This repository contains Jupyter Notebook files for predicting the cost of medical treatment for patients. The predictive models are developed using machine learning techniques and utilize a dataset with various patient attributes and associated costs.
The dataset used for this project is stored in the data folder, which includes the following files:
train.csv: Contains the training dataset.test.csv: Contains the test dataset.train_large.csv: Contains a larger training dataset.
These datasets consist of patient information such as age, gender, BMI, smoking status, and medical charges. They serve as the foundation for training and evaluating the predictive models.
The following Jupyter Notebook files are included:
features.ipynb: This notebook explores the dataset, performs feature engineering, and prepares the data for model training.linear.ipynb: This notebook focuses on Part A of the project, implementing and evaluating a linear regression model.part_b.ipynb: This notebook covers Part B of the project, implementing and evaluating a specific model or approach.part_c.ipynb: This notebook addresses Part C of the project, implementing and evaluating another specific model or approach.
During the project's execution, the following files will be generated:
model_outputfile_a.txt: Stores the model output for Part A.outputfile_a.txt: Contains the output generated during the execution of Part A.grade_a.py: Evaluates and grades the results of Part A.model_outputfile_b.txt: Stores the model output for Part B.outputfile_b.txt: Contains the output generated during the execution of Part B.grade_b.py: Evaluates and grades the results of Part B.model_weightfile_a.txt: Stores the weights of the trained model for Part A.weightfile_a.txt: Contains the weights of the trained model for Part A.model_weightfile_b.txt: Stores the weights of the trained model for Part B.weightfile_b.txt: Contains the weights of the trained model for Part B.outputfile_c.txt: Contains the output generated during the execution of Part C.
Please note that these files are generated as part of the project workflow and are used for evaluation and grading purposes.
To run the notebooks:
-
Clone this repository:
git clone https://github.com/AkshatGadhwal/Patient-Cost-Prediction.git -
Open the desired notebook (e.g.,
features.ipynb,linear.ipynb, etc.) in Jupyter Notebook or Jupyter Lab. -
Follow the instructions within the notebook to execute code cells and explore data analysis, model training, and evaluation.
Contributions to this project are welcome. If you have suggestions, improvements, or bug fixes, please submit a pull request or open an issue to discuss the changes.
This project is licensed under the MIT License.