Parkinson's Disease Detection is an Internship Project conducted during Data Analytics Training at Inflow Technologies. The project involves the development of a user interface using Streamlit and utilizes a pickle file for making predictions. The pickle file contains the training and testing data for a Random Forest Classifier, which was chosen over the Support Vector Machine due to its higher accuracy.
The primary objective of the Parkinson's Disease Detection project is to create a streamlined and user-friendly interface for detecting Parkinson's disease in individuals. Streamlit, a popular Python library, is employed to construct the interface, ensuring an intuitive and interactive experience for users.
For the prediction process, the project employs a Random Forest Classifier model. The model is trained using a dataset containing relevant features and labels to identify Parkinson's disease accurately. A separate dataset is used for testing the model's performance and evaluating its accuracy. Through extensive experimentation, it was determined that the Random Forest Classifier outperformed the Support Vector Machine in terms of accuracy, making it the preferred choice for this particular project.
The trained Random Forest Classifier model is saved in a pickle file format, allowing for easy storage and retrieval of the model. The Streamlit user interface refers to this pickle file to make predictions on new data samples. By inputting the relevant information into the interface, users can obtain predictions regarding the likelihood of Parkinson's disease.
In summary, the Parkinson's Disease Detection internship project at Inflow Technologies utilizes Streamlit to build a user interface and leverages a Random Forest Classifier model stored in a pickle file for accurate predictions, as it exhibited superior performance compared to the Support Vector Machine.
