Importing MOJO Pipelines from Driverless AI

MOJO scoring pipeline artifacts, created in Driverless AI, can be used in Spark to carry out predictions in parallel using the Sparkling Water API. This section shows how to load and run predictions on the MOJO scoring pipeline in Sparkling Water.

Note: Sparkling Water is backward compatible with MOJO versions produced by different Driverless AI versions.

One advantage of scoring the MOJO artifacts is that H2OContext does not have to be created if we only want to run predictions on MOJOs using Spark. It is also important to mention that the format of prediction on MOJOs from Driverless AI differs from predictions on H2O-3 MOJOs. The format of Driverless AI prediction is explained bellow.

Requirements

To use the MOJO scoring pipeline, a Driverless AI license has to be passed to Spark. This can be achieved via --jars argument of the Spark launcher scripts.

Note: In Local Spark mode, please use --driver-class-path to specify the path to the license file.

We also need Sparkling Water distribution which can be obtained from H2O Download page. After we downloaded the Sparkling Water distribution, extract it, and go to the extracted directory.

The MOJO scoring pipeline is included in the mojo.zip archive downloaded from Driverless AI. The archive also contains a mojo runtime library, examples and other files. The only file which is important for scoring with Sparkling Water is pipeline.mojo. Thus before running Sparkling Water, extract the mojo.zip archive and copy pipeline.mojo to a location of your choice.

unzip /path/to/mojo.zip -d /tmp/mojo.zip.extracted
cp /tmp/mojo.zip.extracted/mojo-pipeline/pipeline.mojo /path/to/pipeline.mojo

Starting a Scoring Environment

First, we need to start a scoring environment for the desired language with a Driverless AI license. There are two variants. We can use Sparkling Water prepared scripts which put required dependencies on the Spark classpath or we can use Spark directly and add the dependencies manually.

Scala

./bin/spark-shell --jars license.sig,jars/sparkling-water-assembly-scoring_2.11-3.40.0.3-1-2.3-all.jar
./bin/sparkling-shell --jars license.sig

Python

export PYTHONPATH="py/h2o_pysparkling_scoring_2.3-3.40.0.3-1-2.3.zip:$PYTHONPATH" # This line is needed only if the Spark distribution contains the bug SPARK-21945.
./bin/pyspark --jars license.sig --py-files py/h2o_pysparkling_scoring_2.3-3.40.0.3-1-2.3.zip
./bin/pysparkling --jars license.sig

At this point, we have a Spark interactive terminal where we can carry out predictions. If we don’t require an interactive environment, we can deploy our scoring logic with ./bin/spark-submit. The parameters will be the same as in the example above.

Loading and Usage of Driverless AI MOJO Model

The Pipeline MOJO model could be loaded as:

Scala

import ai.h2o.sparkling.ml.models._
val settings = H2OMOJOSettings(predictionCol = "fruit_type")
val mojo = H2OMOJOPipelineModel.createFromMojo("file:///path/to/pipeline.mojo", settings)

Python

from pysparkling.ml import *
settings = H2OMOJOSettings(predictionCol = "fruit_type")
mojo = H2OMOJOPipelineModel.createFromMojo("file:///path/to/pipeline.mojo", settings)

In the examples above settings is an optional argument. If it’s not specified, the default values are used.

Prepare the dataset to score on:

Scala

val dataFrame = spark.read.option("header", "true").option("inferSchema", "true").csv("file:///path/to/data.csv")

Python

dataFrame = spark.read.option("header", "true").option("inferSchema", "true").csv("file:///path/to/data.csv")

And finally, score the mojo on the loaded dataset:

Scala

val predictions = mojo.transform(dataFrame)

Python

predictions = mojo.transform(dataFrame)

We can select the predictions as:

Scala

predictions.select("prediction")

Python

predictions.select("prediction")

The output data frame contains all the original columns plus the prediction column which is by default named prediction. The prediction column contains all the prediction detail. Its name can be modified via the H2OMOJOSettings object.

Predictions Format

The predictionCol contains sub-columns with names corresponding to the columns Driverless AI identified as output columns. For example, if Driverless API MOJO pipeline contains one output column AGE ( for example regression problem), the prediction column contains another sub-column named AGE. If The MOJO pipeline contains multiple output columns, such as VALID.0 and VALID.1 (for example classification problems), the prediction column contains two sub-columns with the aforementioned names.

If this option is disabled, the predictionCol contains the array of predictions without the column names. For example, if the Driverless API MOJO pipeline contains one output column AGE ( for example regression problem), the prediction column contains an array of size 1 with the predicted value. If The MOJO pipeline contains multiple output columns, such as VALID.0 and VALID.1 (for example classification problems), the prediction column contains an array of size 2 containing predicted probabilities for each class.

By default, this option is enabled.

Overriding MOJO library

Both full distribution and the scoring package include MOJO2 Runtime Implementation (ai.h2o:mojo2-runtime-impl) so you don’t have to worry about it. We try to update it to the newest possible version when releasing Sparkling Water, however in some cases you might want to override the dependency yourself.

To do that add the MOJO2 jar to the jars list before the Sparkling Water scoring jar:

Scala

./bin/spark-shell --jars license.sig,mojo2-runtime-impl-2.7.5.jar,jars/sparkling-water-assembly-scoring_2.11-3.40.0.3-1-2.3-all.jar
./bin/sparkling-shell --jars license.sig,mojo2-runtime-impl-2.7.5.jar,jars/sparkling-water-assembly-scoring_2.11-3.40.0.3-1-2.3-all.jar

Python

export PYTHONPATH="py/h2o_pysparkling_scoring_2.3-3.40.0.3-1-2.3.zip:$PYTHONPATH" # This line is needed only if the Spark distribution contains the bug SPARK-21945.
./bin/pyspark --jars license.sig,mojo2-runtime-impl-2.7.5.jar --py-files py/h2o_pysparkling_scoring_2.3-3.40.0.3-1-2.3.zip
./bin/pysparkling --jars license.sig,mojo2-runtime-impl-2.7.5.jar

As mentioned above, in local Spark mode, please use --driver-class-path.

Customizing the MOJO Settings

We can configure the output and format of predictions via the H2OMOJOSettings. The available options are

  • predictionCol - Specifies the name of the generated prediction column. The default value is prediction.

  • withContributions - If enabled, it appends the contributions column to the input dataset. The column contains sub-columns with Shapley values for the original features from the dataset. By default, this option is disabled.

  • withInternalContributions - If enabled, it appends the internal_contributions column to the input dataset. The column contains sub-columns with Shapley values for the transformed features entering the models inside MOJO pipeline. By default, this option is disabled.

  • withPredictionInterval - If enabled, it appends additional columns with prediction intervals under the prediction column. By default, this option is disabled.

  • scoringBulkSize - A number of records passed at once to the underlying mojo2 runtime library.

Troubleshooting

If you see the following exception during loading the MOJO pipeline:

  • java.io.IOException: MOJO doesn't contain resource mojo/pipeline.pb, then it means you are adding incompatible mojo-runtime.jar on your classpath. It is not required and also not suggested to put the JAR on the classpath as Sparkling Water already bundles the correct dependencies.

  • java.io.IOException: None of 2 available pipeline factories [pbuf, toml] can read this mojo., then you most-likely passed the whole mojo.zip archive to the createFromMojo method instead of the pipeline.mojo file, which is contained in the archive.

  • A similar error to java.lang.ClassCastException: Mojo column of type Float32 can be assigned Java values only from the following types: [class java.lang.Short, class java.lang.Double, class java.lang.Byte, class java.lang.Integer, class java.lang.Float], Java class on the input was: Long, then call the method getFeatureTypes() to get a map/dictionary from feature names to expected types. Identify a feature with the expected type Float32` and ``Long` type in the dataset for scoring and manually cast the feature column from ``Long to Double or Integer.