Added urgency, brand impact and issue categories

app.py

@@ -4,12 +4,7 @@ import pandas as pd
 import numpy as np
 import os
 from datetime import datetime
-import plotly.graph_objects as go
-from plotly.subplots import make_subplots
-import base64
-import io
 
-# [Previous imports and constants remain the same]
 # Initialize the classification pipelines
 sentiment_classifier = pipeline("zero-shot-classification", model="facebook/bart-large-mnli")
 
@@ -19,7 +14,7 @@ URGENCY_LABELS = ["critical", "high", "medium", "low"]
 BRAND_IMPACT_LABELS = ["severe", "moderate", "minimal"]
 ISSUE_CATEGORIES = ["product", "service", "security", "fraud", "compliance", "technical", "billing", "general"]
 
-# [Previous keyword definitions and helper functions remain the same]
+# Keywords for critical issue detection
 CRITICAL_KEYWORDS = {
     'security': ['hack', 'breach', 'leaked', 'stolen', 'unauthorized', 'privacy'],
     'fraud': ['scam', 'fraud', 'fake', 'unauthorized charge', 'stolen'],
@@ -27,65 +22,77 @@ CRITICAL_KEYWORDS = {
     'sensitive': ['racist', 'discrimination', 'harassment', 'abuse', 'offensive']
 }
 
-def create_pie_charts(df):
+def classify_text(text, labels, classifier):
     """
-    Create pie charts for Urgency, Brand Impact, and Critical Issues
+    Perform zero-shot classification on text
     """
-    # Create a figure with subplots
-    fig = make_subplots(
-        rows=1, cols=3,
-        subplot_titles=('Urgency Distribution', 'Brand Impact Distribution', 'Critical Issues Distribution'),
-        specs=[[{'type':'pie'}, {'type':'pie'}, {'type':'pie'}]]
-    )
-
-    # Urgency Pie Chart
-    urgency_counts = df['urgency'].value_counts()
-    fig.add_trace(
-        go.Pie(labels=urgency_counts.index, values=urgency_counts.values,
-               marker_colors=['#FF0000', '#FFA500', '#FFFF00', '#90EE90']),
-        row=1, col=1
-    )
-
-    # Brand Impact Pie Chart
-    # impact_counts = df['brand_impact'].value_counts()
-    # fig.add_trace(
-    #     go.Pie(labels=impact_counts.index, values=impact_counts.values,
-    #            marker_colors=['#FF0000', '#FFA500', '#90EE90']),
-    #     row=1, col=2
-    # )
-
-    # Critical Issues Pie Chart
-    # Split the combined issues and count unique occurrences
-    all_issues = df[df['critical_issues'] != 'none']['critical_issues'].str.split('|').explode()
-    # if len(all_issues) == 0:
-    #     issue_counts = pd.Series({'No Critical Issues': 1})
-    # else:
-    #     issue_counts = all_issues.value_counts()
-
-    # fig.add_trace(
-    #     go.Pie(labels=issue_counts.index, values=issue_counts.values,
-    #            marker_colors=['#FF0000', '#FFA500', '#FFFF00', '#90EE90', '#4169E1']),
-    #     row=1, col=3
-    # )
-
-    # Update layout
-    fig.update_layout(
-        height=400,
-        width=1200,
-        showlegend=True,
-        title_text="Analysis Distribution",
-    )
-
-    # Save the plot to a bytes buffer
-    buf = io.BytesIO()
-    fig.write_image(buf, format='png')
-    buf.seek(0)
-
-    return buf
+    result = classifier(text, labels)
+    return result['labels'][0], result['scores'][0]
+
+def detect_critical_issues(text):
+    """
+    Detect critical issues based on keywords
+    """
+    text_lower = text.lower()
+    issues = []
+
+    for category, keywords in CRITICAL_KEYWORDS.items():
+        if any(keyword in text_lower for keyword in keywords):
+            issues.append(category)
+
+    return issues
+
+def determine_urgency(text, sentiment, critical_issues):
+    """
+    Determine urgency level based on content, sentiment, and critical issues
+    """
+    if critical_issues:
+        return "critical"
+    elif "!" in text or "?" in text or any(word in text.lower() for word in ['urgent', 'asap', 'immediately']):
+        return "high"
+    elif sentiment == "negative":
+        return "medium"
+    else:
+        return "low"
+
+def analyze_brand_impact(text, sentiment, critical_issues):
+    """
+    Analyze potential brand impact
+    """
+    if critical_issues or sentiment == "negative" and ("share" in text.lower() or "viral" in text.lower()):
+        return "severe"
+    elif sentiment == "negative":
+        return "moderate"
+    else:
+        return "minimal"
+
+def generate_recommendations(row):
+    """
+    Generate actionable recommendations based on analysis
+    """
+    recommendations = []
+
+    if row['urgency'] == 'critical':
+        recommendations.append("Immediate escalation required - Route to crisis management team")
+
+    if 'security' in row['critical_issues']:
+        recommendations.append("Engage security team for immediate investigation")
+    elif 'fraud' in row['critical_issues']:
+        recommendations.append("Route to fraud prevention team for investigation")
+    elif 'compliance' in row['critical_issues']:
+        recommendations.append("Escalate to legal/compliance team for review")
+
+    if row['brand_impact'] == 'severe':
+        recommendations.append("Engage PR team for reputation management strategy")
+
+    if row['sentiment'] == 'negative':
+        recommendations.append("Priority customer outreach needed for resolution")
+
+    return ' | '.join(recommendations) if recommendations else "Standard response protocol"
 
 def process_csv(file):
     """
-    Process posts from CSV file with enhanced analysis and visualizations
+    Process posts from CSV file with enhanced analysis
     """
     try:
         # Read the input CSV file
@@ -135,12 +142,6 @@ def process_csv(file):
         # Save results
         results_df.to_csv(output_file, index=False)
 
-        # Generate pie charts
-        charts_buf = create_pie_charts(results_df)
-        charts_file = f"analysis_charts_{timestamp}.png"
-        with open(charts_file, 'wb') as f:
-            f.write(charts_buf.getvalue())
-
         # Generate summary statistics
         total_posts = len(results_df)
         critical_posts = len(results_df[results_df['urgency'] == 'critical'])
@@ -156,15 +157,14 @@ Negative Sentiment Posts: {negative_sentiment}
 Severe Brand Impact Posts: {severe_impact}
 
 The detailed analysis has been saved to: {output_file}
-Charts have been saved to: {charts_file}
         """
 
-        return [output_file, charts_file], summary
+        return output_file, summary
 
     except Exception as e:
-        return [None, None], f"Error processing CSV: {str(e)}"
+        return None, f"Error processing CSV: {str(e)}"
 
-# [Previous example file creation function remains the same]
+# Create example CSV file
 def create_example_file():
     """
     Create an example CSV file for demonstration
@@ -197,7 +197,7 @@ iface = gr.Interface(
         )
     ],
     outputs=[
-        gr.File(label="Download Analysis Files", file_count="multiple"),
+        gr.File(label="Download Detailed Analysis"),
         gr.Textbox(label="Analysis Summary", max_lines=10)
     ],
     title="Enhanced Social Media Analysis System",
@@ -208,7 +208,6 @@ iface = gr.Interface(
     - Brand Impact Assessment
     - Critical Issue Detection
     - Actionable Recommendations
-    - Visual Analytics
 
     Input CSV format:
     - Required columns: 'post_id', 'text'
@@ -224,4 +223,4 @@ if __name__ == "__main__":
         iface.launch()
     finally:
         if os.path.exists(example_file):
-            os.remove(example_file)
+            os.remove(example_file)