Update app.py

app.py

@@ -214,4 +214,83 @@ niche_trends = solved_df.groupby('content_type')['sentiment'].mean().sort_values
 logging.info("Top Performing Content Types by Sentiment:")
 print(niche_trends)
 
+# Viral Potential of Posts
+logging.info("Training model for viral potential prediction...")
+viral_threshold = engagement_df['engagement_rate'].quantile(0.9)
+engagement_df['viral'] = engagement_df['engagement_rate'].apply(lambda x: 1 if x >= viral_threshold else 0)
+solved_df['viral'] = engagement_df['viral']
+
+# Features for viral potential prediction
+features = ['caption_length', 'hashtag_count', 'sentiment', 'content_type_encoded', 'media_type_encoded']
+X = solved_df[features]
+y = solved_df['viral']
+
+# Split data into training and testing sets
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+
+# Train a Random Forest Classifier
+viral_model = RandomForestClassifier(random_state=42)
+viral_model.fit(X_train, y_train)
+
+# Evaluate the model
+y_pred = viral_model.predict(X_test)
+accuracy = accuracy_score(y_test, y_pred)
+logging.info(f"Viral Potential Model Accuracy: {accuracy:.4f}")
+
+# Feature importance
+importance = viral_model.feature_importances_
+for feature, score in zip(features, importance):
+    logging.info(f"Feature Importance - {feature}: {score:.4f}")
+
+# Engagement Rate Predictions
+logging.info("Training model for engagement rate prediction...")
+features = ['caption_length', 'hashtag_count', 'sentiment', 'content_type_encoded', 'media_type_encoded', 'posting_time_encoded']
+X = solved_df[features]
+y = engagement_df['engagement_rate']
+
+# Split data into training and testing sets
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+
+# Train an XGBoost Regressor
+engagement_model = XGBRegressor(random_state=42)
+engagement_model.fit(X_train, y_train)
+
+# Evaluate the model
+y_pred = engagement_model.predict(X_test)
+mae = mean_absolute_error(y_test, y_pred)
+logging.info(f"Engagement Rate Prediction Model - MAE: {mae:.4f}")
+
+# Feature importance
+importance = engagement_model.feature_importances_
+for feature, score in zip(features, importance):
+    logging.info(f"Feature Importance - {feature}: {score:.4f}")
+
+# Which Type of Posts Yield Greater Results When Promoted
+logging.info("Training model for promotion prediction...")
+promotion_threshold = engagement_df['engagement_rate'].quantile(0.8)
+engagement_df['promote'] = engagement_df['engagement_rate'].apply(lambda x: 1 if x >= promotion_threshold else 0)
+solved_df['promote'] = engagement_df['promote']
+
+# Features for promotion prediction
+features = ['caption_length', 'hashtag_count', 'sentiment', 'content_type_encoded', 'media_type_encoded']
+X = solved_df[features]
+y = solved_df['promote']
+
+# Split data into training and testing sets
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+
+# Train a Logistic Regression Model
+promotion_model = LogisticRegression(random_state=42)
+promotion_model.fit(X_train, y_train)
+
+# Evaluate the model
+y_pred = promotion_model.predict(X_test)
+accuracy = accuracy_score(y_test, y_pred)
+logging.info(f"Promotion Prediction Model Accuracy: {accuracy:.4f}")
+
+# Analyze content type impact
+content_type_impact = solved_df.groupby('content_type')['promote'].mean().sort_values(ascending=False)
+logging.info("Content Type Impact on Promotion:")
+print(content_type_impact)
+
 logging.info("Analysis complete!")