Upload app.py

app.py

@@ -11,7 +11,6 @@ try:
     models = joblib.load('email_quality_models.pkl')
     scaler = joblib.load('feature_scaler.pkl')
     day_encoder = joblib.load('day_encoder.pkl')
-    list_encoder = joblib.load('list_encoder.pkl')
     feature_names = joblib.load('feature_names.pkl')
     model_results = joblib.load('model_results.pkl')
 except Exception as e:
@@ -53,50 +52,115 @@ def section_score(features):
     score = max(0, min(100, score))
     return score
 
-def analyze_email_complete(subject, preview_text, campaign_name, body_text, day_of_week, 
-                         email_list, send_time, total_recipients, target_metric):
-    # Extract features for each section
+def section_suggestion(section, features):
+    # Simple, section-specific suggestions
+    if section == "subject":
+        if features['length'] > 50:
+            return "Try shortening your subject line for better impact."
+        if features['emoji_count'] == 0:
+            return "Add an emoji to make your subject line stand out."
+        if features['exclamation_count'] == 0:
+            return "Consider adding an exclamation mark for urgency."
+        return "Your subject line looks good!"
+    elif section == "preview":
+        if features['length'] < 20:
+            return "Add more detail to your preview text."
+        if features['emoji_count'] == 0:
+            return "Try adding an emoji to your preview text."
+        return "Your preview text is engaging!"
+    elif section == "body":
+        if features['word_count'] < 50:
+            return "Consider a longer, more detailed email body."
+        if features['exclamation_count'] == 0:
+            return "Try using an exclamation mark to highlight key points."
+        return "Your email body is well-structured!"
+    return ""
+
+def predict_email_performance(subject, preview_text, campaign_name, body_text, day_of_week, send_time, target_metric):
+    # Extract text features
+    subject_features = extract_text_features(subject)
+    campaign_features = extract_text_features(campaign_name)
+    preview_features = extract_text_features(preview_text)
+    body_features = extract_text_features(body_text)
+    # Parse send time
+    try:
+        send_hour = datetime.strptime(send_time, '%I:%M %p').hour
+    except:
+        send_hour = 9  # Default to 9 AM
+    # Encode categorical variables
+    try:
+        day_encoded = day_encoder.transform([day_of_week])[0]
+    except:
+        day_encoded = 0  # Default encoding
+    # Create feature vector (no list or audience size)
+    features = [
+        500000,  # Placeholder for audience size (kept for model compatibility)
+        send_hour,
+        day_encoded,
+        0  # Placeholder for list (kept for model compatibility)
+    ]
+    # Add text features in correct order
+    for prefix, feats in zip(['subject_', 'campaign_', 'preview_'], [subject_features, campaign_features, preview_features]):
+        for suffix in ['length', 'word_count', 'exclamation_count', 'question_count', 'emoji_count', 'number_count', 'caps_ratio']:
+            features.append(feats[suffix])
+    # For body, just append features (if you want to use them in the model, retrain with these features)
+    for suffix in ['length', 'word_count', 'exclamation_count', 'question_count', 'emoji_count', 'number_count', 'caps_ratio']:
+        features.append(body_features[suffix])
+    # Scale features (truncate or pad to match model input)
+    features = features[:len(feature_names)]
+    features_scaled = scaler.transform([features])
+    # Make prediction
+    model = models[target_metric]
+    prediction = model.predict(features_scaled)[0]
+    # Convert to percentage and ensure reasonable bounds
+    if target_metric == 'open_rate':
+        prediction = max(0, min(1, prediction)) * 100
+    elif target_metric == 'click_rate':
+        prediction = max(0, min(0.5, prediction)) * 100
+    else:  # unsubscribe_rate
+        prediction = max(0, min(0.1, prediction)) * 100
+    return prediction
+
+def analyze_email_complete(subject, preview_text, campaign_name, body_text, day_of_week, send_time, target_metric):
+    # Section features and scores
     subject_features = extract_text_features(subject)
     preview_features = extract_text_features(preview_text)
     body_features = extract_text_features(body_text)
-    
-    # Section scores (placeholder logic)
     subject_score = section_score(subject_features)
     preview_score = section_score(preview_features)
     body_score = section_score(body_features)
-    
-    # Overall performance score (dynamic placeholder: weighted avg of section scores)
+    # Section suggestions
+    subject_sugg = section_suggestion("subject", subject_features)
+    preview_sugg = section_suggestion("preview", preview_features)
+    body_sugg = section_suggestion("body", body_features)
+    # Overall performance score (weighted avg)
     performance_score = int(round(0.4 * subject_score + 0.3 * preview_score + 0.3 * body_score))
-    
+    # Predicted metric
+    predicted_value = predict_email_performance(subject, preview_text, campaign_name, body_text, day_of_week, send_time, target_metric)
     # Sentiment analysis
     text_for_sentiment = f"{subject}\n{preview_text}\n{body_text}"
     sentiment_result = sentiment(text_for_sentiment)[0]
-    
     # Zero-shot classification
     labels = ["engaging", "promotional", "informative", "urgent", "personal"]
     classification_result = classifier(text_for_sentiment, labels)
-    
-    # Recommendations (simple, based on features)
-    recommendations = []
-    if subject_features['length'] > 50:
-        recommendations.append(f"📧 Consider shortening your subject line (currently {subject_features['length']} chars)")
-    if subject_features['emoji_count'] == 0:
-        recommendations.append("😊 Consider adding an emoji to your subject line")
-    if preview_features['length'] < 20:
-        recommendations.append("👀 Add more detail to your preview text")
-    if body_features['word_count'] < 50:
-        recommendations.append("✍️ Consider a longer, more detailed email body")
-    if sentiment_result['label'] == "NEGATIVE":
-        recommendations.append("😬 Try a more positive tone in your email")
-    
     # Format output
+    metric_label = {
+        "open_rate": "Open Rate",
+        "click_rate": "Click Rate",
+        "unsubscribe_rate": "Unsubscribe Rate"
+    }[target_metric]
     output = f"""
 ## 📊 Performance Score: {performance_score}/100
 
-### ✂️ Section Scores
-- **Subject Line:** {subject_score}/100
-- **Preview Text:** {preview_score}/100
-- **Body Text:** {body_score}/100
+### 🎯 Predicted {metric_label}: {predicted_value:.2f}%
+
+### ✂️ Section Scores & Suggestions
+- **Subject Line:** {subject_score}/100  
+  _Suggestion: {subject_sugg}_
+- **Preview Text:** {preview_score}/100  
+  _Suggestion: {preview_sugg}_
+- **Body Text:** {body_score}/100  
+  _Suggestion: {body_sugg}_
 
 ### 📈 Sentiment Analysis
 - **Sentiment:** {sentiment_result['label']} (confidence: {sentiment_result['score']:.2f})
@@ -105,30 +169,17 @@ def analyze_email_complete(subject, preview_text, campaign_name, body_text, day_
 """
     for i, (label, score) in enumerate(zip(classification_result['labels'][:3], classification_result['scores'][:3])):
         output += f"- **{label.title()}**: {score:.2f}\n"
-    if recommendations:
-        output += "\n### 💡 Recommendations\n"
-        for rec in recommendations[:5]:
-            output += f"{rec}\n"
     output += f"""
 ### 📋 Email Details
 - **Subject Length:** {subject_features['length']} characters
 - **Preview Length:** {preview_features['length']} characters
 - **Body Word Count:** {body_features['word_count']} words
 - **Send Time:** {send_time} on {day_of_week}
-- **Target Audience:** {int(total_recipients):,} recipients
 """
     return output
 
 # Available options
 day_options = ['Monday', 'Tuesday', 'Wednesday', 'Thursday', 'Friday', 'Saturday', 'Sunday']
-list_options = [
-    'C4 - Very Engaged',
-    'C4 - Less Engaged', 
-    'C4 - Very Engaged, C4 - Less Engaged',
-    'C4 - Re-Engage',
-    'New Users added in last 30 days (all entry points)',
-    'FMP: 2024 Premium Users Opted In to Weekly'
-]
 
 demo = gr.Interface(
     fn=analyze_email_complete,
@@ -138,20 +189,18 @@ demo = gr.Interface(
         gr.Textbox(label="📋 Campaign Name", placeholder="Enter campaign name"),
         gr.Textbox(label="📝 Email Body", placeholder="Paste your email body here"),
         gr.Dropdown(choices=day_options, label="📅 Day of Week", value="Thursday"),
-        gr.Dropdown(choices=list_options, label="📮 Email List", value="C4 - Very Engaged"),
         gr.Textbox(label="⏰ Send Time", placeholder="9:00 AM", value="9:00 AM"),
-        gr.Number(label="👥 Total Recipients", value=500000),
-        gr.Radio(choices=['open_rate', 'click_rate', 'unsubscribe_rate'], 
+        gr.Radio(choices=['open_rate', 'click_rate', 'unsubscribe_rate'],
                 label="🎯 Target Metric", value='click_rate')
     ],
     outputs=gr.Markdown(),
     title="🚀 Email Performance Predictor - Forks Over Knives",
-    description="Predict email performance and get actionable recommendations based on your campaign data",
+    description="Predict email performance and get actionable, section-specific recommendations based on your campaign data",
     examples=[
-        ["Wrap Up Your Monday with Flavor 🌯🥑", "Ready in minutes—perfect for lunch, dinner, or...", 
-         "Meatless Monday | Black Bean Avo Wraps", "Try our new wraps! They're delicious and easy to make.", "Monday", "C4 - Very Engaged", "9:00 AM", 545464, "click_rate"],
-        ["NEW Special Issue: Plant-Based Bowls", "Get your first look inside the latest issue...", 
-         "Plant-Based Bowls Special Issue", "Discover 50+ new recipes in this special issue.", "Saturday", "C4 - Very Engaged, C4 - Less Engaged", "1:30 AM", 650681, "open_rate"]
+        ["Wrap Up Your Monday with Flavor 🌯🥑", "Ready in minutes—perfect for lunch, dinner, or...",
+         "Meatless Monday | Black Bean Avo Wraps", "Try our new wraps! They're delicious and easy to make.", "Monday", "9:00 AM", "click_rate"],
+        ["NEW Special Issue: Plant-Based Bowls", "Get your first look inside the latest issue...",
+         "Plant-Based Bowls Special Issue", "Discover 50+ new recipes in this special issue.", "Saturday", "1:30 AM", "open_rate"]
     ]
 )