---
name: "heri-eval"
section: "1"
platform: "linux"
package: "herisvm"
version: "0.9.0-2"
release: "Debian 13 (Trixie)"
platforms: ["linux"]
url: "https://new.carta.tech/heri-eval"
---

# heri-eval(1)

evaluate classification algorithm

## NAME

heri-eval - evaluate classification algorithm

## SYNOPSIS

**heri-eval** \[OPTIONS\] *dataset* \[-- SVM\_TRAIN\_OPTIONS\]

## DESCRIPTION

**heri-eval** runs training algorithm on *dataset* and then evaluate it using testing set, specified by option *-e*. If option *-n* was applied, cross-validation is used for evaluation, training and testing on different folds are run in parallel, thus utilizing available CPUs. If *-r* is used, the dataset is splitted into training and testing datasets randomly with the specified ratio, and then holdout is run.

## OPTIONS

- **-h, --help**

  Display help information.

- **-f**

  Enable output of per-fold statistics. See **-M***f*.

- **-n** *N*

  Enable T\**N*-fold cross-validation mode and set the number of folds to *N*.

- **-r** *ratio*

  Split the dataset into training and testing parts with the specified ratio of their sizes (in percents).

- **-t** *T*

  Enable *T*\*N-fold cross-validation mode and set the number of runs to *T* which 1 by default.

- **-e** *testing\_dataset*

  Enable hold-out mode and set the testing dataset.

- **-T** *threshold*

  Set the minimum threshold for making a classification decision. If this flag is applied, micro-average precision, recall, and F1 are calculated instead of accuracy.

- **-o** *filename*

  Save predictions from testing sets to the specified file.

  Format: outcome\_class prediction\_class \[score\]

- **-O** *filename*

  Save incorrectly classified objects to the specified file.

  Format: #object\_number: outcome\_class prediction\_class \[score\])

- **-m** *filename*

  Save confusion matrix to the specified file.

  Format: frequency : outcome\_class prediction\_class

- **-p** *opts*

  Pass the specified *opts* to **[heri-stat(1)](/heri-stat/1.md)**.

- **-s** *opts*

  Pass the specified *opts* to **[heri-split(1)](/heri-split/1.md)**.

- **-M** *chars*

  Sets the output mode where chars are: t -- output total statistics, f -- output per-fold statistics, c -- output cross-fold statistics. The default is "-M tc".

- **-S** *seed*

  Pass the specified *seed* to **[heri-split(1)](/heri-split/1.md)**.

- **-K**

  Keep temporary directory after exiting.

- **-D**

  Turn on the debugging mode, implies -K.

## EXAMPLES

```
 heri-eval -e testing_set.libsvm training_set.libsvm -- -s 0 -t 0
 export SVM_TRAIN_CMD='liblinear-train'
 export SVM_PREDICT_CMD='liblinear-predict'
 heri-eval -p '-mr' -n 5 training_set.libsvm -- -s 4 -q
 heri-eval -p '-mr' -n 5 training_set.libsvm -- -s 4 -q
 export SVM_TRAIN_CMD='scikit_rf-train --estimators=400'
 export SVM_PREDICT_CMD='scikit_rf-predict'
 heri-eval -p '-c' -Mt -t 50 -r 70 dataset.libsvm
```

## ENVIRONMENT

- *SVM\_TRAIN\_CMD*

  Training utility, e.g., liblinear-train (the default is svm-train).

- *SVM\_PREDICT\_CMD*

  Predicting utility, e.g., liblinear-predict (the default is svm-predict).

- *SVM\_HERI\_STAT\_CMD*

  Utility for calculating statistics (the default is **[heri-stat(1)](/heri-stat/1.md)**).

- *SVM\_HERI\_STAT\_ADDONS\_CMD*

  Utility for calculating additional statistics (the default is **[heri-stat-addons(1)](/heri-stat-addons/1.md)**).

- *SVM\_HERI\_SPLIT\_CMD*

  Utility for splitting the dataset (the default is **[heri-split(1)](/heri-split/1.md)**).

- *TMPDIR*

  Temporary directory (the default is /tmp).

## HOME

\<http://github.com/cheusov/herisvm\>

## SEE ALSO

[**heri-split**(1)](/heri-split/1.md) [**heri-stat**(1)](/heri-stat/1.md)