commit

app.py

@@ -1,4 +1,3 @@
-from fastapi import FastAPI
 from utils.logging_utils import setup_logging
 from scripts.train_viral_potential import train_viral_potential
 from scripts.train_engagement_rate import train_engagement_rate
@@ -10,27 +9,18 @@ from scripts.analyze_engagement import analyze_engagement
 # Set up logging
 setup_logging()
 
-# Initialize FastAPI app
-app = FastAPI()
-
-@app.get("/")
-def read_root():
-    return {"message": "Instagram AI Backend"}
-
-@app.post("/train-models")
-def train_models():
+# Main application logic
+if __name__ == "__main__":
+    # Train and export models
     train_viral_potential()
     train_engagement_rate()
     train_promotion_strategy()
     train_time_series()
-    return {"message": "Models trained successfully"}
 
-@app.post("/analyze-engagement")
-def analyze_engagement_endpoint():
+    # Analyze engagement data
     analyze_engagement()
-    return {"message": "Engagement analysis completed"}
 
-@app.post("/analyze-image")
-def analyze_image_endpoint(image_url: str, caption: str):
-    analyze_image_url(image_url, caption)
-    return {"message": "Image analysis completed"}
+    # Analyze an example image
+    image_url = "https://example.com/path/to/image.jpg"
+    caption = "This is a beautiful sunset!"
+    analyze_image_url(image_url, caption)

scripts/train_engagement_rate.py

@@ -23,4 +23,5 @@ def train_engagement_rate():
     print(f"Engagement Rate Prediction Model - MAE: {mae:.4f}")
 
     # Save the model
-    joblib.dump(engagement_model, "models/engagement_rate_model.pkl")
+    joblib.dump(engagement_model, "models/engagement_rate_model.pkl")
+    print("Engagement Rate Model saved to models/engagement_rate_model.pkl")

scripts/train_promotion_strategy.py

@@ -26,4 +26,5 @@ def train_promotion_strategy():
     print(f"Promotion Prediction Model Accuracy: {accuracy:.4f}")
 
     # Save the model
-    joblib.dump(promotion_model, "models/promotion_strategy_model.pkl")
+    joblib.dump(promotion_model, "models/promotion_strategy_model.pkl")
+    print("Promotion Strategy Model saved to models/promotion_strategy_model.pkl")

scripts/train_time_series.py

@@ -19,4 +19,5 @@ def train_time_series():
     prophet_model.fit(time_series_data)
 
     # Save the model
-    joblib.dump(prophet_model, "models/prophet_model.pkl")
+    joblib.dump(prophet_model, "models/prophet_model.pkl")
+    print("Prophet Model saved to models/prophet_model.pkl")

scripts/train_viral_potential.py

@@ -26,4 +26,5 @@ def train_viral_potential():
     print(f"Viral Potential Model Accuracy: {accuracy:.4f}")
 
     # Save the model
-    joblib.dump(viral_model, "models/viral_potential_model.pkl")
+    joblib.dump(viral_model, "models/viral_potential_model.pkl")
+    print("Viral Potential Model saved to models/viral_potential_model.pkl")