Codeunit 2003 "ML Prediction Management"

Base Application · System.AI · BC23-30 · source at ea08af5e · facts from BC29

Events published

OnBeforeTrain(var Model: Text; var Quality: Decimal; var CallAzureEndPoint: Boolean) (integration)
- subscribers: Codeunit 1952 “LP Subscribers” SendTraceTagOnBeforeModelTrain
OnBeforePredict(var RecordVariant: Variant; var CallAzureEndPoint: Boolean) (integration)
- subscribers: Codeunit 1952 “LP Subscribers” SendTraceTagOnBeforeModelPredict
OnBeforeEvaluate(Model: Text; var Quality: Decimal; var RecordVariant: Variant; var CallAzureEndPoint: Boolean) (integration)
- subscribers: Codeunit 1952 “LP Subscribers” SendTraceTagOnBeforeModelEvaluate

Procedures

DefaultInitialize()
Initialize(Uri: Text[250]; Key: SecretText; TimeOutSeconds: Integer) Δ BC24 + BC24 − BC27
InitializeWithKeyVaultCredentials(TimeOutSeconds: Integer)
SetMessageHandler(MessageHandler: DotNet HttpMessageHandler)
SetRecord(RecordVariant: Variant)
GetRecord(var RecordVariant: Variant)
AddFeature(FeatureFieldNo: Integer)
SetLabel(LabelFieldNo: Integer)
SetConfidence(ConfidenceFieldNo: Integer)
SetTrainingPercent(TrainingPercentValue: Decimal)
GetTrainingPercent(): Decimal
Train(var Model: Text; var Quality: Decimal)
Predict(Model: Text)
Evaluate(Model: Text; var Quality: Decimal)
PlotModel(Model: Text; Features: Text; Labels: Text): Text
DownloadPlot(PdfDataBase64: Text; ModelName: Text)
IsDataSufficientForClassification(): Boolean
IsDataSufficientForRegression(): Boolean
IsDataSufficientBase(var RecRef: RecordRef): Boolean
GetParameter(Name: Text): Text
GetInput(RowNo: Integer; ColumnNo: Integer): Text
GetInputLength(): Integer
MaxNoFeatures(): Integer
GetMachineLearningCredentials(var MLApiUri: Text[250]; var MLApiKey: SecretText; var LimitType: Option; var Limit: Decimal) Δ BC24 Δ BC24 − BC27

Plus 8 local procedures.

Triggers

OnRun

Calls

From the extracted call graph of BC29 (graphify-al on the snapshot checkout): calls whose target is known from a declared type or an Object::"Name" argument. Interface dispatch and calls through events are not counted, so the list is not complete.

Codeunit 2001 “Azure ML Connector” (24 calls: CreateDummyInput → AddInputColumnName, CreateDummyInput → AddInputRow, CreateDummyInput → AddInputValue, …)
Codeunit 701 “Data Type Management” (7 calls: CreateInput → GetRecordRef, IsDataSufficientBase → GetRecordRef, LoadPrediction → GetRecordRef, …)
Codeunit 2006 “Azure AI Usage” (2 calls: InitializeWithKeyVaultCredentials → GetResourceLimit, InitializeWithKeyVaultCredentials → GetTotalProcessingTime)
Codeunit 4100 “Temp Blob” (2 calls: DownloadPlot → CreateInStream, DownloadPlot → CreateOutStream)
Codeunit 10 “Type Helper” (1 call: IsDataSufficientForClassification → CalculateLog)
Codeunit 2004 “Machine Learning KeyVaultMgmt.” (1 call: GetMachineLearningCredentials → GetMachineLearningCredentials)
Codeunit 4110 “Base64 Convert” (1 call: DownloadPlot → FromBase64)
Codeunit 8617 “Config. Validate Management” (1 call: LoadPrediction → EvaluateValueWithValidate)

Called by

Codeunit 1951 “LP Model Management” (10 calls: EvaluateModel → Evaluate, InvokeShowModelFromUi → DownloadPlot, InvokeShowModelFromUi → Initialize, …)
Codeunit 1950 “LP Prediction Mgt.” (6 calls: PredictIsLate → Initialize, PredictIsLate → InitializeWithKeyVaultCredentials, PredictIsLate → Predict, …)
Table 1951 “LP ML Input Data” (4 calls: AddParametersToMgt → AddFeature, AddParametersToMgt → SetConfidence, AddParametersToMgt → SetLabel, …)
Codeunit 2005 “Azure AI Usage Impl.” (1 call: GetSingleInstance → GetMachineLearningCredentials)

Ask your agent

Procedure bodies are not stored here (D10). The call sections above are our own, per object, from the BC29 call graph. For a procedure body or the calls of one procedure, ask bc-code-atlas (external, by Stefan Maron, MIT; default corpus w1-28), which the bc-observatory plugin connects: bcatlas_resolve_node(object_type: "codeunit", object_name: "ML Prediction Management"), then bcatlas_get_procedure_body or bcatlas_get_neighbors on the returned id.