How to get the coefficient of the Logistic Regression in mlr3?

user_13048347 0
Viewed 404

I have just started using mlr3 and still very unfamiliar with the syntax, I have two questions:

  1. How can I access the coefficient from the trained Logistic Regression in mlr3?
  2. I am dealing with a extremely imbalanced dataset, 98% vs 2%, and there are over 2million rows in this dataset, I tried to use SMOTE method, but it is very slow, because it can be done very soon in python, so is there any mistake in my code? Here is my code:
task = TaskClassif$new("pcs",backend =pcs,target = "navigator",positive = "1" )
table(task$truth())

po_over = po("classbalancing",id="oversample",adjust="minor",reference="minor",shuffle=F,ratio=16)
table(po_over$train(list(task))$output$truth())

learner = mlr_learners$get("classif.rpart")
learner$predict_type = "prob"

learner = po_over %>>% learner

resampling = rsmp("holdout",ratio=0.8)

rr = resample(task,learner,resampling,store_models = T)

res <- rr$prediction()
auto1 <- autoplot(res)
auto2 <- autoplot(res,type='roc')

rr$score(msr("classif.acc"))$classif.acc %>% print()

and for the SMOTE:

gr_smote =
  po("colapply", id = "int_to_num",
    applicator = as.numeric, affect_columns = selector_type("integer")) %>>%
  po("smote", dup_size = 15) %>>%
  po("colapply", id = "num_to_int",
    applicator = function(x) as.integer(round(x, 0L)), affect_columns = selector_type("numeric"))
mlr3 r
1 Answers

Here's what I gathered for your question #1

  1. Create a data set with approximately 98% 1's and 2% 0's

  2. Make tasks of training and testing

  3. (1) Create overbalancing po thing

    (2) Create learner this way, the way in you original code won't work with po

  4. Train the learner on train set

  5. Test on test set

library(mlr3)
library(dplyr)
library(mlr3pipelines)
set.seed(10)

pcs=data.frame(a=runif(1000), b=runif(1000))
pcs = pcs %>%
  mutate(c=2*a+3*b, d=ifelse(c>.6, 1, 0), navigator=factor(d)) %>%
  select(-c, -d)

task = TaskClassif$new("pcs",backend =pcs,target = "navigator",positive = "1" )
train_set = sample(task$nrow, 0.8 * task$nrow)
test_set = setdiff(seq_len(task$nrow), train_set)

task_train <- task$clone()$filter(train_set)
task_test  <- task$clone()$filter(test_set)

po_over1= po("classbalancing")
po_over1$param_set$values=list(ratio=16, reference="minor", adjust="minor", shuffle=FALSE)

learner=GraphLearner$new(
  po_over1 %>>% 
    po("learner", lrn("classif.rpart", 
                      predict_type="prob"))
)

learner$train(task_train)

pred=learner$predict(task_test)

output:

learner$model
#' You can see the predicted probability by following the decision tree
#' e.g. say you have a data point a and b
#' first check that b>=.112 or b<.112 (nodes 2 and 3)
#' etc.
1) root 1085 304 1 (0.71981567 0.28018433)  
  2) b>=0.1122314 728  16 1 (0.97802198 0.02197802)  
    4) a>=0.007176245 709   0 1 (1.00000000 0.00000000) *
    5) a< 0.007176245 19   3 0 (0.15789474 0.84210526) *
  3) b< 0.1122314 357  69 0 (0.19327731 0.80672269)  
    6) a>=0.246552 65   0 1 (1.00000000 0.00000000) *
    7) a< 0.246552 292   4 0 (0.01369863 0.98630137) *

#Test predictions
pred$confusion
        truth
response   1   0
       1 195   1
       0   0   4

This is for question #2 SMOTE

gr_smote =
  po("colapply", id = "int_to_num",
     applicator = as.numeric, affect_columns = selector_type("integer")) %>>%
  po("smote", dup_size = 15) %>>%
  po("colapply", id = "num_to_int",
     applicator = function(x) as.integer(round(x, 0L)), affect_columns = selector_type("numeric"))

learner=GraphLearner$new(
  gr_smote %>>% po("learner", lrn("classif.rpart", predict_type="prob"))
)
learner$train(task_train)
learner$model
1) root 1085 304 1 (0.7198157 0.2801843)  
  2) b>=0.5 391   0 1 (1.0000000 0.0000000) *
  3) b< 0.5 694 304 1 (0.5619597 0.4380403)  
    6) a>=0.5 203   0 1 (1.0000000 0.0000000) *
    7) a< 0.5 491 187 0 (0.3808554 0.6191446) *

pred=learner$predict(task_test)
pred$confusion
        truth
response   1   0
       1 159   0
       0  36   5
user_144042310
Related