Update app.py

app.py

@@ -98,13 +98,26 @@ def extract_frames(text):
         logging.error(f"Groq API error: {e}")
         return extract_frames_fallback(text)
 
-# Fallback method for frame extraction
+# Fallback method for frame extraction (with categorization of Major, Significant, Minor)
 def extract_frames_fallback(text):
     detected_frames = set()
+    frame_focus = {"Major Focus": [], "Significant Focus": [], "Minor Mention": []}
     text_lower = text.lower()
+    
     for category, keywords in frame_categories.items():
-        if any(word in text_lower for word in keywords):
-            detected_frames.add(category)
+        keyword_count = sum(word in text_lower for word in keywords)
+        if keyword_count > 3:
+            frame_focus["Major Focus"].append(category)
+        elif keyword_count > 1:
+            frame_focus["Significant Focus"].append(category)
+        elif keyword_count > 0:
+            frame_focus["Minor Mention"].append(category)
+    
+    # Return categorized frames
+    for focus, categories in frame_focus.items():
+        for category in categories:
+            detected_frames.add(f"{focus}: {category}")
+    
     return list(detected_frames)
 
 # Extract captions from DOCX
@@ -121,64 +134,55 @@ def extract_captions_from_docx(docx_file):
             captions[current_post].append(text)
     return {post: " ".join(lines) for post, lines in captions.items() if lines}
 
-# Extract metadata from Excel file
+# Function to extract metadata from an Excel file
 def extract_metadata_from_excel(excel_file):
     try:
         df = pd.read_excel(excel_file)
-        metadata = df.set_index("Post Number").to_dict(orient="index")
-        return metadata
+        # Ensure the required columns are present
+        required_columns = ["Date", "Media Type", "Number of Pictures", "Number of Videos", "Number of Audios", "Likes", "Comments", "Tagged Audience"]
+        if not all(col in df.columns for col in required_columns):
+            st.error("Excel file is missing required columns.")
+            return []
+        extracted_data = []
+        for index, row in df.iterrows():
+            post_data = {
+                "Post Number": f"Post {index + 1}",
+                "Date of Post": row.get("Date", "N/A"),
+                "Media Type": row.get("Media Type", "N/A"),
+                "Number of Pictures": row.get("Number of Pictures", 0),
+                "Number of Videos": row.get("Number of Videos", 0),
+                "Number of Audios": row.get("Number of Audios", 0),
+                "Likes": row.get("Likes", 0),
+                "Comments": row.get("Comments", 0),
+                "Tagged Audience": row.get("Tagged Audience", "No"),
+            }
+            extracted_data.append(post_data)
+        return extracted_data
     except Exception as e:
-        logging.error(f"Error reading Excel file: {e}")
-        return {}
+        logging.error(f"Error processing Excel file: {e}")
+        return []
 
 # Merge metadata from Excel with the generated data
 def merge_metadata_with_generated_data(generated_data, excel_metadata):
-    for post, metadata in excel_metadata.items():
-        if post in generated_data:
-            generated_data[post].update(metadata)
+    for post_data in excel_metadata:
+        post_number = post_data["Post Number"]
+        if post_number in generated_data:
+            generated_data[post_number].update(post_data)
+        else:
+            generated_data[post_number] = post_data
     return generated_data
 
-# Function to create the final DOCX with structured output (without tables)
-def create_structured_output_without_table(merged_data, output_path):
+# Function to create DOCX from extracted data
+def create_docx_from_data(extracted_data):
     doc = Document()
-    doc.add_heading('Extracted Social Media Data', 0)
-
-    # Loop through each post and add its structured data
-    for sr_no, (post, data) in enumerate(merged_data.items(), 1):
-        doc.add_heading(f'Post {sr_no}', level=1)
-
-        # Adding the details for each post
-        doc.add_paragraph(f"Date of Post: {data.get('Date of Post', 'N/A')}")
-        doc.add_paragraph(f"Media Type: {data.get('Media Type', 'N/A')}")
-        doc.add_paragraph(f"No of Pictures: {data.get('No of Pictures', 0)}")
-        doc.add_paragraph(f"No of Videos: {data.get('No of Videos', 0)}")
-        doc.add_paragraph(f"No of Audios: {data.get('No of Audios', 0)}")
-        doc.add_paragraph(f"Likes: {data.get('Likes', 'N/A')}")
-        doc.add_paragraph(f"Comments: {data.get('Comments', 'N/A')}")
-        doc.add_paragraph(f"Tagged Audience: {data.get('Tagged Audience', 'No')}")
-        doc.add_paragraph(f"Caption: {data.get('Full Caption', 'N/A')}")
-        doc.add_paragraph(f"Language of Caption: {data.get('Language', 'N/A')}")
-        doc.add_paragraph(f"Total No of Hashtags: {len(data.get('Hashtags', []))}")
-        
-        if data.get('Hashtags'):
-            doc.add_paragraph(f"Hashtags: {', '.join(data['Hashtags'])}")
-        else:
-            doc.add_paragraph("Hashtags: N/A")
-        
-        # Adding Frames for each post
-        doc.add_heading("Frames", level=2)
-        if data.get("Frames"):
-            for frame in data['Frames']:
-                doc.add_paragraph(f"- {frame}")
-        else:
-            doc.add_paragraph("No Frames available")
+    for post_number, data in extracted_data.items():
+        doc.add_heading(post_number, level=1)
+        for key, value in data.items():
+            doc.add_paragraph(f"{key}: {value}")
+        doc.add_paragraph("\n")  # Add a line break between posts
+    return doc
 
-        doc.add_paragraph("\n")  # Add a space between posts
-
-    # Save the document
-    doc.save(output_path)
-
-# Streamlit app setup
+# Streamlit app
 st.title("AI-Powered Activism Message Analyzer")
 
 st.write("Enter text or upload a DOCX/Excel file for analysis:")
@@ -195,18 +199,60 @@ uploaded_excel = st.file_uploader("Upload an Excel file", type=["xlsx"])
 # Initialize output dictionary
 output_data = {}
 
-# Extract and process data based on file uploads or input text
+# Process Text Input
+if input_text:
+    output_data["Manual Input"] = {
+        "Full Caption": input_text,
+        "Language": detect_language(input_text),
+        "Tone": extract_tone(input_text),
+        "Hashtags": extract_hashtags(input_text),
+        "Frames": extract_frames(input_text),
+    }
+    st.success("Analysis completed for text input.")
+
+# Process DOCX file
 if uploaded_docx:
-    output_data = extract_captions_from_docx(uploaded_docx)
+    captions = extract_captions_from_docx(uploaded_docx)
+    for caption, text in captions.items():
+        output_data[caption] = {
+            "Full Caption": text,
+            "Language": detect_language(text),
+            "Tone": extract_tone(text),
+            "Hashtags": extract_hashtags(text),
+            "Frames": extract_frames(text),
+        }
+    st.success(f"Analysis completed for {len(captions)} posts from DOCX.")
+
+# Process Excel file
+if uploaded_excel:
+    with st.spinner("Processing Excel file..."):
+        excel_metadata = extract_metadata_from_excel(uploaded_excel)
+        if excel_metadata:
+            st.success(f"Excel metadata extracted with {len(excel_metadata)} posts.")
+        else:
+            st.warning("No valid data extracted from the Excel file.")
+
+# Merge and display final data
 if uploaded_excel:
-    metadata = extract_metadata_from_excel(uploaded_excel)
-    output_data = merge_metadata_with_generated_data(output_data, metadata)
+    output_data = merge_metadata_with_generated_data(output_data, excel_metadata)
+
+# Display results in collapsible sections for better UI
+if output_data:
+    for post_number, data in output_data.items():
+        with st.expander(post_number):
+            for key, value in data.items():
+                st.write(f"**{key}:** {value}")
 
-# Generate output
+# Create DOCX file for download
 if output_data:
-    # Call the function to generate the DOCX report
-    create_structured_output_without_table(output_data, "final_output.docx")
-    st.write("The DOCX file has been created and saved!")
-    st.download_button("Download DOCX", data=open("final_output.docx", "rb"), file_name="final_output.docx")
+    doc = create_docx_from_data(output_data)
+    docx_io = io.BytesIO()
+    doc.save(docx_io)
+    docx_io.seek(0)
 
-# Further refinement can be added for additional features as necessary
+    st.download_button(
+        label="Download Extracted Data as DOCX",
+        data=docx_io,
+        file_name="extracted_data.docx",
+        mime="application/vnd.openxmlformats-officedocument.wordprocessingml.document"
+    )