Package: aifeducation 0.3.3

aifeducation: Artificial Intelligence for Education

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 'keras', 'tensorflow', and '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. Lee (2013) <https://www.researchgate.net/publication/280581078_Pseudo-Label_The_Simple_and_Efficient_Semi-Supervised_Learning_Method_for_Deep_Neural_Networks>, Cascante-Bonilla et al. (2020) <doi:10.48550/arXiv.2001.06001>) and imbalanced data via the creation of synthetic cases (e.g. Bunkhumpornpat et al. (2012) <doi:10.1007/s10489-011-0287-y>). 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.

Authors:Berding Florian [aut, cre], Pargmann Julia [ctb], Riebenbauer Elisabeth [ctb], Rebmann Karin [ctb], Slopinski Andreas [ctb]

aifeducation_0.3.3.tar.gz
aifeducation_0.3.3.zip(r-4.5)aifeducation_0.3.3.zip(r-4.4)aifeducation_0.3.3.zip(r-4.3)
aifeducation_0.3.3.tgz(r-4.4-x86_64)aifeducation_0.3.3.tgz(r-4.4-arm64)aifeducation_0.3.3.tgz(r-4.3-x86_64)aifeducation_0.3.3.tgz(r-4.3-arm64)
aifeducation_0.3.3.tar.gz(r-4.5-noble)aifeducation_0.3.3.tar.gz(r-4.4-noble)
aifeducation_0.3.3.tgz(r-4.4-emscripten)aifeducation_0.3.3.tgz(r-4.3-emscripten)
aifeducation.pdf |aifeducation.html
aifeducation/json (API)
NEWS

# Install 'aifeducation' in R:
install.packages('aifeducation', repos = c('https://fberding.r-universe.dev', 'https://cloud.r-project.org'))

Peer review:

Bug tracker:https://github.com/fberding/aifeducation/issues

Uses libs:
  • c++– GNU Standard C++ Library v3
Datasets:

    On CRAN:

    4.70 score 8 scripts 279 downloads 40 exports 63 dependencies

    Last updated 7 months agofrom:e659443e01. Checks:OK: 1 ERROR: 5 NOTE: 3. Indexed: yes.

    TargetResultDate
    Doc / VignettesOKOct 12 2024
    R-4.5-win-x86_64NOTEOct 12 2024
    R-4.5-linux-x86_64ERROROct 12 2024
    R-4.4-win-x86_64NOTEOct 12 2024
    R-4.4-mac-x86_64ERROROct 12 2024
    R-4.4-mac-aarch64ERROROct 12 2024
    R-4.3-win-x86_64NOTEOct 12 2024
    R-4.3-mac-x86_64ERROROct 12 2024
    R-4.3-mac-aarch64ERROROct 12 2024

    Exports:aifeducation_configarray_to_matrixbow_pp_create_basic_text_repbow_pp_create_vocab_draftcalc_standard_classification_measurescheck_aif_py_modulesclean_pytorch_log_transformerscombine_embeddingscreate_bert_modelcreate_deberta_v2_modelcreate_funnel_modelcreate_longformer_modelcreate_roberta_modelcreate_synthetic_unitsEmbeddedTextget_coder_metricsget_n_chunksget_synthetic_casesinstall_py_modulesis.null_or_naload_ai_modelmatrix_to_array_csave_ai_modelset_config_cpu_onlyset_config_gpu_low_memoryset_config_os_environ_loggerset_config_tf_loggerset_transformers_loggerstart_aifeducation_studioTextEmbeddingClassifierNeuralNetTextEmbeddingModelto_categorical_ctrain_tune_bert_modeltrain_tune_deberta_v2_modeltrain_tune_funnel_modeltrain_tune_longformer_modeltrain_tune_roberta_modelupdate_aifeducation_progress_barupdate_aifeducation_progress_bar_epochsupdate_aifeducation_progress_bar_steps

    Dependencies:abindclicodetoolscolorspacecpp11dbscandoParalleldplyrfansifarverFNNforeachgenericsggalluvialggplot2gluegridExtragtablehereigraphiotarelrirrirrCACisobanditeratorsjsonlitelabelinglatticelazyevallifecyclelpSolvemagrittrMASSMatrixmgcvmunsellnlmepillarpkgconfigplyrpngpurrrR6rappdirsRColorBrewerRcppRcppArmadilloRcppTOMLreshape2reticulaterlangrprojrootscalessmotefamilystringistringrtibbletidyrtidyselectutf8vctrsviridisLitewithr

    01 Get started

    Rendered fromaifeducation.Rmdusingknitr::rmarkdownon Oct 12 2024.

    Last update: 2024-04-15
    Started: 2023-04-14

    03 Sharing and Using Trained AI/Models

    Rendered fromsharing_and_publishing.Rmdusingknitr::rmarkdownon Oct 12 2024.

    Last update: 2024-03-17
    Started: 2023-04-27

    Readme and manuals

    Help Manual

    Help pageTopics
    R6 object of class AifeducationConfigurationaifeducation_config
    R6 class for settting the global machine learning framework.AifeducationConfiguration
    Array to matrixarray_to_matrix
    Prepare texts for text embeddings with a bag of word approach.bow_pp_create_basic_text_rep
    Function for creating a first draft of a vocabulary This function creates a list of tokens which refer to specific universal part-of-speech tags (UPOS) and provides the corresponding lemmas.bow_pp_create_vocab_draft
    Calculate standard classification measurescalc_standard_classification_measures
    Check if all necessary python modules are availablecheck_aif_py_modules
    Combine embedded textscombine_embeddings
    Function for creating a new transformer based on BERTcreate_bert_model
    Function for creating a new transformer based on DeBERTa-V2create_deberta_v2_model
    Function for creating a new transformer based on Funnel Transformercreate_funnel_model
    Function for creating a new transformer based on Longformercreate_longformer_model
    Function for creating a new transformer based on RoBERTacreate_roberta_model
    Create synthetic unitscreate_synthetic_units
    Embedded textEmbeddedText
    Calculate reliability measures based on content analysisget_coder_metrics
    Get the number of chunks/sequences for each caseget_n_chunks
    Create synthetic cases for balancing training dataget_synthetic_cases
    Installing necessary python modules to an environmentinstall_py_modules
    Loading models created with 'aifeducation'load_ai_model
    Reshape matrix to arraymatrix_to_array_c
    Saving models created with 'aifeducation'save_ai_model
    Setting cpu only for 'tensorflow'set_config_cpu_only
    Setting gpus' memory usageset_config_gpu_low_memory
    Sets the level for logging information in tensor flow.set_config_os_environ_logger
    Sets the level for logging information in tensor flow.set_config_tf_logger
    Sets the level for logging information of the 'transformers' library.set_transformers_logger
    Aifeducation Studiostart_aifeducation_studio
    Text embedding classifier with a neural netTextEmbeddingClassifierNeuralNet
    Text embedding modelTextEmbeddingModel
    Transforming classes to one-hot encodingto_categorical_c
    Function for training and fine-tuning a BERT modeltrain_tune_bert_model
    Function for training and fine-tuning a DeBERTa-V2 modeltrain_tune_deberta_v2_model
    Function for training and fine-tuning a Funnel Transformer modeltrain_tune_funnel_model
    Function for training and fine-tuning a Longformer modeltrain_tune_longformer_model
    Function for training and fine-tuning a RoBERTa modeltrain_tune_roberta_model
    Update master progress bar in aifeducation shiny app.update_aifeducation_progress_bar
    Update epoch progress bar in aifeducation shiny app.update_aifeducation_progress_bar_epochs
    Update step/batch progress bar in aifeducation shiny app.update_aifeducation_progress_bar_steps