Create app.py

app.py

@@ -0,0 +1,122 @@
+import os
+import joblib
+import pandas as pd
+from fastapi import FastAPI, HTTPException
+from pydantic import BaseModel
+
+# Load the trained model
+script_dir = os.path.dirname(os.path.abspath(__file__))
+model_path = os.path.join(script_dir, "district_yield_pipeline.pkl")
+
+model_loaded = False
+model = None
+
+if os.path.exists(model_path):
+    try:
+        model = joblib.load(model_path)
+        model_loaded = True
+        print("Model loaded successfully!")
+    except Exception as e:
+        print(f"Error loading model file: {e}")
+else:
+    print(f"Model file not found at: {model_path}")
+    print(f"Available files: {os.listdir(script_dir)}")
+
+class PredictionInput(BaseModel):
+    crop: str
+    season: str
+    state: str
+    area: float
+    annual_rainfall: float
+    fertilizer: float
+    pesticide: float
+    year: int
+
+class PredictionOutput(BaseModel):
+    prediction: str
+    insights: str
+
+app = FastAPI(
+    title="Crop Yield Prediction API",
+    description="API for predicting crop yields based on agricultural parameters",
+    version="1.0.0"
+)
+
+@app.get("/health")
+def health_check():
+    return {"status": "healthy", "model_loaded": model_loaded}
+
+@app.post("/predict", response_model=PredictionOutput)
+def predict(input_data: PredictionInput):
+    if not model_loaded:
+        raise HTTPException(status_code=500, detail="Model not loaded. Please check if the model file exists.")
+    
+    try:
+        # Create input dataframe
+        df = pd.DataFrame({
+            'Crop': [input_data.crop],
+            'Season': [input_data.season],
+            'State': [input_data.state],
+            'Area': [input_data.area],
+            'Annual_Rainfall': [input_data.annual_rainfall],
+            'Fertilizer': [input_data.fertilizer],
+            'Pesticide': [input_data.pesticide],
+            'Year': [input_data.year]
+        })
+        
+        # Make prediction (import numpy here if needed, but not required)
+        import numpy as np
+        prediction = model.predict(df)[0]
+        
+        # Format output
+        result_text = f"""
+### 🌾 Prediction Results
+
+**Predicted Crop Yield:** `{prediction:.2f}` tonnes/hectare
+
+---
+
+**Input Summary:**
+- 🌱 **Crop:** {input_data.crop}
+- 📅 **Season:** {input_data.season}
+- 📍 **State:** {input_data.state}
+- 📏 **Area:** {input_data.area} hectares
+- 🌧️ **Annual Rainfall:** {input_data.annual_rainfall} mm
+- 💊 **Fertilizer:** {input_data.fertilizer} kg
+- 🧪 **Pesticide:** {input_data.pesticide} kg
+- 📅 **Year:** {input_data.year}
+
+---
+
+**Yield Category:**
+"""
+        
+        # Add yield interpretation
+        if prediction < 1:
+            result_text += "⚠️ **Low Yield** - Consider improving farming practices"
+        elif prediction < 5:
+            result_text += "✅ **Moderate Yield** - Good performance"
+        elif prediction < 50:
+            result_text += "🌟 **High Yield** - Excellent performance"
+        else:
+            result_text += "🏆 **Exceptional Yield** - Outstanding performance"
+        
+        # Additional insights
+        insights = f"""
+### 💡 Insights & Recommendations
+
+Based on the prediction of **{prediction:.2f} tonnes/hectare**:
+
+1. **Water Management:** With {input_data.annual_rainfall} mm of rainfall, ensure proper irrigation during dry spells.
+2. **Nutrient Balance:** Current fertilizer usage is {input_data.fertilizer} kg. Monitor soil health regularly.
+3. **Pest Control:** Pesticide usage at {input_data.pesticide} kg. Follow integrated pest management practices.
+4. **Area Optimization:** Managing {input_data.area} hectares requires strategic planning for maximum efficiency.
+
+**Note:** This prediction is based on historical data and machine learning models. 
+Actual yields may vary based on weather conditions, soil quality, and farming practices.
+"""
+        
+        return PredictionOutput(prediction=result_text, insights=insights)
+        
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=f"Error making prediction: {str(e)}")