# Import libraries
import numpy as np
import matplotlib.pyplot as plt
from sklearn.ensemble import RandomForestRegressor
from sklearn.model_selection import train_test_split
from sklearn.metrics import mean_squared_error, r2_score
# Generate synthetic regression data
np.random.seed(42)
X = np.linspace(0, 10, 200).reshape(-1, 1)
y = 3 * X.squeeze()**2 + 5 * X.squeeze() + 10 + np.random.randn(200) * 10
# Split the dataset
X_train, X_test, y_train, y_test = train_test_split(
X, y, test_size=0.2, random_state=42
)
# Create Random Forest Regressor
rf_model = RandomForestRegressor(
n_estimators=200,
max_depth=10,
min_samples_split=5,
random_state=42
)
# Train the model
rf_model.fit(X_train, y_train)
# Predict on test data
y_pred = rf_model.predict(X_test)
# Model evaluation
print("Mean Squared Error:", mean_squared_error(y_test, y_pred))
print("R2 Score:", r2_score(y_test, y_pred))
# Sort values for smooth plotting
sorted_idx = X_test.squeeze().argsort()
# Plot actual vs predicted values
plt.figure()
plt.scatter(X_test, y_test)
plt.plot(X_test[sorted_idx], y_pred[sorted_idx])
plt.xlabel("Input Feature (X)")
plt.ylabel("Target Value (y)")
plt.title("Random Forest Regression")
plt.show()
