Developer Index

This page lists the types and functions that are internal to the DCCR package. Because they are not part of the public API, these names might change relatively frequently between versions and so should not be relied upon.

All internal names are listed in the Index, and each of these entries link to the docstrings in the Docs section.

Index

This section contains a list of internal names that link to their corresponding Documentation.

Methods

Types

Constants

Docs

Documentation for all internal names are listed below.

DCCR.ARG_CLASS_LABELS — Constant

ARGCLASSLABELS

Description

Common docstring: argument for the class labels as strings used for plot axes.

source
DCCR.ARG_PERCENTAGES — Constant

ARG_PERCENTAGES

Description

Common docstring: argument flag to use a custom percentage formatter during plotting.

source
DCCR.ARG_Y — Constant

ARG_Y

Description

Common docstring: argument for the true target values.

source
DCCR.ARG_Y_HAT — Constant

ARGYHAT

Description

Common docstring: argument for the classifier's target outputs.

source
DCCR.ARG_Y_HAT_TRAIN — Constant

ARGYHAT_TRAIN

Description

Common docstring: argument for the target estimates on the training data.

source
DCCR.ARG_Y_HAT_VAL — Constant

ARGYHAT_VAL

Description

Common docstring: argument for classifier validation data estimates.

source
DCCR.BLOCK_TYPES — Constant

BLOCK_TYPES

Description

The names of the blocks that are encountered during L2 experiments.

source
DCCR.COMMON_DOC — Constant

COMMON_DOC

Description

Docstring prefix denoting that the constant is used as a common docstring element for other docstrings.

source
DCCR.JSON_INDENT — Constant

JSON_INDENT

Description

Constant for pretty indentation spacing in JSON files.

source
DCCR.LOG_STATES — Constant

LOG_STATES

Description

The enumerated states that an L2 logger log can be in.

source
DCCR.SAVE_MAP — Constant

SAVE_MAP

Description

Dictionary mapping the names of result save types to the private wrapper functions that implement them.

source
DCCR.pubu_9 — Constant

Purple-blue-9 ColorScheme, inferred from the RGB values

source
DCCR.ylgn_9 — Constant

Yellow-green-9 ColorScheme, inferred from the RGB values.

source
DCCR.DDVFAAgent — Type
struct DDVFAAgent <: DCCR.Agent

Summary

DDVFA-based L2 Agent.

Fields

  • agent::AdaptiveResonance.DDVFA: The DDVFA module.
  • params::Dict: Parameters used for l2logging.
  • scenario::DCCR.ExperienceQueueContainer: Container for the Experience Queue.
source
DCCR.DDVFAAgent — Method
DDVFAAgent(
    ddvfa_opts::AdaptiveResonance.opts_DDVFA,
    scenario_dict::AbstractDict
) -> DCCR.DDVFAAgent

Summary

Constructor for a DDVFAAgent using the scenario dictionary and optional DDVFA keyword argument options.

Arguments

  • opts::AbstractDict: keyword arguments for DDVFA options.
  • scenario::AbstractDict: l2logger scenario as a dictionary.

Method List / Definition Locations

DDVFAAgent(ddvfa_opts, scenario_dict)

defined at /home/runner/work/DCCR/DCCR/src/lib/l2/agents.jl:78.

source
DCCR.DDVFAAgent — Method
DDVFAAgent(
    ddvfa_opts::AdaptiveResonance.opts_DDVFA
) -> DCCR.DDVFAAgent

Summary

Creates a DDVFA agent with an empty experience queue.

Arguments

  • ddvfa_opts::opts_DDVFA: the options struct used to initialize the DDVFA module and set the logging params.

Method List / Definition Locations

DDVFAAgent(ddvfa_opts)

defined at /home/runner/work/DCCR/DCCR/src/lib/l2/agents.jl:51.

source
DCCR.Data — Type
abstract type Data

Summary

Abstract supertype for all Data structs in this library.

Fields

source
DCCR.DataSplitCombined — Type
struct DataSplitCombined <: DCCR.MatrixData

Summary

A struct for combining training and validation data, containing only train and test splits.

Fields

source
DCCR.Experience — Type
struct Experience

Summary

Experience block for an agent.

Taken from l2logger_template.

Fields

  • task_name::String: The task name.
  • block_type::String: The block type, valid values are ∈ ["train", "test"].
  • update_model::Bool: Flag for updating the model (i.e., true is to train, false is to classify).
source
DCCR.Experience — Method
Experience(
    task_name::AbstractString,
    seq_nums::DCCR.SequenceNums,
    block_type::AbstractString
) -> DCCR.Experience

Summary

Constructs an Experience, setting the update_model field based upon the block type.

Arguments

  • task_name::AbstractString: the name of the current task.
  • seq_nums::SequenceNums: the block and experience number of the Experience.
  • block_type::AbstractString: the block type ∈ ["train", "test"]. Using "train" sets update_model to true, "test" to false.

Method List / Definition Locations

Experience(task_name, seq_nums, block_type)

defined at /home/runner/work/DCCR/DCCR/src/lib/l2/experience.jl:76.

source
DCCR.ExperienceQueueContainer — Type
struct ExperienceQueueContainer

Summary

Container for the ExperienceQueue and some statistics about it.

Fields

  • stats::Dict{String, Any}: The statistics about the queue. NOTE These statistics reflect the queue at construction, not after any processing.
source
DCCR.Features — Type

Features

Description

Definition of features as a matrix of floating-point numbers of dimension (featuredim, nsamples).

source
DCCR.Labels — Type

Labels

Description

Definition of labels as a vector of strings.

source
DCCR.MatrixData — Type
abstract type MatrixData <: DCCR.Data

Summary

Abstract type for Data structs that represent features as matrices.

Fields

source
DCCR.SequenceNums — Type
struct SequenceNums

Summary

Sequence numbers for a block and Experience.

Taken from l2logger_template.

Fields

  • block_num::Int64: The block number.
  • exp_num::Int64: The experience number.
  • task_num::Int64: The task-specific count.
source
DCCR.StatsDict — Type

StatsDict

Description

Alias for a statistics dictionary being string keys mapping to any object.

source
DCCR.Targets — Type

Targets

Description

Definition of targets as a vector of integers.

source
DCCR.VectoredData — Type
abstract type VectoredData <: DCCR.Data

Summary

Abstract type for Data structs that represent features as vectors of matrices.

Fields

source
DCCR.collect_all_activations — Method
collect_all_activations(
    data_dirs::AbstractArray,
    cell::Integer
) -> Any

Summary

Return just the yolo activations from a list of data directories.

Arguments

  • data_dirs::AbstractArray: the data directories to load the yolo activations from.
  • cell::Integer: the number of cells corresponding to the windowing procedure.

Method List / Definition Locations

collect_all_activations(data_dirs, cell)

defined at /home/runner/work/DCCR/DCCR/src/lib/c3/functions.jl:43.

source
DCCR.collect_all_activations_labeled — Method
collect_all_activations_labeled(
    data_dirs::Vector{String},
    cell::Integer
) -> Tuple{Any, Vector{Int64}, Vector{String}}

Summary

Return the yolo activations, training targets, and condensed labels list from a list of data directories.

Arguments

  • data_dirs::Vector{String}: the directories to load the data from.
  • cell::Integer: the number of cells to use in the windowed averaging procedure.

Method List / Definition Locations

collect_all_activations_labeled(data_dirs, cell)

defined at /home/runner/work/DCCR/DCCR/src/lib/c3/functions.jl:64.

source
DCCR.create_accuracy_groupedbar — Method
create_accuracy_groupedbar(
    data::DCCR.DataSplit,
    y_hat_train::AbstractVector{T} where T<:Integer,
    y_hat::AbstractVector{T} where T<:Integer,
    class_labels::Vector{String};
    percentages
) -> Plots.Plot

Summary

Return a grouped bar chart with class accuracies.

Arguments

  • data::DataSplit: the original dataset with a train, val, and test split.

  • y_hat_train::IntegerVector: the classifier estimates from the training data.

  • y_hat::IntegerVector: the approximated targets generated by the classifier.

  • class_labels::Vector{String}: the string labels to use for the plot axes.

  • percentages::Bool=false: optional, flag to use the custom percentage formatter or not.

Method List / Definition Locations

create_accuracy_groupedbar(
    data,
    y_hat_train,
    y_hat,
    class_labels;
    percentages
)

defined at /home/runner/work/DCCR/DCCR/src/lib/c3/functions.jl:738.

source
DCCR.create_boxplot — Method
create_boxplot(
    data::AbstractMatrix{T} where T<:Real,
    class_labels::Vector{String};
    percentages,
    bounds,
    violin_bandwidth
) -> Any

Summary

Return a colored and formatted boxplot of the data.

Arguments

  • data::RealMatrix: the data as a 2-D matrix of real values.

  • class_labels::Vector{String}: the string labels to use for the plot axes.

  • percentages::Bool=false: optional, flag to use the custom percentage formatter or not.

  • bounds::Tuple{Float, Float}=(0.45, 1.0): optional, the bounds for the y-lim bounds of the plot.

  • violin_bandwidth::Real=0.01: the bandwidth parameter passed to the violin plot.

Method List / Definition Locations

create_boxplot(
    data,
    class_labels;
    percentages,
    bounds,
    violin_bandwidth
)

defined at /home/runner/work/DCCR/DCCR/src/lib/c3/functions.jl:868.

source
DCCR.create_comparison_groupedbar — Method
create_comparison_groupedbar(
    data::DCCR.DataSplit,
    y_hat_val::AbstractVector{T} where T<:Integer,
    y_hat::AbstractVector{T} where T<:Integer,
    class_labels::Vector{String};
    percentages,
    extended
) -> Plots.Plot

Summary

Return a grouped bar chart with comparison bars.

Arguments

  • data::DataSplit: the original dataset with a train, val, and test split.

  • y_hat_val::IntegerVector: the classifier estimates from the validation data.

  • y_hat::IntegerVector: the approximated targets generated by the classifier.

  • class_labels::Vector{String}: the string labels to use for the plot axes.

  • percentages::Bool=false: optional, flag to use the custom percentage formatter or not.

  • extended::Bool=false: if the plot needs to be extended to another category, compensating for misclassification.

  • ``

Method List / Definition Locations

create_comparison_groupedbar(
    data,
    y_hat_val,
    y_hat,
    class_labels;
    percentages,
    extended
)

defined at /home/runner/work/DCCR/DCCR/src/lib/c3/functions.jl:795.

source
DCCR.create_complex_condensed_plot — Function
create_complex_condensed_plot(
    perfs,
    vals,
    class_labels
) -> Tuple{Plots.Plot, Any}
create_complex_condensed_plot(
    perfs,
    vals,
    class_labels,
    percentages::Bool
) -> Tuple{Plots.Plot, Any}

Summary

Create and return a complex condensed scenario plot.

Method List / Definition Locations

create_complex_condensed_plot(perfs, vals, class_labels)
create_complex_condensed_plot(
    perfs,
    vals,
    class_labels,
    percentages
)

defined at /home/runner/work/DCCR/DCCR/src/lib/c3/functions.jl:1046.

source
DCCR.create_complex_condensed_plot_alt — Function
create_complex_condensed_plot_alt(
    perfs,
    vals,
    class_labels
) -> Tuple{Plots.Plot, Vector{Any}, Vector{Any}}
create_complex_condensed_plot_alt(
    perfs,
    vals,
    class_labels,
    percentages::Bool
) -> Tuple{Plots.Plot, Vector{Any}, Vector{Any}}

Summary

Create and return an alternate complex condensed scenario plot.

Method List / Definition Locations

create_complex_condensed_plot_alt(perfs, vals, class_labels)
create_complex_condensed_plot_alt(
    perfs,
    vals,
    class_labels,
    percentages
)

defined at /home/runner/work/DCCR/DCCR/src/lib/c3/functions.jl:1118.

source
DCCR.create_condensed_plot — Function
create_condensed_plot(perfs, class_labels) -> Plots.Plot
create_condensed_plot(
    perfs,
    class_labels,
    percentages::Bool
) -> Plots.Plot

Summary

Create and return a simplified condensed scenario plot.

Method List / Definition Locations

create_condensed_plot(perfs, class_labels)
create_condensed_plot(perfs, class_labels, percentages)

defined at /home/runner/work/DCCR/DCCR/src/lib/c3/functions.jl:1005.

source
DCCR.create_confusion_heatmap — Method
create_confusion_heatmap(
    class_labels::Vector{String},
    y::AbstractVector{T} where T<:Integer,
    y_hat::AbstractVector{T} where T<:Integer
) -> Plots.Plot

Summary

Returns a handle to a labeled and annotated heatmap plot of the confusion matrix.

Arguments

  • class_labels::Vector{String}: the string labels to use for the plot axes.

  • y::IntegerVector: the true targets as integers.

  • y_hat::IntegerVector: the approximated targets generated by the classifier.

Method List / Definition Locations

create_confusion_heatmap(class_labels, y, y_hat)

defined at /home/runner/work/DCCR/DCCR/src/lib/c3/functions.jl:580.

source
DCCR.create_custom_confusion_heatmap — Method
create_custom_confusion_heatmap(
    class_labels::Vector{String},
    norm_cm::AbstractMatrix{T} where T<:Real
) -> Plots.Plot

Summary

Returns a handle to a labeled and annotated heatmap plot of the confusion matrix.

Arguments

  • class_labels::Vector{String}: the string labels to use for the plot axes.

  • norm_cm::RealMatrix: the normalized confuction matrix to plot as a heatmap.

Method List / Definition Locations

create_custom_confusion_heatmap(class_labels, norm_cm)

defined at /home/runner/work/DCCR/DCCR/src/lib/c3/functions.jl:658.

source
DCCR.create_inverted_boxplot — Method
create_inverted_boxplot(
    data::AbstractMatrix{T} where T<:Real,
    class_labels::Vector{String};
    percentages,
    bounds
) -> Any

Summary

Return a colored and formatted boxplot of the data.

Arguments

  • data::RealMatrix: the data as a 2-D matrix of real values.

  • class_labels::Vector{String}: the string labels to use for the plot axes.

  • percentages::Bool=false: optional, flag to use the custom percentage formatter or not.

  • bounds::Tuple{Float, Float}=(0.45, 1.0): optional, the bounds for the y-lim bounds of the plot.

Method List / Definition Locations

create_inverted_boxplot(
    data,
    class_labels;
    percentages,
    bounds
)

defined at /home/runner/work/DCCR/DCCR/src/lib/c3/functions.jl:937.

source
DCCR.df_column_to_matrix — Method
df_column_to_matrix(
    df::DataFrames.DataFrame,
    row::Symbol
) -> Any

Summary

Convert a column of lists in a DataFrame into a matrix for analysis.

Arguments

  • df::DataFrame: the DataFrame containing the column of lists.
  • row::Symbol: the symbolic name of the row in the DataFrame to convert into a matrix.

Method List / Definition Locations

df_column_to_matrix(df, row)

defined at /home/runner/work/DCCR/DCCR/src/lib/c3/functions.jl:494.

source
DCCR.dist_exp_parse — Function
dist_exp_parse() -> Any
dist_exp_parse(description::AbstractString) -> Any

Summary

Parses the command line for common options in distributed experiments.

Arguments

  • description::AbstractString: optional positional, the script description for the parser

Method List / Definition Locations

dist_exp_parse()
dist_exp_parse(description)

defined at /home/runner/work/DCCR/DCCR/src/lib/c3/utils.jl:141.

source
DCCR.evaluate_agent! — Method
evaluate_agent!(
    agent::DCCR.Agent,
    experience::DCCR.Experience,
    data::DCCR.VectoredData
) -> Dict

Summary

Evaluates a single agent on a single experience, training or testing as needed.

Arguments

  • agent::Agent: the Agent to evaluate.
  • exp::Experience: the Experience to use for training/testing.

Method List / Definition Locations

evaluate_agent!(agent, experience, data)

defined at /home/runner/work/DCCR/DCCR/src/lib/l2/agents.jl:149.

source
DCCR.exp_parse — Function
exp_parse() -> Any
exp_parse(description::AbstractString) -> Any

Summary

Parses the command line for common options in serial (non-distributed) experiments.

Arguments

  • description::AbstractString: optional positional, the script description for the parser

Method List / Definition Locations

exp_parse()
exp_parse(description)

defined at /home/runner/work/DCCR/DCCR/src/lib/c3/utils.jl:115.

source
DCCR.feature_preprocess — Method
feature_preprocess(
    dt::StatsBase.ZScoreTransform,
    scaling::Real,
    data::AbstractMatrix{T} where T<:Real
) -> Any

Summary

Preprocesses one dataset of features, scaling and squashing along the feature axes.

Arguments

  • dt::ZScoreTransform: the Gaussian statistics of the features.
  • scaling::Real: the sigmoid scaling parameter.
  • data::RealMatrix: the 2-D matrix of features to transform.

Method List / Definition Locations

feature_preprocess(dt, scaling, data)

defined at /home/runner/work/DCCR/DCCR/src/lib/c3/functions.jl:120.

source
DCCR.get_accuracies — Method
get_accuracies(
    y::AbstractVector{T} where T<:Integer,
    y_hat::AbstractVector{T} where T<:Integer,
    n_classes::Integer
) -> Any

Summary

Get a list of the percentage accuracies.

Arguments

  • y::IntegerVector: the target values.
  • y_hat::IntegerVector: the agent's estimates.
  • n_classes::Integer: the number of total classes in the test set.

Method List / Definition Locations

get_accuracies(y, y_hat, n_classes)

defined at /home/runner/work/DCCR/DCCR/src/lib/c3/functions.jl:413.

source
DCCR.get_argparsesettings — Function
get_argparsesettings() -> Any
get_argparsesettings(description::AbstractString) -> Any

Summary

Common function for how ArgParseSettings are generated in the project.

Arguments

  • description::AbstractString: optional positional, the script description for the parser

Method List / Definition Locations

get_argparsesettings()
get_argparsesettings(description)

defined at /home/runner/work/DCCR/DCCR/src/lib/c3/utils.jl:99.

source
DCCR.get_confusion — Method
get_confusion(
    y::AbstractVector{T} where T<:Integer,
    y_hat::AbstractVector{T} where T<:Integer,
    n_classes::Integer
) -> Matrix{Int64}

Summary

Wrapper method for getting the raw confusion matrix.

Arguments

  • y::IntegerVector: the target values.
  • y_hat::IntegerVector: the agent's estimates.
  • n_classes::Integer: the number of total classes in the test set.

Method List / Definition Locations

get_confusion(y, y_hat, n_classes)

defined at /home/runner/work/DCCR/DCCR/src/lib/c3/functions.jl:385.

source
DCCR.get_deindexed_data — Method
get_deindexed_data(
    data::DCCR.DataSplitIndexed,
    order::AbstractVector{T} where T<:Integer
) -> DCCR.DataSplit

Summary

Turn a DataSplitIndexed into a DataSplit with the given train/test order.

Arguments

  • data::DataSplitIndexed: the indexed data to consolidate back into a DataSplit.
  • order::IntegerVector: the order used by the indexed data for correctly deindexing.

Method List / Definition Locations

get_deindexed_data(data, order)

defined at /home/runner/work/DCCR/DCCR/src/lib/c3/functions.jl:284.

source
DCCR.get_dist — Method
get_dist(
    data::AbstractMatrix{T} where T<:Real
) -> StatsBase.ZScoreTransform

Summary

Get the distribution parameters for preprocessing.

Arguments

  • data::RealMatrix: a 2-D matrix of features for computing the Gaussian statistics of.

Method List / Definition Locations

get_dist(data)

defined at /home/runner/work/DCCR/DCCR/src/lib/c3/functions.jl:108.

source
DCCR.get_index_from_name — Method
get_index_from_name(
    labels::Array{T<:AbstractString, 1},
    name::AbstractString
) -> Any

Summary

Gets an integer index of where a string name appears in a list of strings.

Arguments

  • labels::Vector{T} where T <: AbstractString: the list of strings to search.
  • name::AbstractString: the name to search for in the list of labels.

Method List / Definition Locations

get_index_from_name(labels, name)

defined at /home/runner/work/DCCR/DCCR/src/lib/l2/agents.jl:131.

source
DCCR.get_manual_split — Method
get_manual_split(
    data::AbstractMatrix{T} where T<:Real,
    targets::AbstractVector{T} where T<:Integer
)

Summary

Wrapper of splitobs, returns a manual train/test x/y split from a data matrix and labels using MLDataUtils.

Arguments

  • data::RealMatrix: the feature data to split into training and testing.
  • targets::IntegerVector: the labels corresponding to the data to split into training and testing.

Method List / Definition Locations

get_manual_split(data, targets)

defined at /home/runner/work/DCCR/DCCR/src/lib/c3/functions.jl:482.

source
DCCR.get_n_categories — Method
get_n_categories(
    ddvfa::AdaptiveResonance.DDVFA,
    n_classes::Int64
) -> Tuple{Vector{Int64}, Vector{Int64}}

Summary

Returns both the number of F2 categories and total number of weights per class as two lists.

Arguments

  • ddvfa::DDVFA: the DDVFA module to calculate the statistics for.
  • n_classes::Int: the number of target classes that the model was trained upon.

Method List / Definition Locations

get_n_categories(ddvfa, n_classes)

defined at /home/runner/work/DCCR/DCCR/src/lib/c3/functions.jl:455.

source
DCCR.get_normalized_confusion — Method
get_normalized_confusion(
    y::AbstractVector{T} where T<:Integer,
    y_hat::AbstractVector{T} where T<:Integer,
    n_classes::Integer
) -> Matrix{Float64}

Summary

Get the normalized confusion matrix.

Arguments

  • y::IntegerVector: the target values.
  • y_hat::IntegerVector: the agent's estimates.
  • n_classes::Integer: the number of total classes in the test set.

Method List / Definition Locations

get_normalized_confusion(y, y_hat, n_classes)

defined at /home/runner/work/DCCR/DCCR/src/lib/c3/functions.jl:397.

source
DCCR.get_orbit_names — Method
get_orbit_names(
    selection::Vector{String}
) -> Tuple{Vector{String}, Vector{String}}

Summary

Map the experiment orbit names to their data directories and plotting class labels.

Arguments

  • selection::Vector{String}: the selection of labels corresponding to both data directories and plotting labels.

Method List / Definition Locations

get_orbit_names(selection)

defined at /home/runner/work/DCCR/DCCR/src/lib/c3/functions.jl:339.

source
DCCR.get_tt_accuracies — Method
get_tt_accuracies(
    data::DCCR.MatrixData,
    y_hat_train::AbstractVector{T} where T<:Integer,
    y_hat::AbstractVector{T} where T<:Integer,
    n_classes::Integer
) -> Tuple{Any, Any}

Summary

Get two lists of the training and testing accuracies.

Arguments

  • data::MatrixData: the training and testing dataset, containing a vector of training and testing labels data.train.y and data.test.y.
  • y_hat_train::IntegerVector: the training estimates.
  • y_hat::IntegerVector: the agent's estimates.
  • n_classes::Integer: the number of total classes in the test set.

Method List / Definition Locations

get_tt_accuracies(data, y_hat_train, y_hat, n_classes)

defined at /home/runner/work/DCCR/DCCR/src/lib/c3/functions.jl:432.

source
DCCR.handle_display — Method
handle_display(
    p::Plots.Plot,
    pargs::Dict{String, Any}
) -> Any

Summary

Handles the display of plots according to arguments parsed by the script.

Arguments

  • p::Plots.Plot: the plot handle to display if necessary.
  • pargs::ParsedArgs: the parsed arguments provided by the script.

Method List / Definition Locations

handle_display(p, pargs)

defined at /home/runner/work/DCCR/DCCR/src/lib/c3/utils.jl:217.

source
DCCR.initialize_exp_queue! — Method
initialize_exp_queue!(
    eqc::DCCR.ExperienceQueueContainer,
    scenario_dict::AbstractDict
)

Summary

Initializes an ExperienceQueueContainer from the provided scenario dictionary.

Arguments

  • eqc::ExperienceQueueContainer: the container with the queue and stats to initialize.
  • scenario_dict::AbstractDict: the dictionary with the scenario regimes and block types.

Method List / Definition Locations

initialize_exp_queue!(eqc, scenario_dict)

defined at /home/runner/work/DCCR/DCCR/src/lib/l2/scenario.jl:56.

source
DCCR.json_save — Method
json_save(filepath::AbstractString, dict::AbstractDict)

Summary

Saves the dictionary to a JSON file.

Arguments

  • filepath::AbstractString: the full file name (with path) to save to.
  • dict::AbstractDict: the dictionary to save to the file.

Method List / Definition Locations

json_save(filepath, dict)

defined at /home/runner/work/DCCR/DCCR/src/lib/l2/common.jl:80.

source
DCCR.load_default_orbit_data — Method
load_default_orbit_data(
    data_dir::AbstractString;
    scaling
) -> Tuple{DCCR.DataSplit, DCCR.DataSplitIndexed, Vector{String}, Vector{String}, Int64}

Summary

Loads the default orbit data configuration.

Arguments

  • data_dir::AbstractString: the relative/absolute directory containing the data.
  • scaling::Float: the sigmoid scaling parameter, default scaling=2.0

Method List / Definition Locations

load_default_orbit_data(data_dir; scaling)

defined at /home/runner/work/DCCR/DCCR/src/lib/c3/functions.jl:1539.

source
DCCR.load_orbits — Method
load_orbits(
    data_dir::AbstractString,
    data_dirs::Vector{String},
    scaling::Real
) -> DCCR.DataSplit

Summary

Load the orbits data and preprocess the features.

Arguments

  • data_dir::AbstractString: the top-level data directory.
  • data_dirs::Vector{String}: the subfolders to load.
  • scaling::Real: the sigmoidal scaling parameter to use.

Method List / Definition Locations

load_orbits(data_dir, data_dirs, scaling)

defined at /home/runner/work/DCCR/DCCR/src/lib/c3/functions.jl:137.

source
DCCR.load_sim_opts — Function
load_sim_opts() -> Any
load_sim_opts(file::AbstractString) -> Any

Summary

Loads and returns the simulation options from the provided YAML file.

Arguments

  • file::AbstractString="default.yml": options the file to load from the options directory.

Method List / Definition Locations

load_sim_opts()
load_sim_opts(file)

defined at /home/runner/work/DCCR/DCCR/src/lib/c3/utils.jl:187.

source
DCCR.load_sim_results — Method
load_sim_results(data_file::AbstractString, args...) -> Any

Summary

Wrapper for loading simulation results with arbitrarily many fields.

Arguments

  • data_file::AbstractString: the location of the datafile for loading.
  • args...: the string names of the files to open.

Method List / Definition Locations

load_sim_results(data_file, args)

defined at /home/runner/work/DCCR/DCCR/src/lib/c3/utils.jl:229.

source
DCCR.log_data — Method
log_data(
    data_logger::PyCall.PyObject,
    experience::DCCR.Experience,
    results::Dict,
    params::Dict;
    status
) -> Any

Summary

Logs data from an L2 Experience.

Arguments

  • data_logger::PyObject: the l2logger DataLogger.
  • exp::Experience: the Experience that the Agent just processed.
  • results::Dict: the results from the Agent's Experience.
  • status::AbstractString: string expressing if the Experience was processed.

Method List / Definition Locations

log_data(data_logger, experience, results, params; status)

defined at /home/runner/work/DCCR/DCCR/src/lib/l2/agents.jl:187.

source
DCCR.pack_data — Method
pack_data(experiment_name::AbstractString) -> String

Summary

Packs the data under the provided experiment name folder into an LFS-tracked tarball.

Arguments

  • experiment_name::AbstractString: the name of the file destination to pack from the unpacked_dir to the packed_dir.

Method List / Definition Locations

pack_data(experiment_name)

defined at /home/runner/work/DCCR/DCCR/src/lib/c3/functions.jl:1501.

source
DCCR.permuted — Method
permuted(
    d::Dict,
    data_indexed::DCCR.DataSplitIndexed,
    opts::AdaptiveResonance.opts_DDVFA
) -> Dict

Summary

Runs a single Monte Carlo simulation of training/testing on shuffled samples.

Arguments

  • d::Dict: a logging dictionary storing simulation parameters.
  • data::DataSplitIndexed: an indexed train/test split of features and labels.
  • opts::opts_DDVFA: the options for DDVFA construction.

Method List / Definition Locations

permuted(d, data_indexed, opts)

defined at /home/runner/work/DCCR/DCCR/src/lib/c3/functions.jl:1317.

source
DCCR.run_scenario — Method
run_scenario(
    agent::DCCR.Agent,
    data::DCCR.VectoredData,
    data_logger::PyCall.PyObject
)

Summary

Runs an agent's scenario.

Arguments

  • agent::Agent: a struct that contains an Agent and scenario.
  • data_logger::PyObject: a l2logger object.

Method List / Definition Locations

run_scenario(agent, data, data_logger)

defined at /home/runner/work/DCCR/DCCR/src/lib/l2/agents.jl:211.

source
DCCR.safe_unpack — Method
safe_unpack(
    experiment_name::AbstractString
) -> Union{Nothing, String}

Summary

If the provided experiment unpacked directory does not exist, this unpacks it.

Arguments

  • experiment_name::AbstractString: the name of the file to unpack from the packed_dir to the unpacked_dir.

Method List / Definition Locations

safe_unpack(experiment_name)

defined at /home/runner/work/DCCR/DCCR/src/lib/c3/functions.jl:1525.

source
DCCR.sanitize_in_list — Method
sanitize_in_list(
    selection_type::AbstractString,
    selection,
    acceptable::Array{T, 1}
)

Summary

Sanitizes a selection within a list of acceptable options.

Arguments

  • selection_type::AbstractString: a string describing the option in case it is misused.
  • selection::Any: a single selection from a list.

Method List / Definition Locations

sanitize_in_list(selection_type, selection, acceptable)

defined at /home/runner/work/DCCR/DCCR/src/lib/l2/common.jl:42.

source
DCCR.save_dccr — Method
save_dccr(
    type::AbstractString,
    object,
    exp_name::AbstractString,
    save_name::AbstractString;
    to_paper
) -> Any

Summary

Saving function for results in the DCCR project.

This function dispatches to the correct private wrapper saving function via the type option, and the to_paper flag determines if the result is also saved to a secondary location, which is mainly used for also saving the result to the cloud location for the journal paper.

Arguments

  • type::AbstractString: the type of object being saved (see SAVE_MAP).
  • object: the object to save as type, whether a figure, table, or something else.
  • exp_name::AbstractString: the name of the experiment, used for the final saving directories.
  • save_name::AbstractString: the name of the save file itself.
  • to_paper::Bool=false: optional, flag for saving to the paper results directory (default false).

Method List / Definition Locations

save_dccr(type, object, exp_name, save_name; to_paper)

defined at /home/runner/work/DCCR/DCCR/src/lib/c3/utils.jl:77.

source
DCCR.shuffled_mc — Method
shuffled_mc(
    d::Dict,
    data::DCCR.DataSplit,
    opts::AdaptiveResonance.opts_DDVFA
)

Summary

Runs a single Monte Carlo simulation of training/testing on shuffled samples.

Arguments

  • d::Dict: a logging dictionary storing simulation parameters.
  • data::DataSplit: a train/test split of features and labels.
  • opts::opts_DDVFA: the options for DDVFA construction.

Method List / Definition Locations

shuffled_mc(d, data, opts)

defined at /home/runner/work/DCCR/DCCR/src/lib/c3/functions.jl:1252.

source
DCCR.unpack_data — Method
unpack_data(experiment_name::AbstractString) -> String

Summary

Unpacks data at the provided experiment name tarball into a working directory.

Arguments

  • experiment_name::AbstractString: the name of the file to unpack from the packed_dir to the unpacked_dir.

Method List / Definition Locations

unpack_data(experiment_name)

defined at /home/runner/work/DCCR/DCCR/src/lib/c3/functions.jl:1513.

source
DCCR.unsupervised_mc — Method
unsupervised_mc(
    d::Dict,
    data::DCCR.DataSplitCombined,
    opts::AdaptiveResonance.opts_DDVFA
) -> Dict

Summary

Runs a single Monte Carlo simulation of supervised training and unsupervised training/testing.

Arguments

  • d::Dict: a logging dictionary storing simulation parameters.
  • data::DataSplitCombined: a train/test split of features and labels.
  • opts::opts_DDVFA: the options for DDVFA construction.

Method List / Definition Locations

unsupervised_mc(d, data, opts)

defined at /home/runner/work/DCCR/DCCR/src/lib/c3/functions.jl:1381.

source