We are celebrating the 10-year anniversary of the Alteryx Community! Learn more and join in on the fun here.
Start Free Trial

Alteryx Machine Learning Discussions

Find answers, ask questions, and share expertise about Alteryx Machine Learning.
Getting Started

Start your learning journey with Alteryx Machine Learning Interactive Lessons

Go to Lessons

ayx_ml_toolkit - Where is the documentation?

tochoa
5 - Atom

I'm using the Assisted Modeling tool (in Version: 2023.2.1.226 Patch: 6), exporting to Python, and trying to delve into the code created by Alteryx.  I haven't been able to find documentation for code such as this, to learn about "make_pipeline_from_components" and "PipelineEntity".  Where can I find documentation for those, and ayx_ml_toolkit in general?

target_metadata = ColumnMetadataEntity(
col_name=target_variable,
col_type=training_metadata[target_variable]["type"]
)


pipeline = make_pipeline_from_components([
feature_typing,
missing_values,
feature_selection,
one_hot_encoding,
classifier
], problem_type="BINARY")

pipeline_entity = PipelineEntity(
training_data=training_data_df,
target=target_metadata,
pipeline=pipeline
)

1 REPLY 1
KGT
13 - Pulsar

So, this was mostly exposed a few years ago, but didn't get that much traction AFAIK, so not sure the status now, and how much it's updated. Those methods/functions (make_pipeline_from_Components etc) are most likely common across a bunch of Alteryx python packages.

 

Here is the EvalML link for instance: https://evalml.alteryx.com/en/stable/api_index.html#pipelines

 

You may need to investigate a fair bit through GitHub in order to find what you are after. I'm not sure exactly where the alteryx_ml_toolkit package doco is unfortunately.

 

Here is the Alteryx Open Source repo, but I thought there was an AYX one as well...