Calculates and writes fit statistics, roc and lift for binary and fit statistics for interval.

diagnosticsJson(
  targetName,
  targetPredicted,
  validadedf = NULL,
  traindf = NULL,
  testdf = NULL,
  type = "binary",
  targetEventValue = 1,
  cutoff = 0.5,
  label.ordering = c(0, 1),
  path = "./",
  noFile = FALSE
)

Arguments

targetName

target variable name (actuals)

targetPredicted

target variable probability column name

validadedf

data.frame where the first column in the yActual (labels/value) and the second is yPrediction (target probability)

traindf

data.frame where the first column in the yActual (labels/value) and the second is yPrediction (target probability)

testdf

data.frame where the first column in the yActual (labels/value) and the second is yPrediction (target probability)

type

"binary" or "interval"

targetEventValue

if type = "binary" target class name for fit stat reference, if model is nominal, all other class will be counted as "not target"

cutoff

cutoff to be used for calculation of miss classification for binary

label.ordering

The default ordering (cf.details) of the classes can be changed by supplying a vector containing the negative and the positive class label. See ROCR::prediction()

path

default to current work dir

noFile

if you don't want to write to a file, only the output

Value

  • list of lists that reflects the 'dmcas_fitstat.json', 'dmcas_roc.json' and 'dmcas_lift.json'

  • 'dmcas_fitstat.json', 'dmcas_roc.json' and 'dmcas_lift.json' files written to path

See also

All parameters are passed to calculateLiftStat(), calculateLiftStat() and calculateLiftStat() for matching parameters.

Examples


df <- data.frame(label = sample(c(1,0), 6000, replace = TRUE),
                prob = runif(6000),
               partition = rep_len(1:3, 6000)) ## partition will be ignored since it is 3rd column
               
diagnosticsJson(df[df$partition == 1, ], 
                 df[df$partition == 2, ],
                 df[df$partition == 3, ],
                 targetName = "label",
                 targetPredicted = "prob",
                 noFile = TRUE
                 )