demo model

app.py

@@ -0,0 +1,142 @@
+# app.py
+# The core FastAPI application for our IGUDAR model
+
+import joblib
+import pandas as pd
+import numpy as np
+from fastapi import FastAPI, HTTPException
+from pydantic import BaseModel
+import warnings
+warnings.filterwarnings('ignore')
+
+# --- 1. DEFINE APP AND LOAD MODELS ---
+
+# Initialize the FastAPI app
+app = FastAPI(
+    title="IGUDAR AI Valuation API",
+    description="An API to serve the trained property valuation model for Moroccan real estate.",
+    version="1.0"
+)
+
+# Load the trained model and preprocessing objects at startup
+# This ensures they are loaded only once, making the API fast.
+try:
+    model = joblib.load("./models/valuation_model.joblib")
+    preprocessing = joblib.load("./models/preprocessing_objects.joblib")
+    
+    # Extract the individual objects from the preprocessing file
+    scaler = preprocessing['scaler']
+    label_encoders = preprocessing['label_encoders']
+    feature_names = preprocessing['feature_names']
+    
+    print("✅ Models and preprocessing objects loaded successfully.")
+
+except FileNotFoundError:
+    print("❌ ERROR: Model or preprocessing files not found. Ensure they are in the /models directory.")
+    model = None # Set to None to handle errors gracefully
+
+# --- 2. DEFINE THE INPUT DATA MODEL ---
+
+# Pydantic model for input data validation.
+# This tells FastAPI what the incoming JSON should look like.
+class PropertyFeatures(BaseModel):
+    size_m2: float
+    bedrooms: int
+    bathrooms: int
+    age_years: int
+    property_type: str
+    city: str
+    infrastructure_score: float
+    economic_score: float
+    lifestyle_score: float
+    investment_score: float
+    neighborhood_tier: int
+    total_amenities: int
+    data_quality: float = 0.9 # Default value
+    has_coordinates: bool = True # Default value
+
+# --- 3. CREATE THE PREDICTION ENDPOINT ---
+
+@app.post("/valuation")
+def predict_valuation(property_data: PropertyFeatures):
+    """
+    Predicts the value of a property based on its features.
+    Accepts a JSON object with property details and returns a prediction.
+    """
+    if model is None:
+        raise HTTPException(status_code=500, detail="Model is not loaded. Check server logs.")
+
+    # Convert the incoming Pydantic model to a dictionary
+    data_dict = property_data.dict()
+    
+    # Start with a dictionary of all zeros for our feature vector
+    features = {name: 0 for name in feature_names}
+
+    # --- Feature Engineering (must EXACTLY match the training script) ---
+    
+    # 1. Direct mapping
+    features.update({
+        'size_m2': data_dict.get('size_m2', 100),
+        'bedrooms': data_dict.get('bedrooms', 2),
+        'bathrooms': data_dict.get('bathrooms', 1),
+        'age_years': min(data_dict.get('age_years', 5), 50),
+        'infrastructure_score': data_dict.get('infrastructure_score', 50),
+        'economic_score': data_dict.get('economic_score', 50),
+        'lifestyle_score': data_dict.get('lifestyle_score', 50),
+        'investment_score': data_dict.get('investment_score', 50),
+        'neighborhood_tier': data_dict.get('neighborhood_tier', 3),
+        'total_amenities': data_dict.get('total_amenities', 20),
+        'data_quality': data_dict.get('data_quality', 0.8)
+    })
+    
+    # 2. Calculated features
+    features['room_density'] = min((features['bedrooms'] + features['bathrooms']) / features['size_m2'], 0.2)
+    features['amenity_density'] = min(features['total_amenities'] / features['size_m2'], 2)
+    features['location_quality'] = (features['infrastructure_score'] * 0.4 + 
+                                   features['economic_score'] * 0.3 + 
+                                   features['lifestyle_score'] * 0.3)
+    features['investment_attractiveness'] = ((5 - features['neighborhood_tier']) * 20 + 
+                                            features['location_quality'] * 0.5 + 
+                                            (10 if data_dict.get('has_coordinates', True) else 0) +
+                                            (features['data_quality'] * 20))
+                                            
+    # NOTE: We can't calculate 'city_median_size' or 'city_infra_avg' for a single prediction.
+    # We will use average values or handle them during training. For now, we leave them as 0.
+    # This is a common challenge in deployment. A better approach would be to have a pre-calculated
+    # dictionary of city stats to look up from. For this demo, this is acceptable.
+
+    # 3. Categorical Encoding
+    for col, le in label_encoders.items():
+        encoded_col_name = f"{col}_encoded"
+        if encoded_col_name in features:
+            try:
+                # Use the loaded encoder to transform the input string
+                value = data_dict.get(col)
+                encoded_value = le.transform([value])[0]
+                features[encoded_col_name] = encoded_value
+            except Exception as e:
+                # If the category is new/unseen, default to 0 (or another strategy)
+                print(f"Warning: Could not encode '{value}' for feature '{col}'. Defaulting to 0. Error: {e}")
+                features[encoded_col_name] = 0
+
+    # Create a DataFrame in the exact order of feature_names
+    df = pd.DataFrame([features])[feature_names]
+
+    # Scale the features using the loaded scaler
+    df_scaled = scaler.transform(df)
+
+    # Make the prediction
+    prediction = model.predict(df_scaled)[0]
+    
+    # Post-process for a clean response
+    predicted_price = round(max(200000, prediction), 0) # Apply minimum realistic price
+    
+    return {
+        "predicted_price_mad": predicted_price,
+        "predicted_price_per_m2": round(predicted_price / data_dict['size_m2'], 0),
+        "model_used": "igudar_valuation_v1_xgboost"
+    }
+
+@app.get("/")
+def read_root():
+    return {"message": "Welcome to the IGUDAR AI Valuation API. Use the /docs endpoint to test."}

models/igudar_fixed_preprocessing_20250620_233500.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7c6b5d64702e089ec7c7b884fee399b0e91be3d6e56690647fac161beb1995d
+size 5675

models/igudar_fixed_valuation_20250620_233500.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd12af4accd24b1de3ab873656fcaeeb8d2535826948cf3868c70f6b4107c1e7
+size 725863

requirements.txt

@@ -0,0 +1,8 @@
+fastapi
+uvicorn
+pandas
+numpy
+scikit-learn
+xgboost
+joblib
+pydantic