Introduction¶

After we have created a model we will typically want to save it as a binary file so it can be deployed for prediction.

Seldon core is a model deployment engine. Here is an excerpt from the seldon documentation for Scikit-learn deployments

Seldon expects that your model has been saved using joblib, and it named as model.joblib. Note that this is the recommended approach to serialise models by the SKLearn project.

Source: https://docs.seldon.io/projects/seldon-core/en/latest/servers/sklearn.html

Saving a model¶

Here we use the joblib Python library to save a model:

In [8]:

# set the random state to make the examples repeatable
import numpy as np
np.random.seed(1)

from sklearn.datasets import load_iris
from sklearn.svm import LinearSVC

iris = load_iris()
X, y = iris.data, iris.target

classifier = LinearSVC()
model = classifier.fit(X, y)

from joblib import dump, load
dump(model, 'iris_model.joblib') 

/opt/conda/lib/python3.9/site-packages/sklearn/svm/_base.py:1206: ConvergenceWarning: Liblinear failed to converge, increase the number of iterations.
  warnings.warn(

Out[8]:

['iris_model.joblib']

We can execute a shell command with !. Let's inspect the saved file:

In [9]:

! ls -l iris_model.joblib

-rw-r--r-- 1 jovyan users 858 Feb 11 15:23 iris_model.joblib

Summary¶

More information on model persistence can be found in the Scikit-learn docs

Previous | Home | Next notebook

In [ ]:

Introduction¶

Saving a model¶

Summary¶

Navigation¶