step=1)
+        num_data = st.number_input("🔶 Please enter the number of rows you want to process 🔶",min_value=2, step=1)
         input_data = pd.read_csv(uploaded_file)
         st.dataframe(input_data)
         st.text('️️ ')
@@ -148,12 +149,15 @@ def main():
 
         #stage 4：Summarization
         st.text('🔶 Processing Summarization 🔶')
-        summarized_text = summarization(top10_negative_str)
-        st.write('Summarized Negative Comments:')
-        st.write(summarized_text[0]["generated_text"])
+        if len(top10_negative_str) == 0:
+          st.write("No Negative Reviews Detected")
+        else:
+          summarized_text = summarization(top10_negative_str)
+          st.write('Summarized Negative Comments:')
+          st.write(summarized_text[0]["generated_text"])
         st.text('️️🟢 Summarization Finished 🟢')
     except:
         st.write("")
-        
+
 if __name__ == "__main__":
     main()