Update app.py

app.py

@@ -1,7 +1,7 @@
 import streamlit as st
 import pandas as pd
 import requests
-import csv
+import json
 
 # Define your API key and endpoint
 api_key = 'AIzaSyAQ4dXlOkF8rPC21f6omTS4p6v-uJ2vVIg'
@@ -37,67 +37,87 @@ def analyze_sentiment(text):
         st.error(f"Request failed with status code {response.status_code}: {response.text}")
         return None
 
-def process_file(file):
+def read_file_content(file, file_type):
     """
-    Process the uploaded file, analyze sentiment for all comments, and display results.
+    Read the entire content of the file based on its type.
     """
-    file_text = file.read().decode('utf-8')
-    sentiment_result = analyze_sentiment(file_text)
-    if sentiment_result:
-        response_text = sentiment_result.get('candidates', [{}])[0].get('content', {}).get('parts', [{}])[0].get('text', '').strip()
+    if file_type == 'csv':
+        df = pd.read_csv(file)
+        text = ' '.join(df.apply(lambda x: ' '.join(x.dropna().astype(str)), axis=1))
+    elif file_type == 'xlsx':
+        df = pd.read_excel(file)
+        text = ' '.join(df.apply(lambda x: ' '.join(x.dropna().astype(str)), axis=1))
+    elif file_type == 'json':
+        df = pd.read_json(file)
+        text = ' '.join(df.apply(lambda x: ' '.join(x.dropna().astype(str)), axis=1))
+    elif file_type == 'txt' or file_type == 'md':
+        text = file.read().decode('utf-8')
+    else:
+        st.error("Unsupported file type.")
+        return None
+    return text
 
-        # Parse comments and sentiments
-        results = []
-        lines = response_text.split('\n')
-        comment = None
-        sentiment = None
-        for line in lines:
-            if line.startswith("Comment:"):
-                comment = line.replace("Comment:", "").strip()
-            elif line.startswith("Sentiment:"):
-                sentiment = line.replace("Sentiment:", "").strip()
-                if comment and sentiment:
-                    results.append((comment, sentiment))
-                    comment = None
-                    sentiment = None
+def process_large_text(text, chunk_size=5000):
+    """
+    Split large text into smaller chunks for processing.
+    """
+    chunks = [text[i:i + chunk_size] for i in range(0, len(text), chunk_size)]
+    return chunks
 
-        # Display results
-        df = pd.DataFrame(results, columns=['Comment/Prompt', 'Sentiment'])
-        st.write("### Predicted Sentiments")
-        st.dataframe(df)
+def display_sentiment_results(response_text, file_name):
+    """
+    Display sentiment analysis results for a single file.
+    """
+    # Parse comments and sentiments
+    results = []
+    lines = response_text.split('\n')
+    comment = None
+    sentiment = None
+    for line in lines:
+        if line.startswith("Comment:"):
+            comment = line.replace("Comment:", "").strip()
+        elif line.startswith("Sentiment:"):
+            sentiment = line.replace("Sentiment:", "").strip()
+            if comment and sentiment:
+                results.append((comment, sentiment))
+                comment = None
+                sentiment = None
 
-        # Sentiment distribution
-        sentiment_counts = df['Sentiment'].value_counts().reset_index()
-        sentiment_counts.columns = ['Sentiment', 'Count']
-        with st.expander("View Sentiment Distribution"):
-            st.bar_chart(sentiment_counts.set_index('Sentiment'))
+    # Display results
+    st.write(f"### Sentiment Analysis Results for **{file_name}**")
+    df_results = pd.DataFrame(results, columns=['Comment/Prompt', 'Sentiment'])
+    st.dataframe(df_results)
 
-        # Suggestions
-        suggestions = []
-        current_section = None
-        for line in lines:
-            if line.startswith("### Suggestions for Improvement:"):
-                current_section = "Suggestions for Improvement"
-            elif current_section and line.startswith("- "):
-                suggestions.append(line.replace("- ", "").strip())
-        if suggestions:
-            st.write("### Suggestions for Improvement")
-            for suggestion in suggestions:
-                st.write(f"- {suggestion}")
-        else:
-            st.warning("No suggestions available.")
+    # Sentiment distribution
+    sentiment_counts = df_results['Sentiment'].value_counts().reset_index()
+    sentiment_counts.columns = ['Sentiment', 'Count']
+    with st.expander(f"View Sentiment Distribution for {file_name}"):
+        st.bar_chart(sentiment_counts.set_index('Sentiment'))
 
-        # CSV download
-        output_file = 'sentiment_analysis_results.csv'
-        df.to_csv(output_file, index=False)
-        st.download_button(
-            label="Download Results as CSV",
-            data=open(output_file, 'rb').read(),
-            file_name=output_file,
-            mime='text/csv',
-        )
+    # Suggestions
+    suggestions = []
+    current_section = None
+    for line in lines:
+        if line.startswith("### Suggestions for Improvement:"):
+            current_section = "Suggestions for Improvement"
+        elif current_section and line.startswith("- "):
+            suggestions.append(line.replace("- ", "").strip())
+    if suggestions:
+        st.write("### Suggestions for Improvement")
+        for suggestion in suggestions:
+            st.write(f"- {suggestion}")
     else:
-        st.error("Sentiment analysis failed.")
+        st.warning("No suggestions available.")
+
+    # CSV download
+    output_file = f"sentiment_analysis_results_{file_name}.csv"
+    df_results.to_csv(output_file, index=False)
+    st.download_button(
+        label=f"Download Results for {file_name} as CSV",
+        data=open(output_file, 'rb').read(),
+        file_name=output_file,
+        mime='text/csv',
+    )
 
 # Streamlit layout
 st.set_page_config(page_title="Sentiment Analysis Tool", layout="wide")
@@ -108,9 +128,9 @@ st.write("Analyze customer feedback with sentiment classification and actionable
 with st.sidebar:
     st.header("Instructions 📄")
     st.write("""
-    1. Upload a CSV file containing customer feedback in the main area.
+    1. Upload one or more files containing customer feedback in the main area.
     2. Analyze real-time feedback using the text input box.
-    3. Download sentiment analysis results as a CSV file.
+    3. Download sentiment analysis results as CSV files.
     """)
     st.write("---")
     st.header("About")
@@ -120,11 +140,27 @@ with st.sidebar:
 tab1, tab2 = st.tabs(["📁 File Analysis", "✍️ Real-Time Feedback"])
 
 with tab1:
-    st.write("### Upload a CSV file for batch sentiment analysis:")
-    uploaded_file = st.file_uploader("Choose a CSV file", type="csv")
-    if uploaded_file is not None:
-        with st.spinner("Processing file..."):
-            process_file(uploaded_file)
+    st.write("### Upload one or more files for batch sentiment analysis:")
+    uploaded_files = st.file_uploader("Choose files", type=["csv", "xlsx", "json", "txt", "md"], accept_multiple_files=True)
+    if uploaded_files:
+        for uploaded_file in uploaded_files:
+            file_type = uploaded_file.name.split('.')[-1]
+            with st.spinner(f"Processing {uploaded_file.name}..."):
+                # Read the entire file content
+                text = read_file_content(uploaded_file, file_type)
+                if text:
+                    # Process large text in chunks if necessary
+                    chunks = process_large_text(text)
+                    combined_results = ""
+                    for chunk in chunks:
+                        sentiment_result = analyze_sentiment(chunk)
+                        if sentiment_result:
+                            response_text = sentiment_result.get('candidates', [{}])[0].get('content', {}).get('parts', [{}])[0].get('text', '').strip()
+                            combined_results += response_text + "\n"
+                    if combined_results:
+                        display_sentiment_results(combined_results, uploaded_file.name)
+                    else:
+                        st.error(f"Sentiment analysis failed for {uploaded_file.name}.")
 
 with tab2:
     st.write("### Enter your feedback for real-time analysis:")
@@ -146,4 +182,4 @@ with tab2:
                     else:
                         st.warning(f"Sentiment: **Unknown** 🤔")
                 else:
-                    st.error("Sentiment analysis failed.")
+                    st.error("Sentiment analysis failed.")