Cheng JiDifference between frequentist and bayesian modelThis sentence I invented deserves a single blog: when you call LogisticRegression().fit, the prediction you get is based on the assumption…Sep 23, 2016Sep 23, 2016
Cheng JiCredit Card Default Prediction with Logistic RegressionIntro: The goal is to predict the probability of credit default based on credit card owner’s characteristics and payment history.Sep 21, 20161Sep 21, 20161
Cheng JiHandling categorical features: get_dummies, OneHotEncoder and multicollinearityGet_dummies is a common way to create dummy variables for categorical features. While it is widely used, there are some drawbacks. First…Sep 5, 20165Sep 5, 20165