This repository contains Python code for predicting Parkinson's disease using machine learning techniques, specifically employing the powerful XGBoost classifier.
What's Included: Data Loading and Exploration: The code loads a Parkinson's disease dataset, explores its structure, and performs initial data analysis to understand the data. Data Preprocessing: The dataset undergoes preprocessing steps, including label encoding for categorical variables and feature scaling for optimal model performance. Exploratory Data Analysis (EDA): Various EDA techniques are employed, such as correlation analysis, histogram plotting, and pair plots, to gain insights into the data. XGBoost Model Training: An XGBoost classifier is trained on the preprocessed data to predict the presence or absence of Parkinson's disease. Model Evaluation: The trained model's accuracy, confusion matrix, and classification report are displayed to assess its predictive capabilities.
The dataset used for this project can be found here