Update app.py

app.py

@@ -46,198 +46,26 @@ tone_categories = {
     "Hopeful": ["optimism", "better future", "faith", "confidence", "looking forward"]
 }
 
-# Predefined frame categories for analysis
+# Frame categories for fallback method
 frame_categories = {
-    "Human Rights & Justice": {
-        "Legal Rights & Reforms": ["law", "justice", "legal", "reforms", "legislation", "rights", "human rights", "court", "trial", "lawsuit", "due process"],
-        "Humanitarian Issues": ["humanitarian", "aid", "refugees", "asylum", "crisis response", "displacement", "famine", "disaster relief", "war victims", "NGO support"],
-        "Civil Liberties": ["freedom", "expression", "privacy", "rights violations", "censorship", "surveillance", "press freedom", "free speech", "whistleblower"],
-        "State Repression & Human Rights Abuses": ["police brutality", "enforced disappearances", "political prisoners", "arbitrary arrests", "martial law", "crackdowns"],
-        "Women's Rights": [
-            "gender equality", "women's empowerment", "reproductive rights", "gender-based violence", "sexual harassment", "domestic violence",
-            "equal pay", "education for women", "child marriage", "women's health", "maternity leave", "women in leadership", "honor killings",
-            "karo kari", "patriarchal oppression", "honor-based violence", "marital violence", "violence against women", "justice for women",
-            "reclaiming women's rights", "female autonomy", "societal control over women", "women's freedom of choice", "women’s bodies, women’s rights",
-            "end honor killings", "violence against women must stop", "say no to patriarchy"
-        ]
-    },
-    "Political & State Accountability": {
-        "Corruption & Governance": ["corruption", "government", "policy", "accountability", "transparency", "bribery", "misuse of power", "scandal", "nepotism", "tax fraud"],
-        "Political Oppression": ["authoritarianism", "censorship", "state control", "dissent", "political prisoners", "dictatorship", "crackdown", "enforced disappearances"],
-        "Elections & Political Representation": ["voting", "elections", "political participation", "democracy", "voter suppression", "fraud", "ballot", "electoral reform"],
-        "Elite Impunity & Judicial Injustice": ["class privilege", "unfair trials", "elite criminals", "unpunished crimes", "legal double standards"]
-    },
-    "Gender & Patriarchy": {
-        "Gender-Based Violence": ["violence", "domestic abuse", "sexual harassment", "femicide", "sexual assault", "stalking", "forced marriage", "honor killings"],
-        "Women's Rights & Equality": ["gender equality", "feminism", "reproductive rights", "patriarchy", "pay gap", "maternal health", "women’s leadership"],
-        "LGBTQ+ Rights": ["queer rights", "LGBTQ+", "gender identity", "trans rights", "homophobia", "pride", "same-sex marriage", "conversion therapy", "non-binary"],
-        "Gender & Healthcare Rights": ["gynecologic health", "menstrual health", "reproductive justice", "medical discrimination", "healthcare access"]
-    },
-    "Religious Freedom & Persecution": {
-        "Religious Discrimination": ["persecution", "intolerance", "sectarianism", "faith-based violence", "hate crime", "blasphemy", "religious hate speech"],
-        "Religious Minorities' Rights": ["minorities", "blasphemy laws", "religious freedom", "forced conversion", "places of worship", "religious refugees"],
-        "Misuse of Blasphemy Laws": ["false accusations", "extrajudicial killings", "mob violence", "sectarian extremism", "judicial bias"],
-        "Forced Conversions & Marriages": ["child abduction", "coercion", "underage marriages", "religious conversion abuse"]
-    },
-    "Grassroots Mobilization": {
-        "Community Activism": ["activism", "grassroots", "volunteering", "local organizing", "community engagement", "mutual aid", "citizen action"],
-        "Protests & Demonstrations": ["march", "strike", "rally", "sit-in", "boycott", "civil disobedience", "public gathering"],
-        "Coalition Building": ["solidarity", "collaboration", "alliances", "mutual aid", "networking", "joint statement", "collective movement"]
-    },
-    "Student Activism": {
-        "Student & Youth Activism": ["student protests", "university activism", "campus safety", "fee hikes", "student unions", "feminist student movements"]
-    },
-    "Environmental Crisis & Activism": {
-        "Climate Change Awareness": ["climate crisis", "global warming", "carbon emissions", "fossil fuels", "sea level rise", "heatwaves", "melting ice caps"],
-        "Conservation & Sustainability": ["deforestation", "wildlife protection", "biodiversity", "reforestation", "green energy", "sustainable agriculture"],
-        "Environmental Justice": ["pollution", "water crisis", "land rights", "indigenous rights", "eco-activism", "environmental racism", "waste management"],
-        "Natural Resource Exploitation & Displacement": ["mining", "deforestation", "water mismanagement", "corporate environmental harm", "land grabs"]
-    },
-    "Anti-Extremism & Anti-Violence": {
-        "Hate Speech & Radicalization": ["hate speech", "extremism", "online radicalization", "propaganda", "far-right groups", "hate groups"],
-        "Mob & Sectarian Violence": ["mob attack", "lynching", "sectarian violence", "hate crimes", "communal riots", "armed militia"],
-        "Counterterrorism & De-Radicalization": ["terrorism", "prevention", "peacebuilding", "rehabilitation", "extremist ideology", "security policy"]
-    },
-    "Social Inequality & Economic Disparities": {
-        "Class Privilege & Labor Rights": ["classism", "labor rights", "unions", "wage gap", "worker exploitation", "fair wages", "labor strikes"],
-        "Poverty & Economic Justice": ["poverty", "inequality", "economic disparity", "wealth gap", "unemployment", "food insecurity"],
-        "Housing & Healthcare": ["housing crisis", "healthcare access", "social safety nets", "homelessness", "Medicaid", "affordable housing"],
-        "Marginalized Labor Rights": ["sanitation workers", "job discrimination", "workplace abuse", "hazardous labor conditions", "fair employment"]
-    },
-    "Activism & Advocacy": {
-        "Policy Advocacy & Legal Reforms": ["campaign", "policy change", "legal advocacy", "legislative reform", "policy shift", "lobbying"],
-        "Social Media Activism": ["hashtags", "digital activism", "awareness campaign", "viral movement", "online protest", "cyber activism"],
-        "Freedom of Expression & Press": ["press freedom", "censorship", "media rights", "journalist safety", "fake news", "whistleblowing"]
-    },
-    "Systemic Oppression": {
-        "Marginalized Communities": ["minorities", "exclusion", "systemic discrimination", "oppression", "intersectionality"],
-        "Racial & Ethnic Discrimination": ["racism", "xenophobia", "ethnic cleansing", "casteism", "racial profiling", "hate speech"],
-        "Institutional Bias": ["institutional racism", "structural oppression", "biased laws", "discriminatory policies"]
-    },
-    "Intersectionality": {
-        "Multiple Oppressions": ["overlapping struggles", "intersecting identities", "double discrimination", "marginalization"],
-        "Women & Marginalized Identities": ["feminism", "queer feminism", "minority women", "disabled women", "indigenous women"],
-        "Global Solidarity Movements": ["transnational activism", "cross-movement solidarity", "international justice"]
-    },
-    "Call to Action": {
-        "Petitions & Direct Action": ["sign petition", "protest", "boycott", "demonstrate", "advocate"],
-        "Fundraising & Support": ["donate", "crowdfunding", "aid support", "mutual aid funds", "relief efforts"],
-        "Policy & Legislative Action": ["policy change", "demand action", "write to lawmakers", "call your representative"]
-    },
-    "Empowerment & Resistance": {
-        "Grassroots Organizing": ["community empowerment", "leadership training", "civil resistance", "community building"],
-        "Revolutionary Movements": ["resistance", "revolt", "revolutionary change", "radical change", "freedom fighters"],
-        "Inspiration & Motivational Messaging": ["hope", "courage", "overcoming struggles", "empowerment", "transformative justice"]
-    },
-    "Climate Justice": {
-        "Indigenous Environmental Activism": ["land rights", "indigenous climate leadership", "tribal land protection", "environmental sovereignty"],
-        "Corporate Accountability": ["big oil", "corporate greed", "environmental negligence", "corporate responsibility"],
-        "Sustainable Development": ["eco-friendly", "renewable energy", "circular economy", "climate resilience"]
-    },
-    "Human Rights Advocacy": {
-        "Criminal Justice Reform": ["police brutality", "wrongful convictions", "prison reform", "mass incarceration"],
-        "Workplace Discrimination & Labor Rights": ["workplace bias", "equal pay", "unions", "workplace harassment"],
-        "International Human Rights": ["humanitarian law", "UN declarations", "international treaties", "human rights violations"]
-    }
+    "Human Rights & Justice": ["rights", "law", "justice", "legal", "humanitarian"],
+    "Political & State Accountability": ["government", "policy", "state", "corruption", "accountability"],
+    "Gender & Patriarchy": ["gender", "women", "violence", "patriarchy", "equality"],
+    "Religious Freedom & Persecution": ["religion", "persecution", "minorities", "intolerance", "faith"],
+    "Grassroots Mobilization": ["activism", "community", "movement", "local", "mobilization"],
+    "Environmental Crisis & Activism": ["climate", "deforestation", "water", "pollution", "sustainability"],
+    "Anti-Extremism & Anti-Violence": ["extremism", "violence", "hate speech", "radicalism", "mob attack"],
+    "Social Inequality & Economic Disparities": ["class privilege", "labor rights", "economic", "discrimination"],
+    "Activism & Advocacy": ["justice", "rights", "demand", "protest", "march", "campaign", "freedom of speech"],
+    "Systemic Oppression": ["discrimination", "oppression", "minorities", "marginalized", "exclusion"],
+    "Intersectionality": ["intersecting", "women", "minorities", "struggles", "multiple oppression"],
+    "Call to Action": ["join us", "sign petition", "take action", "mobilize", "support movement"],
+    "Empowerment & Resistance": ["empower", "resist", "challenge", "fight for", "stand up"],
+    "Climate Justice": ["environment", "climate change", "sustainability", "biodiversity", "pollution"],
+    "Human Rights Advocacy": ["human rights", "violations", "honor killing", "workplace discrimination", "law reform"]
 }
 
-# --------------------------
-# Helper function to add a frame analysis table to the current post's section
-# --------------------------
-
-def add_frame_analysis_table(doc, full_text, frame_categories):
-    """
-    For the given full_text (from a single post), counts keyword occurrences for each frame
-    from frame_categories and creates a table with 5 columns:
-      Frame | Major Focus | Significant Focus | Minor Mention | Not Applicable
-    The highest-count frame is marked as "Major Focus", the next two as "Significant Focus",
-    remaining detected frames with positive counts are "Minor Mention", and frames with zero counts
-    are marked as "Not Applicable".
-    This table is added directly to the provided doc.
-    """
-    # Count keyword occurrences for each frame
-    frame_counts = {}
-    text_lower = full_text.lower()
-    for main_cat, subcats in frame_categories.items():
-        for subcat, keywords in subcats.items():
-            frame_label = f"{main_cat} → {subcat}"
-            count = 0
-            for keyword in keywords:
-                count += len(re.findall(r'\b' + re.escape(keyword.lower()) + r'\b', text_lower))
-            frame_counts[frame_label] = count
-
-    # Determine focus level
-    frames_with_counts = [(frame, count) for frame, count in frame_counts.items() if count > 0]
-    frames_with_counts.sort(key=lambda x: x[1], reverse=True)
-    frame_focus = {}
-    if frames_with_counts:
-        for i, (frame, count) in enumerate(frames_with_counts):
-            if i == 0:
-                frame_focus[frame] = "Major Focus"
-            elif i < 3:
-                frame_focus[frame] = "Significant Focus"
-            else:
-                frame_focus[frame] = "Minor Mention"
-    # Frames with zero count become "Not Applicable"
-    for frame, count in frame_counts.items():
-        if count == 0:
-            frame_focus[frame] = "Not Applicable"
-
-    # Create the table in the current document
-    doc.add_paragraph("Frame Analysis:")
-    table = doc.add_table(rows=1, cols=5)
-    table.style = 'Table Grid'
-    hdr_cells = table.rows[0].cells
-    hdr_cells[0].text = "Frame"
-    hdr_cells[1].text = "Major Focus"
-    hdr_cells[2].text = "Significant Focus"
-    hdr_cells[3].text = "Minor Mention"
-    hdr_cells[4].text = "Not Applicable"
-
-    for frame in sorted(frame_focus.keys()):
-        category = frame_focus[frame]
-        row_cells = table.add_row().cells
-        row_cells[0].text = frame
-        row_cells[1].text = "✔ Major Focus" if category == "Major Focus" else "Major Focus"
-        row_cells[2].text = "✔ Significant Focus" if category == "Significant Focus" else "Significant Focus"
-        row_cells[3].text = "✔ Minor Mention" if category == "Minor Mention" else "Minor Mention"
-        row_cells[4].text = "✔ Not Applicable" if category == "Not Applicable" else "Not Applicable"
-
-# --------------------------
-# Merged DOCX creation function with inline frame analysis for each post
-# --------------------------
-
-def create_merged_docx(extracted_data, frame_categories):
-    """
-    Creates a DOCX document where, for each post, all details (from extracted_data)
-    are displayed. Instead of a textual "Frames" field, an inline frame analysis table
-    (based on the post's "Full Caption" and frame_categories) is inserted.
-    """
-    doc = Document()
-    ordered_keys = [
-        "Post Number", "Date of Post", "Media Type", "Number of Pictures",
-        "Number of Videos", "Number of Audios", "Likes", "Comments",
-        "Tagged Audience", "Full Caption", "Language", "Tone", "Hashtags"
-    ]
-    
-    for post_number, data in extracted_data.items():
-        doc.add_heading(post_number, level=1)
-        for key in ordered_keys:
-            value = data.get(key, "N/A")
-            if key in ["Tone", "Hashtags"]:
-                value = ", ".join(value) if isinstance(value, list) else value
-            doc.add_paragraph(f"**{key}:** {value}")
-        # Instead of displaying a textual Frames field, add the frame analysis table here
-        full_text = data.get("Full Caption", "")
-        if full_text:
-            add_frame_analysis_table(doc, full_text, frame_categories)
-        doc.add_paragraph("\n")
-    return doc
-
-# --------------------------
-# Other utility functions remain unchanged (language detection, tone extraction, etc.)
-# --------------------------
-
+# Detect language
 def detect_language(text):
     try:
         return detect(text)
@@ -245,17 +73,17 @@ def detect_language(text):
         logging.error(f"Error detecting language: {e}")
         return "unknown"
 
+# Extract tone using Groq API (or fallback method)
 def extract_tone(text):
     try:
-        response = llm.chat([
-            {"role": "system", "content": "Analyze the tone of the following text and provide descriptive tone labels."},
-            {"role": "user", "content": text}
-        ])
+        response = llm.chat([{"role": "system", "content": "Analyze the tone of the following text and provide descriptive tone labels."},
+                             {"role": "user", "content": text}])
         return response["choices"][0]["message"]["content"].split(", ")
     except Exception as e:
         logging.error(f"Groq API error: {e}")
         return extract_tone_fallback(text)
 
+# Fallback method for tone extraction
 def extract_tone_fallback(text):
     detected_tones = set()
     text_lower = text.lower()
@@ -264,9 +92,73 @@ def extract_tone_fallback(text):
             detected_tones.add(category)
     return list(detected_tones) if detected_tones else ["Neutral"]
 
+# Extract hashtags
 def extract_hashtags(text):
     return re.findall(r"#\w+", text)
 
+# -------------------------------------------------------------------
+# New functions for frame categorization and display
+# -------------------------------------------------------------------
+
+def get_frame_category_mapping(text):
+    """
+    Returns a mapping of every frame (from frame_categories) to one of the four categories.
+    Detected frames are assigned a focus level based on keyword frequency:
+      - Top detected: "Major Focus"
+      - Next up to two: "Significant Focus"
+      - Remaining detected: "Minor Mention"
+    Frames not detected get "Not Applicable".
+    """
+    text_lower = text.lower()
+    # Calculate frequency for each frame
+    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
+
+    # Identify detected frames (frequency > 0) and sort descending
+    detected = [(frame, freq) for frame, freq in frame_freq.items() if freq > 0]
+    detected.sort(key=lambda x: x[1], reverse=True)
+
+    category_mapping = {}
+    if detected:
+        # Highest frequency frame as Major Focus
+        category_mapping[detected[0][0]] = "Major Focus"
+        # Next up to two frames as Significant Focus
+        for frame, _ in detected[1:3]:
+            category_mapping[frame] = "Significant Focus"
+        # Remaining detected frames as Minor Mention
+        for frame, _ in detected[3:]:
+            category_mapping[frame] = "Minor Mention"
+    # For frames not detected, assign Not Applicable
+    for frame in frame_categories.keys():
+        if frame not in category_mapping:
+            category_mapping[frame] = "Not Applicable"
+    return category_mapping
+
+def format_frame_categories_table(mapping):
+    """
+    Returns a markdown-formatted table that displays each frame along with four columns:
+    Major Focus, Significant Focus, Minor Mention, and Not Applicable.
+    A tick (✓) is shown only in the column corresponding to the assigned category.
+    """
+    header = "| Frame | Major Focus | Significant Focus | Minor Mention | Not Applicable |\n"
+    header += "| --- | --- | --- | --- | --- |\n"
+    rows = ""
+    tick = "✓"
+    for frame, category in mapping.items():
+        major = tick if category == "Major Focus" else ""
+        significant = tick if category == "Significant Focus" else ""
+        minor = tick if category == "Minor Mention" else ""
+        not_applicable = tick if category == "Not Applicable" else ""
+        rows += f"| {frame} | {major} | {significant} | {minor} | {not_applicable} |\n"
+    return header + rows
+
+# -------------------------------------------------------------------
+# Existing functions for file processing
+# -------------------------------------------------------------------
+
+# Extract captions from DOCX
 def extract_captions_from_docx(docx_file):
     doc = Document(docx_file)
     captions = {}
@@ -280,6 +172,7 @@ 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
 def extract_metadata_from_excel(excel_file):
     try:
         df = pd.read_excel(excel_file)
@@ -289,18 +182,38 @@ def extract_metadata_from_excel(excel_file):
         logging.error(f"Error processing Excel file: {e}")
         return []
 
+# Merge metadata with generated analysis
 def merge_metadata_with_generated_data(generated_data, excel_metadata):
     for post_data in excel_metadata:
         post_number = f"Post {post_data.get('Post Number', len(generated_data) + 1)}"
         if post_number in generated_data:
             generated_data[post_number].update(post_data)
         else:
-            generated_data[post_number] = post_data
+            generated_data[post_number] = post_data  
     return generated_data
 
-# --------------------------
-# Streamlit App
-# --------------------------
+# Create DOCX file matching the uploaded format
+def create_docx_from_data(extracted_data):
+    doc = Document()
+    for post_number, data in extracted_data.items():
+        doc.add_heading(post_number, level=1)
+        ordered_keys = [
+            "Post Number", "Date of Post", "Media Type", "Number of Pictures",
+            "Number of Videos", "Number of Audios", "Likes", "Comments", "Tagged Audience",
+            "Full Caption", "Language", "Tone", "Hashtags", "Frames"
+        ]
+        for key in ordered_keys:
+            value = data.get(key, "N/A")
+            if key in ["Tone", "Hashtags"]:
+                value = ", ".join(value) if isinstance(value, list) else value
+            # For Frames, simply add the table text as is.
+            doc.add_paragraph(f"**{key}:** {value}")
+        doc.add_paragraph("\n")
+    return doc
+
+# -------------------------------------------------------------------
+# Streamlit App UI
+# -------------------------------------------------------------------
 
 st.title("AI-Powered Coding Sheet Generator")
 st.write("Enter text or upload a DOCX/Excel file for analysis:")
@@ -310,37 +223,50 @@ uploaded_docx = st.file_uploader("Upload a DOCX file", type=["docx"])
 uploaded_excel = st.file_uploader("Upload an Excel file", type=["xlsx"])
 
 output_data = {}
+
 if input_text:
+    # Process manual input text
+    frame_mapping = get_frame_category_mapping(input_text)
+    frames_table = format_frame_categories_table(frame_mapping)
     output_data["Manual Input"] = {
         "Full Caption": input_text,
         "Language": detect_language(input_text),
         "Tone": extract_tone(input_text),
         "Hashtags": extract_hashtags(input_text),
-        "Frames": None  # Frame analysis will be computed inline
+        "Frames": frames_table,  # Markdown table displaying frame categories
     }
 
 if uploaded_docx:
     captions = extract_captions_from_docx(uploaded_docx)
     for caption, text in captions.items():
+        frame_mapping = get_frame_category_mapping(text)
+        frames_table = format_frame_categories_table(frame_mapping)
         output_data[caption] = {
             "Full Caption": text,
             "Language": detect_language(text),
             "Tone": extract_tone(text),
             "Hashtags": extract_hashtags(text),
-            "Frames": None  # Inline frame analysis will be added
+            "Frames": frames_table,
         }
 
 if uploaded_excel:
     excel_metadata = extract_metadata_from_excel(uploaded_excel)
     output_data = merge_metadata_with_generated_data(output_data, excel_metadata)
 
+# Display results in collapsible sections
 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}")
-    merged_docx = create_merged_docx(output_data, frame_categories)
-    merged_docx_io = io.BytesIO()
-    merged_docx.save(merged_docx_io)
-    merged_docx_io.seek(0)
-    st.download_button("Download Merged Analysis DOCX", data=merged_docx_io, file_name="merged_analysis.docx")
+                if key == "Frames":
+                    st.markdown(f"**{key}:**\n{value}")
+                else:
+                    st.write(f"**{key}:** {value}")
+
+# Generate DOCX output for download
+if output_data:
+    docx_output = create_docx_from_data(output_data)
+    docx_io = io.BytesIO()
+    docx_output.save(docx_io)
+    docx_io.seek(0)
+    st.download_button("Download Merged Analysis as DOCX", data=docx_io, file_name="coding_sheet.docx")