Please enable JavaScript.
Coggle requires JavaScript to display documents.
Larsen Chapter 16-18 (16.3: Blueprints (16.3.1 Imputation (Regularized…
Larsen Chapter 16-18
16.3: Blueprints
16.3.1 Imputation
Regularized Logistic Regression Model- categorical features are one-hot encoded & numerical features have their missing values imputed
16.3.2 Standardization
Standardize a numeric feature= scales differing standard deviations so that the mean value of the feature is set to zero and the std. deviation is set to "unit variance" (one).
16.3.3 One-Hot Encoding
Def= for any categorical feature that fulfills certain requirements, a new feature is created for every category that exists within the original feature
-
-
16.2 Accuracy Trade-Offs
Efficient Frontier- the line drawn between the dots closest to the X and Y axes which denotes that speed & accuracy are negatively correlated.
-
-
17.3 ROC Curve
Confusion Matrix=Left of 2x2 matrix is what should have happened, Top of matrix is what actually happened
Four Quadrants= True Negative, True Positive, False Positive, False Negative
DataRobot sorts target features alphanumerically and treats the lowest value as negative and the highest value as positive
-
-
-