Use custom software spec to create statsmodels function.ipynb

Kernel: watsonx-ai-samples-py-312

Use custom software specification to create statsmodels function describing data with ibm-watsonx-ai

This notebook demonstrates how to deploy in watsonx.ai Runtime service as Python function with statsmodel, which requires creation of custom software specification using requirements.txt file with all required libraries.

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

Learning goals

The learning goals of this notebook are:

• Working with the watsonx.ai instance

• Creating custom software specification

• Online deployment of python function

• Scoring data using deployed function

Contents

This notebook contains the following parts:

1. Setup

2. Function creation

3. Function upload

4. Web service creation

5. Scoring

6. Clean up

7. Summary and next steps

1. Set up the environment

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

• Contact with your IBM Cloud Pak® for Data administrator and ask them for your account credentials

Install dependencies

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

%pip install wget | tail -n 1
%pip install -U ibm-watsonx-ai | tail -n 1
%pip install statsmodels | tail -n 1

Successfully installed wget-3.2
Successfully installed anyio-4.11.0 cachetools-6.2.2 certifi-2025.11.12 charset_normalizer-3.4.4 h11-0.16.0 httpcore-1.0.9 httpx-0.28.1 ibm-cos-sdk-2.14.3 ibm-cos-sdk-core-2.14.3 ibm-cos-sdk-s3transfer-2.14.3 ibm-watsonx-ai-1.4.6 idna-3.11 jmespath-1.0.1 lomond-0.3.3 numpy-2.3.5 pandas-2.2.3 pytz-2025.2 requests-2.32.5 sniffio-1.3.1 tabulate-0.9.0 typing_extensions-4.15.0 tzdata-2025.2 urllib3-2.5.0
Successfully installed patsy-1.0.2 scipy-1.16.3 statsmodels-0.14.5

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.

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

Use the admin's api_key to authenticate WML services:

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="5.3",
)

Alternatively you can use the admin's password:

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="5.3",
    )

Create APIClient instance

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

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 watsonx.ai, you need to set space which you will be using.

client.set.default_space(space_id)

'SUCCESS'

2. Create function

In this section you will learn how to create deployable function with statsmodels module calculating describition of a given data.

Create deployable callable which uses statsmodels library

def deployable_callable():
    """
    Deployable python function with score
    function implemented.
    """

    try:
        from statsmodels.stats.descriptivestats import describe
    except ModuleNotFoundError as e:
        print(f"statsmodels not installed: {str(e)}")
        raise

    def score(payload):
        """
        Score method.
        """
        try:
            data = payload["input_data"][0]["values"]
            return {"predictions": [{"values": str(describe(data))}]}
        except Exception as e:
            return {"predictions": [{"values": [repr(e)]}]}

    return score

Test callable locally

import numpy as np

score_function = deployable_callable()

data = np.random.randn(10, 10)
data_description = score_function({"input_data": [{"values": data}]})

print(data_description["predictions"][0]["values"])

                          0          1          2          3           4  \
nobs              10.000000  10.000000  10.000000  10.000000   10.000000   
missing            0.000000   0.000000   0.000000   0.000000    0.000000   
mean              -0.083638  -0.050098   0.020492  -0.142479   -0.002989   
std_err            0.269590   0.381256   0.295694   0.313932    0.305275   
upper_ci           0.444749   0.697151   0.600042   0.472816    0.595338   
lower_ci          -0.612025  -0.797346  -0.559058  -0.757775   -0.601316   
std                0.852519   1.205638   0.935067   0.992740    0.965363   
iqr                0.575500   1.694432   0.951992   1.475172    1.699130   
iqr_normal         0.426619   1.256085   0.705713   1.093546    1.259567   
mad                0.608134   0.941202   0.692788   0.776608    0.827567   
mad_normal         0.762183   1.179622   0.868282   0.973334    1.037201   
coef_var         -10.192989 -24.065722  45.631417  -6.967606 -322.943959   
range              2.564929   3.309147   3.047444   3.203102    2.596324   
max                1.667413   1.370861   1.661702   1.484946    1.218249   
min               -0.897516  -1.938286  -1.385742  -1.718156   -1.378075   
skew               1.189520  -0.406203   0.332216   0.057278   -0.287005   
kurtosis           3.032307   1.922372   2.333173   2.082519    1.543272   
jarque_bera        2.358698   0.758869   0.369220   0.356206    1.021476   
jarque_bera_pval   0.307479   0.684248   0.831428   0.836856    0.600052   
mode              -0.897516  -1.938286  -1.385742  -1.718156   -1.378075   
mode_freq          0.100000   0.100000   0.100000   0.100000    0.100000   
median            -0.263502   0.080095  -0.096555  -0.189843    0.160358   
1%                -0.881626  -1.929054  -1.348652  -1.664221   -1.363925   
5%                -0.818066  -1.892126  -1.200291  -1.448478   -1.307328   
10%               -0.738617  -1.845966  -1.014841  -1.178800   -1.236582   
25%               -0.675339  -0.757138  -0.491718  -0.877516   -0.891532   
50%               -0.263502   0.080095  -0.096555  -0.189843    0.160358   
75%               -0.099839   0.937295   0.460274   0.597656    0.807599   
90%                1.249221   1.322948   1.262937   0.922722    0.903711   
95%                1.458317   1.346905   1.462319   1.203834    1.060980   
99%                1.625594   1.366070   1.621825   1.428723    1.186795   

                          5          6          7          8          9  
nobs              10.000000  10.000000  10.000000  10.000000  10.000000  
missing            0.000000   0.000000   0.000000   0.000000   0.000000  
mean              -0.366604   0.155053  -0.260099   0.558822  -0.097734  
std_err            0.212456   0.176030   0.430871   0.296286   0.248851  
upper_ci           0.049802   0.500064   0.584392   1.139532   0.390004  
lower_ci          -0.783011  -0.189959  -1.104591  -0.021889  -0.585473  
std                0.671845   0.556654   1.362534   0.936940   0.786935  
iqr                0.464245   0.981761   1.597027   1.427654   1.142442  
iqr_normal         0.344145   0.727781   1.183878   1.058322   0.846893  
mad                0.456036   0.476937   1.084414   0.810962   0.650101  
mad_normal         0.571557   0.597752   1.359111   1.016390   0.814780  
coef_var          -1.832616   3.590094  -5.238514   1.676634  -8.051780  
range              2.402212   1.590744   4.183076   2.675908   2.230299  
max                1.145256   0.904397   1.783463   2.083895   0.834640  
min               -1.256956  -0.686348  -2.399613  -0.592013  -1.395658  
skew               0.946186  -0.105337  -0.089132   0.152338  -0.243300  
kurtosis           3.766786   1.558013   2.000850   1.673272   1.785632  
jarque_bera        1.737098   0.884879   0.429200   0.772097   0.713113  
jarque_bera_pval   0.419560   0.642467   0.806864   0.679738   0.700083  
mode              -1.256956  -0.686348  -2.399613  -0.592013  -1.395658  
mode_freq          0.100000   0.100000   0.100000   0.100000   0.100000  
median            -0.460046   0.169624   0.008150   0.668493  -0.151084  
1%                -1.242689  -0.661584  -2.355526  -0.584597  -1.363861  
5%                -1.185619  -0.562530  -2.179177  -0.554932  -1.236671  
10%               -1.114282  -0.438712  -1.958742  -0.517851  -1.077683  
25%               -0.651555  -0.327994  -1.222621  -0.282464  -0.536062  
50%               -0.460046   0.169624   0.008150   0.668493  -0.151084  
75%               -0.187310   0.653767   0.374406   1.145190   0.606380  
90%                0.231835   0.714157   1.465882   1.576343   0.802512  
95%                0.688545   0.809277   1.624673   1.830119   0.818576  
99%                1.053914   0.885373   1.751705   2.033140   0.831428  

3. Upload Python function

In this section you will learn how to upload the Python function to watsonx.ai.

Custom software_specification

Create new software specification based on runtime-25.1-py3.12.

requirements_txt_content = "statsmodels==0.14.4"

with open("requirements.txt", "w") as file:
    file.write(requirements_txt_content)

base_sw_spec_id = client.software_specifications.get_id_by_name("runtime-25.1-py3.12")

The requirements.txt file describes details of package extension. Now you need to store new package extension using APIClient.

meta_prop_pkg_extn = {
    client.package_extensions.ConfigurationMetaNames.NAME: "statsmodels env",
    client.package_extensions.ConfigurationMetaNames.DESCRIPTION: "Environment with statsmodels",
    client.package_extensions.ConfigurationMetaNames.TYPE: "requirements_txt",
}

pkg_extn_details = client.package_extensions.store(
    meta_props=meta_prop_pkg_extn, file_path="requirements.txt"
)
pkg_extn_id = client.package_extensions.get_id(pkg_extn_details)
pkg_extn_url = client.package_extensions.get_href(pkg_extn_details)

Creating package extension
SUCCESS

Create new software specification and add created package extention to it.

meta_prop_sw_spec = {
    client.software_specifications.ConfigurationMetaNames.NAME: "statsmodels software_spec",
    client.software_specifications.ConfigurationMetaNames.DESCRIPTION: "Software specification for statsmodels",
    client.software_specifications.ConfigurationMetaNames.BASE_SOFTWARE_SPECIFICATION: {
        "guid": base_sw_spec_id
    },
}

sw_spec_details = client.software_specifications.store(meta_props=meta_prop_sw_spec)
sw_spec_id = client.software_specifications.get_id(sw_spec_details)

client.software_specifications.add_package_extension(sw_spec_id, pkg_extn_id)

SUCCESS

'SUCCESS'

Get the details of created software specification

import json

print(json.dumps(client.software_specifications.get_details(sw_spec_id), indent=2))

{
  "metadata": {
    "name": "statsmodels software_spec",
    "asset_id": "78f46fe3-81f0-4ab9-a4b8-351694cb9652",
    "href": "/v2/software_specifications/78f46fe3-81f0-4ab9-a4b8-351694cb9652",
    "asset_type": "software_specification",
    "created_at": "2025-11-19T07:43:37Z",
    "life_cycle": {
      "since_version": "5.2.0"
    }
  },
  "entity": {
    "software_specification": {
      "type": "derived",
      "display_name": "statsmodels software_spec",
      "package_extensions": [
        {
          "metadata": {
            "space_id": "e4509fba-55db-48c5-94a6-08c399762bf2",
            "usage": {
              "last_updated_at": "2025-11-19T07:43:31Z",
              "last_updater_id": "1000331001",
              "last_update_time": 1763538211266,
              "last_accessed_at": "2025-11-19T07:43:31Z",
              "last_access_time": 1763538211266,
              "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,
            "is_primary_attachment_downloadable": true,
            "name": "statsmodels env",
            "description": "Environment with statsmodels",
            "tags": [
              "dsx"
            ],
            "asset_type": "package_extension",
            "origin_country": "us",
            "rating": 0,
            "total_ratings": 0,
            "catalog_id": "4e9e58b2-20cf-4108-91a3-fdafc7a65be7",
            "created": 1763538209913,
            "created_at": "2025-11-19T07:43:29Z",
            "owner_id": "1000331001",
            "size": 19,
            "version": 0,
            "asset_state": "available",
            "asset_attributes": [
              "package_extension"
            ],
            "asset_id": "f4dc15e2-f2f1-4cf5-9dc0-ae8b022c8763",
            "asset_category": "USER",
            "creator_id": "1000331001",
            "is_branched": true
          },
          "entity": {
            "package_extension": {
              "type": "requirements_txt",
              "object_key": "package_extension/statsmodels_env_UnwJk1lKT.txt",
              "interpreter": "pip"
            }
          }
        }
      ],
      "base_software_specification": {
        "guid": "f47ae1c3-198e-5718-b59d-2ea471561e9e",
        "href": "/v2/software_specifications/f47ae1c3-198e-5718-b59d-2ea471561e9e"
      },
      "software_configuration": {
        "included_packages": [
          {
            "name": "autoai_libs",
            "version": "3.0.6",
            "type": "pip"
          },
          {
            "name": "autoai_ts_libs",
            "version": "5.0.5",
            "type": "pip"
          },
          {
            "name": "beautifulsoup4",
            "version": "4.13.3",
            "type": "pip"
          },
          {
            "name": "bokeh",
            "version": "3.7.2",
            "type": "pip"
          },
          {
            "name": "caikit",
            "version": "0.28.1",
            "type": "pip"
          },
          {
            "name": "cplex",
            "version": "22.1.2.0",
            "type": "pip"
          },
          {
            "name": "docplex",
            "version": "2.30.251",
            "type": "pip"
          },
          {
            "name": "ffmpeg",
            "version": "7.1+ibmpyeco",
            "type": "pip"
          },
          {
            "name": "ibm-watson-openscale",
            "version": "3.1.2",
            "type": "pip"
          },
          {
            "name": "ibm_watsonx_ai",
            "version": "1.4.5",
            "type": "pip"
          },
          {
            "name": "ipywidgets",
            "version": "8.1.5",
            "type": "pip"
          },
          {
            "name": "keras",
            "version": "3.12.0",
            "type": "pip"
          },
          {
            "name": "lale",
            "version": "0.9.0",
            "type": "pip"
          },
          {
            "name": "lightgbm",
            "version": "4.5.0+ibmpyeco.1",
            "type": "pip"
          },
          {
            "name": "lightning",
            "version": "2.5.1.post0",
            "type": "pip"
          },
          {
            "name": "lightning-utilities",
            "version": "0.14.3",
            "type": "pip"
          },
          {
            "name": "lxml",
            "version": "5.4.0",
            "type": "pip"
          },
          {
            "name": "matplotlib",
            "version": "3.10.1",
            "type": "pip"
          },
          {
            "name": "networkx",
            "version": "3.4.2",
            "type": "pip"
          },
          {
            "name": "numpy",
            "version": "2.0.2",
            "type": "pip"
          },
          {
            "name": "onnx",
            "version": "1.17.0",
            "type": "pip"
          },
          {
            "name": "onnxconverter-common",
            "version": "1.14.0+ibmpyeco",
            "type": "pip"
          },
          {
            "name": "onnxruntime",
            "version": "1.21.0",
            "type": "pip"
          },
          {
            "name": "opencv-python-headless",
            "version": "4.10.0.84",
            "type": "pip"
          },
          {
            "name": "openpyxl",
            "version": "3.1.5",
            "type": "pip"
          },
          {
            "name": "pandas",
            "version": "2.2.3",
            "type": "pip"
          },
          {
            "name": "pillow",
            "version": "11.1.0",
            "type": "pip"
          },
          {
            "name": "plotly",
            "version": "6.0.1",
            "type": "pip"
          },
          {
            "name": "py4j",
            "version": "0.10.9.9",
            "type": "pip"
          },
          {
            "name": "pyarrow",
            "version": "19.0.0",
            "type": "pip"
          },
          {
            "name": "pyjnius",
            "version": "1.6.1",
            "type": "pip"
          },
          {
            "name": "pytorch-lightning",
            "version": "2.5.0.post0",
            "type": "pip"
          },
          {
            "name": "pyviz_comms",
            "version": "3.0.6",
            "type": "pip"
          },
          {
            "name": "scikit-image",
            "version": "0.25.2",
            "type": "pip"
          },
          {
            "name": "scikit-learn",
            "version": "1.6.1",
            "type": "pip"
          },
          {
            "name": "scipy",
            "version": "1.15.2",
            "type": "pip"
          },
          {
            "name": "seaborn",
            "version": "0.13.2",
            "type": "pip"
          },
          {
            "name": "sentencepiece",
            "version": "0.2.0",
            "type": "pip"
          },
          {
            "name": "skl2onnx",
            "version": "1.18.0",
            "type": "pip"
          },
          {
            "name": "snapml",
            "version": "1.16.2",
            "type": "pip"
          },
          {
            "name": "sparkmagic",
            "version": "0.23.0",
            "type": "pip"
          },
          {
            "name": "statsmodels",
            "version": "0.14.4",
            "type": "pip"
          },
          {
            "name": "sympy",
            "version": "1.13.1",
            "type": "pip"
          },
          {
            "name": "tensorflow_cpu",
            "version": "2.18.1",
            "type": "pip"
          },
          {
            "name": "tensorflow-datasets",
            "version": "4.9.7+ibmpyeco",
            "type": "pip"
          },
          {
            "name": "tensorflow-hub",
            "version": "0.16.1",
            "type": "pip"
          },
          {
            "name": "tensorflow-metadata",
            "version": "1.16.1+ibmpyeco",
            "type": "pip"
          },
          {
            "name": "tensorflow-model-optimization",
            "version": "0.8.0+ibmpyeco",
            "type": "pip"
          },
          {
            "name": "tensorflow-probability",
            "version": "0.25.0",
            "type": "pip"
          },
          {
            "name": "tensorflow-text",
            "version": "2.18.1",
            "type": "pip"
          },
          {
            "name": "tf_keras",
            "version": "2.18.0",
            "type": "pip"
          },
          {
            "name": "tf2onnx",
            "version": "1.16.1+ibmpyeco",
            "type": "pip"
          },
          {
            "name": "tokenizers",
            "version": "0.21.0",
            "type": "pip"
          },
          {
            "name": "torch",
            "version": "2.6.0+ibmpyeco",
            "type": "pip"
          },
          {
            "name": "torchdata",
            "version": "0.9.0+cpu",
            "type": "pip"
          },
          {
            "name": "torchmetrics",
            "version": "1.7.0",
            "type": "pip"
          },
          {
            "name": "torchvision",
            "version": "0.21.0+ibmpyeco",
            "type": "pip"
          },
          {
            "name": "transformers",
            "version": "4.52.4",
            "type": "pip"
          },
          {
            "name": "watson-nlp",
            "version": "5.10.2",
            "type": "pip"
          },
          {
            "name": "xgboost-cpu",
            "version": "2.1.4",
            "type": "pip"
          },
          {
            "name": "xlrd",
            "version": "2.0.1",
            "type": "pip"
          }
        ],
        "platform": {
          "name": "python",
          "version": "3.12",
          "facilities": [
            "pyvenv"
          ]
        }
      }
    }
  }
}

Store the function

meta_props = {
    client.repository.FunctionMetaNames.NAME: "statsmodels function",
    client.repository.FunctionMetaNames.SOFTWARE_SPEC_ID: sw_spec_id,
}

function_details = client.repository.store_function(
    meta_props=meta_props, function=deployable_callable
)
function_id = client.repository.get_function_id(function_details)

Get function details

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

{
  "metadata": {
    "name": "statsmodels function",
    "space_id": "e4509fba-55db-48c5-94a6-08c399762bf2",
    "resource_key": "907bb544-05d3-4901-8268-4bf3cd92d0b2",
    "id": "d937e9be-22b7-4e0d-a0f4-d37f3b26b7bb",
    "created_at": "2025-11-19T07:44:04Z",
    "rov": {
      "member_roles": {
        "1000331001": {
          "user_iam_id": "1000331001",
          "roles": [
            "OWNER"
          ]
        }
      }
    },
    "owner": "1000331001"
  },
  "entity": {
    "software_spec": {
      "id": "78f46fe3-81f0-4ab9-a4b8-351694cb9652"
    },
    "type": "python"
  }
}

Note: You can see that function is successfully stored in watsonx.ai Runtime service.

client.repository.list_functions()

4. Create online deployment

You can use commands bellow to create online deployment for stored function (web service).

Create online deployment of a Python function

metadata = {
    client.deployments.ConfigurationMetaNames.NAME: "Deployment of statsmodels function",
    client.deployments.ConfigurationMetaNames.ONLINE: {},
}

function_deployment = client.deployments.create(function_id, meta_props=metadata)

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

Synchronous deployment creation for id: 'd937e9be-22b7-4e0d-a0f4-d37f3b26b7bb' 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='fd2b8062-fb20-4313-82b0-9f0d60d63bbc'
-----------------------------------------------------------------------------------------------

client.deployments.list()

Get deployment id.

deployment_id = client.deployments.get_id(function_deployment)
deployment_id

'fd2b8062-fb20-4313-82b0-9f0d60d63bbc'

5. Scoring

You can send new scoring records to web-service deployment using score method.

scoring_payload = {"input_data": [{"values": data}]}

predictions = client.deployments.score(deployment_id, scoring_payload)
print(data_description["predictions"][0]["values"])

                          0          1          2          3           4  \
nobs              10.000000  10.000000  10.000000  10.000000   10.000000   
missing            0.000000   0.000000   0.000000   0.000000    0.000000   
mean              -0.083638  -0.050098   0.020492  -0.142479   -0.002989   
std_err            0.269590   0.381256   0.295694   0.313932    0.305275   
upper_ci           0.444749   0.697151   0.600042   0.472816    0.595338   
lower_ci          -0.612025  -0.797346  -0.559058  -0.757775   -0.601316   
std                0.852519   1.205638   0.935067   0.992740    0.965363   
iqr                0.575500   1.694432   0.951992   1.475172    1.699130   
iqr_normal         0.426619   1.256085   0.705713   1.093546    1.259567   
mad                0.608134   0.941202   0.692788   0.776608    0.827567   
mad_normal         0.762183   1.179622   0.868282   0.973334    1.037201   
coef_var         -10.192989 -24.065722  45.631417  -6.967606 -322.943959   
range              2.564929   3.309147   3.047444   3.203102    2.596324   
max                1.667413   1.370861   1.661702   1.484946    1.218249   
min               -0.897516  -1.938286  -1.385742  -1.718156   -1.378075   
skew               1.189520  -0.406203   0.332216   0.057278   -0.287005   
kurtosis           3.032307   1.922372   2.333173   2.082519    1.543272   
jarque_bera        2.358698   0.758869   0.369220   0.356206    1.021476   
jarque_bera_pval   0.307479   0.684248   0.831428   0.836856    0.600052   
mode              -0.897516  -1.938286  -1.385742  -1.718156   -1.378075   
mode_freq          0.100000   0.100000   0.100000   0.100000    0.100000   
median            -0.263502   0.080095  -0.096555  -0.189843    0.160358   
1%                -0.881626  -1.929054  -1.348652  -1.664221   -1.363925   
5%                -0.818066  -1.892126  -1.200291  -1.448478   -1.307328   
10%               -0.738617  -1.845966  -1.014841  -1.178800   -1.236582   
25%               -0.675339  -0.757138  -0.491718  -0.877516   -0.891532   
50%               -0.263502   0.080095  -0.096555  -0.189843    0.160358   
75%               -0.099839   0.937295   0.460274   0.597656    0.807599   
90%                1.249221   1.322948   1.262937   0.922722    0.903711   
95%                1.458317   1.346905   1.462319   1.203834    1.060980   
99%                1.625594   1.366070   1.621825   1.428723    1.186795   

                          5          6          7          8          9  
nobs              10.000000  10.000000  10.000000  10.000000  10.000000  
missing            0.000000   0.000000   0.000000   0.000000   0.000000  
mean              -0.366604   0.155053  -0.260099   0.558822  -0.097734  
std_err            0.212456   0.176030   0.430871   0.296286   0.248851  
upper_ci           0.049802   0.500064   0.584392   1.139532   0.390004  
lower_ci          -0.783011  -0.189959  -1.104591  -0.021889  -0.585473  
std                0.671845   0.556654   1.362534   0.936940   0.786935  
iqr                0.464245   0.981761   1.597027   1.427654   1.142442  
iqr_normal         0.344145   0.727781   1.183878   1.058322   0.846893  
mad                0.456036   0.476937   1.084414   0.810962   0.650101  
mad_normal         0.571557   0.597752   1.359111   1.016390   0.814780  
coef_var          -1.832616   3.590094  -5.238514   1.676634  -8.051780  
range              2.402212   1.590744   4.183076   2.675908   2.230299  
max                1.145256   0.904397   1.783463   2.083895   0.834640  
min               -1.256956  -0.686348  -2.399613  -0.592013  -1.395658  
skew               0.946186  -0.105337  -0.089132   0.152338  -0.243300  
kurtosis           3.766786   1.558013   2.000850   1.673272   1.785632  
jarque_bera        1.737098   0.884879   0.429200   0.772097   0.713113  
jarque_bera_pval   0.419560   0.642467   0.806864   0.679738   0.700083  
mode              -1.256956  -0.686348  -2.399613  -0.592013  -1.395658  
mode_freq          0.100000   0.100000   0.100000   0.100000   0.100000  
median            -0.460046   0.169624   0.008150   0.668493  -0.151084  
1%                -1.242689  -0.661584  -2.355526  -0.584597  -1.363861  
5%                -1.185619  -0.562530  -2.179177  -0.554932  -1.236671  
10%               -1.114282  -0.438712  -1.958742  -0.517851  -1.077683  
25%               -0.651555  -0.327994  -1.222621  -0.282464  -0.536062  
50%               -0.460046   0.169624   0.008150   0.668493  -0.151084  
75%               -0.187310   0.653767   0.374406   1.145190   0.606380  
90%                0.231835   0.714157   1.465882   1.576343   0.802512  
95%                0.688545   0.809277   1.624673   1.830119   0.818576  
99%                1.053914   0.885373   1.751705   2.033140   0.831428  

6. 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.

7. Summary and next steps

You successfully completed this notebook! You learned how to use watsonx.ai for function deployment and scoring with custom software_spec.

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

Authors

Jan Sołtysik, Software Engineer Intern at watsonx.ai.

Rafał Chrzanowski, Software Engineer Intern at watsonx.ai.

Copyright © 2020-2026 IBM. This notebook and its source code are released under the terms of the MIT License.