GitHub Repository: ibm/watson-machine-learning-samples
Path: blob/master/cpd5.2/notebooks/python_sdk/lifecycle-management/Use AutoAI and AI lifecycle to predict credit risk.ipynb
⁶³⁹⁷ views

Kernel: watsonx-ai-samples-py-312

Use AutoAI and AI lifecycle to predict credit risk with `ibm-watsonx-ai`

This notebook contains the steps and code to demonstrate support of AI Lifecycle features of am AutoAI model in watsonx.ai. It contains steps and code to work with ibm-watsonx-ai library available in PyPI repository. It also introduces commands for training, persisting and deploying model, scoring it, updating the model and redeploying it.

Some familiarity with Python is helpful. This notebook uses Python 3.12.

Learning goals

The learning goals of this notebook are:

Work with watsonx.ai experiments to train AutoAI models.
Persist an external model in watsonx.ai repository.
Deploy model for online scoring using client library.
Score sample records using client library.
Update previously persisted model.
Redeploy model in-place.

This notebook contains the following parts:

1. Set up the environment

Before you use the sample code in this notebook, contact with your Cloud Pak for Data administrator and ask for your account credentials.

Install dependencies

Note: ibm-watsonx-ai documentation can be found here.

In [ ]:

%pip install -U wget | tail -n 1
%pip install -U lale | tail -n 1
%pip install -U autoai-libs | tail -n 1
%pip install "scikit-learn==1.6.1" | tail -n 1
%pip install -U ibm-watsonx-ai | tail -n 1

Successfully installed wget-3.2
Requirement already satisfied: sortedcontainers~=2.2 in /opt/user-env/pyt6/lib64/python3.12/site-packages (from portion->jsonsubschema>=0.0.6->lale) (2.4.0)
Successfully installed autoai-libs-3.0.3
Requirement already satisfied: threadpoolctl>=3.1.0 in /opt/user-env/pyt6/lib64/python3.12/site-packages (from scikit-learn==1.6.1) (3.6.0)
Successfully installed ibm-watsonx-ai-1.3.20

Define credentials

Authenticate the watsonx.ai Runtime service on IBM Cloud Pak for Data. You need to provide the admin's username and the platform url.

In [ ]:

username = "PASTE YOUR USERNAME HERE"
url = "PASTE THE PLATFORM URL HERE"

Use the admin's api_key to authenticate watsonx.ai Runtime services:

In [ ]:

import getpass
from ibm_watsonx_ai import Credentials

credentials = Credentials(
    username=username,
    api_key=getpass.getpass("Enter your watsonx.ai API key and hit enter: "),
    url=url,
    instance_id="openshift",
    version="5.2",
)

Alternatively you can use the admin's password:

In [3]:

import getpass
from ibm_watsonx_ai import Credentials

if "credentials" not in locals() or not credentials.api_key:
    credentials = Credentials(
        username=username,
        password=getpass.getpass("Enter your watsonx.ai password and hit enter: "),
        url=url,
        instance_id="openshift",
        version="5.2",
    )

Out[3]:

Enter your watsonx.ai password and hit enter:  ········

Create `APIClient` instance

In [4]:

from ibm_watsonx_ai import APIClient

client = APIClient(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 [5]:

space_id = "PASTE YOUR SPACE ID HERE"

You can use the list method to print all existing spaces.

In [ ]:

client.spaces.list(limit=10)

To be able to interact with all resources available in watsonx.ai, you need to set space which you will be using.

In [6]:

client.set.default_space(space_id)

Out[6]:

'SUCCESS'

2. Optimizer definition

Training data connection

Define connection information to training data CSV file. This example uses the German Credit Risk dataset.

The dataset can be downloaded from here.

In [7]:

filename = "credit_risk_training_light.csv"

Download training data from git repository.

In [8]:

import os, wget

url = "https://raw.githubusercontent.com/IBM/watsonx-ai-samples/master/cpd5.2/data/credit_risk/credit_risk_training_light.csv"
if not os.path.isfile(filename):
    wget.download(url)

In [9]:

asset_details = client.data_assets.create("credit_risk_training", filename)
asset_details

Out[9]:

Creating data asset...
SUCCESS

{'metadata': {'space_id': '9c4eb218-96e8-41e0-8cd5-f783504a11ea',
  'usage': {'last_updated_at': '2025-05-22T11:39:54Z',
   'last_updater_id': '1000331001',
   'last_update_time': 1747913994246,
   'last_accessed_at': '2025-05-22T11:39:54Z',
   'last_access_time': 1747913994246,
   'last_accessor_id': '1000331001',
   'access_count': 0},
  'rov': {'mode': 0,
   'collaborator_ids': {},
   'member_roles': {'1000331001': {'user_iam_id': '1000331001',
     'roles': ['OWNER']}}},
  'is_linked_with_sub_container': False,
  'name': 'credit_risk_training',
  'description': '',
  'asset_type': 'data_asset',
  'origin_country': 'us',
  'resource_key': 'credit_risk_training',
  'rating': 0.0,
  'total_ratings': 0,
  'catalog_id': '32c875f2-f104-4801-9d5f-a0987098790c',
  'created': 1747913994246,
  'created_at': '2025-05-22T11:39:54Z',
  'owner_id': '1000331001',
  'size': 0,
  'version': 2.0,
  'asset_state': 'available',
  'asset_attributes': ['data_asset'],
  'asset_id': 'd414512e-a854-49c3-a8fc-cceff65dd884',
  'asset_category': 'USER',
  'creator_id': '1000331001',
  'is_branched': True,
  'guid': 'd414512e-a854-49c3-a8fc-cceff65dd884',
  'href': '/v2/assets/d414512e-a854-49c3-a8fc-cceff65dd884?space_id=9c4eb218-96e8-41e0-8cd5-f783504a11ea',
  'last_updated_at': '2025-05-22T11:39:54Z'},
 'entity': {'data_asset': {'mime_type': 'text/csv'}}}

In [10]:

from ibm_watsonx_ai.helpers import DataConnection, AssetLocation


credit_risk_conn = DataConnection(
    location=AssetLocation(asset_id=client.data_assets.get_id(asset_details))
)

training_data_reference = [credit_risk_conn]

Optimizer configuration

Provide the input information for AutoAI optimizer:

name - experiment name
prediction_type - type of the problem
prediction_column - target column name
scoring - optimization metric

In [11]:

from ibm_watsonx_ai.experiment import AutoAI

experiment = AutoAI(credentials, space_id=space_id)

pipeline_optimizer = experiment.optimizer(
    name="Credit Risk Prediction - AutoAI",
    prediction_type=AutoAI.PredictionType.BINARY,
    prediction_column="Risk",
    scoring=AutoAI.Metrics.ROC_AUC_SCORE,
)

Configuration parameters can be retrieved via get_params().

In [12]:

pipeline_optimizer.get_params()

Out[12]:

{'name': 'Credit Risk Prediction - AutoAI',
 'desc': '',
 'prediction_type': 'binary',
 'prediction_column': 'Risk',
 'prediction_columns': None,
 'timestamp_column_name': None,
 'scoring': 'roc_auc',
 'holdout_size': None,
 'max_num_daub_ensembles': None,
 't_shirt_size': 'm',
 'train_sample_rows_test_size': None,
 'include_only_estimators': None,
 'include_batched_ensemble_estimators': None,
 'backtest_num': None,
 'lookback_window': None,
 'forecast_window': None,
 'backtest_gap_length': None,
 'cognito_transform_names': None,
 'csv_separator': ',',
 'excel_sheet': None,
 'encoding': 'utf-8',
 'positive_label': None,
 'drop_duplicates': True,
 'outliers_columns': None,
 'text_processing': None,
 'word2vec_feature_number': None,
 'daub_give_priority_to_runtime': None,
 'text_columns_names': None,
 'sampling_type': None,
 'sample_size_limit': None,
 'sample_rows_limit': None,
 'sample_percentage_limit': None,
 'number_of_batch_rows': None,
 'n_parallel_data_connections': None,
 'test_data_csv_separator': ',',
 'test_data_excel_sheet': None,
 'test_data_encoding': 'utf-8',
 'categorical_imputation_strategy': None,
 'numerical_imputation_strategy': None,
 'numerical_imputation_value': None,
 'imputation_threshold': None,
 'retrain_on_holdout': True,
 'feature_columns': None,
 'pipeline_types': None,
 'supporting_features_at_forecast': None,
 'numerical_columns': None,
 'categorical_columns': None,
 'confidence_level': None,
 'incremental_learning': None,
 'early_stop_enabled': None,
 'early_stop_window_size': None,
 'time_ordered_data': None,
 'feature_selector_mode': None,
 'run_id': None}

3. Experiment run

Call the fit() method to trigger the AutoAI experiment. You can either use interactive mode (synchronous job) or background mode (asychronous job) by specifying background_model=True.

In [13]:

run_details = pipeline_optimizer.fit(
    training_data_reference=training_data_reference, background_mode=False
)

Out[13]:

Training job f2a01a01-0f16-4e0d-9748-895e7b795c4a completed: 100%|████████| [01:11<00:00,  1.39it/s]

You can use the get_run_status() method to monitor AutoAI jobs in background mode.

In [14]:

pipeline_optimizer.get_run_status()

Out[14]:

'completed'

Load trained model

In [15]:

pipeline = pipeline_optimizer.get_pipeline()

Reading training data from COS

In [16]:

train_df = pipeline_optimizer.get_data_connections()[0].read()

train_X = train_df.drop(["Risk"], axis=1).values
train_y = train_df.Risk.values

4. Persist and Deploy trained AutoAI model

In this section you will learn how to deploy and score pipeline model as webservice using WML instance.

Online deployment creation

In [17]:

from ibm_watsonx_ai.deployment import WebService

service = WebService(credentials, source_space_id=space_id)

service.create(
    experiment_run_id=run_details["metadata"]["id"],
    model="Pipeline_1",
    deployment_name="AutoAI credit-risk deployment",
)

Out[17]:

Preparing an AutoAI Deployment...
Published model uid: b78e56d5-6a90-477b-8ab8-b58d5e5ce1ed
Deploying model b78e56d5-6a90-477b-8ab8-b58d5e5ce1ed using V4 client.


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

Synchronous deployment creation for id: 'b78e56d5-6a90-477b-8ab8-b58d5e5ce1ed' started

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


initializing
Note: online_url is deprecated and will be removed in a future release. Use serving_urls instead.
.....
ready


-----------------------------------------------------------------------------------------------
Successfully finished deployment creation, deployment_id='433799b3-5756-4563-96f1-603ab2f5ff1e'
-----------------------------------------------------------------------------------------------

Deployment object could be printed to show basic information:

In [ ]:

print(service)

To show all available information about the deployment use the .get_params() method:

In [ ]:

service.get_params()

Scoring of webservice

You can make scoring request by calling score() on deployed pipeline.

In [20]:

predictions = service.score(payload=train_df.drop(["Risk"], axis=1).iloc[:10])
predictions

Out[20]:

{'predictions': [{'fields': ['prediction', 'probability'],
   'values': [['No Risk', [0.815472082175866, 0.18452791782413402]],
    ['No Risk', [0.7501849542379176, 0.24981504576208238]],
    ['Risk', [0.44323551396938976, 0.5567644860306102]],
    ['No Risk', [0.7860837153311935, 0.2139162846688065]],
    ['Risk', [0.10388810002019544, 0.8961118999798046]],
    ['Risk', [0.05423329461659787, 0.9457667053834021]],
    ['Risk', [0.39761734701550944, 0.6023826529844906]],
    ['No Risk', [0.7195913804536169, 0.2804086195463831]],
    ['No Risk', [0.8252891188726867, 0.1747108811273132]],
    ['Risk', [0.05226738963105093, 0.9477326103689491]]]}]}

If you want to work with the web service in an external Python application you can retrieve the service object by:

Initialize the service by service = WebService(wml_credentials)
Get deployment_id by service.list() method
Get webservice object by service.get('deployment_id') method

After that you can call service.score() method.

Deleting deployment

You can delete the existing deployment by calling the service.delete() command. To list the existing web services you can use service.list().

5. Refine and persist new version of the model

In this section, you'll learn how to store new refinement version of your model in watsonx.ai repository.

In this section you learn how to refine and retrain the best pipeline returned by AutoAI. There are many ways to refine a pipeline. For illustration, simply replace the final estimator in the pipeline by an interpretable model. The call to wrap_imported_operators() augments scikit-learn operators with schemas for hyperparameter tuning.

In [21]:

from sklearn.linear_model import LogisticRegression as LR
from sklearn.tree import DecisionTreeClassifier as Tree
from sklearn.neighbors import KNeighborsClassifier as KNN
from lale.lib.lale import Hyperopt
from lale import wrap_imported_operators

wrap_imported_operators()

Pipeline decomposition and new definition

Start by removing the last step of the pipeline, i.e., the final estimator.

In [22]:

prefix = pipeline.remove_last().freeze_trainable()
prefix.export_to_sklearn_pipeline()

Out[22]:

Next, add a new final step, which consists of a choice of three estimators. In this code, | is the or combinator (algorithmic choice). It defines a search space for another optimizer run.

In [23]:

new_pipeline = prefix >> (LR | Tree | KNN)

New optimizer `Hyperopt` configuration and training

To automatically select the algorithm and tune its hyperparameters, we create an instance of the Hyperopt optimizer and fit it to the data.

In [24]:

from sklearn.model_selection import train_test_split

X_train, X_test, y_train, y_test = train_test_split(
    train_X, train_y, test_size=0.15, random_state=33
)

In [25]:

hyperopt = Hyperopt(estimator=new_pipeline, cv=3, max_evals=20, scoring="roc_auc")
hyperopt_pipelines = hyperopt.fit(X_train, y_train)

Out[25]:

100%|██████████| 20/20 [00:08<00:00,  2.34trial/s, best loss: -0.7994345630215195]
1 out of 20 trials failed, call summary() for details.
Run with verbose=True to see per-trial exceptions.

In [26]:

pipeline_model = hyperopt_pipelines.get_pipeline(astype="sklearn")

Save newly refined pipeline

In [27]:

import joblib

model_path = "refined_pipeline.pickle"
joblib.dump(pipeline_model, model_path)

Out[27]:

['refined_pipeline.pickle']

In [28]:

import tarfile

with tarfile.open(model_path + ".tar.gz", "w:gz") as tar:
    tar.add(model_path)
model_path += ".tar.gz"

Publish new version of the model

Download current version of the model

In [29]:

model_id = service.get_params()["entity"]["asset"]["id"]
deployment_id = service.get_params()["metadata"]["id"]

Out[29]:

Note: online_url is deprecated and will be removed in a future release. Use serving_urls instead.
Note: online_url is deprecated and will be removed in a future release. Use serving_urls instead.

In [30]:

downloaded_model_name = "current_model.zip"
client.repository.download(model_id, downloaded_model_name)

Out[30]:

Successfully saved model content to file: 'current_model.zip'

'/home/wsuser/work/current_model.zip'

In [31]:

import zipfile

with zipfile.ZipFile(downloaded_model_name, "r") as zip_ref:
    zip_ref.extractall()

Create archive containing updated model

In [32]:

updated_model_path = "updated_model.zip"
with zipfile.ZipFile(updated_model_path, "w") as zip_ref:
    zip_ref.write(model_path)
    zip_ref.write("pipeline-model.json")

Save the current model version

In [33]:

import json

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

Out[33]:

{
  "metadata": {
    "name": "P1",
    "space_id": "9c4eb218-96e8-41e0-8cd5-f783504a11ea",
    "resource_key": "81444767-8506-4af1-9fd3-9b2b2dd4b3a6",
    "id": "b78e56d5-6a90-477b-8ab8-b58d5e5ce1ed",
    "created_at": "2025-05-22T11:41:53Z",
    "rev": "1",
    "commit_info": {
      "committed_at": "2025-05-22T11:44:01Z"
    },
    "rov": {
      "member_roles": {
        "1000331001": {
          "user_iam_id": "1000331001",
          "roles": [
            "OWNER"
          ]
        }
      }
    },
    "owner": "1000331001"
  },
  "entity": {
    "pipeline": {
      "id": "91cd7ec2-6bda-417e-82d1-ff8368b03952"
    },
    "software_spec": {
      "id": "8c1a58c6-62b5-4dc4-987a-df751c2756b6",
      "name": "hybrid_0.1"
    },
    "type": "wml-hybrid_0.1",
    "training_data_references": [
      {
        "type": "data_asset",
        "connection": null,
        "location": {
          "href": "/v2/assets/d414512e-a854-49c3-a8fc-cceff65dd884?space_id=9c4eb218-96e8-41e0-8cd5-f783504a11ea",
          "id": "d414512e-a854-49c3-a8fc-cceff65dd884",
          "space_id": "9c4eb218-96e8-41e0-8cd5-f783504a11ea"
        },
        "schema": {
          "id": "auto_ai_kb_input_schema",
          "fields": [
            {
              "name": "CheckingStatus",
              "type": "other",
              "nullable": false
            },
            {
              "name": "LoanDuration",
              "type": "double",
              "nullable": false
            },
            {
              "name": "CreditHistory",
              "type": "other",
              "nullable": false
            },
            {
              "name": "LoanPurpose",
              "type": "other",
              "nullable": false
            },
            {
              "name": "LoanAmount",
              "type": "double",
              "nullable": false
            },
            {
              "name": "ExistingSavings",
              "type": "other",
              "nullable": false
            },
            {
              "name": "EmploymentDuration",
              "type": "other",
              "nullable": false
            },
            {
              "name": "InstallmentPercent",
              "type": "double",
              "nullable": false
            },
            {
              "name": "Sex",
              "type": "other",
              "nullable": false
            },
            {
              "name": "OthersOnLoan",
              "type": "other",
              "nullable": false
            },
            {
              "name": "CurrentResidenceDuration",
              "type": "double",
              "nullable": false
            },
            {
              "name": "OwnsProperty",
              "type": "other",
              "nullable": false
            },
            {
              "name": "Age",
              "type": "double",
              "nullable": false
            },
            {
              "name": "InstallmentPlans",
              "type": "other",
              "nullable": false
            },
            {
              "name": "Housing",
              "type": "other",
              "nullable": false
            },
            {
              "name": "ExistingCreditsCount",
              "type": "double",
              "nullable": false
            },
            {
              "name": "Job",
              "type": "other",
              "nullable": false
            },
            {
              "name": "Dependents",
              "type": "double",
              "nullable": false
            },
            {
              "name": "Telephone",
              "type": "other",
              "nullable": false
            },
            {
              "name": "ForeignWorker",
              "type": "other",
              "nullable": false
            },
            {
              "name": "Risk",
              "type": "other",
              "nullable": false
            }
          ]
        }
      }
    ],
    "schemas": {
      "input": [
        {
          "id": "auto_ai_kb_input_schema",
          "fields": [
            {
              "name": "CheckingStatus",
              "type": "other",
              "nullable": false
            },
            {
              "name": "LoanDuration",
              "type": "double",
              "nullable": false
            },
            {
              "name": "CreditHistory",
              "type": "other",
              "nullable": false
            },
            {
              "name": "LoanPurpose",
              "type": "other",
              "nullable": false
            },
            {
              "name": "LoanAmount",
              "type": "double",
              "nullable": false
            },
            {
              "name": "ExistingSavings",
              "type": "other",
              "nullable": false
            },
            {
              "name": "EmploymentDuration",
              "type": "other",
              "nullable": false
            },
            {
              "name": "InstallmentPercent",
              "type": "double",
              "nullable": false
            },
            {
              "name": "Sex",
              "type": "other",
              "nullable": false
            },
            {
              "name": "OthersOnLoan",
              "type": "other",
              "nullable": false
            },
            {
              "name": "CurrentResidenceDuration",
              "type": "double",
              "nullable": false
            },
            {
              "name": "OwnsProperty",
              "type": "other",
              "nullable": false
            },
            {
              "name": "Age",
              "type": "double",
              "nullable": false
            },
            {
              "name": "InstallmentPlans",
              "type": "other",
              "nullable": false
            },
            {
              "name": "Housing",
              "type": "other",
              "nullable": false
            },
            {
              "name": "ExistingCreditsCount",
              "type": "double",
              "nullable": false
            },
            {
              "name": "Job",
              "type": "other",
              "nullable": false
            },
            {
              "name": "Dependents",
              "type": "double",
              "nullable": false
            },
            {
              "name": "Telephone",
              "type": "other",
              "nullable": false
            },
            {
              "name": "ForeignWorker",
              "type": "other",
              "nullable": false
            }
          ]
        }
      ],
      "output": []
    },
    "label_column": "Risk",
    "metrics": [
      {
        "timestamp": "2025-05-22T11:40:28Z",
        "ml_metrics": {
          "holdout_accuracy": 0.72,
          "holdout_average_precision": 0.5175996610541083,
          "holdout_balanced_accuracy": 0.7610294117647058,
          "holdout_f1": 0.7586206896551724,
          "holdout_neg_log_loss": -0.5151502877721112,
          "holdout_precision": 0.9166666666666666,
          "holdout_recall": 0.6470588235294118,
          "holdout_roc_auc": 0.8088235294117647,
          "training_accuracy": 0.7187987987987988,
          "training_average_precision": 0.9205829210523921,
          "training_balanced_accuracy": 0.752635046113307,
          "training_f1": 0.7674399674399673,
          "training_neg_log_loss": -0.5532545596504036,
          "training_precision": 0.9041835357624831,
          "training_recall": 0.6666666666666666,
          "training_roc_auc": 0.8273031316509577
        },
        "context": {
          "intermediate_model": {
            "name": "P1",
            "process": "pre_hpo_d_output",
            "location": {
              "pipeline": "/spaces/9c4eb218-96e8-41e0-8cd5-f783504a11ea/assets/auto_ml/auto_ml.0627b7f6-8708-4c13-b0c9-5d91455561d9/wml_data/f2a01a01-0f16-4e0d-9748-895e7b795c4a/data/automl/pre_hpo_d_output/Pipeline1/pipeline.json",
              "pipeline_model": "/spaces/9c4eb218-96e8-41e0-8cd5-f783504a11ea/assets/auto_ml/auto_ml.0627b7f6-8708-4c13-b0c9-5d91455561d9/wml_data/f2a01a01-0f16-4e0d-9748-895e7b795c4a/data/automl/pre_hpo_d_output/Pipeline1/pipeline-model.json",
              "model": "/spaces/9c4eb218-96e8-41e0-8cd5-f783504a11ea/assets/auto_ml/auto_ml.0627b7f6-8708-4c13-b0c9-5d91455561d9/wml_data/f2a01a01-0f16-4e0d-9748-895e7b795c4a/data/automl/pre_hpo_d_output/Pipeline1/model.pickle"
            },
            "schema_location": "/spaces/9c4eb218-96e8-41e0-8cd5-f783504a11ea/assets/auto_ml/auto_ml.0627b7f6-8708-4c13-b0c9-5d91455561d9/wml_data/f2a01a01-0f16-4e0d-9748-895e7b795c4a/data/automl/pre_hpo_d_output/Pipeline1/schema.json",
            "notebook_location": "/spaces/9c4eb218-96e8-41e0-8cd5-f783504a11ea/assets/auto_ml/auto_ml.0627b7f6-8708-4c13-b0c9-5d91455561d9/wml_data/f2a01a01-0f16-4e0d-9748-895e7b795c4a/data/automl/pre_hpo_d_output/Pipeline1/notebook.ipynb",
            "pipeline_nodes": [
              "PreprocessingTransformer",
              "SnapLogisticRegression"
            ],
            "composition_steps": [
              "Split_TrainingHoldout",
              "TrainingDataset_full_224_20",
              "Datetime_FE",
              "TrainingDataset_full_224_20",
              "Preprocessor_default",
              "DAUB"
            ],
            "duration": 418
          },
          "phase": "pre_hpo_d_output",
          "classes": [
            "Risk",
            "No Risk"
          ],
          "binary_classification": {
            "confusion_matrix": [
              {
                "true_class": "Risk",
                "tp": 7,
                "tn": 11,
                "fp": 6,
                "fn": 1
              },
              {
                "true_class": "No Risk",
                "tp": 11,
                "tn": 7,
                "fp": 1,
                "fn": 6
              }
            ],
            "roc_curve": [
              {
                "true_class": "Risk",
                "tpr": [
                  0,
                  0.125,
                  0.5,
                  0.5,
                  0.625,
                  0.625,
                  0.75,
                  0.75,
                  0.875,
                  0.875,
                  1,
                  1
                ],
                "fpr": [
                  0,
                  0,
                  0,
                  0.11764705882352941,
                  0.11764705882352941,
                  0.23529411764705882,
                  0.23529411764705882,
                  0.4117647058823529,
                  0.4117647058823529,
                  0.7647058823529411,
                  0.7647058823529411,
                  1
                ],
                "thresholds": [
                  1,
                  0.9421695470809937,
                  0.856395423412323,
                  0.7958160042762756,
                  0.7922008037567139,
                  0.6506691575050354,
                  0.6433809399604797,
                  0.4648997485637665,
                  0.4328538179397583,
                  0.13455311954021454,
                  0.1330871284008026,
                  0.057326167821884155
                ]
              },
              {
                "true_class": "No Risk",
                "tpr": [
                  0,
                  0.058823529411764705,
                  0.23529411764705882,
                  0.23529411764705882,
                  0.5882352941176471,
                  0.5882352941176471,
                  0.7647058823529411,
                  0.7647058823529411,
                  0.8823529411764706,
                  0.8823529411764706,
                  1,
                  1
                ],
                "fpr": [
                  0,
                  0,
                  0,
                  0.125,
                  0.125,
                  0.25,
                  0.25,
                  0.375,
                  0.375,
                  0.5,
                  0.5,
                  1
                ],
                "thresholds": [
                  1,
                  0.9426738619804382,
                  0.8750686049461365,
                  0.8669129014015198,
                  0.568006694316864,
                  0.5671461820602417,
                  0.4318302571773529,
                  0.35661906003952026,
                  0.215621680021286,
                  0.20779918134212494,
                  0.20379875600337982,
                  0.057830434292554855
                ]
              }
            ]
          },
          "features_importance": [
            {
              "stage": "Mean",
              "computation_type": "",
              "features": {
                "Age": 0.2788,
                "CheckingStatus": 0.0462,
                "CreditHistory": 0.0318,
                "CurrentResidenceDuration": 0.0252,
                "Dependents": 0.008,
                "EmploymentDuration": 0.0165,
                "ExistingCreditsCount": 0.0031,
                "ExistingSavings": 0.0228,
                "ForeignWorker": 0,
                "Housing": 0.0047,
                "InstallmentPercent": 0.0069,
                "InstallmentPlans": 0.0028,
                "Job": 0.009,
                "LoanAmount": 0.2862,
                "LoanDuration": 0.0696,
                "LoanPurpose": 0.0916,
                "OthersOnLoan": 0.0349,
                "OwnsProperty": 0.0368,
                "Sex": 0.0173,
                "Telephone": 0.0077
              }
            }
          ],
          "target_column": "Risk",
          "incremental_training": {},
          "prediction_type": "binary"
        }
      }
    ],
    "hybrid_pipeline_software_specs": [
      {
        "name": "autoai-kb_rt25.1-py3.12"
      }
    ],
    "training_id": "f2a01a01-0f16-4e0d-9748-895e7b795c4a",
    "data_preprocessing": [
      {
        "stage": "sampling",
        "input": {
          "rows": 249,
          "columns": 21
        },
        "output": {
          "rows": 249,
          "columns": 21
        },
        "props": {
          "type": "stratified"
        }
      },
      {
        "stage": "cleansing",
        "input": {
          "rows": 249,
          "columns": 21
        },
        "output": {
          "rows": 249,
          "columns": 21
        },
        "props": {
          "duplicated_rows_count": 0
        }
      }
    ],
    "content_import_state": "completed"
  }
}

Update the model

In [34]:

metadata = {client.repository.ModelMetaNames.NAME: "AutoAI credit-risk updated model"}

published_model = client.repository.update_model(
    model_id=model_id, update_model=updated_model_path, updated_meta_props=metadata
)

Save new model revision of the updated model

In [35]:

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

Out[35]:

{
  "metadata": {
    "name": "AutoAI credit-risk updated model",
    "space_id": "9c4eb218-96e8-41e0-8cd5-f783504a11ea",
    "resource_key": "73dd6496-5468-4080-ab0e-2f50aeb7cbe6",
    "id": "b78e56d5-6a90-477b-8ab8-b58d5e5ce1ed",
    "created_at": "2025-05-22T11:41:53Z",
    "rev": "2",
    "commit_info": {
      "committed_at": "2025-05-22T11:44:04Z"
    },
    "rov": {
      "member_roles": {
        "1000331001": {
          "user_iam_id": "1000331001",
          "roles": [
            "OWNER"
          ]
        }
      }
    },
    "owner": "1000331001"
  },
  "entity": {
    "pipeline": {
      "id": "91cd7ec2-6bda-417e-82d1-ff8368b03952"
    },
    "software_spec": {
      "id": "8c1a58c6-62b5-4dc4-987a-df751c2756b6",
      "name": "hybrid_0.1"
    },
    "type": "wml-hybrid_0.1",
    "training_data_references": [
      {
        "type": "data_asset",
        "connection": null,
        "location": {
          "href": "/v2/assets/d414512e-a854-49c3-a8fc-cceff65dd884?space_id=9c4eb218-96e8-41e0-8cd5-f783504a11ea",
          "id": "d414512e-a854-49c3-a8fc-cceff65dd884",
          "space_id": "9c4eb218-96e8-41e0-8cd5-f783504a11ea"
        },
        "schema": {
          "id": "auto_ai_kb_input_schema",
          "fields": [
            {
              "name": "CheckingStatus",
              "type": "other",
              "nullable": false
            },
            {
              "name": "LoanDuration",
              "type": "double",
              "nullable": false
            },
            {
              "name": "CreditHistory",
              "type": "other",
              "nullable": false
            },
            {
              "name": "LoanPurpose",
              "type": "other",
              "nullable": false
            },
            {
              "name": "LoanAmount",
              "type": "double",
              "nullable": false
            },
            {
              "name": "ExistingSavings",
              "type": "other",
              "nullable": false
            },
            {
              "name": "EmploymentDuration",
              "type": "other",
              "nullable": false
            },
            {
              "name": "InstallmentPercent",
              "type": "double",
              "nullable": false
            },
            {
              "name": "Sex",
              "type": "other",
              "nullable": false
            },
            {
              "name": "OthersOnLoan",
              "type": "other",
              "nullable": false
            },
            {
              "name": "CurrentResidenceDuration",
              "type": "double",
              "nullable": false
            },
            {
              "name": "OwnsProperty",
              "type": "other",
              "nullable": false
            },
            {
              "name": "Age",
              "type": "double",
              "nullable": false
            },
            {
              "name": "InstallmentPlans",
              "type": "other",
              "nullable": false
            },
            {
              "name": "Housing",
              "type": "other",
              "nullable": false
            },
            {
              "name": "ExistingCreditsCount",
              "type": "double",
              "nullable": false
            },
            {
              "name": "Job",
              "type": "other",
              "nullable": false
            },
            {
              "name": "Dependents",
              "type": "double",
              "nullable": false
            },
            {
              "name": "Telephone",
              "type": "other",
              "nullable": false
            },
            {
              "name": "ForeignWorker",
              "type": "other",
              "nullable": false
            },
            {
              "name": "Risk",
              "type": "other",
              "nullable": false
            }
          ]
        }
      }
    ],
    "schemas": {
      "input": [
        {
          "id": "auto_ai_kb_input_schema",
          "fields": [
            {
              "name": "CheckingStatus",
              "type": "other",
              "nullable": false
            },
            {
              "name": "LoanDuration",
              "type": "double",
              "nullable": false
            },
            {
              "name": "CreditHistory",
              "type": "other",
              "nullable": false
            },
            {
              "name": "LoanPurpose",
              "type": "other",
              "nullable": false
            },
            {
              "name": "LoanAmount",
              "type": "double",
              "nullable": false
            },
            {
              "name": "ExistingSavings",
              "type": "other",
              "nullable": false
            },
            {
              "name": "EmploymentDuration",
              "type": "other",
              "nullable": false
            },
            {
              "name": "InstallmentPercent",
              "type": "double",
              "nullable": false
            },
            {
              "name": "Sex",
              "type": "other",
              "nullable": false
            },
            {
              "name": "OthersOnLoan",
              "type": "other",
              "nullable": false
            },
            {
              "name": "CurrentResidenceDuration",
              "type": "double",
              "nullable": false
            },
            {
              "name": "OwnsProperty",
              "type": "other",
              "nullable": false
            },
            {
              "name": "Age",
              "type": "double",
              "nullable": false
            },
            {
              "name": "InstallmentPlans",
              "type": "other",
              "nullable": false
            },
            {
              "name": "Housing",
              "type": "other",
              "nullable": false
            },
            {
              "name": "ExistingCreditsCount",
              "type": "double",
              "nullable": false
            },
            {
              "name": "Job",
              "type": "other",
              "nullable": false
            },
            {
              "name": "Dependents",
              "type": "double",
              "nullable": false
            },
            {
              "name": "Telephone",
              "type": "other",
              "nullable": false
            },
            {
              "name": "ForeignWorker",
              "type": "other",
              "nullable": false
            }
          ]
        }
      ],
      "output": []
    },
    "label_column": "Risk",
    "metrics": [
      {
        "timestamp": "2025-05-22T11:40:28Z",
        "ml_metrics": {
          "holdout_accuracy": 0.72,
          "holdout_average_precision": 0.5175996610541083,
          "holdout_balanced_accuracy": 0.7610294117647058,
          "holdout_f1": 0.7586206896551724,
          "holdout_neg_log_loss": -0.5151502877721112,
          "holdout_precision": 0.9166666666666666,
          "holdout_recall": 0.6470588235294118,
          "holdout_roc_auc": 0.8088235294117647,
          "training_accuracy": 0.7187987987987988,
          "training_average_precision": 0.9205829210523921,
          "training_balanced_accuracy": 0.752635046113307,
          "training_f1": 0.7674399674399673,
          "training_neg_log_loss": -0.5532545596504036,
          "training_precision": 0.9041835357624831,
          "training_recall": 0.6666666666666666,
          "training_roc_auc": 0.8273031316509577
        },
        "context": {
          "intermediate_model": {
            "name": "P1",
            "process": "pre_hpo_d_output",
            "location": {
              "pipeline": "/spaces/9c4eb218-96e8-41e0-8cd5-f783504a11ea/assets/auto_ml/auto_ml.0627b7f6-8708-4c13-b0c9-5d91455561d9/wml_data/f2a01a01-0f16-4e0d-9748-895e7b795c4a/data/automl/pre_hpo_d_output/Pipeline1/pipeline.json",
              "pipeline_model": "/spaces/9c4eb218-96e8-41e0-8cd5-f783504a11ea/assets/auto_ml/auto_ml.0627b7f6-8708-4c13-b0c9-5d91455561d9/wml_data/f2a01a01-0f16-4e0d-9748-895e7b795c4a/data/automl/pre_hpo_d_output/Pipeline1/pipeline-model.json",
              "model": "/spaces/9c4eb218-96e8-41e0-8cd5-f783504a11ea/assets/auto_ml/auto_ml.0627b7f6-8708-4c13-b0c9-5d91455561d9/wml_data/f2a01a01-0f16-4e0d-9748-895e7b795c4a/data/automl/pre_hpo_d_output/Pipeline1/model.pickle"
            },
            "schema_location": "/spaces/9c4eb218-96e8-41e0-8cd5-f783504a11ea/assets/auto_ml/auto_ml.0627b7f6-8708-4c13-b0c9-5d91455561d9/wml_data/f2a01a01-0f16-4e0d-9748-895e7b795c4a/data/automl/pre_hpo_d_output/Pipeline1/schema.json",
            "notebook_location": "/spaces/9c4eb218-96e8-41e0-8cd5-f783504a11ea/assets/auto_ml/auto_ml.0627b7f6-8708-4c13-b0c9-5d91455561d9/wml_data/f2a01a01-0f16-4e0d-9748-895e7b795c4a/data/automl/pre_hpo_d_output/Pipeline1/notebook.ipynb",
            "pipeline_nodes": [
              "PreprocessingTransformer",
              "SnapLogisticRegression"
            ],
            "composition_steps": [
              "Split_TrainingHoldout",
              "TrainingDataset_full_224_20",
              "Datetime_FE",
              "TrainingDataset_full_224_20",
              "Preprocessor_default",
              "DAUB"
            ],
            "duration": 418
          },
          "phase": "pre_hpo_d_output",
          "classes": [
            "Risk",
            "No Risk"
          ],
          "binary_classification": {
            "confusion_matrix": [
              {
                "true_class": "Risk",
                "tp": 7,
                "tn": 11,
                "fp": 6,
                "fn": 1
              },
              {
                "true_class": "No Risk",
                "tp": 11,
                "tn": 7,
                "fp": 1,
                "fn": 6
              }
            ],
            "roc_curve": [
              {
                "true_class": "Risk",
                "tpr": [
                  0,
                  0.125,
                  0.5,
                  0.5,
                  0.625,
                  0.625,
                  0.75,
                  0.75,
                  0.875,
                  0.875,
                  1,
                  1
                ],
                "fpr": [
                  0,
                  0,
                  0,
                  0.11764705882352941,
                  0.11764705882352941,
                  0.23529411764705882,
                  0.23529411764705882,
                  0.4117647058823529,
                  0.4117647058823529,
                  0.7647058823529411,
                  0.7647058823529411,
                  1
                ],
                "thresholds": [
                  1,
                  0.9421695470809937,
                  0.856395423412323,
                  0.7958160042762756,
                  0.7922008037567139,
                  0.6506691575050354,
                  0.6433809399604797,
                  0.4648997485637665,
                  0.4328538179397583,
                  0.13455311954021454,
                  0.1330871284008026,
                  0.057326167821884155
                ]
              },
              {
                "true_class": "No Risk",
                "tpr": [
                  0,
                  0.058823529411764705,
                  0.23529411764705882,
                  0.23529411764705882,
                  0.5882352941176471,
                  0.5882352941176471,
                  0.7647058823529411,
                  0.7647058823529411,
                  0.8823529411764706,
                  0.8823529411764706,
                  1,
                  1
                ],
                "fpr": [
                  0,
                  0,
                  0,
                  0.125,
                  0.125,
                  0.25,
                  0.25,
                  0.375,
                  0.375,
                  0.5,
                  0.5,
                  1
                ],
                "thresholds": [
                  1,
                  0.9426738619804382,
                  0.8750686049461365,
                  0.8669129014015198,
                  0.568006694316864,
                  0.5671461820602417,
                  0.4318302571773529,
                  0.35661906003952026,
                  0.215621680021286,
                  0.20779918134212494,
                  0.20379875600337982,
                  0.057830434292554855
                ]
              }
            ]
          },
          "features_importance": [
            {
              "stage": "Mean",
              "computation_type": "",
              "features": {
                "Age": 0.2788,
                "CheckingStatus": 0.0462,
                "CreditHistory": 0.0318,
                "CurrentResidenceDuration": 0.0252,
                "Dependents": 0.008,
                "EmploymentDuration": 0.0165,
                "ExistingCreditsCount": 0.0031,
                "ExistingSavings": 0.0228,
                "ForeignWorker": 0,
                "Housing": 0.0047,
                "InstallmentPercent": 0.0069,
                "InstallmentPlans": 0.0028,
                "Job": 0.009,
                "LoanAmount": 0.2862,
                "LoanDuration": 0.0696,
                "LoanPurpose": 0.0916,
                "OthersOnLoan": 0.0349,
                "OwnsProperty": 0.0368,
                "Sex": 0.0173,
                "Telephone": 0.0077
              }
            }
          ],
          "target_column": "Risk",
          "incremental_training": {},
          "prediction_type": "binary"
        }
      }
    ],
    "hybrid_pipeline_software_specs": [
      {
        "name": "autoai-kb_rt25.1-py3.12"
      }
    ],
    "training_id": "f2a01a01-0f16-4e0d-9748-895e7b795c4a",
    "data_preprocessing": [
      {
        "stage": "sampling",
        "input": {
          "rows": 249,
          "columns": 21
        },
        "output": {
          "rows": 249,
          "columns": 21
        },
        "props": {
          "type": "stratified"
        }
      },
      {
        "stage": "cleansing",
        "input": {
          "rows": 249,
          "columns": 21
        },
        "output": {
          "rows": 249,
          "columns": 21
        },
        "props": {
          "duplicated_rows_count": 0
        }
      }
    ],
    "content_import_state": "completed"
  }
}

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

Get model rev number from creation details:

In [36]:

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

List list existing revisions of the model

In [37]:

client.repository.list_models_revisions(model_id)

Out[37]:

Get details of updated model

In [38]:

print(json.dumps(client.repository.get_details(model_id), indent=2))

Out[38]:

{
  "metadata": {
    "name": "AutoAI credit-risk updated model",
    "space_id": "9c4eb218-96e8-41e0-8cd5-f783504a11ea",
    "resource_key": "73dd6496-5468-4080-ab0e-2f50aeb7cbe6",
    "id": "b78e56d5-6a90-477b-8ab8-b58d5e5ce1ed",
    "created_at": "2025-05-22T11:41:53Z",
    "commit_info": {
      "committed_at": "2025-05-22T11:41:53Z"
    },
    "rov": {
      "member_roles": {
        "1000331001": {
          "user_iam_id": "1000331001",
          "roles": [
            "OWNER"
          ]
        }
      }
    },
    "owner": "1000331001"
  },
  "entity": {
    "pipeline": {
      "id": "91cd7ec2-6bda-417e-82d1-ff8368b03952"
    },
    "software_spec": {
      "id": "8c1a58c6-62b5-4dc4-987a-df751c2756b6",
      "name": "hybrid_0.1"
    },
    "type": "wml-hybrid_0.1",
    "training_data_references": [
      {
        "type": "data_asset",
        "connection": null,
        "location": {
          "href": "/v2/assets/d414512e-a854-49c3-a8fc-cceff65dd884?space_id=9c4eb218-96e8-41e0-8cd5-f783504a11ea",
          "id": "d414512e-a854-49c3-a8fc-cceff65dd884",
          "space_id": "9c4eb218-96e8-41e0-8cd5-f783504a11ea"
        },
        "schema": {
          "id": "auto_ai_kb_input_schema",
          "fields": [
            {
              "name": "CheckingStatus",
              "type": "other",
              "nullable": false
            },
            {
              "name": "LoanDuration",
              "type": "double",
              "nullable": false
            },
            {
              "name": "CreditHistory",
              "type": "other",
              "nullable": false
            },
            {
              "name": "LoanPurpose",
              "type": "other",
              "nullable": false
            },
            {
              "name": "LoanAmount",
              "type": "double",
              "nullable": false
            },
            {
              "name": "ExistingSavings",
              "type": "other",
              "nullable": false
            },
            {
              "name": "EmploymentDuration",
              "type": "other",
              "nullable": false
            },
            {
              "name": "InstallmentPercent",
              "type": "double",
              "nullable": false
            },
            {
              "name": "Sex",
              "type": "other",
              "nullable": false
            },
            {
              "name": "OthersOnLoan",
              "type": "other",
              "nullable": false
            },
            {
              "name": "CurrentResidenceDuration",
              "type": "double",
              "nullable": false
            },
            {
              "name": "OwnsProperty",
              "type": "other",
              "nullable": false
            },
            {
              "name": "Age",
              "type": "double",
              "nullable": false
            },
            {
              "name": "InstallmentPlans",
              "type": "other",
              "nullable": false
            },
            {
              "name": "Housing",
              "type": "other",
              "nullable": false
            },
            {
              "name": "ExistingCreditsCount",
              "type": "double",
              "nullable": false
            },
            {
              "name": "Job",
              "type": "other",
              "nullable": false
            },
            {
              "name": "Dependents",
              "type": "double",
              "nullable": false
            },
            {
              "name": "Telephone",
              "type": "other",
              "nullable": false
            },
            {
              "name": "ForeignWorker",
              "type": "other",
              "nullable": false
            },
            {
              "name": "Risk",
              "type": "other",
              "nullable": false
            }
          ]
        }
      }
    ],
    "schemas": {
      "input": [
        {
          "id": "auto_ai_kb_input_schema",
          "fields": [
            {
              "name": "CheckingStatus",
              "type": "other",
              "nullable": false
            },
            {
              "name": "LoanDuration",
              "type": "double",
              "nullable": false
            },
            {
              "name": "CreditHistory",
              "type": "other",
              "nullable": false
            },
            {
              "name": "LoanPurpose",
              "type": "other",
              "nullable": false
            },
            {
              "name": "LoanAmount",
              "type": "double",
              "nullable": false
            },
            {
              "name": "ExistingSavings",
              "type": "other",
              "nullable": false
            },
            {
              "name": "EmploymentDuration",
              "type": "other",
              "nullable": false
            },
            {
              "name": "InstallmentPercent",
              "type": "double",
              "nullable": false
            },
            {
              "name": "Sex",
              "type": "other",
              "nullable": false
            },
            {
              "name": "OthersOnLoan",
              "type": "other",
              "nullable": false
            },
            {
              "name": "CurrentResidenceDuration",
              "type": "double",
              "nullable": false
            },
            {
              "name": "OwnsProperty",
              "type": "other",
              "nullable": false
            },
            {
              "name": "Age",
              "type": "double",
              "nullable": false
            },
            {
              "name": "InstallmentPlans",
              "type": "other",
              "nullable": false
            },
            {
              "name": "Housing",
              "type": "other",
              "nullable": false
            },
            {
              "name": "ExistingCreditsCount",
              "type": "double",
              "nullable": false
            },
            {
              "name": "Job",
              "type": "other",
              "nullable": false
            },
            {
              "name": "Dependents",
              "type": "double",
              "nullable": false
            },
            {
              "name": "Telephone",
              "type": "other",
              "nullable": false
            },
            {
              "name": "ForeignWorker",
              "type": "other",
              "nullable": false
            }
          ]
        }
      ],
      "output": []
    },
    "label_column": "Risk",
    "metrics": [
      {
        "timestamp": "2025-05-22T11:40:28Z",
        "ml_metrics": {
          "holdout_accuracy": 0.72,
          "holdout_average_precision": 0.5175996610541083,
          "holdout_balanced_accuracy": 0.7610294117647058,
          "holdout_f1": 0.7586206896551724,
          "holdout_neg_log_loss": -0.5151502877721112,
          "holdout_precision": 0.9166666666666666,
          "holdout_recall": 0.6470588235294118,
          "holdout_roc_auc": 0.8088235294117647,
          "training_accuracy": 0.7187987987987988,
          "training_average_precision": 0.9205829210523921,
          "training_balanced_accuracy": 0.752635046113307,
          "training_f1": 0.7674399674399673,
          "training_neg_log_loss": -0.5532545596504036,
          "training_precision": 0.9041835357624831,
          "training_recall": 0.6666666666666666,
          "training_roc_auc": 0.8273031316509577
        },
        "context": {
          "intermediate_model": {
            "name": "P1",
            "process": "pre_hpo_d_output",
            "location": {
              "pipeline": "/spaces/9c4eb218-96e8-41e0-8cd5-f783504a11ea/assets/auto_ml/auto_ml.0627b7f6-8708-4c13-b0c9-5d91455561d9/wml_data/f2a01a01-0f16-4e0d-9748-895e7b795c4a/data/automl/pre_hpo_d_output/Pipeline1/pipeline.json",
              "pipeline_model": "/spaces/9c4eb218-96e8-41e0-8cd5-f783504a11ea/assets/auto_ml/auto_ml.0627b7f6-8708-4c13-b0c9-5d91455561d9/wml_data/f2a01a01-0f16-4e0d-9748-895e7b795c4a/data/automl/pre_hpo_d_output/Pipeline1/pipeline-model.json",
              "model": "/spaces/9c4eb218-96e8-41e0-8cd5-f783504a11ea/assets/auto_ml/auto_ml.0627b7f6-8708-4c13-b0c9-5d91455561d9/wml_data/f2a01a01-0f16-4e0d-9748-895e7b795c4a/data/automl/pre_hpo_d_output/Pipeline1/model.pickle"
            },
            "schema_location": "/spaces/9c4eb218-96e8-41e0-8cd5-f783504a11ea/assets/auto_ml/auto_ml.0627b7f6-8708-4c13-b0c9-5d91455561d9/wml_data/f2a01a01-0f16-4e0d-9748-895e7b795c4a/data/automl/pre_hpo_d_output/Pipeline1/schema.json",
            "notebook_location": "/spaces/9c4eb218-96e8-41e0-8cd5-f783504a11ea/assets/auto_ml/auto_ml.0627b7f6-8708-4c13-b0c9-5d91455561d9/wml_data/f2a01a01-0f16-4e0d-9748-895e7b795c4a/data/automl/pre_hpo_d_output/Pipeline1/notebook.ipynb",
            "pipeline_nodes": [
              "PreprocessingTransformer",
              "SnapLogisticRegression"
            ],
            "composition_steps": [
              "Split_TrainingHoldout",
              "TrainingDataset_full_224_20",
              "Datetime_FE",
              "TrainingDataset_full_224_20",
              "Preprocessor_default",
              "DAUB"
            ],
            "duration": 418
          },
          "phase": "pre_hpo_d_output",
          "classes": [
            "Risk",
            "No Risk"
          ],
          "binary_classification": {
            "confusion_matrix": [
              {
                "true_class": "Risk",
                "tp": 7,
                "tn": 11,
                "fp": 6,
                "fn": 1
              },
              {
                "true_class": "No Risk",
                "tp": 11,
                "tn": 7,
                "fp": 1,
                "fn": 6
              }
            ],
            "roc_curve": [
              {
                "true_class": "Risk",
                "tpr": [
                  0,
                  0.125,
                  0.5,
                  0.5,
                  0.625,
                  0.625,
                  0.75,
                  0.75,
                  0.875,
                  0.875,
                  1,
                  1
                ],
                "fpr": [
                  0,
                  0,
                  0,
                  0.11764705882352941,
                  0.11764705882352941,
                  0.23529411764705882,
                  0.23529411764705882,
                  0.4117647058823529,
                  0.4117647058823529,
                  0.7647058823529411,
                  0.7647058823529411,
                  1
                ],
                "thresholds": [
                  1,
                  0.9421695470809937,
                  0.856395423412323,
                  0.7958160042762756,
                  0.7922008037567139,
                  0.6506691575050354,
                  0.6433809399604797,
                  0.4648997485637665,
                  0.4328538179397583,
                  0.13455311954021454,
                  0.1330871284008026,
                  0.057326167821884155
                ]
              },
              {
                "true_class": "No Risk",
                "tpr": [
                  0,
                  0.058823529411764705,
                  0.23529411764705882,
                  0.23529411764705882,
                  0.5882352941176471,
                  0.5882352941176471,
                  0.7647058823529411,
                  0.7647058823529411,
                  0.8823529411764706,
                  0.8823529411764706,
                  1,
                  1
                ],
                "fpr": [
                  0,
                  0,
                  0,
                  0.125,
                  0.125,
                  0.25,
                  0.25,
                  0.375,
                  0.375,
                  0.5,
                  0.5,
                  1
                ],
                "thresholds": [
                  1,
                  0.9426738619804382,
                  0.8750686049461365,
                  0.8669129014015198,
                  0.568006694316864,
                  0.5671461820602417,
                  0.4318302571773529,
                  0.35661906003952026,
                  0.215621680021286,
                  0.20779918134212494,
                  0.20379875600337982,
                  0.057830434292554855
                ]
              }
            ]
          },
          "features_importance": [
            {
              "stage": "Mean",
              "computation_type": "",
              "features": {
                "Age": 0.2788,
                "CheckingStatus": 0.0462,
                "CreditHistory": 0.0318,
                "CurrentResidenceDuration": 0.0252,
                "Dependents": 0.008,
                "EmploymentDuration": 0.0165,
                "ExistingCreditsCount": 0.0031,
                "ExistingSavings": 0.0228,
                "ForeignWorker": 0,
                "Housing": 0.0047,
                "InstallmentPercent": 0.0069,
                "InstallmentPlans": 0.0028,
                "Job": 0.009,
                "LoanAmount": 0.2862,
                "LoanDuration": 0.0696,
                "LoanPurpose": 0.0916,
                "OthersOnLoan": 0.0349,
                "OwnsProperty": 0.0368,
                "Sex": 0.0173,
                "Telephone": 0.0077
              }
            }
          ],
          "target_column": "Risk",
          "incremental_training": {},
          "prediction_type": "binary"
        }
      }
    ],
    "hybrid_pipeline_software_specs": [
      {
        "name": "autoai-kb_rt25.1-py3.12"
      }
    ],
    "training_id": "f2a01a01-0f16-4e0d-9748-895e7b795c4a",
    "data_preprocessing": [
      {
        "stage": "sampling",
        "input": {
          "rows": 249,
          "columns": 21
        },
        "output": {
          "rows": 249,
          "columns": 21
        },
        "props": {
          "type": "stratified"
        }
      },
      {
        "stage": "cleansing",
        "input": {
          "rows": 249,
          "columns": 21
        },
        "output": {
          "rows": 249,
          "columns": 21
        },
        "props": {
          "duplicated_rows_count": 0
        }
      }
    ],
    "content_import_state": "completed"
  }
}

6. Redeploy and score new version of the model

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

In [39]:

metadata = {
    client.deployments.ConfigurationMetaNames.ASSET: {"id": model_id, "rev": rev_id}
}

updated_deployment = client.deployments.update(deployment_id, changes=metadata)

Out[39]:

Since ASSET is patched, deployment need to be restarted. 

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

Deployment update for id: '433799b3-5756-4563-96f1-603ab2f5ff1e' started

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

updating........
ready

---------------------------------------------------------------------------------------------
Successfully finished deployment update, deployment_id='433799b3-5756-4563-96f1-603ab2f5ff1e'
---------------------------------------------------------------------------------------------

Wait for the deployment update:

In [40]:

import time

status = None
while status not in ["ready", "failed"]:
    print(".", end=" ")
    time.sleep(2)
    deployment_details = client.deployments.get_details(deployment_id)
    status = deployment_details["entity"]["status"].get("state")

print("\nDeployment update finished with status: ", status)

Out[40]:

. Note: online_url is deprecated and will be removed in a future release. Use serving_urls instead.

Deployment update finished with status:  ready

Get updated deployment details

In [41]:

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

Out[41]:

Note: online_url is deprecated and will be removed in a future release. Use serving_urls instead.
{
  "entity": {
    "asset": {
      "id": "b78e56d5-6a90-477b-8ab8-b58d5e5ce1ed",
      "rev": "2"
    },
    "chat_enabled": false,
    "custom": {},
    "deployed_asset_type": "model",
    "hybrid_pipeline_hardware_specs": [
      {
        "hardware_spec": {
          "id": "e7ed1d6c-2e89-42d7-aed5-863b972c1d2b",
          "name": "S",
          "num_nodes": 1
        },
        "node_runtime_id": "auto_ai.kb"
      }
    ],
    "name": "AutoAI credit-risk deployment",
    "online": {},
    "space_id": "9c4eb218-96e8-41e0-8cd5-f783504a11ea",
    "status": {
      "inference": [
        {
          "url": "https://cpd-cpd-instance.apps.ocpwmlautoai-x86-2-nonfips.cp.fyre.ibm.com/ml/v4/deployments/433799b3-5756-4563-96f1-603ab2f5ff1e/predictions"
        }
      ],
      "message": {
        "level": "warning",
        "text": "Successfully patched the asset."
      },
      "online_url": {
        "url": "https://cpd-cpd-instance.apps.ocpwmlautoai-x86-2-nonfips.cp.fyre.ibm.com/ml/v4/deployments/433799b3-5756-4563-96f1-603ab2f5ff1e/predictions"
      },
      "serving_urls": [
        "https://cpd-cpd-instance.apps.ocpwmlautoai-x86-2-nonfips.cp.fyre.ibm.com/ml/v4/deployments/433799b3-5756-4563-96f1-603ab2f5ff1e/predictions"
      ],
      "state": "ready"
    }
  },
  "metadata": {
    "created_at": "2025-05-22T11:41:56.099Z",
    "id": "433799b3-5756-4563-96f1-603ab2f5ff1e",
    "last_updater_id": "1000331001",
    "modified_at": "2025-05-22T11:44:52.296Z",
    "name": "AutoAI credit-risk deployment",
    "owner": "1000331001",
    "space_id": "9c4eb218-96e8-41e0-8cd5-f783504a11ea"
  },
  "system": {
    "warnings": [
      {
        "id": "Deprecated",
        "message": "online_url is deprecated and will be removed in a future release. Use serving_urls instead."
      }
    ]
  }
}

Score updated model

In [42]:

scoring_payload = {"input_data": [{"values": train_df.drop(["Risk"], axis=1).iloc[:5]}]}

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

In [43]:

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

In [44]:

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

Out[44]:

{
  "predictions": [
    {
      "fields": [
        "prediction",
        "probability"
      ],
      "values": [
        [
          "No Risk",
          [
            0.815472082175866,
            0.18452791782413402
          ]
        ],
        [
          "No Risk",
          [
            0.7501849542379176,
            0.24981504576208238
          ]
        ],
        [
          "Risk",
          [
            0.44323551396938976,
            0.5567644860306102
          ]
        ],
        [
          "No Risk",
          [
            0.7860837153311935,
            0.2139162846688065
          ]
        ],
        [
          "Risk",
          [
            0.10388810002019544,
            0.8961118999798046
          ]
        ]
      ]
    }
  ]
}

7. 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.

8. Summary and next steps

You successfully completed this notebook!

Check out our Online Documentation for more samples, tutorials, documentation, how-tos, and blog posts.

Authors

Jan Sołtysik, Intern at watsonx.ai

Rafał Chrzanowski, Software Engineer Intern at watsonx.ai.

Use AutoAI and AI lifecycle to predict credit risk with `ibm-watsonx-ai`

Learning goals

Contents

1. Set up the environment

Install dependencies

Define credentials

Create `APIClient` instance

Working with spaces

2. Optimizer definition

Training data connection

Optimizer configuration

3. Experiment run

Load trained model

Reading training data from COS

4. Persist and Deploy trained AutoAI model

Online deployment creation

Scoring of webservice

Deleting deployment

5. Refine and persist new version of the model

Pipeline refinement with Lale

Pipeline decomposition and new definition

New optimizer `Hyperopt` configuration and training

Save newly refined pipeline

Publish new version of the model

Download current version of the model

Create archive containing updated model

Save the current model version

Update the model

Save new model revision of the updated model

List list existing revisions of the model

Get details of updated model

6. Redeploy and score new version of the model

Get updated deployment details

Score updated model

7. Clean up

8. Summary and next steps

Authors

Product

Resources

Company

Use AutoAI and AI lifecycle to predict credit risk with ibm-watsonx-ai

Learning goals

Contents

1. Set up the environment

Install dependencies

Define credentials

Create APIClient instance

Working with spaces

2. Optimizer definition

Training data connection

Optimizer configuration

3. Experiment run

Load trained model

Reading training data from COS

4. Persist and Deploy trained AutoAI model

Online deployment creation

Scoring of webservice

Deleting deployment

5. Refine and persist new version of the model

Pipeline refinement with Lale

Pipeline decomposition and new definition

New optimizer Hyperopt configuration and training

Save newly refined pipeline

Publish new version of the model

Download current version of the model

Create archive containing updated model

Save the current model version

Update the model

Save new model revision of the updated model

List list existing revisions of the model

Get details of updated model

6. Redeploy and score new version of the model

Get updated deployment details

Score updated model

7. Clean up

8. Summary and next steps

Authors

Use AutoAI and AI lifecycle to predict credit risk with `ibm-watsonx-ai`

Create `APIClient` instance

New optimizer `Hyperopt` configuration and training