nupurgupta5292/Predicting-Clinical-Depression

Utilized Quality of Living data collected for a rural population in Kenya to develop and test several machine learning models including Linear Regression, Support Vector Machine (SVM), Decision Trees, Random Forest and Deep Neural Networks. Also developed UI for the user to determine their possibility of being depressed and visualized the existing data trends using Tableau # Prediciting Clinical Depression Utilized Quality of Living data collected for a rural population in Kenya to develop and test several supervised machine learning models including Linear Regression, Support Vector Machine (SVM), Decision Trees, Random Forest and Deep Neural Networks. Also developed UI for the user to determine their possibility of being depressed and visualized the existing data trends using Tableau ## Getting Started * Clone the repository to your system * Go to depression_predictor --> script.py. Run the flask app on local environment * The local static address should open the UI for the model, where the data is pre-populated for 67 year old, depressed female * Populate the data according to the user to see their results ### Prerequisites and Built With * Python libraries: Numpy, Scipy, Scikit-learn, TensorFlow, Keras, Pandas * Jupyter Notebook - For live code and visualizations * Flask API - Middleman for UI and the prediction model * Tableau - Used to visualize exisiting trends * MS PowerPoint ## Contributors See the list of contributors who participated in this project. ## Acknowledgments * Bootcamp Instructor: Kasturi Kundu * Bootcamp TAs: Jason Grein, Sadaf Sadeghian