This is the MIWrapper classifier, as implemented in Weka:

Send your input to the algorithm as a simple Json object, with the following options:

mode: One of train/update/load. Use "train" to train a new classifier, use "update" if you have new instances to train an existing updateable classifier, use "load" to load an existing classifier for classifying test data
trainUrl: The path to the training data that you uploaded to our Data API
testUrl: The path to the test data that you would like to get the labels using this classifier (optional if you would like to use the cross-validation option)
modelUrl: The path that you would like to either save the model that is trained or if you would like to load an already trained and saved model
cv: The number of cross-validation folds that you would like to use
options: A string that contains any options that you would like to specifically set for this classifier (format: param name followed by desired value separated by space: e.g. "-C 5 -t 2"). For options specific to this classifier, please see Wekadocs linked above
classIndex: Specify the index of the class values in the test set (caution: When using a test set, assumes that the class values are at the last index if the classIndex parameter is not specified, so please arrange accordingly)

Writing good docs:

Communicate Value

A good introduction should make it clear why someone might use your API.

Show and Tell

Give examples of using your API and explain those examples.

Easy to Skim

Ensure your docs are structured such that familiar users can quickly jump to the content they want.


Revisit your docs after making breaking changes or adding new features to keep them up-to-date.