VolhaP87

ds-classification_workflow_pipelines-efd32

Stroke_Prediction_Analysis

Predicted if patients would develop stroke in their lifetime given clinical features of the patients. Applied one hot encoding and SMOTE-NC. Modeled the data using baseline and tuned Logistic Regression, Decision Tree, Bagged Trees, Random Forest, AdaBoost, Gradient Boosting, XGBoost, Naïve Bayes, KNN, SVM. Achieved recall score of 97%.

dsc-building-an-object-oriented-simulation-lab

dsc-building-an-svm-from-scratch-lab

dsc-building-an-svm-using-scikit-learn-lab

dsc-derivatives-chain-rule

dsc-document-classification-with-naive-bayes

dsc-document-classification-with-naive-bayes-lab

dsc-gaussian-naive-bayes

dsc-gaussian-naive-bayes-lab

dsc-gradient-boosting-lab

dsc-gridsearchcv-lab

dsc-kernels-in-scikit-learn-lab

dsc-knn-with-scikit-learn-lab

dsc-linalg-dot-product-properties-lab

dsc-linalg-python-vs-numpy-lab

dsc-linalg-vector-addition-codealong

dsc-linalg-vector-matrices-numpy-lab

dsc-nonparametric-models-lab

dsc-object-oriented-attributes-with-functions

dsc-object-oriented-attributes-with-functions-lab

dsc-object-oriented-shopping-cart-lab

dsc-pca-in-scikitlearn

dsc-pickle

dsc-pickling-pipelines

dsc-pipelines-lab-v2-1

dsc-refactoring-with-pipelines

dsc-rules-for-derivatives-lab

dsc-tree-ensembles-random-forests-lab

dsc-xgboost-lab