-
This dataset is composed of a range of biomedical voice measurements from 31 people, 23 with Parkinson's disease (PD). Each column in the table is a particular voice measure, and each row corresponds one of 195 voice recording from these individuals ("name" column). The main aim of the data is to discriminate healthy people from those with PD, according to "status" column which is set to 0 for healthy and 1 for PD.
-
I used pandas, numpy, seaborn, matplotlib, xgboost, scipy, and sklearn libraries to do Exploratory Data Analysis (EDA), Data Visualzation, Data Cleaning/Filtering, and Building Models
-
I made Logistic Regression Model, Decision Tree Model, Random Forest Classifier Model, Bagging Model, Boosting Model, XGBoost Model, SVM (Support Vector Machine) Model, and KNN (k-Nearest Neighbors) Model.
-
WebApp link of SVM Model Deployment on same project: https://parkinson-detector-svm.herokuapp.com/
-
SVM Model Codes: https://github.com/Abis47/Parkinson_Detection-SVM_WebApp
-
Report Link: https://drive.google.com/file/d/1kV3tpKN9Tvym6khtmexqmV-klmiS5HLx/view?usp=sharing
-
Dataset Download Link: https://archive.ics.uci.edu/ml/datasets/parkinsons
Abis47/Parkinson_Detection-KNN_WebApp
Parkinson Disease Prediction using KNN Model followed by Deployment of Model as an WebApp using Heroku
Jupyter Notebook