mlr01

mlr01

library(mlr3)

## Warning: package 'mlr3' was built under R version 3.6.2

library(mlr3viz)


task = tsk("pima")$select(c("age", "glucose", "insulin"))
learner = lrn("classif.rpart", predict_type = "prob")
rr = resample(task, learner, rsmp("cv", folds = 10))

## INFO  [15:42:13.979] Applying learner 'classif.rpart' on task 'pima' (iter 1/10) 
## INFO  [15:42:14.116] Applying learner 'classif.rpart' on task 'pima' (iter 2/10) 
## INFO  [15:42:14.155] Applying learner 'classif.rpart' on task 'pima' (iter 3/10) 
## INFO  [15:42:14.185] Applying learner 'classif.rpart' on task 'pima' (iter 4/10) 
## INFO  [15:42:14.206] Applying learner 'classif.rpart' on task 'pima' (iter 5/10) 
## INFO  [15:42:14.225] Applying learner 'classif.rpart' on task 'pima' (iter 6/10) 
## INFO  [15:42:14.256] Applying learner 'classif.rpart' on task 'pima' (iter 7/10) 
## INFO  [15:42:14.279] Applying learner 'classif.rpart' on task 'pima' (iter 8/10) 
## INFO  [15:42:14.295] Applying learner 'classif.rpart' on task 'pima' (iter 9/10) 
## INFO  [15:42:14.316] Applying learner 'classif.rpart' on task 'pima' (iter 10/10)

# Default plot for task
autoplot(task)

# Pairs plot from GGally
##install.packages("GGally")

library(GGally)

## Warning: package 'GGally' was built under R version 3.6.2

## Loading required package: ggplot2

## Registered S3 method overwritten by 'GGally':
##   method from   
##   +.gg   ggplot2

autoplot(task, type = "pairs")

## Warning: Removed 5 rows containing non-finite values (stat_boxplot).

## Warning: Removed 374 rows containing non-finite values (stat_boxplot).

## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

## Warning in (function (data, mapping, alignPercent = 0.6, method =
## "pearson", : Removed 5 rows containing missing values

## Warning in (function (data, mapping, alignPercent = 0.6, method =
## "pearson", : Removed 374 rows containing missing values

## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

## Warning: Removed 5 rows containing non-finite values (stat_bin).

## Warning: Removed 5 rows containing missing values (geom_point).

## Warning: Removed 5 rows containing non-finite values (stat_density).

## Warning in (function (data, mapping, alignPercent = 0.6, method =
## "pearson", : Removed 375 rows containing missing values

## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

## Warning: Removed 374 rows containing non-finite values (stat_bin).

## Warning: Removed 374 rows containing missing values (geom_point).

## Warning: Removed 375 rows containing missing values (geom_point).

## Warning: Removed 374 rows containing non-finite values (stat_density).

library(precrec)

## Warning: package 'precrec' was built under R version 3.6.2

# ROC curve for the ResampleResult
autoplot(rr, type = "roc")

library("mlr3")
task = tsk("iris")
learner = lrn("classif.rpart")


# train a model of this learner for a subset of the task
learner$train(task, row_ids = 1:120)
# this is what the decision tree looks like
learner$model

## n= 120 
## 
## node), split, n, loss, yval, (yprob)
##       * denotes terminal node
## 
## 1) root 120 70 setosa (0.41666667 0.41666667 0.16666667)  
##   2) Petal.Length< 2.45 50  0 setosa (1.00000000 0.00000000 0.00000000) *
##   3) Petal.Length>=2.45 70 20 versicolor (0.00000000 0.71428571 0.28571429)  
##     6) Petal.Length< 4.95 49  1 versicolor (0.00000000 0.97959184 0.02040816) *
##     7) Petal.Length>=4.95 21  2 virginica (0.00000000 0.09523810 0.90476190) *

predictions = learner$predict(task, row_ids = 121:150)
predictions

## <PredictionClassif> for 30 observations:
##     row_id     truth   response
##        121 virginica  virginica
##        122 virginica versicolor
##        123 virginica  virginica
## ---                            
##        148 virginica  virginica
##        149 virginica  virginica
##        150 virginica  virginica

# accuracy of our model on the test set of the final 30 rows
predictions$score(msr("classif.acc"))

## classif.acc 
##   0.8333333