Artificial Intelligence for Education
Generate test embeddings
Generate ID suffix for objects
Generate test tensors
Country Alpha 3 Codes
Assign cases to batches
Called arguments
Dictionary of layers
Generate layer documentation
Magnitudes of an argument
Get the number of chunks/sequences for each case
Definition of an argument
Calculate Gwet's AC1 and AC2
HuggingFaceTokenizer
Inspect Temporary directory
Install 'AI for Education - Studio' on a machine
Abstract class for large data sets containing text embeddings
Server function for: graphical user interface for showing the license.
Load and re-load all python scripts
Loading objects created with 'aifeducation'
Load and re-load python scripts
Load target data for long running tasks
Reshape matrix to array
Base class for models using neural nets
Print duration of a test on CI
Print message
Convert R array for arrow data set
Reset log for loss information
Run python file
Saving objects created with 'aifeducation'
Sets the level for logging information of the 'transformers' library
Aifeducation Studio
Transform tensor to matrix
Tensor_to_numpy
Text embedding model
Transforming classes to one-hot encoding
Base class for tokenizers
List of all available Tokenizers
Generate description for text embeddings
Get test data
Time stamp
Generate documentation of all layers for an vignette or article
Calculate recall, precision, and f1-scores
Clean pytorch log of transformers
Graphical user interface for displaying the reliability of classifiers...
Function that resets a log file.
Create directory if not exists
Create object#'
Add missing arguments to a list of arguments
Get names of classifiers
Base class for objects using a pytorch model as core model.
Base class for most objects
Number of cores for multiple tasks
BERT-Transformer
Abstract class for all BaseModels
DeBERTa V2
Calculate Cohen's Kappa
Funnel transformer
ModernBert
MPNet
RoBERTa
List of all available BaseModels
Generate documentation for a classifier class
Create config for R interfaces
Estimate tokenizer statistics
Print message (cat())
Set sample size for argument combinations
Check if all necessary python modules are available
Check arguments automatically
Check class and type
Convert class vector to arrow data set
Abstract class for all classifiers that use numerical representations ...
Create synthetic units
Convert data.frame to arrow data set
Data manager for classification tasks
List of all available types of data sets
Create rd formula
Abstract class for small data sets containing text embeddings
Calculate Fleiss' Kappa
Generate combinations of arguments
Calculate reliability measures based on content analysis
Print arguments
Get names of deprecated objects
Generate documentation for core models
Dictionary of classifier types
Dictionary of core models
Dictionary of input types
Get file extension
Generate static test tensor
Get dictionary of all parameters
Description of an argument
Generate layer documentation
Get versions of a specific python package
Get versions of python components
Recommended version of python packages
Create synthetic cases for balancing training data
Install aifeducation on a machine
Installing necessary python modules to an environment
Calculate Kendall's coefficient of concordance w
Validate a new point
K-Nearest Neighbor OveRsampling approach (KNNOR)
Calculate Krippendorff's Alpha
Abstract base class for large data sets
Abstract class for large data sets containing raw texts
Function for setting up a python environment within R.
Print message (message())
Convert arrow data set to an arrow data set
Random bool on Continuous Integration
Function for reading a log file in R
Function for reading a log file containing a record of the loss during...
Reduce to unique cases
Server function for: graphical user interface for displaying the relia...
Summarize arguments from shiny input
Summarizing tracked sustainability data
Text embedding classifier with a neural net
Text embedding classifier with a ProtoNet
Text embedding classifier with a ProtoNet
Text embedding classifier with a neural net
Base class for classifiers relying on numerical representations of tex...
Base class for regular classifiers relying on EmbeddedText or LargeDat...
Text embedding classifier with a neural net
Text embedding classifier with a ProtoNet
Feature extractor for reducing the number for dimensions of text embed...
Convert list of tensors into numpy arrays
Updates an existing installation of 'aifeducation' on a machine
WordPieceTokenizer
Write log
In social and educational settings, the use of Artificial Intelligence (AI) is a challenging task. Relevant data is often only available in handwritten forms, or the use of data is restricted by privacy policies. This often leads to small data sets. Furthermore, in the educational and social sciences, data is often unbalanced in terms of frequencies. To support educators as well as educational and social researchers in using the potentials of AI for their work, this package provides a unified interface for neural nets in 'PyTorch' to deal with natural language problems. In addition, the package ships with a shiny app, providing a graphical user interface. This allows the usage of AI for people without skills in writing python/R scripts. The tools integrate existing mathematical and statistical methods for dealing with small data sets via pseudo-labeling (e.g. Cascante-Bonilla et al. (2020) <doi:10.48550/arXiv.2001.06001>) and imbalanced data via the creation of synthetic cases (e.g. Islam et al. (2012) <doi:10.1016/j.asoc.2021.108288>). Performance evaluation of AI is connected to measures from content analysis which educational and social researchers are generally more familiar with (e.g. Berding & Pargmann (2022) <doi:10.30819/5581>, Gwet (2014) <ISBN:978-0-9708062-8-4>, Krippendorff (2019) <doi:10.4135/9781071878781>). Estimation of energy consumption and CO2 emissions during model training is done with the 'python' library 'codecarbon'. Finally, all objects created with this package allow to share trained AI models with other people.
Useful links