LinearRegression.py

import pandas as pd
import matplotlib.pyplot as plt
from sklearn.linear_model import LinearRegression
from sklearn.model_selection import train_test_split
from sklearn.metrics import mean_squared_error, r2_score

# Load the CSV file
data = pd.read_csv('TeleCom.csv')
df = pd.DataFrame(data)
# Show the Last few rows
print("Bottom Data Samples for testing:")
print(data.tail())

# Show the first few rows for model training consistency
'''print("Top Data Samples for testing:")
print(data.tail())'''

# Extract relevant columns
X = data[['Salary']]  # Independent variable
y = data['TaxDeduction']  # Dependent variable

# Split data into train and test sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Create and train the linear regression model
model = LinearRegression()
model.fit(X_train, y_train)

# Predict using the model
y_pred = model.predict(X_test)

# Evaluate some aspects of the model
print(f"R² score: {r2_score(y_test, y_pred):.4f}")
print(f"Mean Squared Error: {mean_squared_error(y_test, y_pred):.2f}")
print(f"Regression Coefficient: {model.coef_[0]:.2f}")
print(f"Intercept: {model.intercept_:.2f}")

#Perform data analysis
print("\nData Analysis:")
print(f"Total number of employees: {len(data)}")
print(f"Number of employees in training set: {len(X_train)}")
print(f"Number of employee in test set: {len(X_test)}")
print(f"Max salary : {df['Salary'].max():.2f}")
print(f"Min salary : {df['Salary'].min():.2f}")

#Mean, max, and min values for Salary and Tax Deduction in the training set
print("\nSalary Training Set Statistics:")
print(f"Mean Salary in training set: {X_train['Salary'].mean():.2f}")
print(f"Max Salary in training set: {X_train['Salary'].max():.2f}")
print(f"Average Salary in training set: {X_train['Salary'].mean():.2f}")
print(f"Min Salary in training set: {X_train['Salary'].min():.2f}")

# Mean, max, and min values for Tax Deduction in the training set
print("\ntex Deduction Training Set Statistics:")
print(f"Mean Tax Deduction in training set: {y_train.mean():.2f}")
print(f"Max Tax Deduction in training set: {y_train.max():.2f}")
print(f"Average Tax Deduction in training set: {y_train.mean():.2f}")
print(f"Min Tax Deduction in training set: {y_train.min():.2f}")

#I display the first 5 predictions
print(f"Predicted values: {y_pred[:5]}")  

# I used a simple if statement to determine if the predicted tax deductions are increasing or decreasing based on the sample test data
if sorted(y_pred)[-1] > sorted(y_pred)[0]:
    print("Predicted tax deductions are increasing.")
else:
    print("Predicted tax deductions are decreasing.")

# Visualize the regression line
plt.figure(figsize=(8, 6))
plt.scatter(X_test, y_test, color='blue', label='Actual Salary')
plt.plot(X_test, y_pred, color='red', linewidth=2, label='Predicted Salary (Regression Line)')
plt.title('Linear Regression: Tax Deduction vs Salary')
plt.xlabel('Salary')
plt.ylabel('Tax Deduction')
plt.legend()
plt.grid(True)
plt.tight_layout()
plt.show()