Update app.py

app.py

@@ -193,6 +193,25 @@ def merge_metadata_with_generated_data(generated_data, excel_metadata):
             generated_data[post_number] = post_data  
     return generated_data
 
+def extract_frame_focus(text):
+    text_lower = text.lower()
+    frame_freq = {}
+    for frame, keywords in frame_categories.items():
+        freq = sum(1 for word in keywords if word in text_lower)
+        frame_freq[frame] = freq
+    detected = sorted(frame_freq.items(), key=lambda x: x[1], reverse=True)
+    frame_mapping_1 = {}
+    if detected:
+        frame_mapping_1[detected[0][0]] = "Major Focus"
+        for frame, _ in detected[1:3]:
+            frame_mapping_1[frame] = "Significant Focus"
+        for frame, _ in detected[3:]:
+            frame_mapping_1[frame] = "Minor Mention"
+    for frame in frame_categories.keys():
+        if frame not in frame_mapping_1:
+            frame_mapping_1[frame] = "Not Applicable"
+    return frame_mapping_1
+
 def generate_abstract(text):
     try:
         response = llm.chat([
@@ -316,20 +335,28 @@ with tabs[0]:
 # Detailed Analysis Tab
 # -------------------------------------------------------------------
 with tabs[1]:
-    st.header("Detailed Analysis of DOCX File")
-    uploaded_docx_analysis = st.file_uploader("Upload DOCX file", type=["docx"], key="detailed_docx")
+    st.title("Detailed DOCX Analysis")
     
-    if uploaded_docx_analysis:
-        captions = extract_captions_from_docx(uploaded_docx_analysis)
+    uploaded_docx = st.file_uploader("Upload DOCX file", type=["docx"])
+    if uploaded_docx:
+        captions = extract_captions_from_docx(uploaded_docx)
         total_posts = len(captions)
         st.write(f"**Total number of posts:** {total_posts}")
         
         language_counter = Counter()
+        tone_counter = Counter()
+        frame_counter = {frame: Counter() for frame in frame_categories.keys()}
         hashtag_counter = Counter()
         
         for post, text in captions.items():
             lang = detect_language(text)
             language_counter[lang] += 1
+            tones = extract_tone(text)
+            for tone in tones:
+                tone_counter[tone] += 1
+            frame_mapping_1 = extract_frame_focus(text)
+            for frame, category in frame_mapping_1.items():
+                frame_counter[frame][category] += 1
             hashtags = extract_hashtags(text)
             for hashtag in hashtags:
                 hashtag_counter[hashtag] += 1
@@ -337,6 +364,13 @@ with tabs[1]:
         st.subheader("Language Distribution")
         st.write(dict(language_counter))
         
+        st.subheader("Tone Distribution")
+        st.write(dict(tone_counter))
+        
+        st.subheader("Frame Distribution")
+        for frame, counts in frame_counter.items():
+            st.write(f"**{frame}:** {dict(counts)}")
+        
         st.subheader("Hashtag Distribution")
         st.write(dict(hashtag_counter))
         
@@ -353,6 +387,14 @@ with tabs[1]:
         for lang, count in language_counter.items():
             doc.add_paragraph(f"{lang}: {count}")
         
+        doc.add_heading("Tone Distribution", level=1)
+        for tone, count in tone_counter.items():
+            doc.add_paragraph(f"{tone}: {count}")
+        
+        doc.add_heading("Frame Distribution", level=1)
+        for frame, counts in frame_counter.items():
+            doc.add_paragraph(f"{frame}: {dict(counts)}")
+        
         doc.add_heading("Hashtag Distribution", level=1)
         for hashtag, count in hashtag_counter.items():
             doc.add_paragraph(f"{hashtag}: {count}")
@@ -364,17 +406,43 @@ with tabs[1]:
         doc.save(docx_io)
         docx_io.seek(0)
         st.download_button("Download Analysis Summary as DOCX", data=docx_io, file_name="analysis_summary.docx")
+    
+    # Create an in-memory Excel file
+    excel_io = io.BytesIO()
+    
+    with pd.ExcelWriter(excel_io, engine="xlsxwriter") as writer:
+        # Language Distribution sheet
+        df_language = pd.DataFrame(list(language_counter.items()), columns=["Language", "Count"])
+        df_language.to_excel(writer, index=False, sheet_name="Language Distribution")
         
-        excel_io = io.BytesIO()
-        with pd.ExcelWriter(excel_io, engine="xlsxwriter") as writer:
-            df_summary = pd.DataFrame({"Metric": ["Total Posts"], "Value": [total_posts]})
-            df_summary.to_excel(writer, sheet_name="Summary", index=False)
-            
-            df_lang = pd.DataFrame(list(language_counter.items()), columns=["Language", "Count"])
-            df_lang.to_excel(writer, sheet_name="Languages", index=False)
-            
-            df_hashtags = pd.DataFrame(list(hashtag_counter.items()), columns=["Hashtag", "Count"])
-            df_hashtags.to_excel(writer, sheet_name="Hashtags", index=False)
+        # Tone Distribution sheet
+        df_tone = pd.DataFrame(list(tone_counter.items()), columns=["Tone", "Count"])
+        df_tone.to_excel(writer, index=False, sheet_name="Tone Distribution")
         
-        excel_io.seek(0)
-        st.download_button("Download Analysis Summary as Excel", data=excel_io, file_name="analysis_summary.xlsx")
+        # Frame Distribution sheet
+        # Convert the nested dictionary (frame_counter) into a DataFrame
+        df_frame = pd.DataFrame.from_dict({frame: dict(counter) for frame, counter in frame_counter.items()}, orient="index").fillna(0).astype(int)
+        df_frame.reset_index(inplace=True)
+        df_frame.rename(columns={"index": "Frame"}, inplace=True)
+        df_frame.to_excel(writer, index=False, sheet_name="Frame Distribution")
+        
+        # Hashtag Distribution sheet
+        df_hashtag = pd.DataFrame(list(hashtag_counter.items()), columns=["Hashtag", "Count"])
+        df_hashtag.to_excel(writer, index=False, sheet_name="Hashtag Distribution")
+        
+        # Abstract & Recommendations sheet
+        df_abstract = pd.DataFrame({"Abstract & Recommendations": [abstract]})
+        df_abstract.to_excel(writer, index=False, sheet_name="Abstract")
+        
+        writer.save()
+    
+    excel_io.seek(0)
+    
+    # Download button for the Excel file
+    st.download_button(
+        label="Download Analysis Data as Excel",
+        data=excel_io,
+        file_name="analysis_data.xlsx",
+        mime="application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"
+    )
+