Update app.py

app.py

@@ -88,16 +88,30 @@ def extract_tone_fallback(text):
 def extract_hashtags(text):
     return re.findall(r"#\w+", text)
 
-# Extract frames using Groq API (or fallback)
+# Extract frames using Groq API (with categorization: Major Focus, Significant Focus, Minor Mention)
 def extract_frames(text):
     try:
-        response = llm.chat([{"role": "system", "content": "Classify the following text into relevant activism frames and assign Major, Significant, or Minor focus."},
+        # Prompt Groq to categorize frames and their focus
+        response = llm.chat([{"role": "system", "content": "Classify the following text into relevant activism frames and categorize each frame as Major Focus, Significant Focus, or Minor Mention."},
                              {"role": "user", "content": text}])
-        return response["choices"][0]["message"]["content"]
+        return parse_frames(response["choices"][0]["message"]["content"])
     except Exception as e:
         logging.error(f"Groq API error: {e}")
         return extract_frames_fallback(text)
 
+# Function to parse Groq response and categorize frames
+def parse_frames(response_text):
+    frame_data = {}
+    lines = response_text.splitlines()
+    for line in lines:
+        if "Major Focus" in line or "Significant Focus" in line or "Minor Mention" in line:
+            category = line.split(":")[0].strip()
+            frame = line.split(":")[1].strip()
+            if category not in frame_data:
+                frame_data[category] = []
+            frame_data[category].append(frame)
+    return frame_data
+
 # Fallback method for frame extraction (with categorization of Major, Significant, Minor)
 def extract_frames_fallback(text):
     detected_frames = set()
@@ -239,27 +253,21 @@ if uploaded_excel:
 tone_filter = st.multiselect("Filter by Tone", options=["Emotional", "Harsh", "Somber", "Motivational", "Informative", "Positive", "Angry", "Fearful", "Sarcastic", "Hopeful"])
 frame_filter = st.multiselect("Filter by Frame", options=["Human Rights & Justice", "Political & State Accountability", "Gender & Patriarchy", "Religious Freedom & Persecution", "Grassroots Mobilization", "Environmental Crisis & Activism", "Anti-Extremism & Anti-Violence", "Social Inequality & Economic Disparities", "Activism & Advocacy", "Systemic Oppression", "Intersectionality", "Call to Action", "Empowerment & Resistance", "Climate Justice", "Human Rights Advocacy"])
 
-# Filtered output
-filtered_data = output_data
-
-# Apply filters
-if tone_filter:
-    filtered_data = {key: value for key, value in filtered_data.items() if any(tone in tone_filter for tone in value["Tone"])}
-if frame_filter:
-    filtered_data = {key: value for key, value in filtered_data.items() if any(frame in frame_filter for frame in value["Frames"])}
+filtered_data = {post_number: data for post_number, data in output_data.items() if
+                 (not tone_filter or any(tone in data["Tone"] for tone in tone_filter)) and
+                 (not frame_filter or any(frame in data["Frames"] for frame in frame_filter))}
 
-# Display results in collapsible sections for better UI
-if filtered_data:
-    for post_number, data in filtered_data.items():
-        with st.expander(post_number):
-            for key, value in data.items():
-                st.write(f"**{key}:** {value}")
+# Displaying the posts in collapsible sections
+for post_number, data in filtered_data.items():
+    with st.expander(post_number):
+        for key, value in data.items():
+            st.write(f"**{key}:** {value}")
 
-# Create DOCX file for download
+# Allow downloading the DOCX file
 if filtered_data:
-    doc = create_docx_from_data(filtered_data)
+    docx_output = create_docx_from_data(filtered_data)
     docx_io = io.BytesIO()
-    doc.save(docx_io)
+    docx_output.save(docx_io)
     docx_io.seek(0)
     st.download_button(label="Download Analysis as DOCX", data=docx_io, file_name="analysis.docx")
 else: