GitHub Repository: ibm/watson-machine-learning-samples
Path: blob/master/cpd4.0/notebooks/python_sdk/lifecycle-management/Use scikit-learn and AI lifecycle capabilities to predict Boston house prices.ipynb
⁶⁴⁰⁵ views

Kernel: Python 3 (ipykernel)

Use scikit-learn and AI lifecycle capabilities to predict Boston house prices with `ibm-watson-machine-learning`

This notebook contains steps and code to demonstrate support of AI Lifecycle features in Watson Machine Learning Service. It contains steps and code to work with ibm-watson-machine-learning library available in PyPI repository. It also 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 3.9.

Learning goals

The learning goals of this notebook are:

Download an externally trained scikit-learn model with dataset.
Persist an external model in Watson Machine Learning repository.
Deploy model for online scoring using client library.
Score sample records using client library.
Update previously persisted model.
Redeploy model in-place.
Scale deployment.

This notebook contains the following parts:

1. Set up the environment

Before you use the sample code in this notebook, you must perform the following setup tasks:

Contact with your Cloud Pack for Data administrator and ask him for your account credentials

Connection to WML

Authenticate the Watson Machine Learning service on IBM Cloud Pack for Data. You need to provide platform url, your username and api_key.

In [ ]:

username = 'PASTE YOUR USERNAME HERE'
api_key = 'PASTE YOUR API_KEY HERE'
url = 'PASTE THE PLATFORM URL HERE'

In [2]:

wml_credentials = {
    "username": username,
    "apikey": api_key,
    "url": url,
    "instance_id": 'openshift',
    "version": '4.0'
}

Alternatively you can use username and password to authenticate WML services.

wml_credentials = {
    "username": ***,
    "password": ***,
    "url": ***,
    "instance_id": 'openshift',
    "version": '4.0'
}

Install and import the `ibm-watson-machine-learning` package

Note: ibm-watson-machine-learning documentation can be found here.

In [ ]:

!pip install -U ibm-watson-machine-learning

In [3]:

from ibm_watson_machine_learning import APIClient

client = APIClient(wml_credentials)

Working with spaces

First of all, you need to create a space that will be used for your work. If you do not have space already created, you can use {PLATFORM_URL}/ml-runtime/spaces?context=icp4data to create one.

Click New Deployment Space
Create an empty space
Go to space Settings tab
Copy space_id and paste it below

Tip: You can also use SDK to prepare the space for your work. More information can be found here.

Action: Assign space ID below

In [ ]:

space_id = 'PASTE YOUR SPACE ID HERE'

You can use list method to print all existing spaces.

In [ ]:

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.

In [4]:

client.set.default_space(space_id)

Out[4]:

'SUCCESS'

2. Download externally created scikit model and data

In this section, you will download externally created scikit models and data used for training it.

In [5]:

import os
import wget

data_dir = 'BOSTON_HOUSE_PRICES_DATA'
if not os.path.isdir(data_dir):
    os.mkdir(data_dir)

model_path = os.path.join(data_dir, 'boston_regressor_0_23_1.tar.gz')
new_model_path = os.path.join(data_dir, 'boston_regressor_new_0_23_1.tar.gz')
if not os.path.isfile(model_path):
    wget.download("https://github.com/IBM/watson-machine-learning-samples/raw/master/cpd4.0/models/scikit/boston_house_price/model/boston_regressor_0_23_1.tar.gz", out=data_dir)  
if not os.path.isfile(new_model_path):
    wget.download("https://github.com/IBM/watson-machine-learning-samples/raw/master/cpd4.0/models/scikit/boston_house_price/model/boston_regressor_new_0_23_1.tar.gz", out=data_dir)

In [6]:

from sklearn import datasets
import pandas as pd

boston_data = datasets.load_boston()
boston_df = pd.DataFrame(boston_data.data)
boston_df.columns = boston_data.feature_names
boston_df['PRICE'] = boston_data.target

In [7]:

train_df = boston_df
test_df = boston_df.drop(['PRICE'], axis=1)

3. Persist externally created scikit model

In this section, you will learn how to store your model in Watson Machine Learning repository by using the Watson Machine Learning Client.

3.1: Publish model

Publish model in Watson Machine Learning repository on Cloud.

Define model name, autor name and email.

In [8]:

sofware_spec_uid = client.software_specifications.get_id_by_name("runtime-22.1-py3.9")

In [9]:

metadata = {
            client.repository.ModelMetaNames.NAME: 'External scikit model',
            client.repository.ModelMetaNames.TYPE: 'scikit-learn_1.0',
            client.repository.ModelMetaNames.SOFTWARE_SPEC_UID: sofware_spec_uid
}

published_model = client.repository.store_model(
    model=model_path,
    meta_props=metadata,
    training_data=train_df)

3.2: Get model details

In [ ]:

import json

published_model_uid = client.repository.get_model_id(published_model)
model_details = client.repository.get_details(published_model_uid)
print(json.dumps(model_details, indent=2))

3.3 Get all models

In [ ]:

models_details = client.repository.list_models(limit=10)

4. Deploy and score in a Cloud

In this section you will learn how to create online scoring and to score a new data record by using the Watson Machine Learning Client.

4.1: Create model deployment

Create online deployment for published model

In [11]:

metadata = {
    client.deployments.ConfigurationMetaNames.NAME: "Deployment of external scikit model",
    client.deployments.ConfigurationMetaNames.ONLINE: {}
}

created_deployment = client.deployments.create(published_model_uid, meta_props=metadata)

Out[11]:

#######################################################################################

Synchronous deployment creation for uid: 'adf70e8b-d060-4f50-b37d-5760797e5052' started

#######################################################################################

initializing.
ready

------------------------------------------------------------------------------------------------
Successfully finished deployment creation, deployment_uid='47fce40d-2e2c-43da-af37-1cd8c131a18d'
------------------------------------------------------------------------------------------------

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.

In [12]:

deployment_uid = client.deployments.get_uid(created_deployment)

Now you can print an online scoring endpoint.

In [13]:

scoring_endpoint = client.deployments.get_scoring_href(created_deployment)
print(scoring_endpoint)

Out[13]:

https://wmlgmc-cpd-wmlgmc.apps.wmlautoai.cp.fyre.ibm.com/ml/v4/deployments/47fce40d-2e2c-43da-af37-1cd8c131a18d/predictions

You can also list existing deployments.

In [ ]:

client.deployments.list(limit=10)

4.2: Get deployment details

In [ ]:

print(json.dumps(client.deployments.get_details(deployment_uid), indent=2))

4.3: Score

You can use below method to do test scoring request against deployed model.

Action: Prepare scoring payload with records to score.

In [15]:

score_0 = list(test_df.iloc[0])
score_1 = list(test_df.iloc[1])

In [16]:

scoring_payload = {"input_data": [{"values": [score_0, score_1]}]}

Use client.deployments.score() method to run scoring.

In [17]:

predictions = client.deployments.score(deployment_uid, scoring_payload)

In [18]:

print(json.dumps(predictions, indent=2))

Out[18]:

{
  "predictions": [
    {
      "fields": [
        "prediction"
      ],
      "values": [
        [
          30.0038433770168
        ],
        [
          25.025562379053415
        ]
      ]
    }
  ]
}

5. Persist new version of the model

In this section, you'll learn how to store new version of your model in Watson Machine Learning repository by using the Watson Machine Learning Client.

5.1: Publish new version of the model

Save the current model version.

In [ ]:

print(json.dumps(client.repository.create_model_revision(published_model_uid), indent=2))

Define new model name and update model content.

In [20]:

metadata = {
            client.repository.ModelMetaNames.NAME: 'External scikit model - updated'
}

published_model = client.repository.update_model(
    model_uid=published_model_uid,
    update_model=new_model_path,
    updated_meta_props=metadata
)

Save new model revision of the updated model.

In [ ]:

new_model_revision = client.repository.create_model_revision(published_model_uid)
print(json.dumps(new_model_revision, indent=2))

Note: Model revisions can be identified by model id and rev number.

Get model rev number from creation details:

In [22]:

rev_id = new_model_revision['metadata'].get('rev')

You can list existing revisions of the model.

In [23]:

client.repository.list_models_revisions(published_model_uid)

Out[23]:

--  -------------------------------  ------------------------
ID  NAME                             CREATED
2   External scikit model - updated  2020-12-08T13:40:52.523Z
1   External scikit model            2020-12-08T13:40:52.523Z
--  -------------------------------  ------------------------

5.2: Get model details

In [ ]:

import json

published_model_uid = client.repository.get_model_id(published_model)
model_details = client.repository.get_details(published_model_uid)

print(json.dumps(model_details, indent=2))

6. Redeploy new version of the model

In this section, you'll learn how to redeploy new version of the model by using the Watson Machine Learning Client.

6.1 Redeploy model

In [25]:

metadata = {
    client.deployments.ConfigurationMetaNames.ASSET: {
        "id": published_model_uid,
        "rev": rev_id
    }
}
    
updated_deployment = client.deployments.update(deployment_uid=deployment_uid, changes=metadata)

Out[25]:

Since ASSET is patched, deployment with new asset id/rev is being started. Monitor the status using deployments.get_details(deployment_uid) api

Wait for the deployment update:

In [26]:

import time

status = None
while status not in ['ready', 'failed']:
    print('.', end=' ')
    time.sleep(2)
    deployment_details = client.deployments.get_details(deployment_uid)
    status = deployment_details['entity']['status'].get('state')
    
print("\nDeployment update finished with status: ", status)

Out[26]:

. . 
Deployment update finished with status:  ready

6.2 Get updated deployment details

In [ ]:

print(json.dumps(client.deployments.get_details(deployment_uid), indent=2))

7. Deployment scaling

In this section, you'll learn how to scale your deployment by creating more copies of stored model with Watson Machine Learning Client. This feature is for providing High-Availability and to support higher throughput

7.1 Scale deployment

In this example, 2 deployment copies will be made.

In [28]:

metadata = {
    client.deployments.ConfigurationMetaNames.NAME: "Deployment of external scikit model - scaling",
    client.deployments.ConfigurationMetaNames.HARDWARE_SPEC: {
        "name": "S",
        "num_nodes": 2
    }
}

In [29]:

scaled_deployment = client.deployments.update(deployment_uid, metadata)

7.2 Get scaled deployment details

In [30]:

print(json.dumps(client.deployments.get_details(deployment_uid), indent=2))

Out[30]:

{
  "entity": {
    "asset": {
      "id": "adf70e8b-d060-4f50-b37d-5760797e5052",
      "rev": "2"
    },
    "custom": {},
    "deployed_asset_type": "model",
    "hardware_spec": {
      "id": "Not_Applicable",
      "name": "S",
      "num_nodes": 2
    },
    "name": "Deployment of external scikit model - scaling",
    "online": {},
    "space_id": "cc59083a-923f-4c35-8947-10c126343bd0",
    "status": {
      "message": {
        "text": "scaling_status: completed;requested_copies: 2;deployed_copies: 2;more_info: Successfully patched the asset ",
        "level": "warning"
      },
      "online_url": {
        "url": "https://wmlgmc-cpd-wmlgmc.apps.wmlautoai.cp.fyre.ibm.com/ml/v4/deployments/47fce40d-2e2c-43da-af37-1cd8c131a18d/predictions"
      },
      "state": "ready"
    }
  },
  "metadata": {
    "created_at": "2020-12-08T13:41:07.003Z",
    "id": "47fce40d-2e2c-43da-af37-1cd8c131a18d",
    "modified_at": "2020-12-08T13:42:27.361Z",
    "name": "Deployment of external scikit model - scaling",
    "owner": "1000330999",
    "space_id": "cc59083a-923f-4c35-8947-10c126343bd0"
  }
}

7.3 Score updated deployment

You can use below method to do test scoring request against deployed model.

Action: Prepare scoring payload with records to score.

In [31]:

score_0 = list(test_df.iloc[0])
score_1 = list(test_df.iloc[1])

In [32]:

scoring_payload = {"input_data": [{"values": [score_0, score_1]}]}

Use client.deployments.score() method to run scoring.

In [33]:

predictions = client.deployments.score(deployment_uid, scoring_payload)

In [34]:

print(json.dumps(predictions, indent=2))

Out[34]:

{
  "predictions": [
    {
      "fields": [
        "prediction"
      ],
      "values": [
        [
          25.340000000000003
        ],
        [
          22.06799999999997
        ]
      ]
    }
  ]
}

8. Clean up

If you want to clean up all created assets:

experiments
trainings
pipelines
model definitions
models
functions
deployments

please follow up this sample notebook.

9. Summary and next steps

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.

Authors

Daniel Ryszka, Software Engineer Jan Sołtysik, Intern

Use scikit-learn and AI lifecycle capabilities to predict Boston house prices with `ibm-watson-machine-learning`

Learning goals

Contents

1. Set up the environment

Connection to WML

Install and import the `ibm-watson-machine-learning` package

Working with spaces

2. Download externally created scikit model and data

3. Persist externally created scikit model

3.1: Publish model

Publish model in Watson Machine Learning repository on Cloud.

3.2: Get model details

3.3 Get all models

4. Deploy and score in a Cloud

4.1: Create model deployment

Create online deployment for published model

4.2: Get deployment details

4.3: Score

5. Persist new version of the model

5.1: Publish new version of the model

5.2: Get model details

6. Redeploy new version of the model

6.1 Redeploy model

6.2 Get updated deployment details

7. Deployment scaling

7.1 Scale deployment

7.2 Get scaled deployment details

7.3 Score updated deployment

8. Clean up

9. Summary and next steps

Authors

Product

Resources

Company

Use scikit-learn and AI lifecycle capabilities to predict Boston house prices with ibm-watson-machine-learning

Learning goals

Contents

1. Set up the environment

Connection to WML

Install and import the ibm-watson-machine-learning package

Working with spaces

2. Download externally created scikit model and data

3. Persist externally created scikit model

3.1: Publish model

Publish model in Watson Machine Learning repository on Cloud.

3.2: Get model details

3.3 Get all models

4. Deploy and score in a Cloud

4.1: Create model deployment

Create online deployment for published model

4.2: Get deployment details

4.3: Score

5. Persist new version of the model

5.1: Publish new version of the model

5.2: Get model details

6. Redeploy new version of the model

6.1 Redeploy model

6.2 Get updated deployment details

7. Deployment scaling

7.1 Scale deployment

7.2 Get scaled deployment details

7.3 Score updated deployment

8. Clean up

9. Summary and next steps

Authors

Use scikit-learn and AI lifecycle capabilities to predict Boston house prices with `ibm-watson-machine-learning`

Install and import the `ibm-watson-machine-learning` package