# Import necessary libraries
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error, r2_score

# Sample Dataset (replace this with your actual dataset)
# Let's assume we have a dataset with features: 'height', 'weight', and 'experience'
data = {
    'height': [150, 160, 170, 180, 190],
    'weight': [50, 60, 70, 80, 90],
    'experience': [2, 3, 4, 5, 6],
    'age': [25, 28, 30, 35, 40]  # This is the target variable
}

# Create a DataFrame
df = pd.DataFrame(data)



# Step 2: Data Preprocessing
# Define features (X) and target (y)
X = df[['height', 'weight', 'experience']]  # Independent variables
y = df['age']  # Dependent variable (age)

# Step 3: Train-Test Split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)

# Step 4: Train the Regression Model (Linear Regression)
model = LinearRegression()
model.fit(X_train, y_train)

# Step 5: Make Predictions
y_pred = model.predict(X_test)

# Step 6: Model Evaluation
# Calculate Mean Squared Error (MSE)
mse = mean_squared_error(y_test, y_pred)
print(f"Mean Squared Error: {mse}")

# Calculate R-squared (R²) value
r2 = r2_score(y_test, y_pred)
print(f"R-squared value: {r2}")