Calculate all measures for sparse ROC

Usage

getThresholdSummary(
  prediction,
  predictionType = "binary",
  typeColumn = "evaluation"
)

Arguments

prediction: A prediction object
predictionType: The type of prediction (binary or survival)
typeColumn: A column that is used to stratify the results

Value

A data.frame with TP, FP, TN, FN, TPR, FPR, accuracy, PPF, FOR and Fmeasure

Details

Calculates the TP, FP, TN, FN, TPR, FPR, accuracy, PPF, FOR and Fmeasure from a prediction object

Examples

prediction <- data.frame(rowId = 1:100, 
                         outcomeCount = stats::rbinom(1:100, 1, prob=0.5),
                         value = runif(100), 
                         evaluation = rep("Train", 100))
summary <- getThresholdSummary(prediction)
str(summary)
#> 'data.frame':	100 obs. of  24 variables:
#>  $ evaluation             : chr  "Train" "Train" "Train" "Train" ...
#>  $ predictionThreshold    : num  0.993 0.97 0.965 0.953 0.935 ...
#>  $ preferenceThreshold    : num  0.992 0.967 0.961 0.947 0.927 ...
#>  $ positiveCount          : num  1 2 3 4 5 6 7 8 9 10 ...
#>  $ negativeCount          : num  99 98 97 96 95 94 93 92 91 90 ...
#>  $ trueCount              : num  53 53 53 53 53 53 53 53 53 53 ...
#>  $ falseCount             : num  47 47 47 47 47 47 47 47 47 47 ...
#>  $ truePositiveCount      : num  1 2 2 2 2 3 4 5 6 6 ...
#>  $ trueNegativeCount      : num  47 47 46 45 44 44 44 44 44 43 ...
#>  $ falsePositiveCount     : num  0 0 1 2 3 3 3 3 3 4 ...
#>  $ falseNegativeCount     : num  52 51 51 51 51 50 49 48 47 47 ...
#>  $ f1Score                : num  0.037 0.0727 0.0714 0.0702 0.069 ...
#>  $ accuracy               : num  0.48 0.49 0.48 0.47 0.46 0.47 0.48 0.49 0.5 0.49 ...
#>  $ sensitivity            : num  0.0189 0.0377 0.0377 0.0377 0.0377 ...
#>  $ falseNegativeRate      : num  0.981 0.962 0.962 0.962 0.962 ...
#>  $ falsePositiveRate      : num  0 0 0.0213 0.0426 0.0638 ...
#>  $ specificity            : num  1 1 0.979 0.957 0.936 ...
#>  $ positivePredictiveValue: num  1 1 0.667 0.5 0.4 ...
#>  $ falseDiscoveryRate     : num  0 0 0.333 0.5 0.6 ...
#>  $ negativePredictiveValue: num  0.475 0.48 0.474 0.469 0.463 ...
#>  $ falseOmissionRate      : num  0.525 0.52 0.526 0.531 0.537 ...
#>  $ positiveLikelihoodRatio: num  Inf Inf 1.774 0.887 0.591 ...
#>  $ negativeLikelihoodRatio: num  0.981 0.962 0.983 1.005 1.028 ...
#>  $ diagnosticOddsRatio    : num  Inf Inf 1.804 0.882 0.575 ...