library(pomodoro)This package was set for the Credit Access studies. But it can be
used for the binary and multiple factor variables. First thing let’s see
the str of the sample_data with str(sample_data).
Since the dataset is huge, let’s take the first 500 rows and set the
study on it.
The following example run the
multinominal logistic model in yvar. The
function simplifies the 80/20 train test set using 10cv after scaled and
center it.
#> Loading required package: ggplot2
#> Loading required package: lattice
#> + Fold01: mtry= 2
#> - Fold01: mtry= 2
#> + Fold01: mtry= 7
#> - Fold01: mtry= 7
#> + Fold01: mtry=12
#> - Fold01: mtry=12
#> + Fold02: mtry= 2
#> - Fold02: mtry= 2
#> + Fold02: mtry= 7
#> - Fold02: mtry= 7
#> + Fold02: mtry=12
#> - Fold02: mtry=12
#> + Fold03: mtry= 2
#> - Fold03: mtry= 2
#> + Fold03: mtry= 7
#> - Fold03: mtry= 7
#> + Fold03: mtry=12
#> - Fold03: mtry=12
#> + Fold04: mtry= 2
#> - Fold04: mtry= 2
#> + Fold04: mtry= 7
#> - Fold04: mtry= 7
#> + Fold04: mtry=12
#> - Fold04: mtry=12
#> + Fold05: mtry= 2
#> - Fold05: mtry= 2
#> + Fold05: mtry= 7
#> - Fold05: mtry= 7
#> + Fold05: mtry=12
#> - Fold05: mtry=12
#> + Fold06: mtry= 2
#> - Fold06: mtry= 2
#> + Fold06: mtry= 7
#> - Fold06: mtry= 7
#> + Fold06: mtry=12
#> - Fold06: mtry=12
#> + Fold07: mtry= 2
#> - Fold07: mtry= 2
#> + Fold07: mtry= 7
#> - Fold07: mtry= 7
#> + Fold07: mtry=12
#> - Fold07: mtry=12
#> + Fold08: mtry= 2
#> - Fold08: mtry= 2
#> + Fold08: mtry= 7
#> - Fold08: mtry= 7
#> + Fold08: mtry=12
#> - Fold08: mtry=12
#> + Fold09: mtry= 2
#> - Fold09: mtry= 2
#> + Fold09: mtry= 7
#> - Fold09: mtry= 7
#> + Fold09: mtry=12
#> - Fold09: mtry=12
#> + Fold10: mtry= 2
#> - Fold10: mtry= 2
#> + Fold10: mtry= 7
#> - Fold10: mtry= 7
#> + Fold10: mtry=12
#> - Fold10: mtry=12
#> Aggregating results
#> Selecting tuning parameters
#> Fitting mtry = 2 on full training set
#> Multi-class area under the curve: 0.7598
Estimate_Models function considers exog and
xadd variables and set multiple models based on the
selected exog and xadd. On the one hand
exog is subtract the selected vector from the dataset and
run the model for all the dataset and for the splits of the
exog. On the other hand xadd add the selected
vectors and run the model. Where the dnames are the unique
values in exog this is to save the model estimates by their
name.
sample_data <- sample_data[c(1:750),]
yvar <- c("Loan.Type")
xvar <- c("sex", "married", "age", "havejob", "educ", "political.afl",
"rural", "region", "fin.intermdiaries", "fin.knowldge", "income")
CCP.RF <- Estimate_Models(sample_data, yvar, xvec = xvar, exog = "political.afl",
xadd = c("networth", "networth_homequity", "liquid.assets"),
type = "RF", dnames = c("0","1"))
#> + Fold01: mtry= 2
#> - Fold01: mtry= 2
#> + Fold01: mtry= 6
#> - Fold01: mtry= 6
#> + Fold01: mtry=11
#> - Fold01: mtry=11
#> + Fold02: mtry= 2
#> - Fold02: mtry= 2
#> + Fold02: mtry= 6
#> - Fold02: mtry= 6
#> + Fold02: mtry=11
#> - Fold02: mtry=11
#> + Fold03: mtry= 2
#> - Fold03: mtry= 2
#> + Fold03: mtry= 6
#> - Fold03: mtry= 6
#> + Fold03: mtry=11
#> - Fold03: mtry=11
#> + Fold04: mtry= 2
#> - Fold04: mtry= 2
#> + Fold04: mtry= 6
#> - Fold04: mtry= 6
#> + Fold04: mtry=11
#> - Fold04: mtry=11
#> + Fold05: mtry= 2
#> - Fold05: mtry= 2
#> + Fold05: mtry= 6
#> - Fold05: mtry= 6
#> + Fold05: mtry=11
#> - Fold05: mtry=11
#> + Fold06: mtry= 2
#> - Fold06: mtry= 2
#> + Fold06: mtry= 6
#> - Fold06: mtry= 6
#> + Fold06: mtry=11
#> - Fold06: mtry=11
#> + Fold07: mtry= 2
#> - Fold07: mtry= 2
#> + Fold07: mtry= 6
#> - Fold07: mtry= 6
#> + Fold07: mtry=11
#> - Fold07: mtry=11
#> + Fold08: mtry= 2
#> - Fold08: mtry= 2
#> + Fold08: mtry= 6
#> - Fold08: mtry= 6
#> + Fold08: mtry=11
#> - Fold08: mtry=11
#> + Fold09: mtry= 2
#> - Fold09: mtry= 2
#> + Fold09: mtry= 6
#> - Fold09: mtry= 6
#> + Fold09: mtry=11
#> - Fold09: mtry=11
#> + Fold10: mtry= 2
#> - Fold10: mtry= 2
#> + Fold10: mtry= 6
#> - Fold10: mtry= 6
#> + Fold10: mtry=11
#> - Fold10: mtry=11
#> Aggregating results
#> Selecting tuning parameters
#> Fitting mtry = 2 on full training set
#> + Fold01: mtry= 2
#> - Fold01: mtry= 2
#> + Fold01: mtry= 6
#> - Fold01: mtry= 6
#> + Fold01: mtry=11
#> - Fold01: mtry=11
#> + Fold02: mtry= 2
#> - Fold02: mtry= 2
#> + Fold02: mtry= 6
#> - Fold02: mtry= 6
#> + Fold02: mtry=11
#> - Fold02: mtry=11
#> + Fold03: mtry= 2
#> - Fold03: mtry= 2
#> + Fold03: mtry= 6
#> - Fold03: mtry= 6
#> + Fold03: mtry=11
#> - Fold03: mtry=11
#> + Fold04: mtry= 2
#> - Fold04: mtry= 2
#> + Fold04: mtry= 6
#> - Fold04: mtry= 6
#> + Fold04: mtry=11
#> - Fold04: mtry=11
#> + Fold05: mtry= 2
#> - Fold05: mtry= 2
#> + Fold05: mtry= 6
#> - Fold05: mtry= 6
#> + Fold05: mtry=11
#> - Fold05: mtry=11
#> + Fold06: mtry= 2
#> - Fold06: mtry= 2
#> + Fold06: mtry= 6
#> - Fold06: mtry= 6
#> + Fold06: mtry=11
#> - Fold06: mtry=11
#> + Fold07: mtry= 2
#> - Fold07: mtry= 2
#> + Fold07: mtry= 6
#> - Fold07: mtry= 6
#> + Fold07: mtry=11
#> - Fold07: mtry=11
#> + Fold08: mtry= 2
#> - Fold08: mtry= 2
#> + Fold08: mtry= 6
#> - Fold08: mtry= 6
#> + Fold08: mtry=11
#> - Fold08: mtry=11
#> + Fold09: mtry= 2
#> - Fold09: mtry= 2
#> + Fold09: mtry= 6
#> - Fold09: mtry= 6
#> + Fold09: mtry=11
#> - Fold09: mtry=11
#> + Fold10: mtry= 2
#> - Fold10: mtry= 2
#> + Fold10: mtry= 6
#> - Fold10: mtry= 6
#> + Fold10: mtry=11
#> - Fold10: mtry=11
#> Aggregating results
#> Selecting tuning parameters
#> Fitting mtry = 2 on full training set
#> + Fold01: mtry= 2
#> - Fold01: mtry= 2
#> + Fold01: mtry= 6
#> - Fold01: mtry= 6
#> + Fold01: mtry=11
#> - Fold01: mtry=11
#> + Fold02: mtry= 2
#> - Fold02: mtry= 2
#> + Fold02: mtry= 6
#> - Fold02: mtry= 6
#> + Fold02: mtry=11
#> - Fold02: mtry=11
#> + Fold03: mtry= 2
#> - Fold03: mtry= 2
#> + Fold03: mtry= 6
#> - Fold03: mtry= 6
#> + Fold03: mtry=11
#> - Fold03: mtry=11
#> + Fold04: mtry= 2
#> - Fold04: mtry= 2
#> + Fold04: mtry= 6
#> - Fold04: mtry= 6
#> + Fold04: mtry=11
#> - Fold04: mtry=11
#> + Fold05: mtry= 2
#> - Fold05: mtry= 2
#> + Fold05: mtry= 6
#> - Fold05: mtry= 6
#> + Fold05: mtry=11
#> - Fold05: mtry=11
#> + Fold06: mtry= 2
#> - Fold06: mtry= 2
#> + Fold06: mtry= 6
#> - Fold06: mtry= 6
#> + Fold06: mtry=11
#> - Fold06: mtry=11
#> + Fold07: mtry= 2
#> - Fold07: mtry= 2
#> + Fold07: mtry= 6
#> - Fold07: mtry= 6
#> + Fold07: mtry=11
#> - Fold07: mtry=11
#> + Fold08: mtry= 2
#> - Fold08: mtry= 2
#> + Fold08: mtry= 6
#> - Fold08: mtry= 6
#> + Fold08: mtry=11
#> - Fold08: mtry=11
#> + Fold09: mtry= 2
#> - Fold09: mtry= 2
#> + Fold09: mtry= 6
#> - Fold09: mtry= 6
#> + Fold09: mtry=11
#> - Fold09: mtry=11
#> + Fold10: mtry= 2
#> - Fold10: mtry= 2
#> + Fold10: mtry= 6
#> - Fold10: mtry= 6
#> + Fold10: mtry=11
#> - Fold10: mtry=11
#> Aggregating results
#> Selecting tuning parameters
#> Fitting mtry = 2 on full training set
#> + Fold01: mtry= 2
#> - Fold01: mtry= 2
#> + Fold01: mtry= 6
#> - Fold01: mtry= 6
#> + Fold01: mtry=11
#> - Fold01: mtry=11
#> + Fold02: mtry= 2
#> - Fold02: mtry= 2
#> + Fold02: mtry= 6
#> - Fold02: mtry= 6
#> + Fold02: mtry=11
#> - Fold02: mtry=11
#> + Fold03: mtry= 2
#> - Fold03: mtry= 2
#> + Fold03: mtry= 6
#> - Fold03: mtry= 6
#> + Fold03: mtry=11
#> - Fold03: mtry=11
#> + Fold04: mtry= 2
#> - Fold04: mtry= 2
#> + Fold04: mtry= 6
#> - Fold04: mtry= 6
#> + Fold04: mtry=11
#> - Fold04: mtry=11
#> + Fold05: mtry= 2
#> - Fold05: mtry= 2
#> + Fold05: mtry= 6
#> - Fold05: mtry= 6
#> + Fold05: mtry=11
#> - Fold05: mtry=11
#> + Fold06: mtry= 2
#> - Fold06: mtry= 2
#> + Fold06: mtry= 6
#> - Fold06: mtry= 6
#> + Fold06: mtry=11
#> - Fold06: mtry=11
#> + Fold07: mtry= 2
#> - Fold07: mtry= 2
#> + Fold07: mtry= 6
#> - Fold07: mtry= 6
#> + Fold07: mtry=11
#> - Fold07: mtry=11
#> + Fold08: mtry= 2
#> - Fold08: mtry= 2
#> + Fold08: mtry= 6
#> - Fold08: mtry= 6
#> + Fold08: mtry=11
#> - Fold08: mtry=11
#> + Fold09: mtry= 2
#> - Fold09: mtry= 2
#> + Fold09: mtry= 6
#> - Fold09: mtry= 6
#> + Fold09: mtry=11
#> - Fold09: mtry=11
#> + Fold10: mtry= 2
#> - Fold10: mtry= 2
#> + Fold10: mtry= 6
#> - Fold10: mtry= 6
#> + Fold10: mtry=11
#> - Fold10: mtry=11
#> Aggregating results
#> Selecting tuning parameters
#> Fitting mtry = 2 on full training set
#> + Fold01: mtry= 2
#> - Fold01: mtry= 2
#> + Fold01: mtry= 6
#> - Fold01: mtry= 6
#> + Fold01: mtry=11
#> - Fold01: mtry=11
#> + Fold02: mtry= 2
#> - Fold02: mtry= 2
#> + Fold02: mtry= 6
#> - Fold02: mtry= 6
#> + Fold02: mtry=11
#> - Fold02: mtry=11
#> + Fold03: mtry= 2
#> - Fold03: mtry= 2
#> + Fold03: mtry= 6
#> - Fold03: mtry= 6
#> + Fold03: mtry=11
#> - Fold03: mtry=11
#> + Fold04: mtry= 2
#> - Fold04: mtry= 2
#> + Fold04: mtry= 6
#> - Fold04: mtry= 6
#> + Fold04: mtry=11
#> - Fold04: mtry=11
#> + Fold05: mtry= 2
#> - Fold05: mtry= 2
#> + Fold05: mtry= 6
#> - Fold05: mtry= 6
#> + Fold05: mtry=11
#> - Fold05: mtry=11
#> + Fold06: mtry= 2
#> - Fold06: mtry= 2
#> + Fold06: mtry= 6
#> - Fold06: mtry= 6
#> + Fold06: mtry=11
#> - Fold06: mtry=11
#> + Fold07: mtry= 2
#> - Fold07: mtry= 2
#> + Fold07: mtry= 6
#> - Fold07: mtry= 6
#> + Fold07: mtry=11
#> - Fold07: mtry=11
#> + Fold08: mtry= 2
#> - Fold08: mtry= 2
#> + Fold08: mtry= 6
#> - Fold08: mtry= 6
#> + Fold08: mtry=11
#> - Fold08: mtry=11
#> + Fold09: mtry= 2
#> - Fold09: mtry= 2
#> + Fold09: mtry= 6
#> - Fold09: mtry= 6
#> + Fold09: mtry=11
#> - Fold09: mtry=11
#> + Fold10: mtry= 2
#> - Fold10: mtry= 2
#> + Fold10: mtry= 6
#> - Fold10: mtry= 6
#> + Fold10: mtry=11
#> - Fold10: mtry=11
#> Aggregating results
#> Selecting tuning parameters
#> Fitting mtry = 6 on full training set
#> + Fold01: mtry= 2
#> - Fold01: mtry= 2
#> + Fold01: mtry= 6
#> - Fold01: mtry= 6
#> + Fold01: mtry=11
#> - Fold01: mtry=11
#> + Fold02: mtry= 2
#> - Fold02: mtry= 2
#> + Fold02: mtry= 6
#> - Fold02: mtry= 6
#> + Fold02: mtry=11
#> - Fold02: mtry=11
#> + Fold03: mtry= 2
#> - Fold03: mtry= 2
#> + Fold03: mtry= 6
#> - Fold03: mtry= 6
#> + Fold03: mtry=11
#> - Fold03: mtry=11
#> + Fold04: mtry= 2
#> - Fold04: mtry= 2
#> + Fold04: mtry= 6
#> - Fold04: mtry= 6
#> + Fold04: mtry=11
#> - Fold04: mtry=11
#> + Fold05: mtry= 2
#> - Fold05: mtry= 2
#> + Fold05: mtry= 6
#> - Fold05: mtry= 6
#> + Fold05: mtry=11
#> - Fold05: mtry=11
#> + Fold06: mtry= 2
#> - Fold06: mtry= 2
#> + Fold06: mtry= 6
#> - Fold06: mtry= 6
#> + Fold06: mtry=11
#> - Fold06: mtry=11
#> + Fold07: mtry= 2
#> - Fold07: mtry= 2
#> + Fold07: mtry= 6
#> - Fold07: mtry= 6
#> + Fold07: mtry=11
#> - Fold07: mtry=11
#> + Fold08: mtry= 2
#> - Fold08: mtry= 2
#> + Fold08: mtry= 6
#> - Fold08: mtry= 6
#> + Fold08: mtry=11
#> - Fold08: mtry=11
#> + Fold09: mtry= 2
#> - Fold09: mtry= 2
#> + Fold09: mtry= 6
#> - Fold09: mtry= 6
#> + Fold09: mtry=11
#> - Fold09: mtry=11
#> + Fold10: mtry= 2
#> - Fold10: mtry= 2
#> + Fold10: mtry= 6
#> - Fold10: mtry= 6
#> + Fold10: mtry=11
#> - Fold10: mtry=11
#> Aggregating results
#> Selecting tuning parameters
#> Fitting mtry = 2 on full training set
#> + Fold01: mtry= 2
#> - Fold01: mtry= 2
#> + Fold01: mtry= 6
#> - Fold01: mtry= 6
#> + Fold01: mtry=11
#> - Fold01: mtry=11
#> + Fold02: mtry= 2
#> - Fold02: mtry= 2
#> + Fold02: mtry= 6
#> - Fold02: mtry= 6
#> + Fold02: mtry=11
#> - Fold02: mtry=11
#> + Fold03: mtry= 2
#> - Fold03: mtry= 2
#> + Fold03: mtry= 6
#> - Fold03: mtry= 6
#> + Fold03: mtry=11
#> - Fold03: mtry=11
#> + Fold04: mtry= 2
#> - Fold04: mtry= 2
#> + Fold04: mtry= 6
#> - Fold04: mtry= 6
#> + Fold04: mtry=11
#> - Fold04: mtry=11
#> + Fold05: mtry= 2
#> - Fold05: mtry= 2
#> + Fold05: mtry= 6
#> - Fold05: mtry= 6
#> + Fold05: mtry=11
#> - Fold05: mtry=11
#> + Fold06: mtry= 2
#> - Fold06: mtry= 2
#> + Fold06: mtry= 6
#> - Fold06: mtry= 6
#> + Fold06: mtry=11
#> - Fold06: mtry=11
#> + Fold07: mtry= 2
#> - Fold07: mtry= 2
#> + Fold07: mtry= 6
#> - Fold07: mtry= 6
#> + Fold07: mtry=11
#> - Fold07: mtry=11
#> + Fold08: mtry= 2
#> - Fold08: mtry= 2
#> + Fold08: mtry= 6
#> - Fold08: mtry= 6
#> + Fold08: mtry=11
#> - Fold08: mtry=11
#> + Fold09: mtry= 2
#> - Fold09: mtry= 2
#> + Fold09: mtry= 6
#> - Fold09: mtry= 6
#> + Fold09: mtry=11
#> - Fold09: mtry=11
#> + Fold10: mtry= 2
#> - Fold10: mtry= 2
#> + Fold10: mtry= 6
#> - Fold10: mtry= 6
#> + Fold10: mtry=11
#> - Fold10: mtry=11
#> Aggregating results
#> Selecting tuning parameters
#> Fitting mtry = 2 on full training set
#> + Fold01: mtry= 2
#> - Fold01: mtry= 2
#> + Fold01: mtry= 6
#> - Fold01: mtry= 6
#> + Fold01: mtry=11
#> - Fold01: mtry=11
#> + Fold02: mtry= 2
#> - Fold02: mtry= 2
#> + Fold02: mtry= 6
#> - Fold02: mtry= 6
#> + Fold02: mtry=11
#> - Fold02: mtry=11
#> + Fold03: mtry= 2
#> - Fold03: mtry= 2
#> + Fold03: mtry= 6
#> - Fold03: mtry= 6
#> + Fold03: mtry=11
#> - Fold03: mtry=11
#> + Fold04: mtry= 2
#> - Fold04: mtry= 2
#> + Fold04: mtry= 6
#> - Fold04: mtry= 6
#> + Fold04: mtry=11
#> - Fold04: mtry=11
#> + Fold05: mtry= 2
#> - Fold05: mtry= 2
#> + Fold05: mtry= 6
#> - Fold05: mtry= 6
#> + Fold05: mtry=11
#> - Fold05: mtry=11
#> + Fold06: mtry= 2
#> - Fold06: mtry= 2
#> + Fold06: mtry= 6
#> - Fold06: mtry= 6
#> + Fold06: mtry=11
#> - Fold06: mtry=11
#> + Fold07: mtry= 2
#> - Fold07: mtry= 2
#> + Fold07: mtry= 6
#> - Fold07: mtry= 6
#> + Fold07: mtry=11
#> - Fold07: mtry=11
#> + Fold08: mtry= 2
#> - Fold08: mtry= 2
#> + Fold08: mtry= 6
#> - Fold08: mtry= 6
#> + Fold08: mtry=11
#> - Fold08: mtry=11
#> + Fold09: mtry= 2
#> - Fold09: mtry= 2
#> + Fold09: mtry= 6
#> - Fold09: mtry= 6
#> + Fold09: mtry=11
#> - Fold09: mtry=11
#> + Fold10: mtry= 2
#> - Fold10: mtry= 2
#> + Fold10: mtry= 6
#> - Fold10: mtry= 6
#> + Fold10: mtry=11
#> - Fold10: mtry=11
#> Aggregating results
#> Selecting tuning parameters
#> Fitting mtry = 6 on full training set
#> + Fold01: mtry= 2
#> - Fold01: mtry= 2
#> + Fold01: mtry= 6
#> - Fold01: mtry= 6
#> + Fold01: mtry=11
#> - Fold01: mtry=11
#> + Fold02: mtry= 2
#> - Fold02: mtry= 2
#> + Fold02: mtry= 6
#> - Fold02: mtry= 6
#> + Fold02: mtry=11
#> - Fold02: mtry=11
#> + Fold03: mtry= 2
#> - Fold03: mtry= 2
#> + Fold03: mtry= 6
#> - Fold03: mtry= 6
#> + Fold03: mtry=11
#> - Fold03: mtry=11
#> + Fold04: mtry= 2
#> - Fold04: mtry= 2
#> + Fold04: mtry= 6
#> - Fold04: mtry= 6
#> + Fold04: mtry=11
#> - Fold04: mtry=11
#> + Fold05: mtry= 2
#> - Fold05: mtry= 2
#> + Fold05: mtry= 6
#> - Fold05: mtry= 6
#> + Fold05: mtry=11
#> - Fold05: mtry=11
#> + Fold06: mtry= 2
#> - Fold06: mtry= 2
#> + Fold06: mtry= 6
#> - Fold06: mtry= 6
#> + Fold06: mtry=11
#> - Fold06: mtry=11
#> + Fold07: mtry= 2
#> - Fold07: mtry= 2
#> + Fold07: mtry= 6
#> - Fold07: mtry= 6
#> + Fold07: mtry=11
#> - Fold07: mtry=11
#> + Fold08: mtry= 2
#> - Fold08: mtry= 2
#> + Fold08: mtry= 6
#> - Fold08: mtry= 6
#> + Fold08: mtry=11
#> - Fold08: mtry=11
#> + Fold09: mtry= 2
#> - Fold09: mtry= 2
#> + Fold09: mtry= 6
#> - Fold09: mtry= 6
#> + Fold09: mtry=11
#> - Fold09: mtry=11
#> + Fold10: mtry= 2
#> - Fold10: mtry= 2
#> + Fold10: mtry= 6
#> - Fold10: mtry= 6
#> + Fold10: mtry=11
#> - Fold10: mtry=11
#> Aggregating results
#> Selecting tuning parameters
#> Fitting mtry = 2 on full training setEstimate_Models gives the results based on the splits of the
exog. Combined_Performance prints out the total performance
of these splits.
Sub.CCP.RF <- list(Mdl.1 = CCP.RF$EstMdl$`D.1+networth`,
Mdl.0 = CCP.RF$EstMdl$`D.0+networth`)
CCP.NoCCP.RF <- Combined_Performance (Sub.CCP.RF)