| """
|
| Model Export Script
|
| Regenerates and exports the trained model with current dependencies
|
| Run this to fix numpy compatibility issues
|
| """
|
|
|
| import os
|
| import sys
|
| import json
|
| import joblib
|
| import numpy as np
|
| import pandas as pd
|
| from sklearn.model_selection import train_test_split
|
| from sklearn.linear_model import LinearRegression
|
| from sklearn.metrics import mean_absolute_error, mean_squared_error, r2_score
|
|
|
| print("\n" + "="*70)
|
| print("📊 Model Export & Regeneration Script")
|
| print("="*70)
|
|
|
|
|
| print("\n[1/5] Loading data...")
|
| try:
|
| df = pd.read_csv("../../cleaned_patient_data.csv")
|
| print(f"✅ Data loaded: {df.shape[0]} samples, {df.shape[1]} features")
|
| except FileNotFoundError:
|
| print("❌ Error: cleaned_patient_data.csv not found!")
|
| print("Expected path: ../../cleaned_patient_data.csv")
|
| sys.exit(1)
|
|
|
|
|
| print("\n[2/5] Preparing features and target...")
|
| X = df.drop(columns=["workload_hours"])
|
| y = df["workload_hours"]
|
|
|
| print(f"✅ Original features: {X.shape[1]}")
|
| print(f" {X.columns.tolist()}")
|
|
|
|
|
| print("\n Computing interaction features...")
|
| X["alert_cognition_interaction"] = X["num_alerts_last_week"] * (30 - X["cognitive_score"])
|
| X["activity_sleep_ratio"] = X["patient_activity_level"] / X["sleep_hours_avg"]
|
| X["cognitive_activity_ratio"] = X["cognitive_score"] * X["patient_activity_level"] / 1000
|
|
|
| print(f"✅ After interaction features: {X.shape[1]}")
|
| print(f" {X.columns.tolist()}")
|
|
|
|
|
| print("\n[3/5] Splitting data...")
|
| X_train, X_test, y_train, y_test = train_test_split(
|
| X, y, test_size=0.2, random_state=42
|
| )
|
| print(f"✅ Training: {X_train.shape[0]} samples")
|
| print(f"✅ Testing: {X_test.shape[0]} samples")
|
|
|
|
|
| print("\n[4/5] Training Linear Regression model...")
|
| model = LinearRegression()
|
| model.fit(X_train, y_train)
|
|
|
|
|
| y_pred = model.predict(X_test)
|
| r2 = r2_score(y_test, y_pred)
|
| mae = mean_absolute_error(y_test, y_pred)
|
| rmse = np.sqrt(mean_squared_error(y_test, y_pred))
|
|
|
| print(f"✅ Model trained!")
|
| print(f" R² Score: {r2:.4f}")
|
| print(f" MAE: {mae:.4f}")
|
| print(f" RMSE: {rmse:.4f}")
|
|
|
| if r2 >= 0.80:
|
| print(f" ✅ DSO Target ACHIEVED (R² ≥ 0.80)")
|
| else:
|
| print(f" ⚠️ DSO Target PENDING (R² = {r2:.4f}, target 0.80)")
|
|
|
|
|
| print("\n[5/5] Exporting model and metadata...")
|
|
|
|
|
| model_path = os.path.join(os.path.dirname(__file__), "workload_predictor.pkl")
|
| joblib.dump(model, model_path)
|
| print(f"✅ Model exported: {model_path}")
|
|
|
|
|
| features_path = os.path.join(os.path.dirname(__file__), "features.json")
|
| with open(features_path, 'w') as f:
|
| json.dump(X.columns.tolist(), f, indent=2)
|
| print(f"✅ Features exported: {features_path}")
|
|
|
|
|
| metadata = {
|
| "model_type": "RandomForestRegressor",
|
| "r2_score": float(r2),
|
| "mae": float(mae),
|
| "rmse": float(rmse),
|
| "n_features": int(X.shape[1]),
|
| "features": X.columns.tolist(),
|
| "training_samples": int(X_train.shape[0]),
|
| "test_samples": int(X_test.shape[0]),
|
| "export_timestamp": pd.Timestamp.now().isoformat(),
|
| "numpy_version": np.__version__,
|
| "sklearn_version": __import__('sklearn').__version__
|
| }
|
|
|
| metadata_path = os.path.join(os.path.dirname(__file__), "model_metadata.json")
|
| with open(metadata_path, 'w') as f:
|
| json.dump(metadata, f, indent=2)
|
| print(f"✅ Metadata exported: {metadata_path}")
|
|
|
| print("\n" + "="*70)
|
| print("✅ Model Export Complete!")
|
| print("="*70)
|
| print("\n📋 Files created/updated:")
|
| print(f" • {model_path}")
|
| print(f" • {features_path}")
|
| print(f" • {metadata_path}")
|
| print("\n🚀 Next: Restart Flask API")
|
| print(" Run: python app.py")
|
| print("="*70 + "\n")
|
|
|
