BYON8Data Scientist
Feb. 2018 - Nov. 2018Stockholm, SwedenData mining with demographic and clinical data:
• Data Acquisition • Exploratory Data Analysis
• Preprocessing: Data imputation data cleaning and feature engineering Algorithms: KNN, Decision Trees, Random Forest, SVM, Logistic Regression. Ensemble Methods: Voting Classifier, Bagging (Bagged K-NN, Bagged Decision Tree), Boosting (Adaptive Boosting, Stochastic Gradient Descent Boosting, XGBoost)
• Model Optimization: Hyper-Parameter Tuning, Regularization
• Model Validation : stratified K-Fold Cross Validation
Tools: Scikit-learn, Pandas, Seaborn, etc. using Python as the main language.