library(mlr3verse)Intro
mlr3pipelines offers a very flexible way to create data preprocessing steps. This is achieved by a modular approach using PipeOps. For detailed overview check the mlr3book.
Recommended prior readings:
This post covers:
- How to apply different preprocessing steps on different features
- How to branch different preprocessing steps, which allows to select the best performing path
- How to tune the whole pipeline
Prerequisites
We load the mlr3verse package which pulls in the most important packages for this example.
We initialize the random number generator with a fixed seed for reproducibility, and decrease the verbosity of the logger to keep the output clearly represented.
set.seed(7832)
lgr::get_logger("mlr3")$set_threshold("warn")
lgr::get_logger("bbotk")$set_threshold("warn")The diabetes classification task will be used.
task_diabetes = tsk("diabetes")
skimr::skim(task_diabetes$data())| Name | task_diabetes$data() |
| Number of rows | 768 |
| Number of columns | 9 |
| Key | NULL |
| _______________________ | |
| Column type frequency: | |
| factor | 1 |
| numeric | 8 |
| ________________________ | |
| Group variables | None |
Variable type: factor
| skim_variable | n_missing | complete_rate | ordered | n_unique | top_counts |
|---|---|---|---|---|---|
| diabetes | 0 | 1 | FALSE | 2 | neg: 488, pos: 280 |
Variable type: numeric
| skim_variable | n_missing | complete_rate | mean | sd | p0 | p25 | p50 | p75 | p100 | hist |
|---|---|---|---|---|---|---|---|---|---|---|
| age | 0 | 1.00 | 33.05 | 11.94 | 21.00 | 24.00 | 28.00 | 41.00 | 81.00 | ▇▂▁▁▁ |
| glucose | 5 | 0.99 | 125.30 | 31.59 | 57.00 | 101.00 | 119.00 | 144.50 | 199.00 | ▁▇▆▃▂ |
| insulin | 405 | 0.47 | 159.05 | 123.34 | 14.00 | 76.00 | 125.00 | 194.00 | 846.00 | ▇▂▁▁▁ |
| mass | 13 | 0.98 | 32.87 | 7.02 | 18.20 | 27.80 | 32.80 | 36.95 | 59.40 | ▃▇▅▁▁ |
| pedigree | 0 | 1.00 | 0.48 | 0.36 | 0.08 | 0.24 | 0.37 | 0.64 | 2.42 | ▇▃▁▁▁ |
| pregnant | 0 | 1.00 | 4.58 | 3.88 | 0.00 | 1.00 | 3.00 | 7.00 | 13.00 | ▇▆▃▂▂ |
| pressure | 35 | 0.95 | 72.59 | 12.19 | 24.00 | 64.00 | 72.00 | 80.00 | 108.00 | ▁▁▇▆▁ |
| triceps | 251 | 0.67 | 29.46 | 9.96 | 7.00 | 22.00 | 30.00 | 36.00 | 63.00 | ▃▇▇▃▁ |
Selection of features for preprocessing steps
Several features of the diabetes task have missing values:
task_diabetes$missings()diabetes age glucose insulin mass pedigree pregnant pressure triceps
0 0 5 405 13 0 0 35 251 A common approach in such situations is to impute the missing values and to add a missing indicator column as explained in the Impute missing variables post. Suppose we want to use
PipeOpImputeHiston the features “glucose”, “mass” and “pressure” andPipeOpImputeMedianon the features “insulin” and “triceps”.
In the following subsections, we show two approaches to implement this.
1. Consider all features and apply the preprocessing step only to certain features
Using the affect_columns argument of a PipeOp to define the variables on which a PipeOp will operate with an appropriate Selector function:
# imputes values based on histogram
imputer_hist = po("imputehist",
affect_columns = selector_name(c("glucose", "mass", "pressure")))
# imputes values using the median
imputer_median = po("imputemedian",
affect_columns = selector_name(c("insulin", "triceps")))
# adds an indicator column for each feature with missing values
miss_ind = po("missind")When PipeOps are constructed this way, they will perform the specified preprocessing step on the appropriate features and pass all the input features to the subsequent steps:
# no missings in "glucose", "mass" and "pressure"
imputer_hist$train(list(task_diabetes))[[1]]$missings()diabetes age insulin pedigree pregnant triceps glucose mass pressure
0 0 405 0 0 251 0 0 0 # no missings in "insulin" and "triceps"
imputer_median$train(list(task_diabetes))[[1]]$missings()diabetes age glucose mass pedigree pregnant pressure insulin triceps
0 0 5 13 0 0 35 0 0 We construct a pipeline that combines imputer_hist and imputer_median. Here, imputer_hist will impute the features “glucose”, “mass” and “pressure”, and imputer_median will impute “insulin” and “triceps”. In each preprocessing step, all the input features are passed to the next step. In the end, we obtain a data set without missing values:
# combine the two impuation methods
impute_graph = imputer_hist %>>% imputer_median
impute_graph$plot(html = FALSE)
impute_graph$train(task_diabetes)[[1]]$missings()diabetes age pedigree pregnant glucose mass pressure insulin triceps
0 0 0 0 0 0 0 0 0 The PipeOpMissInd operator replaces features with missing values with a missing value indicator:
miss_ind$train(list(task_diabetes))[[1]]$data() diabetes missing_glucose missing_insulin missing_mass missing_pressure missing_triceps
<fctr> <fctr> <fctr> <fctr> <fctr> <fctr>
1: neg present missing present present present
2: pos present missing present present missing
3: neg present missing present present present
4: neg present missing present present missing
5: neg present missing present present present
---
764: pos present missing present present present
765: pos present present present present present
766: neg present present present present present
767: neg present missing present present missing
768: neg present missing present present missingObviously, this step can not be applied to the already imputed data as there are no missing values. If we want to combine the previous two imputation steps with a third step that adds missing value indicators, we would need to PipeOpCopy the data two times and supply the first copy to impute_graph and the second copy to miss_ind using gunion(). Finally, the two outputs can be combined with PipeOpFeatureUnion:
impute_missind = po("copy", 2) %>>%
gunion(list(impute_graph, miss_ind)) %>>%
po("featureunion")
impute_missind$plot(html = FALSE)
impute_missind$train(task_diabetes)[[1]]$data() diabetes age pedigree pregnant glucose mass pressure insulin triceps missing_glucose missing_insulin
<fctr> <num> <num> <num> <num> <num> <num> <num> <num> <fctr> <fctr>
1: neg 28 0.240 0 194 28.5 50 125 45 present missing
2: pos 44 0.828 8 129 27.6 84 125 30 present missing
3: neg 26 0.696 2 132 38.2 72 125 42 present missing
4: neg 39 0.192 6 184 24.7 62 125 30 present missing
5: neg 22 0.178 4 108 31.6 58 125 32 present missing
---
764: pos 43 0.346 10 92 33.1 50 125 28 present missing
765: pos 26 1.162 0 181 35.8 58 474 27 present present
766: neg 60 0.460 6 130 34.2 106 540 27 present present
767: neg 24 0.206 2 146 27.7 72 125 30 present missing
768: neg 41 0.187 6 115 27.6 72 125 30 present missing
missing_mass missing_pressure missing_triceps
<fctr> <fctr> <fctr>
1: present present present
2: present present missing
3: present present present
4: present present missing
5: present present present
---
764: present present present
765: present present present
766: present present present
767: present present missing
768: present present missing2. Select the features for each preprocessing step and apply the preprocessing steps to this subset
We can use the PipeOpSelect to select the appropriate features and then apply the desired impute PipeOp on them:
imputer_hist_2 = po("select",
selector = selector_name(c("glucose", "mass", "pressure")),
id = "slct1") %>>% # unique id so we can combine it in a pipeline with other select PipeOps
po("imputehist")
imputer_hist_2$plot(html = FALSE)
imputer_hist_2$train(task_diabetes)[[1]]$data() diabetes glucose mass pressure
<fctr> <num> <num> <num>
1: neg 194 28.5 50
2: pos 129 27.6 84
3: neg 132 38.2 72
4: neg 184 24.7 62
5: neg 108 31.6 58
---
764: pos 92 33.1 50
765: pos 181 35.8 58
766: neg 130 34.2 106
767: neg 146 27.7 72
768: neg 115 27.6 72imputer_median_2 =
po("select", selector = selector_name(c("insulin", "triceps")), id = "slct2") %>>%
po("imputemedian")
imputer_median_2$train(task_diabetes)[[1]]$data() diabetes insulin triceps
<fctr> <num> <num>
1: neg 125 45
2: pos 125 30
3: neg 125 42
4: neg 125 30
5: neg 125 32
---
764: pos 125 28
765: pos 474 27
766: neg 540 27
767: neg 125 30
768: neg 125 30To reproduce the result of the fist example (1.), we need to copy the data four times and apply imputer_hist_2, imputer_median_2 and miss_ind on each of the three copies. The fourth copy is required to select the features without missing values and to append it to the final result. We can do this as follows:
other_features = task_diabetes$feature_names[task_diabetes$missings()[-1] == 0]
imputer_missind_2 = po("copy", 4) %>>%
gunion(list(imputer_hist_2,
imputer_median_2,
miss_ind,
po("select", selector = selector_name(other_features), id = "slct3"))) %>>%
po("featureunion")
imputer_missind_2$plot(html = FALSE)
imputer_missind_2$train(task_diabetes)[[1]]$data() diabetes glucose mass pressure insulin triceps missing_glucose missing_insulin missing_mass missing_pressure
<fctr> <num> <num> <num> <num> <num> <fctr> <fctr> <fctr> <fctr>
1: neg 194 28.5 50 125 45 present missing present present
2: pos 129 27.6 84 125 30 present missing present present
3: neg 132 38.2 72 125 42 present missing present present
4: neg 184 24.7 62 125 30 present missing present present
5: neg 108 31.6 58 125 32 present missing present present
---
764: pos 92 33.1 50 125 28 present missing present present
765: pos 181 35.8 58 474 27 present present present present
766: neg 130 34.2 106 540 27 present present present present
767: neg 146 27.7 72 125 30 present missing present present
768: neg 115 27.6 72 125 30 present missing present present
missing_triceps age pedigree pregnant
<fctr> <num> <num> <num>
1: present 28 0.240 0
2: missing 44 0.828 8
3: present 26 0.696 2
4: missing 39 0.192 6
5: present 22 0.178 4
---
764: present 43 0.346 10
765: present 26 1.162 0
766: present 60 0.460 6
767: missing 24 0.206 2
768: missing 41 0.187 6Note that when there is one input channel, it is automatically copied as many times as needed for the downstream PipeOps. In other words, the code above works also without po("copy", 4):
imputer_missind_3 = gunion(list(imputer_hist_2,
imputer_median_2,
miss_ind,
po("select", selector = selector_name(other_features), id = "slct3"))) %>>%
po("featureunion")
imputer_missind_3$train(task_diabetes)[[1]]$data() diabetes glucose mass pressure insulin triceps missing_glucose missing_insulin missing_mass missing_pressure
<fctr> <num> <num> <num> <num> <num> <fctr> <fctr> <fctr> <fctr>
1: neg 194 28.5 50 125 45 present missing present present
2: pos 129 27.6 84 125 30 present missing present present
3: neg 132 38.2 72 125 42 present missing present present
4: neg 184 24.7 62 125 30 present missing present present
5: neg 108 31.6 58 125 32 present missing present present
---
764: pos 92 33.1 50 125 28 present missing present present
765: pos 181 35.8 58 474 27 present present present present
766: neg 130 34.2 106 540 27 present present present present
767: neg 146 27.7 72 125 30 present missing present present
768: neg 115 27.6 72 125 30 present missing present present
missing_triceps age pedigree pregnant
<fctr> <num> <num> <num>
1: present 28 0.240 0
2: missing 44 0.828 8
3: present 26 0.696 2
4: missing 39 0.192 6
5: present 22 0.178 4
---
764: present 43 0.346 10
765: present 26 1.162 0
766: present 60 0.460 6
767: missing 24 0.206 2
768: missing 41 0.187 6Usually, po("copy") is required when there are more than one input channels and multiple output channels, and their numbers do not match.
Branching
We can not know if the combination of a learner with this preprocessing graph will benefit from the imputation steps and the added missing value indicators. Maybe it would have been better to just use imputemedian on all the variables. We could investigate this assumption by adding an alternative path to the graph with the mentioned imputemedian. This is possible using the “branch” PipeOp:
imputer_median_3 = po("imputemedian", id = "simple_median") # add the id so it does not clash with `imputer_median`
branches = c("impute_missind", "simple_median") # names of the branches
graph_branch = po("branch", branches) %>>%
gunion(list(impute_missind, imputer_median_3)) %>>%
po("unbranch")
graph_branch$plot(html = FALSE)
Tuning the pipeline
To finalize the graph, we combine it with a rpart learner:
graph = graph_branch %>>%
lrn("classif.rpart")
graph$plot(html = FALSE)
To define the parameters to be tuned, we first check the available ones in the graph:
as.data.table(graph$param_set)[, .(id, class, lower, upper, nlevels)] id class lower upper nlevels
<char> <char> <num> <num> <num>
1: branch.selection ParamFct NA NA 2
2: imputehist.affect_columns ParamUty NA NA Inf
3: imputemedian.affect_columns ParamUty NA NA Inf
4: missind.which ParamFct NA NA 2
5: missind.type ParamFct NA NA 4
6: missind.affect_columns ParamUty NA NA Inf
7: simple_median.affect_columns ParamUty NA NA Inf
8: classif.rpart.cp ParamDbl 0 1 Inf
9: classif.rpart.keep_model ParamLgl NA NA 2
10: classif.rpart.maxcompete ParamInt 0 Inf Inf
11: classif.rpart.maxdepth ParamInt 1 30 30
12: classif.rpart.maxsurrogate ParamInt 0 Inf Inf
13: classif.rpart.minbucket ParamInt 1 Inf Inf
14: classif.rpart.minsplit ParamInt 1 Inf Inf
15: classif.rpart.surrogatestyle ParamInt 0 1 2
16: classif.rpart.usesurrogate ParamInt 0 2 3
17: classif.rpart.xval ParamInt 0 Inf InfWe decide to jointly tune the "branch.selection", "classif.rpart.cp" and "classif.rpart.minbucket" hyperparameters:
search_space = ps(
branch.selection = p_fct(c("impute_missind", "simple_median")),
classif.rpart.cp = p_dbl(0.001, 0.1),
classif.rpart.minbucket = p_int(1, 10))In order to tune the graph, it needs to be converted to a learner:
graph_learner = as_learner(graph)
cv3 = rsmp("cv", folds = 3)
cv3$instantiate(task_diabetes) # to generate folds for cross validation
instance = tune(
tuner = tnr("random_search"),
task = task_diabetes,
learner = graph_learner,
resampling = rsmp("cv", folds = 3),
measure = msr("classif.ce"),
search_space = search_space,
term_evals = 5)
as.data.table(instance$archive, unnest = NULL, exclude_columns = c("x_domain", "uhash", "resample_result")) branch.selection classif.rpart.cp classif.rpart.minbucket classif.ce runtime_learners timestamp warnings
<char> <num> <int> <num> <num> <POSc> <int>
1: simple_median 0.06039370 4 0.2799479 0.458 2026-11-04 19:42:27 0
2: impute_missind 0.08838643 3 0.2812500 0.980 2026-11-04 19:42:28 0
3: simple_median 0.06849620 4 0.2799479 0.446 2026-11-04 19:42:28 0
4: impute_missind 0.01160007 3 0.2981771 0.808 2026-11-04 19:42:28 0
5: simple_median 0.08184096 4 0.2799479 0.445 2026-11-04 19:42:29 0
errors batch_nr
<int> <int>
1: 0 1
2: 0 2
3: 0 3
4: 0 4
5: 0 5The best performance in this short tuned experiment was achieved with:
instance$result branch.selection classif.rpart.cp classif.rpart.minbucket learner_param_vals x_domain classif.ce
<char> <num> <int> <list> <list> <num>
1: simple_median 0.0603937 4 <list[9]> <list[3]> 0.2799479Conclusion
This post shows ways on how to specify features on which preprocessing steps are to be performed. In addition it shows how to create alternative paths in the learner graph. The preprocessing steps that can be used are not limited to imputation. Check the list of available PipeOp.