# Monitoring models with OpenScale (Notebook) There are several ways of configuring Watson OpenScale to monitor machine learning deployments, including the automatic configuration, using the GUI tool, a more manual configuration using the APIs, and some combintation of these. For this exercise we're going to configure our OpenScale service by running a Jupyter Notebook. This provides examples of using the OpenScale Python APIs programatically. This lab is comprised of the following steps: 1. [Open the notebook](#1-open-the-notebook) 2. [Update credentials](#2-update-credentials) 3. [Run the notebook](#3-run-the-notebook) 4. [Get transactions for Explainability](#4-get-transactions-for-explainability) ## 1. Open the notebook If you [Created the Project](https://ibm-developer.gitbook.io/cloudpakfordata-telco-workshop/getting-started/pre-work#2-create-a-project-and-deployment-space) using the [Customer-Churn-Project.zip](https://github.ibm.com/IBMDeveloper/cp4d-workshop-telco-churn/tree/master/projects/Customer-Churn-Project.zip) file, your notebook will be present in that project, under the `Assets` tab: ![Project from zip assets tab](https://2515897395-files.gitbook.io/~/files/v0/b/gitbook-legacy-files/o/assets%2F-M0YTFb_WdaBDnhlXs-q%2Fsync%2F799c9d41e9fd3b14493796bf51d0dbbfb47e4477.png?generation=1595273046954672\&alt=media) You may now skip to the next step [Update credentials](#2-update-credentials) ## Import the notebook (If you are not using the Project Import pre-work steps) > NOTE: You should probably not need this step, and should only perform it if instructed to. If, for some reason, you have not followed the [Create a Project and Deployment Space](https://ibm-developer.gitbook.io/cloudpakfordata-telco-workshop/getting-started/pre-work#2-create-a-project-and-deployment-space) step in the Pre-work to import [Customer-Churn-Project.zip](https://github.ibm.com/IBMDeveloper/cp4d-workshop-telco-churn/tree/master/projects/Customer-Churn-Project.zip), then you will need to import the notebook file by itself. Use the following steps for that. At the project overview click the *Add to project* button, and choose *Notebook* or click *New notebook* option next to the Notebooks section. ![Add a new asset](https://2515897395-files.gitbook.io/~/files/v0/b/gitbook-legacy-files/o/assets%2F-M0YTFb_WdaBDnhlXs-q%2Fsync%2Fd076c7df32a67e6a23d29cd1b11bacac3429a985.png?generation=1595273045939445\&alt=media) On the next panel select the *From URL* tab, give your notebook a name, provide the following URL, and choose the Python 3.6 environment: ```bash https://raw.githubusercontent.com/IBM/cloudpakfordata-telco-churn-workshop/master/notebooks/openscale-full-configuration.ipynb ``` > The notebook is hosted in the same repo as [the workshop](https://github.com/IBM/cloudpakfordata-telco-churn-workshop). > > * **Notebook**: [openscale-full-configuration.ipynb](https://raw.githubusercontent.com/IBM/cloudpakfordata-telco-churn-workshop/master/notebooks/openscale-full-configuration.ipynb) > * **Notebook with output**: [openscale-full-configuration-with-output.ipynb](https://raw.githubusercontent.com/IBM/cloudpakfordata-telco-churn-workshop/master/notebooks/with-output/openscale-full-configuration-with-output.ipynb) ![Add notebook name and URL](https://2515897395-files.gitbook.io/~/files/v0/b/gitbook-legacy-files/o/assets%2F-M0YTFb_WdaBDnhlXs-q%2Fsync%2F7cd58270a754e887c419056c6bbbdb945aa938cc.png?generation=1595273026396337\&alt=media) When the Jupyter notebook is loaded and the kernel is ready then we can start executing cells. ![Notebook loaded](https://2515897395-files.gitbook.io/~/files/v0/b/gitbook-legacy-files/o/assets%2F-M0YTFb_WdaBDnhlXs-q%2Fsync%2F8b03c89e5a5b4bfb9d265173e3373e012a77ab81.png?generation=1595273046600164\&alt=media) ### 2. Update credentials * In the notebook section 1.2 you will add your ICP platform credentials for the `WOS_CREDENTIALS`. * For the `url` field, change `https://w.x.y.z` to use the URL your ICP cluster, i.e something like: `"url": "https://zen-cpd-zen.omid-cp4d-v5-2bef1f4b4097001da9502000c44fc2b2-0001.us-south.containers.appdomain.cloud"`. * For the `username`, use your login username. * For the `password`, user your login password. ### 3. Run the notebook > **Important**: *Make sure that you stop the kernel of your notebook(s) when you are done, in order to prevent leaking of memory resources!* ![Stop kernel](https://2515897395-files.gitbook.io/~/files/v0/b/gitbook-legacy-files/o/assets%2F-M0YTFb_WdaBDnhlXs-q%2Fsync%2Fc1d53c6af7e75ea6fcc31ddeaaaaa8cb57782c37.png?generation=1595272995416364\&alt=media) Spend an minute looking through the sections of the notebook to get an overview. You will run cells individually by highlighting each cell, then either click the `Run` button at the top of the notebook. While the cell is running, an asterisk (`[*]`) will show up to the left of the cell. When that cell has finished executing a sequential number will show up (i.e. `[17]`). ### 4. Get transactions for Explainability Under `8.9 Identify transactions for Explainability` run the cell. It will produce a series of UIDs for indidvidual ML scoring transactions. Copy one or more of them to examine in the next section. --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://ibm-developer.gitbook.io/cloudpakfordata-telco-workshop/telco-workshop/openscale-notebook.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.