Package index • aifeducation

For Users

Installation and Configuration

check_aif_py_modules(): Check if all necessary python modules are available

get_recommended_py_versions(): Recommended version of python packages

install_aifeducation(): Install aifeducation on a machine

install_aifeducation_studio(): Install 'AI for Education - Studio' on a machine

install_py_modules(): Installing necessary python modules to an environment

prepare_session(): Function for setting up a python environment within R.

set_transformers_logger(): Sets the level for logging information of the 'transformers' library

update_aifeducation(): Updates an existing installation of 'aifeducation' on a machine

AI for Education Studio

start_aifeducation_studio(): Aifeducation Studio

Saving and Loading

load_from_disk(): Loading objects created with 'aifeducation'

save_to_disk(): Saving objects created with 'aifeducation'

Data Management

EmbeddedText: Abstract class for small data sets containing text embeddings

LargeDataSetForText: Abstract class for large data sets containing raw texts

LargeDataSetForTextEmbeddings: Abstract class for large data sets containing text embeddings

Tokenizer

HuggingFaceTokenizer: HuggingFaceTokenizer

WordPieceTokenizer: WordPieceTokenizer

Base Models and Transformers

BaseModelBert: BERT-Transformer

BaseModelDebertaV2: DeBERTa V2

BaseModelFunnel: Funnel transformer

BaseModelModernBert: ModernBert

BaseModelMPNet: MPNet

BaseModelRoberta: RoBERTa

Text Embedding Models

TEFeatureExtractor: Feature extractor for reducing the number for dimensions of text embeddings.

TextEmbeddingModel: Text embedding model

Classification models based on text embeddings

TEClassifierParallel: Text embedding classifier with a neural net

TEClassifierParallelPrototype: Text embedding classifier with a ProtoNet

TEClassifierProtoNet: Text embedding classifier with a ProtoNet

TEClassifierRegular: Text embedding classifier with a neural net

TEClassifierSequential: Text embedding classifier with a neural net

TEClassifierSequentialPrototype: Text embedding classifier with a ProtoNet

Oversampling Approaches

knnor(): K-Nearest Neighbor OveRsampling approach (KNNOR)

Performance Measures

calc_standard_classification_measures(): Calculate recall, precision, and f1-scores

cohens_kappa(): Calculate Cohen's Kappa

fleiss_kappa(): Calculate Fleiss' Kappa

get_coder_metrics(): Calculate reliability measures based on content analysis

gwet_ac(): Calculate Gwet's AC1 and AC2

kendalls_w(): Calculate Kendall's coefficient of concordance w

kripp_alpha(): Calculate Krippendorff's Alpha

For Developers

R6 Classes

AIFEBaseModel: Base class for objects using a pytorch model as core model.

AIFEMaster: Base class for most objects

BaseModelCore: Abstract class for all BaseModels

ClassifiersBasedOnTextEmbeddings: Abstract class for all classifiers that use numerical representations of texts instead of words.

DataManagerClassifier: Data manager for classification tasks

LargeDataSetBase: Abstract base class for large data sets

ModelsBasedOnTextEmbeddings: Base class for models using neural nets

TEClassifiersBasedOnProtoNet: Base class for classifiers relying on numerical representations of texts instead of words that use the architecture of Protonets and its corresponding training techniques.

TEClassifiersBasedOnRegular: Base class for regular classifiers relying on EmbeddedText or LargeDataSetForTextEmbeddings as input

TokenizerBase: Base class for tokenizers

Utils for Tokenizer

calc_tokenizer_statistics(): Estimate tokenizer statistics

Oversampling Approaches

knnor_is_same_class(): Validate a new point

Parameter Management

BaseModelsIndex: List of all available BaseModels

DataSetsIndex: List of all available types of data sets

get_called_args(): Called arguments

get_depr_obj_names(): Get names of deprecated objects

get_magnitude_values(): Magnitudes of an argument

get_param_def(): Definition of an argument

get_param_dict(): Get dictionary of all parameters

get_param_doc_desc(): Description of an argument

get_TEClassifiers_class_names(): Get names of classifiers

TokenizerIndex: List of all available Tokenizers

File Management

create_dir(): Create directory if not exists

get_file_extension(): Get file extension

Utils General

auto_n_cores(): Number of cores for multiple tasks

create_object(): Create object#'

create_synthetic_units_from_matrix(): Create synthetic units

generate_id(): Generate ID suffix for objects

get_n_chunks(): Get the number of chunks/sequences for each case

get_synthetic_cases_from_matrix(): Create synthetic cases for balancing training data

get_time_stamp(): Time stamp

matrix_to_array_c(): Reshape matrix to array

tensor_to_matrix_c(): Transform tensor to matrix

to_categorical_c(): Transforming classes to one-hot encoding

Utils Documentation

build_documentation_for_model(): Generate documentation for a classifier class

build_layer_stack_documentation_for_vignette(): Generate documentation of all layers for an vignette or article

get_desc_for_core_model_architecture(): Generate documentation for core models

get_layer_documentation(): Generate layer documentation

get_parameter_documentation(): Generate layer documentation

Utils Python

get_py_package_version(): Get versions of a specific python package

get_py_package_versions(): Get versions of python components

load_all_py_scripts(): Load and re-load all python scripts

load_py_scripts(): Load and re-load python scripts

run_py_file(): Run python file

Utils Python for Data Management

class_vector_to_py_dataset(): Convert class vector to arrow data set

data.frame_to_py_dataset(): Convert data.frame to arrow data set

get_batches_index(): Assign cases to batches

prepare_r_array_for_dataset(): Convert R array for arrow data set

py_dataset_to_embeddings(): Convert arrow data set to an arrow data set

reduce_to_unique(): Reduce to unique cases

tensor_list_to_numpy(): Convert list of tensors into numpy arrays

tensor_to_numpy(): Tensor_to_numpy

Utils Logging

cat_message(): Print message (cat())

clean_pytorch_log_transformers(): Clean pytorch log of transformers

output_message(): Print message

print_message(): Print message (message())

read_log(): Function for reading a log file in R

read_loss_log(): Function for reading a log file containing a record of the loss during training.

reset_log(): Function that resets a log file.

reset_loss_log(): Reset log for loss information

write_log(): Write log

Utils Sustainability Tracking

get_alpha_3_codes(): Country Alpha 3 Codes

Utils Argument Checks

check_all_args(): Check arguments automatically

check_class_and_type(): Check class and type

Utils for AI for Education Studio

add_missing_args(): Add missing arguments to a list of arguments

long_load_target_data(): Load target data for long running tasks

summarize_args_for_long_task(): Summarize arguments from shiny input

Utils Test of the Package

check_adjust_n_samples_on_CI(): Set sample size for argument combinations

generate_args_for_tests(): Generate combinations of arguments

generate_embeddings(): Generate test embeddings

generate_tensors(): Generate test tensors

get_current_args_for_print(): Print arguments

get_fixed_test_tensor(): Generate static test tensor

get_test_data_for_classifiers(): Get test data

random_bool_on_CI(): Random bool on Continuous Integration