Retrain Final Pipeline¶

First, we'll initialize a client with our server credentials and store it 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')

We'll then load the new data we want to use to retrain the model.

In [14]:

ds = dai.datasets.create('iris_new.csv', name='new_iris')

ds = dai.datasets.create('iris_new.csv', name='new_iris')

Complete 100% - [4/4] Computing column statistics

Then, we get the most recent version of an experiment with 'iris' in the name.

In [15]:

ex = [ex for ex in dai.experiments.list() if 'iris' in ex.name][0]

ex = [ex for ex in dai.experiments.list() if 'iris' in ex.name][0]

Finally, we'll use the experiment's retrain() method with final_pipeline_only=True to retrain the model.

In [16]:

ex.retrain(train_dataset=ds, final_pipeline_only=True)

ex.retrain(train_dataset=ds, final_pipeline_only=True)

Experiment launched at: http://localhost:12345/#experiment?key=a3e052ca-6003-11ea-919d-0242ac110002
Complete 100% - Status: Complete                                            

Out[16]:

<class 'driverlessai.experiments.Model'> a3e052ca-6003-11ea-919d-0242ac110002