Learn R Programming

processpredictR

The goal of processpredictR is to perform prediction tasks on processes using event logs and Transformer models.

Installation

You can install the development version of processpredictR from GitHub with:

# install.packages("devtools")
devtools::install_github("bupaverse/processpredictR")


```r
library(processpredictR)

Copy Link

Version

Install

install.packages('processpredictR')

Monthly Downloads

638

Version

0.1.0

License

MIT + file LICENSE

Maintainer

Gert Janssenswillen

Last Published

January 17th, 2023

Functions in processpredictR (0.1.0)

max_case_length

Calculate the maximum length of a case / number of activities in the longest trace in an event log
num_outputs

Calculate number of outputs (target variables)
reexports

Default compile function for ProcessTransformer model
split_train_test

Splits the preprocessed data.frame.
%>%

Pipe operator
plot.ppred_predictions

Plot Methods
ppred_predictions

ppred_predictions object
prepare_examples

Convert a dataset of type log into a preprocessed format.
create_vocabulary

Create a vocabulary
get_vocabulary

Utils
ppred_model

ppred_model object
ppred_examples_df

ppred_examples_df object
vocab_size

Calculate the vocabulary size, i.e. the sum of number of activities, outcome labels and padding keys
create_model

Define transformer model
confusion_matrix

Confusion matrix for predictions
print.ppred_model

Print methods
stack_layers

Stacks a keras layer on top of existing model
processpredictR

processpredictR
tokenize

Tokenize features and target of a processed dataset of class ppred_examples_df