Module transerror

source code

Utility class to compute the transfer error of classifiers.

Classes

[hide private]

SummaryStatistics
Basic class to collect targets/predictions and report summary statistics

ROCCurve
Generic class for ROC curve computation and plotting

ConfusionMatrix
Class to contain information and display confusion matrix.

RegressionStatistics
Class to contain information and display on regression results.

ClassifierError
Compute (or return) some error of a (trained) classifier on a dataset.

TransferError
Compute the transfer error of a (trained) classifier on a dataset.

ConfusionBasedError
For a given classifier report an error based on internally computed error measure (given by some ConfusionMatrix stored in some state variable of Classifier).

Functions

[hide private]

_p2(x, prec=2)
Helper to print depending on the type nicely. For some reason %.2g for 100 prints exponential form which is ugly

source code

Imports: copy, N, StringIO, log10, ceil, externals, meanPowerFx, rootMeanPowerFx, RMSErrorFx, CorrErrorFx, CorrErrorPFx, RelativeRMSErrorFx, MeanMismatchErrorFx, AUCErrorFx, warning, StateVariable, ClassWithCollections, enhancedDocString, table2string, autoNullDist, debug, nanmean

Home

Trees

Indices

Help