ibm-watson-machine-learning¶This notebook contains steps and code to demonstrate how to persist and deploy locally trained scikit-learn model in Watson Machine Learning Service. This notebook contains steps and code to work with ibm-watson-machine-learning library available in PyPI repository. This notebook introduces commands for getting model and training data, persisting model, deploying model, scoring it, updating the model and redeploying it.
-Some familiarity with Python is helpful. This notebook uses Python 3.6 with the ibm-watson-machine-learning package.
+Some familiarity with Python is helpful. This notebook uses Python 3.8 with the ibm-watson-machine-learning package.
The learning goals of this notebook are:
Before you use the sample code in this notebook, you must perform the following setup tasks:
Authenticate the Watson Machine Learning service on IBM Cloud. You need to provide platform api_key and instance location.
You can use IBM Cloud CLI to retrieve platform API Key and instance location.
API Key can be generated in the following way:
@@ -14312,84 +14115,86 @@Tip: Your Cloud API key can be generated by going to the Users section of the Cloud console. From that page, click your name, scroll down to the API Keys section, and click Create an IBM Cloud API key. Give your key a name and click Create, then copy the created key and paste it below. You can also get a service specific url by going to the Endpoint URLs section of the Watson Machine Learning docs. You can check your instance location in your Watson Machine Learning (WML) Service instance details.
You can also get service specific apikey by going to the Service IDs section of the Cloud Console. From that page, click Create, then copy the created key and paste it below.
Action: Enter your api_key and location in the following cell.
api_key = 'PASTE YOUR PLATFORM API KEY HERE'
location = 'PASTE YOUR INSTANCE LOCATION HERE'
wml_credentials = {
"apikey": api_key,
"url": 'https://' + location + '.ml.cloud.ibm.com'
}
!pip install -U ibm-watson-machine-learning
from ibm_watson_machine_learning import APIClient
client = APIClient(wml_credentials)
First, you need to create a space that will be used for your work. If you do not have space already created, you can use Deployment Spaces Dashboard to create one.
Action: Assign space ID below
-space_id = 'PASTE YOUR SPACE ID HERE'
-You can use list method to print all existing spaces.
client.spaces.list(limit=10)
To be able to interact with all resources available in Watson Machine Learning, you need to set space which you will be using.
client.set.default_space(space_id)
+
+
+In [ ]:
+
+
+space_id = 'PASTE YOUR SPACE ID HERE'
-
-
+
'SUCCESS'
To be able to interact with all resources available in Watson Machine Learning, you need to set the space which you will be using.
client.set.default_space(space_id)
+As a first step, you will load the data from scikit-learn sample datasets and perform a basic exploration.
import sklearn
from sklearn import datasets
digits = datasets.load_digits()
Loaded toy dataset consists of 8x8 pixels images of hand-written digits.
Let's display first digit data and label using data and target.
-print(digits.data[0].reshape((8, 8)))
-print(digits.data[0])
+[[ 0. 0. 5. 13. 9. 1. 0. 0.] - [ 0. 0. 13. 15. 10. 15. 5. 0.] - [ 0. 3. 15. 2. 0. 11. 8. 0.] - [ 0. 4. 12. 0. 0. 8. 8. 0.] - [ 0. 5. 8. 0. 0. 9. 8. 0.] - [ 0. 4. 11. 0. 1. 12. 7. 0.] - [ 0. 2. 14. 5. 10. 12. 0. 0.] - [ 0. 0. 6. 13. 10. 0. 0. 0.]] --
digits.target[0]
+
+
+In [ ]:
+
+
+print(digits.data[0].reshape((8, 8)))
-
+
-0
digits.target[0]
+In the next step, you will count data examples.
In next step, you will count data examples.
-samples_count = len(digits.images)
print("Number of samples: " + str(samples_count))
Number of samples: 1797 --
Prepare data
train_data = digits.data[: int(0.7*samples_count)]
train_labels = digits.target[: int(0.7*samples_count)]
@@ -14683,275 +14420,250 @@ 2.2. Create a scikit-learn modelprint("Number of scoring records : " + str(len(score_data)))
Number of training records: 1257 -Number of testing records : 360 -Number of scoring records : 180 -+
Create pipeline
Next, you'll create scikit-learn pipeline.
In ths step, you will import scikit-learn machine learning packages that will be needed in next cells.
from sklearn.pipeline import Pipeline
from sklearn import preprocessing
from sklearn import svm, metrics
Standardize features by removing the mean and scaling to unit variance.
scaler = preprocessing.StandardScaler()
Next, define estimators you want to use for classification. Support Vector Machines (SVM) with radial basis function as kernel is used in the following example.
clf = svm.SVC(kernel='rbf')
Let's build the pipeline now. This pipeline consists of transformer and an estimator.
pipeline = Pipeline([('scaler', scaler), ('svc', clf)])
Train model
Now, you can train your SVM model by using the previously defined pipeline and train data.
model = pipeline.fit(train_data, train_labels)
Evaluate model
You can check your model quality now. To evaluate the model, use test data.
predicted = model.predict(test_data)
print("Evaluation report: \n\n%s" % metrics.classification_report(test_labels, predicted))
Evaluation report: - - precision recall f1-score support - - 0 1.00 0.97 0.99 37 - 1 0.97 0.97 0.97 34 - 2 1.00 0.97 0.99 36 - 3 1.00 0.94 0.97 35 - 4 0.78 0.97 0.87 37 - 5 0.97 0.97 0.97 38 - 6 0.97 0.86 0.91 36 - 7 0.92 0.97 0.94 35 - 8 0.91 0.89 0.90 35 - 9 0.97 0.92 0.94 37 - - accuracy 0.94 360 - macro avg 0.95 0.94 0.95 360 -weighted avg 0.95 0.94 0.95 360 - --
You can tune your model now to achieve better accuracy. For simplicity of this example tuning section is omitted.
In this section, you will learn how to store your model in Watson Machine Learning repository by using the IBM Watson Machine Learning SDK.
Define model name, autor name and email.
sofware_spec_uid = client.software_specifications.get_id_by_name("default_py3.7")
+sofware_spec_uid = client.software_specifications.get_id_by_name("default_py3.8")
print(sofware_spec_uid)
+metadata = {
client.repository.ModelMetaNames.NAME: 'Scikit model',
client.repository.ModelMetaNames.TYPE: 'scikit-learn_0.23',
@@ -14965,22 +14677,23 @@ Publish m
training_target=train_labels)
import json
published_model_uid = client.repository.get_model_uid(published_model)
@@ -14988,58 +14701,66 @@ 3.2: Get model detailsprint(json.dumps(model_details, indent=2))
models_details = client.repository.list_models()
In this section you will learn how to create online scoring and to score a new data record by using the IBM Watson Machine Learning SDK.
metadata = {
client.deployments.ConfigurationMetaNames.NAME: "Deployment of scikit model",
client.deployments.ConfigurationMetaNames.ONLINE: {}
@@ -15048,313 +14769,190 @@ Create online deployment f
created_deployment = client.deployments.create(published_model_uid, meta_props=metadata)
- -####################################################################################### - -Synchronous deployment creation for uid: '0669ec40-29a7-47cd-8179-cfdbb8a4bdcc' started - -####################################################################################### - - -initializing -ready - - ------------------------------------------------------------------------------------------------- -Successfully finished deployment creation, deployment_uid='2e94a9bf-20df-4e06-a00f-37b2e94de242' ------------------------------------------------------------------------------------------------- - - -+
Note: Here we use the deployment url saved in the published_model object. In next section, we show how to retrieve the deployment url from a Watson Machine Learning instance.
Note: Here we use deployment url saved in published_model object. In next section, we show how to retrive deployment url from Watson Machine Learning instance.
-deployment_uid = client.deployments.get_uid(created_deployment)
Now you can print an online scoring endpoint.
scoring_endpoint = client.deployments.get_scoring_href(created_deployment)
print(scoring_endpoint)
https://wml-fvt.ml.test.cloud.ibm.com/ml/v4/deployments/2e94a9bf-20df-4e06-a00f-37b2e94de242/predictions -+
You can also list existing deployments.
You can also list existing deployments.
-client.deployments.list()
client.deployments.get_details(deployment_uid)
{'entity': {'asset': {'id': '0669ec40-29a7-47cd-8179-cfdbb8a4bdcc'},
- 'custom': {},
- 'deployed_asset_type': 'model',
- 'hardware_spec': {'id': 'Not_Applicable', 'name': 'S', 'num_nodes': 1},
- 'name': 'Deployment of scikit model',
- 'online': {},
- 'space_id': 'dba54737-1397-4499-9e82-1c67360ba597',
- 'status': {'online_url': {'url': 'https://wml-fvt.ml.test.cloud.ibm.com/ml/v4/deployments/2e94a9bf-20df-4e06-a00f-37b2e94de242/predictions'},
- 'state': 'ready'}},
- 'metadata': {'created_at': '2020-10-07T13:26:06.813Z',
- 'id': '2e94a9bf-20df-4e06-a00f-37b2e94de242',
- 'modified_at': '2020-10-07T13:26:06.813Z',
- 'name': 'Deployment of scikit model',
- 'owner': 'IBMid-5500067NJD',
- 'space_id': 'dba54737-1397-4499-9e82-1c67360ba597'}}
You can use the following method to do test scoring request against deployed model.
You can use the following method to do test scoring request against deployed model.
+Action: Prepare scoring payload with records to score.
Action: Prepare scoring payload with records to score.
-score_0 = list(score_data[0])
score_1 = list(score_data[1])
scoring_payload = {"input_data": [{"values": [score_0, score_1]}]}
Use client.deployments.score() method to run scoring.
predictions = client.deployments.score(deployment_uid, scoring_payload)
-print(json.dumps(predictions, indent=2))
+
+
+In [ ]:
+
+
+predictions = client.deployments.score(deployment_uid, scoring_payload)
-
+
-{
- "predictions": [
- {
- "fields": [
- "prediction"
- ],
- "values": [
- [
- 5
- ],
- [
- 4
- ]
- ]
- }
- ]
-}
-
-print(json.dumps(predictions, indent=2))
+If you want to clean up all created assets:
You successfully completed this notebook! You learned how to use scikit-learn machine learning as well as Watson Machine Learning for model creation and deployment. Check out our Online Documentation for more samples, tutorials, documentation, how-tos, and blog posts.
Daniel Ryszka, Software Engineer
Copyright © 2020 IBM. This notebook and its source code are released under the terms of the MIT License.