MACHINE LEARNING

Salary Prediction Tool

A Linear Regression model that predicts professional salaries based on years of experience with approx. 89% accuracy.

Machine Learning Python Scikit-Learn Regression

Problem & Solutions

The Salary Prediction Tool solves a classic supervised learning problem: predicting a continuous variable (Salary) based on an independent variable (Years of Experience). By training a Linear Regression model, we establish a correlation trend line that can forecast earnings for any given experience level.

89%

Accuracy

30

Data Points

Model Implementation

1. Load & Split

We load the dataset using Pandas and split it into training (80%) and testing (20%) sets using train_test_split. This ensures the model is evaluated on unseen data.

model.py

import pandas as pd
from sklearn.model_selection import train_test_split

data = pd.read_csv("Salary.csv")
x = data[["YearsExperience"]]
y = data[["Salary"]]

xtrain, xtest, ytrain, ytest = train_test_split(x, y, test_size=0.2, random_state=42)

2. Train Model

We initialize Scikit-Learn's LinearRegression algorithm and fit it to our training data, helping the model learn the relationship between experience and salary.

model.py

from sklearn.linear_model import LinearRegression

model = LinearRegression()
model.fit(xtrain, ytrain)

3. Prediction & Evaluation

Finally, we predict salaries for the test set and score the model's accuracy. The result confirms how well our regression line fits the data.

model.py

y_pred = model.predict(xtest)
accuracy = model.score(xtest, ytest)

print(f"Model Accuracy: {accuracy}") 
# Output: ~0.89

Outcomes & Final Thoughts

This project successfully implemented a machine learning pipeline to forecast professional income. Key takeaways include:

Linear Regression Mastery: Demonstrated clear understanding of fitting a regression line to minimize error.
Data Visualization: Utilized plotting libraries to inspect data distribution before training.
High Accuracy: Achieved an accuracy score of approximately 89%, indicating strong predictive capability.

View More Projects Back to Top