Create examples for the Multinomial Models section in the Python documentation

[exalate-issue-sync]

The http://docs.h2o.ai/h2o/latest-stable/h2o-py/docs/model_categories.html#module-h2o.model.multinomial section in the Python documentation is missing examples.

The source file is located at h2o-3/h2o-py/model/multinomial.py

Multinomial examples are available in this https://github.com/h2oai/h2o-3/blob/master/h2o-py/tests/testdir_misc/pyunit_metric_accessors.py#L414

Note that the following in the test is incorrect (line 423):

{code}
gbm.distribution="multinomial"
{code}

Replace that line with the following to build the model:

{code}
gbm = H2OGradientBoostingEstimator(nfolds=3, distribution=distribution)
{code}

The examples use the cars dataset:
cars = h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/junit/cars_20mpg.csv")

[exalate-issue-sync]

Angela Bartz commented: You can use the following example for the confusion matrix. This is a little different than the binomial example:

{code}
import h2o
h2o.init()
from h2o.estimators.gbm import H2OGradientBoostingEstimator

cars = h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/junit/cars_20mpg.csv")
cars["cylinders"] = cars["cylinders"].asfactor()
r = cars[0].runif()
train = cars[r > .2]
valid = cars[r <= .2]
response_col = "cylinders"
distribution = "multinomial"
predictors = ["displacement","power","weight","acceleration","year"]

gbm = H2OGradientBoostingEstimator(nfolds=3, distribution=distribution)
gbm.train(x=predictors,y=response_col, training_frame=train, validation_frame=valid)
confusion_matrix = gbm.confusion_matrix(train)
{code}

[h2o-ops]

JIRA Issue Migration Info

Jira Issue: PUBDEV-6728
Assignee: hannah.tillman
Reporter: Angela Bartz
State: Resolved
Fix Version: 3.28.0.1
Attachments: N/A
Development PRs: Available

Linked PRs from JIRA

#3762