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 r2_score
from sklearn.preprocessing import StandardScaler

# Generating random features with at least 50 occurrences each
np.random.seed(42)

feature1 = np.random.randint(0, 10, size=100)
feature2 = np.random.randint(0, 10, size=100)
feature3 = np.random.randint(0, 10, size=100)
feature4 = np.random.randint(0, 10, size=100)
feature5 = np.random.randint(0, 10, size=100)
target = np.random.randint(0, 100, size=100)

# Creating a Pandas data frame
data = {
    'Feature1': feature1,
    'Feature2': feature2,
    'Feature3': feature3,
    'Feature4': feature4,
    'Feature5': feature5,
    'Target': target
}

df = pd.DataFrame(data)

# Splitting the data into features and target
X = df.drop('Target', axis=1)
y = df['Target']

# Normalizing the data using StandardScaler
scaler = StandardScaler()
X_scaled = scaler.fit_transform(X)

# Splitting the normalized data into train and test sets
X_train, X_test, y_train, y_test = train_test_split(X_scaled, y, test_size=0.2, random_state=42)

# Fitting the linear regression model
reg_model = LinearRegression()
reg_model.fit(X_train, y_train)

# Predicting the target variable for both train and test sets
y_train_pred = reg_model.predict(X_train)
y_test_pred = reg_model.predict(X_test)

# Calculating R² scores for train and test sets
r2_train = r2_score(y_train, y_train_pred)
r2_test = r2_score(y_test, y_test_pred)

# Printing the R² scores
print("R² score for train set:", r2_train)
print("R² score for test set:", r2_test)