FAQ

General ML configuration related questions

Where can I find the ML configuration file?

The <ML_HOME>/repository/conf/machine-learner.xml file includes all the ML-specific configurations.

How can I change the ML datasource name?

The default name is jdbc/WSO2ML_DB. You can change it by changing the value of the <DataSourceName> element in the <ML_HOME>/repository/conf/machine-learner.xml file. For more information, see ML-specific configurations.

How can I change the sample points size that ML use to generate summary statistics?

Default size is 10000. You can change it by changing the value of the <SampleSize> property within the <SummaryStatisticsSettings> element in the <ML_HOME>/repository/conf/machine-learner.xml file. For more information, see ML-specific configurations.

How can I change the directory which holds datasets?

By default, the <ML_HOME>/datasets/ directory holds datasets, and the default storage type is ‘file’. You can change it by changing the value of the <StorageDirectory> property within the <DatasetStorage> element in the <ML_HOME>/repository/conf/machine-learner.xml file. For more information, see ML-specific configurations.

How can I change the directory with models?

By default, the <ML_HOME>/models/ directory holds models, and default storage type is ‘file’. You can change it by changing the value of the <StorageDirectory> property within the <ModelStorage> element in the <ML_HOME>/repository/conf/machine-learner.xml file. For more information, see ML-specific configurations.

How can I increase ML thread pool size?

WSO2 ML uses threads in a thread pool to run different tasks such as dataset summary generation and model generation etc. You can control the size of this thread pool by changing the value of the following property in the <ML_HOME>/repository/conf/machine-learner.xml file: <Property name="ml.thread.pool.size" value="100"/> For more information, see ML-specific configurations.

Where should I configure the email addresses of recipients whom will be notified upon a model generation?

You can configure WSO2 ML to send emails on the completion of a model generation. You can have a comma-separated set of email addresses as the value of the <EmailNotificationEndpoint> property in the <ML_HOME>/repository/conf/machine-learner.xml file. For more information on configuring email support, see Enabling Email Notifications.

How can I change datasets storage to HDFS?

If you want to change the dataset storage type to HDFS, change the value of the <StorageType> property within the <DatasetStorage> element to ‘hdfs’. For more information, see ML-specific configurations.

How can I change model storage to HDFS?

If you want to change the model storage type to HDFS, change the value of the <StorageType> property within the <ModelStorage> element to ‘hdfs’. For more information, see ML-specific configurations.

How can I give a HDFS URL?

If you want to store your datasets and models in an HDFS, you need to enter HDFS URL as the value of the <HdfsURL> property in the <ML_HOME>/repository/conf/machine-learner.xml file. For more information, see ML-specific configurations.

Data related questions

What should be the format of my dataset?

WSO2 ML currently supports the following formats.

CSV with comma separated values
TSV with tab separated values

Where can I have my data?

Data can be retrieved from the following sources.

File system
Hadoop distributed file system
WSO2 Data Analytics Server table

Do I need to have a header row in my dataset?

It is not mandatory to have a header row. If the dataset does not have a header row, it will be indicated when you upload the dataset. Then WSO2 ML will generate a header similar to V1, V2 .. Vn. See Creating a Dataset for more information.

Is there a file size limit to my dataset?

Yes, currently it is 100MB. You can change it via the following property in <ML_HOME>/bin/wso2server.bat file (for Windows) or <ML_HOME>/bin/wso2server.sh file (for Linux).

100MB = 100 x 1024 x 1024 = 104857600 Bytes

-Dorg.apache.cxf.io.CachedOutputStream.Threshold=104857600 \

Algorithm related questions

Does ML support numerical prediction?

Yes it does. The following algorithms are available in this version.

Linear Regression
Ridge Regression
Lasso Regression

See How to Select an Algorithm in WSO2 ML for more information

Does ML support classification algorithms?

Yes it does. The classification algorithms currently supported are as follows.

Logistic Regression with Stochastic Gradient Descent
Logistic Regression with Limited memory Broyden-Fletcher-Goldfarb-Shanno
Decision tree
Random forest
Naive bayes

See How to Select an Algorithm in WSO2 ML for more information

Does ML support clustering algorithms?

At present, very primitive support is available for clustering. K-means is the only clustering algorithm supported for this ML version. We have plans to improve on this area. Please contact us if you are someone who is interested to learn more about these plans.

Analysis related questions

What type of data preprocessing does WSO2 ML support?

It supports feature selection and missing value filling/filtering.

Can I get an insight about the dataset before creating an analysis out of it?

Yes, WSO2 ML supports dataset exploration functionality with multiple visualization techniques. See Exploring Data for more information.

Model related questions

How can I find the details of a built model?

How can I calculate the accuracy for a given model?

Can I download a built model?

Does you support exporting models in PMML format?

Can I use a built model in a Java program?

How can I make predictions for a test dataset using ML UI wizard?

Once you build a model, you can make predictions to a test dataset by uploading a csv/tsv file from the Predict page in the ML UI. See Making Predictions for more information.

Can I use a built model in other WSO2 products?

Yes, you can use the generated models in WSO2 ESB with the Predict mediator and in WSO2 CEP with CEP ML Extension.