'''
This code uses XGBoost egression model on  for Multivariate Inputs 
(Predicting a Single Target with 5 features).

'''
import time

import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
from sklearn.metrics import mean_absolute_error, mean_squared_error, r2_score
from sklearn.model_selection import train_test_split
from xgboost import XGBRegressor

# Load CSV dataset and define feature columns and target column name
start_cpu = time.process_time()
df = pd.read_csv("WT_Dummy_Fatigue.csv")

features = [
    "wind_speed_mps",
    "turb_intensity",
    "yaw_misalignment_deg",
    "design_load_kN",
]
target = "fatigue_life_years"

X = df[features]
y = df[target]

# Split data into training (70%) and testing (30%) sets
X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.3, random_state=42
)

# Initialize and train the XGBoost Regressor
model = XGBRegressor(
    n_estimators=100, learning_rate=0.1, max_depth=5, random_state=42
)
model.fit(X_train, y_train)

# Make predictions on the test set
y_pred = model.predict(X_test)

# Evaluate model performance
mae = mean_absolute_error(y_test, y_pred)
r2 = r2_score(y_test, y_pred)

print("\n===== XGBoost Regressor Performance")
print(f"Mean Absolute Error [years]: {mae:,.2f}")
print(f"R-squared Score: {r2:.4f}")

# Plot Predicted vs. Actual values
plt.figure(figsize=(7, 6))
plt.scatter(y_test, y_pred, alpha=0.75, color="b", s=20, label="Predictions")

# Perfect predictions line (diagonal)
lims = [
    min(y_test.min(), y_pred.min()),
    max(y_test.max(), y_pred.max()),
]
plt.plot(lims, lims, "--", color="r", label="Perfect Fit")

plt.xlabel("Actual Values")
plt.ylabel("Predicted Values")
plt.title("XGBoost Regressor: Predicted vs. Actual Values")
plt.legend()
plt.grid(True, linestyle=":", alpha=0.75)
plt.savefig("WT_Fatigue_XGBoost.png")

end_cpu = time.process_time()
cpu_duration = np.round(end_cpu - start_cpu, 1)
print(f"CPU time to execute ML algorithm: {cpu_duration} [s]\n")