AutoDoc¶

This page describes the AutoDoc API, which lets you access AutoDoc reports in the Driverless AI.

First, initialize a client with your server credentials and store them in the variable dai.

In [1]:

import driverlessai

dai = driverlessai.Client(address='http://localhost:12345', username='py', password='py')

import driverlessai dai = driverlessai.Client(address='http://localhost:12345', username='py', password='py')

Next, get the experiment that you are interested in.

In [2]:

experiments = dai.experiments.list()
ex = experiments[0]

experiments = dai.experiments.list() ex = experiments[0]

Interact with AutoDoc associated to an Experiment¶

Then get the AutoDoc associated with the experiment.

In [3]:

autodoc = ex.autodoc()

autodoc = ex.autodoc()

Complete 100.00% - Rendering section Appendix.NLP Appendix (48/52)

Download the AutoDoc.

In [4]:

autodoc.download()

autodoc.download()

Out[4]:

'report.docx'

Create a new AutoDoc for an experiment¶

You can create new AutoDoc reports with different configurations for existing experiments. For a comprehensive list of AutoDoc configuration overrides, please refer Driverless AI AutoDoc settings page.

In [5]:

autodoc = dai.autodocs.create(
    experiment=ex,
    autodoc_report_name="report_with_config_override",
)

autodoc = dai.autodocs.create( experiment=ex, autodoc_report_name="report_with_config_override", )

Complete 100.00% - Rendering section Appendix.NLP Appendix (48/52)                   

In [6]:

autodoc.download()

autodoc.download()

Out[6]:

'report_with_config_override.docx'