Skip to content

Commit 79221a7

Browse files
Juliana-MoraisJuliana-Morais
committed
new tutorials
1 parent 281498a commit 79221a7

56 files changed

Lines changed: 686 additions & 0 deletions

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

‎tutorials/cp-aibus-dar-swagger-soc-model/cp-aibus-dar-swagger-soc-model.md‎

Lines changed: 131 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,131 @@
1+
---
2+
parser: v2
3+
auto_validation: true
4+
time: 15
5+
tags: [tutorial>beginner, topic>machine-learning, topic>artificial-intelligence, topic>cloud, software-product>sap-business-technology-platform, software-product>sap-ai-business-services, software-product>data-attribute-recommendation, tutorial>free-tier]
6+
primary_tag: topic>machine-learning
7+
author_name: Juliana Morais
8+
author_profile: https://github.com/Juliana-Morais
9+
---
10+
11+
# Use the Sales Order Completion (SOC) Business Blueprint to Train a Machine Learning Model
12+
<!-- description --> Train a machine learning model for the Data Attribute Recommendation service, using the Sales Order Completion (SOC) business blueprint.
13+
14+
## You will learn
15+
- How to train a machine learning model using the Sales Order Completion (SOC) business blueprint
16+
- How to deploy a machine learning model to get predictions for missing fields in sales order documents
17+
18+
---
19+
20+
### Authorize Swagger UI
21+
22+
23+
In the service key you created for Data Attribute Recommendation in the previous tutorial: [Use Free Tier to Set Up Account for Data Attribute Recommendation and Get Service Key](cp-aibus-dar-booster-free-key) or [Use Trial to Set Up Account for Data Attribute Recommendation and Get Service Key](cp-aibus-dar-booster-key), you find a section called `swagger` (as highlighted in the image below) with three entries, called `dm` (data manager), `mm` (model manager) and `inference`.
24+
25+
<!-- border -->![Service Key](service-key-details.png)
26+
27+
For this tutorial, copy the URL of the Swagger UI for `mm` and open it in a browser tab. The Swagger UI for the model manager allows you to train a machine learning model, to delete it, to deploy the model as well as to `undeploy` the model.
28+
29+
>After finishing this tutorial, keep the Swagger UI for `mm` open to perform the clean up tasks in [Use the Sales Order Completion (SOC) Business Blueprint to Predict Missing Sales Order Fields](cp-aibus-dar-swagger-soc-predict).
30+
31+
1. To be able to use the Swagger UI endpoints, you need to authorize yourself. In the top right corner, click **Authorize**.
32+
33+
<!-- border -->![Authorize](swagger-authorize.png)
34+
35+
2. Get the `access_token` value created in the previous tutorial: [Get OAuth Access Token for Data Attribute Recommendation Using Any Web Browser](cp-aibus-dar-web-oauth-token), then add **Bearer** (with capitalized "B") in front of it, and enter in the **Value** field.
36+
37+
```
38+
Bearer <access_token>
39+
```
40+
41+
3. Click **Authorize** and then click **Close**.
42+
43+
<!-- border -->![Authorize](swagger-token.png)
44+
45+
46+
47+
### Create a training job
48+
49+
50+
To train a machine learning model using the data that you uploaded in [Use a Sales Order Completion (SOC) Dataset Schema to Upload Training Data to Data Attribute Recommendation](cp-aibus-dar-swagger-soc-upload), you create a training job.
51+
52+
With each training job you provide a model template or a business blueprint which combines data processing rules and machine learning model architecture. You can find the list of available model templates [here](https://help.sap.com/docs/Data_Attribute_Recommendation/105bcfd88921418e8c29b24a7a402ec3/1e76e8c636974a06967552c05d40e066.html), and the list of available business blueprints [here](https://help.sap.com/docs/Data_Attribute_Recommendation/105bcfd88921418e8c29b24a7a402ec3/091eace025e14793be0e83ef2109b349.html).
53+
54+
The Sales Order Completion (SOC) business blueprint that you use in this tutorial is suited to predict missing sales order fields that are needed for completion.
55+
56+
To create the training job, proceed as follows:
57+
58+
1. Expand the endpoint **POST /jobs** by clicking on it. Then click **Try it out**.
59+
60+
<!-- border -->![Training Job Endpoint](job-endpoint.png)
61+
62+
2. In the text area, replace the parameter value for `datasetId` with the `id` of your dataset that you have created in [Use a Sales Order Completion (SOC) Dataset Schema to Upload Training Data to Data Attribute Recommendation](cp-aibus-dar-swagger-soc-upload). Delete the `modelTemplateId` line from the **Request body**. Replace the parameter value `modelName` with your model name, `soc_tutorial_model`, for example. Make sure the parameter value for `businessBlueprintId` is `9d15125d-2b7b-4136-8872-1ddd337cf36f`, which is the ID of the SOC business blueprint. Click **Execute** to create the training job.
63+
64+
<!-- border -->![Training Job Execute](job-execute.png)
65+
66+
3. In the response of the service, you find the `id` of your training job. Copy the `id` as you'll need it in the next step. Along side the `id`, you find the training job's current status. Initially, the status is `PENDING` which says that the training job is in queue but has not started yet.
67+
68+
<!-- border -->![Training Job Response](job-response.png)
69+
70+
You have successfully created a training job.
71+
72+
73+
74+
### Check training job status
75+
76+
77+
To know when your training job has ended, you have to frequently check its status. For that, proceed as follows:
78+
79+
1. Expand the endpoint `GET /jobs/{jobId}` by clicking on it. Then click **Try it out**.
80+
81+
<!-- border -->![Training Job Status Endpoint](job-status-endpoint.png)
82+
83+
2. Fill the parameter `jobId` with `id` of your training job that you copied in the previous step. Click **Execute**.
84+
85+
<!-- border -->![Training Job Status Execute](job-status-execute.png)
86+
87+
3. In the response, you find again the current status of your training job along with other details. Immediately after creation of the training job, the status is `PENDING`. Shortly after, it changes to `RUNNING` which means that the model is being trained. The training of the sample data usually takes about 5 minutes to complete but may run longer, up to a few hours due to limited availability of resources in the free tier environment. You can check the status every now and then. Once training is finished, the status changes to `SUCCEEDED` which means the service has created a machine learning model and you can proceed.
88+
89+
<!-- border -->![Training Job Status Response](job-status-response.png)
90+
91+
You have successfully trained a machine learning model.
92+
93+
94+
95+
### Deploy machine learning model
96+
97+
98+
To use the trained model, you need to deploy it. Once deployed, the model is ready to make predictions. To deploy your model, proceed as follows:
99+
100+
1. Expand the endpoint `POST /deployments` by clicking on it. Then click **Try it out**.
101+
102+
<!-- border -->![Deployment Endpoint](deploy-endpoint.png)
103+
104+
2. In the text area, replace the parameter `modelName` with the name of your model (`soc_tutorial_model`). Click **Execute** to deploy the model.
105+
106+
<!-- border -->![Deployment Execute](deploy-execute.png)
107+
108+
3. In the response of the service, you find the `id` of the deployment and its status. Initially, the status is `PENDING`, indicating the deployment is in progress. Make sure to copy the `id` as you need it in the next step.
109+
110+
<!-- border -->![Deployment Response](deploy-response.png)
111+
112+
113+
114+
### Check deployment status
115+
116+
117+
Finally, you have to ensure that your model is deployed successfully in order to use it for predictions. To check the status of your deployment, proceed as follows:
118+
119+
1. Expand the endpoint `GET /deployments/{id}` by clicking on it. Then click **Try it out**.
120+
121+
<!-- border -->![Deployment Status Endpoint](deploy-status-endpoint.png)
122+
123+
2. Fill the parameter `deploymentId` with the `id` of your deployment that you copied in the previous step. Click **Execute**.
124+
125+
<!-- border -->![Deployment Status Execute](deploy-status-execute.png)
126+
127+
3. In the response of the service, you find the current status of the deployment. If the status is `SUCCEEDED`, your deployment is done. If the status is still `PENDING`, check back in a few minutes.
128+
129+
<!-- border -->![Deployment Status Execute](deploy-status-response.png)
130+
131+
You have successfully trained a machine learning model and deployed it. Next, you'll use your model to make predictions.

‎tutorials/cp-aibus-dar-swagger-soc-model/deploy-endpoint.png‎

28.3 KB
Loading

‎tutorials/cp-aibus-dar-swagger-soc-model/deploy-execute.png‎

25.9 KB
Loading

‎tutorials/cp-aibus-dar-swagger-soc-model/deploy-response.png‎

32 KB
Loading

‎tutorials/cp-aibus-dar-swagger-soc-model/deploy-status-endpoint.png‎

28.3 KB
Loading

‎tutorials/cp-aibus-dar-swagger-soc-model/deploy-status-execute.png‎

19.6 KB
Loading

‎tutorials/cp-aibus-dar-swagger-soc-model/deploy-status-response.png‎

38.1 KB
Loading

‎tutorials/cp-aibus-dar-swagger-soc-model/job-endpoint.png‎

41.1 KB
Loading

‎tutorials/cp-aibus-dar-swagger-soc-model/job-execute.png‎

28.8 KB
Loading

‎tutorials/cp-aibus-dar-swagger-soc-model/job-response.png‎

45.3 KB
Loading

0 commit comments

Comments
 (0)