models/xgboost/add_accuracy.py

import pandas as pd
import numpy as np
from xgboost import XGBClassifier
from sklearn.metrics import accuracy_score
from data_preparation.prepare_dataset import get_numpy_splits
import os

print("Loading dataset for evaluation...")
splits, _, _, _ = get_numpy_splits(
    model_name="face_orientation",
    split_ratios=(0.7, 0.15, 0.15),
    seed=42,
    scale=False
)
X_train, y_train = splits["X_train"], splits["y_train"]
X_val,   y_val   = splits["X_val"],   splits["y_val"]

csv_path = 'models/xgboost/sweep_results_all_40.csv'
df = pd.read_csv(csv_path)

# We will calculate accuracy for each row
accuracies = []

print(f"Re-evaluating {len(df)} configurations for accuracy. This will take a few minutes...")
for idx, row in df.iterrows():
    params = {
        "n_estimators": int(row["n_estimators"]),
        "max_depth": int(row["max_depth"]),
        "learning_rate": float(row["learning_rate"]),
        "subsample": float(row["subsample"]),
        "colsample_bytree": float(row["colsample_bytree"]),
        "reg_alpha": float(row["reg_alpha"]),
        "reg_lambda": float(row["reg_lambda"]),
        "random_state": 42,
        "use_label_encoder": False,
        "verbosity": 0,
        "eval_metric": "logloss"
    }
    
    # Train the exact same model quickly
    model = XGBClassifier(**params)
    model.fit(X_train, y_train)
    
    # Get validation predictions and calculate accuracy
    val_preds = model.predict(X_val)
    acc = accuracy_score(y_val, val_preds)
    accuracies.append(round(acc, 4))
    
    if (idx + 1) % 5 == 0:
        print(f"Processed {idx + 1}/{len(df)} trials...")

# Add accuracy column and save back to CSV
df.insert(2, 'val_accuracy', accuracies)
df.to_csv(csv_path, index=False)

print(f"\nDone! Updated {csv_path} with 'val_accuracy'.")
# Display the top 5 by accuracy now just to see
top5_acc = df.nlargest(5, 'val_accuracy')[['task_id', 'val_accuracy', 'val_f1', 'val_loss']]
print("\nTop 5 Trials by Accuracy:")
print(top5_acc.to_string(index=False))