Student Marks Prediction using ML Welcome to the Student Marks Predictor project! This repository contains a comprehensive Python project developed to predict student marks based on their study hours. Utilizing machine learning techniques, particularly linear regression, this project aims to assist educators and students in understanding the correlation between study hours and academic performance.
Data Visualization: Explore the dataset visually using matplotlib, gaining insights into the relationship between students’ study hours and their marks. Data Cleaning: Handle missing values in the dataset with robust data cleaning techniques, ensuring data integrity and reliability. Model Training: Employ scikit-learn’s LinearRegression model to train on the dataset, enabling accurate prediction of student marks. Model Evaluation: Assess the performance of the trained model using metrics such as the R-squared score, providing insights into the model’s effectiveness. Model Fine-tuning: Fine-tune the trained model by visualizing the regression line on a scatter plot, enhancing predictive accuracy and reliability. Model Persistence: Save the trained machine learning model using joblib, facilitating future use and deployment in various applications.
Clone the Repository: Clone this repository to your local machine using git clone https://github.com/your-username/Paa-Fail-Model.git. Navigate to the Repository: Access the cloned repository directory using cd Student-Marks-Prediction-using-ML. Open the Notebook: Launch the Jupyter Notebook prediction.ipynb to explore and run the project code. Explore and Run: Dive into the notebook to explore the dataset, train the predictive model, evaluate its performance, and fine-tune as needed. Contribute: Feel free to contribute to the project by suggesting improvements, reporting issues, or adding new features via pull requests. Dataset The dataset (have your own datasets) contains information on students study hours and marks. It serves as the foundation for training and testing the predictive model.
pip install -r requirements.txt
model.ipynb: Jupyter Notebook containing the Python code for the entire project, from data exploration to model training and evaluation. student_info.csv: Dataset containing students’ study hours and marks, used for training and testing the predictive model. predicted_data.xlsx: Excel file storing the predicted student marks generated by the trained model. student_mark_predictor.pkl: Pickle file containing the trained machine learning model for persistence and future use. Feel free to explore, learn, and contribute! 📚🚀