bagged.outliertrees {bagged.outliertrees}  R Documentation 
Fit Bagged OutlierTrees ensemble model to normal data with perhaps some outliers.
bagged.outliertrees( df, ntrees = 100L, subsampling_rate = 0.25, max_depth = 4L, min_gain = 0.01, z_norm = 2.67, z_outlier = 8, pct_outliers = 0.01, min_size_numeric = 25L, min_size_categ = 50L, categ_split = "binarize", categ_outliers = "tail", numeric_split = "raw", cols_ignore = NULL, follow_all = FALSE, gain_as_pct = TRUE, nthreads = parallel::detectCores() )
df 
Data Frame with normal data that might contain some outliers. See details for allowed column types. 
ntrees 
Controls the ensemble size (i.e. the number of OutlierTrees or bootstrapped training sets). A large value is always recommended to build a robust and stable ensemble. Should be decreased if training is taking too much time. 
subsampling_rate 
Subsampling rate used for bootstrapping. A small rate results in smaller bootstrapped training sets, which should not suffer from the masking effect. This parameter should be adjusted given the size of the training data (perhaps a smaller value for large training data and conversely). 
max_depth 
Maximum depth of the trees to grow. Can also pass zero, in which case it will only look for outliers with no conditions (i.e. takes each column as a 1d distribution and looks for outliers in there independently of the values in other columns). 
min_gain 
Minimum gain that a split has to produce in order to consider it (both in terms of looking
for outliers in each branch, and in considering whether to continue branching from them). Note that default
value for GritBot is 1e6, with 
z_norm 
Maximum Zvalue (from standard normal distribution) that can be considered as a normal observation. Note that simply having values above this will not automatically flag observations as outliers, nor does it assume that columns follow normal distributions. Also used for categorical and ordinal columns for building approximate confidence intervals of proportions. 
z_outlier 
Minimum Zvalue that can be considered as an outlier. There must be a large gap in the Zvalue of the next observation in sorted order to consider it as outlier, given by (z_outlier  z_norm). Decreasing this parameter is likely to result in more observations being flagged as outliers. Ignored for categorical and ordinal columns. 
pct_outliers 
Approximate max percentage of outliers to expect in a given branch. 
min_size_numeric 
Minimum size that branches need to have when splitting a numeric column. In order to look for outliers in a given branch for a numeric column, it must have a minimum of twice this number of observations. 
min_size_categ 
Minimum size that branches need to have when splitting a categorical or ordinal column. In order to look for outliers in a given branch for a categorical, ordinal, or boolean column, it must have a minimum of twice this number of observations. 
categ_split 
How to produce categoricalbycategorical splits. Options are:

categ_outliers 
How to look for outliers in categorical variables. Options are:

numeric_split 
How to determine the split point in numeric variables. Options are:
This doesn't affect how outliers are determined in the training data passed in 
cols_ignore 
Vector containing columns which will not be split, but will be evaluated for usage
in splitting other columns. Can pass either a logical (boolean) vector with the same number of columns
as 
follow_all 
Whether to continue branching from each split that meets the size and gain criteria. This will produce exponentially many more branches, and if depth is large, might take forever to finish. Will also produce a lot more spurious outiers. Not recommended. 
gain_as_pct 
Whether the minimum gain above should be taken in absolute terms, or as a percentage of
the standard deviation (for numerical columns) or shannon entropy (for categorical columns). Taking it in
absolute terms will prefer making more splits on columns that have a large variance, while taking it as a
percentage might be more restrictive on them and might create deeper trees in some columns. For GritBot
this parameter would always be 
nthreads 
Number of parallel threads to use when fitting the model. 
An object with the fitted model that can be used to detect more outliers in new data.
GritBot software: https://www.rulequest.com/gritbotinfo.html
Cortes, David. "Explainable outlier detection through decision tree conditioning." arXiv preprint arXiv:2001.00636 (2020).
predict.bagged.outliertrees print.bagged.outlieroutputs hypothyroid
library(bagged.outliertrees) ### example dataset with interesting outliers data(hypothyroid) ### fit a Bagged OutlierTrees model model < bagged.outliertrees(hypothyroid, ntrees = 10, subsampling_rate = 0.5, z_outlier = 6, nthreads = 1 ) ### use the fitted model to find outliers in the training dataset outliers < predict(model, newdata = hypothyroid, min_outlier_score = 0.5, nthreads = 1 ) ### print the top10 outliers in humanreadable format print(outliers, outliers_print = 10)