Search Archives

If we have to perform 100 iterations of the out-of-sample bootstrap, do we need to just enter the number 100 as: trainControl (method="boot", number = 100) Regards [[alternative HTML version deleted]]

Hi to everyone I just wanted to know if the dalex package of the mlr3 provides the same functions (i.e. variable importance) as provided by the scott-knott-esd test? Warm regards [[alternative HTML version deleted]]

How the hyperparameter settings via adaptive resampling is different from the one obtained from grid search or random search? Both grid and random searches provide best parameters values and the same is achieved using adaptive resampling. [[alternative HTML version deleted]]

Hi, If I am using caret and MAE metric, how can we get median of MAE in easy manner. cart <-train(Result ~ ., data = tr, method = "rf", metric = "MAE", preProc = c("center", "scale", "nzv"), trControl = ctr) [[alternative HTML version deleted]]

Hi I have continuous data I.e regression based. If I have residuals for algorithm 1 and algorithm 2 like this, X=resid(alg1) and y=resid (alg2) Can we perform the Wilcoxon test as. Wilcox.test(x,y) Thanks...

I have the following data from resample svm= svm$resample$RMSE nn= nn$resample$RMSE we perform the statistical tests like wilcox.test(svm, nn) I have a question, can we perform the scott-knot ESD test here? if yes...

Hi, suddenly the packages I installed not working. It gives me the error: Error: package or namespace load failed for ?farff? in loadNamespace(i, c(lib.loc, .libPaths()), versionCheck = vI[[i]]): namespace ?rlang? 0.4.7 is already loaded, but...

Why do I get the following error when my variable in the 'if statement' has no missing values. I check with is.na(my variable) and it has no missing values Error in if (fraction <= 1) { : missing value where TRUE...

Hi If I have to select specific rows and all columns of a dataframe, I use: rows= df[1:12 , ] However, how to select rows if our required rows are not in sequence i.e. if we need to select...

Hello everyone I want to know (1) In which cases, we need to use set.seed while building ML models? (2) Which is the exact location we need to put the set.seed function i.e. when we split data...

Hello everyone (1) Can we get the details like the confusion matrix with continuous data? (2) How can we get the mean absolute error for an individual instance? For example, if the ground truth is 4 and our model predicted...

Hello everyone I have a variable with about 5000 different values var1= c(0, 123, 400, .....4988) I want to convert it into different levels for some comparisons like if value is between 1-100 do something else do other...

Hello everyone While I am working to identify the correlated metrics on my data, I am getting the following error? My data has no missing or Inf values as all other operations (model training etc) could be done without any...

Hi I have values like: var= c(0, 0, 0,0, 0, 14, 0, 14, 0, 2, 3) I want to show these values in a boxplot boxplot (var) However, the boxplot shows only the zero values and the value...

Hello, I want to download a package and it gives me the error: WARNING: Rtools is required to build R packages, but no version of Rtools compatible with R 4.2.0 was found. (Only the following incompatible version(s...

I am using mlr3 'fast nearest neighbor' leaner i.e. fnn Its parameter is 'k' which has a default value of 1. When I use tuning using random search, I set the parameter of k as: lower= 0, upper=3...

I am using nlr3 'fast nearest neighbor' leaner i.e. fnn Its parameter is km which has a default value of 1. When I use tuning using random search, I set the parameter of k as: lower= 0, upper=3...

I cannot run the "ranger" model with caret. I am only using the farff and caret libraries and the following code: boot <- trainControl(method = "cv", number=10) c1 <-train(act_effort ~ ., data = tr, method = "ranger", tuneLength = 5, metric = "MAE", preProc...

I have a ggplot2 which has x-values 0-200 and y values 0-10 p=plot(mydata) p+xlim(0, 200) I want to show what is the y value when we have 75 as x value. The graph...

Hello I am using feature selection using AutoSpearman but I have no idea what to do after the 'plotVarClus' function, which is just a graph and red bars are going out of the input metrics. My question is what is...