Summary method for the evalbin function
# S3 method for evalbin summary(object, prn = TRUE, dec = 3, ...)
| object | Return value from |
|---|---|
| prn | Print full table of measures per model and bin |
| dec | Number of decimals to show |
| ... | further arguments passed to or from other methods |
See https://radiant-rstats.github.io/docs/model/evalbin.html for an example in Radiant
evalbin to summarize results
plot.evalbin to plot results
data.frame(buy = dvd$buy, pred1 = runif(20000), pred2 = ifelse(dvd$buy == "yes", 1, 0)) %>% evalbin(c("pred1", "pred2"), "buy") %>% summary()#> Evaluate predictions for binary response models #> Data : . #> Results for : All #> Predictors : pred1, pred2 #> Response : buy #> Level : yes in buy #> Bins : 10 #> Cost:Margin : 1 : 2 #> #> pred bins nr_obs nr_resp resp_rate gains profit ROME cum_prop cum_resp #> pred1 10 2,000 529 0.265 0.101 -942.000 -0.471 0.100 529 #> pred1 9 2,000 513 0.257 0.098 -1,916.000 -0.479 0.200 1,042 #> pred1 8 2,000 536 0.268 0.102 -2,844.000 -0.474 0.300 1,578 #> pred1 7 2,000 523 0.262 0.100 -3,798.000 -0.475 0.400 2,101 #> pred1 6 2,000 494 0.247 0.094 -4,810.000 -0.481 0.500 2,595 #> pred1 5 2,000 520 0.260 0.099 -5,770.000 -0.481 0.600 3,115 #> pred1 4 2,000 555 0.278 0.106 -6,660.000 -0.476 0.700 3,670 #> pred1 3 2,000 535 0.268 0.102 -7,590.000 -0.474 0.800 4,205 #> pred1 2 2,000 549 0.275 0.105 -8,492.000 -0.472 0.900 4,754 #> pred1 1 2,000 492 0.246 0.094 -9,508.000 -0.475 1.000 5,246 #> pred2 3 5,246 5,246 1.000 1.000 5,246.000 1.000 0.262 5,246 #> pred2 10 14,754 0 0.000 0.000 -9,508.000 -0.475 1.000 5,246 #> cum_resp_rate cum_lift cum_gains #> 0.265 1.008 0.101 #> 0.261 0.993 0.199 #> 0.263 1.003 0.301 #> 0.263 1.001 0.400 #> 0.260 0.989 0.495 #> 0.260 0.990 0.594 #> 0.262 0.999 0.700 #> 0.263 1.002 0.802 #> 0.264 1.007 0.906 #> 0.262 1.000 1.000 #> 1.000 3.812 1.000 #> 0.262 1.000 1.000