With IBM Watson NLP, IBM introduced a common library for natural language processing, document understanding, translation, and trust. IBM Watson NLP brings everything under one umbrella for consistency and ease of development and deployment. This tutorial walks you through the process of setting up your environment to use the IBM Watson NLP Library. The tutorial is a prerequisite to working with the Watson NLP Library.

The watson_nlp library is available on IBM Watson Studio as a runtime library so that you can directly use it for model training, evaluation, and prediction. The following figure shows the IBM Watson NLP architecture.

Setting up your environment

To begin working with IBM Watson NLP, you set up a Python notebook environment that uses Watson Studio on IBM Cloud so that you can use the watson_nlp library. There are two ways to set up your environment:

For IBM Business Partners who have access to the IBM Tech Zone, you can reserve your environment there.
If you do not have access to the IBM Tech zone, you can load the notebook directly into your Watson Studio project.

Reserve your environment

Note: If you can't reserve an environment on the IBM Tech Zone, but you have access to a Watson Studio instance, you can skip steps 1 and 2 for reserving your environment.

Find the environment tile under the Sentiment Analysis or Emotion Classification tab, and click Reserve to reserve a Watson Studio environment. (For any other use case, the Tech Zone collection name might be different, but the step remains the same. So, you can find the right collection, and click Reserve.)
Follow the instructions in the invitation email that you receive to join an IBM cloud account. Your environment should be ready within a few minutes. When the environment is ready, you receive a second email similar to the one shown in the following figure.
Log in to IBM Cloud Pak for Data. If you are using the IBM Tech Zone environment, after you log in, ensure that you are using cloud account 2577353 - tsglwatson. You can check the name of the current account in the bar at the top of the screen. If necessary, change the account by using the drop-down menu. From the IBM Cloud Pak for Data dashboard, find the tile for the project that you want to work with. For this tutorial, the name of this project has the prefix sentiment-analysis. (This name is different for Emotion classification, Topic Modeling, Text Classification, and Entities Extraction use cases.) After the project is open, you can view the notebooks and data assets of the project by using the Assets tab.

Note: If you are not using the IBM Tech Zone environment, you do not have access to this IBM cloud account. You can load the Sentiment Analysis pretrained model notebook or the Emotion Classification pretrained notebook (or any other NLP notebook depending on your use case) into your Watson Studio project directly. Follow the instructions for creating notebook from URL to load the notebook.
Define the environment in which these notebooks will run. To begin, click the Manage tab.
Click Environments from the navigation bar on the left, then click the Templates tab. Finally, click New template.
Create an environment template that contains the watson_nlp library. Begin by giving your environment template a name like Watson NLP. In the Hardware configuration field, select at least 4 vCPU and 16 GB RAM. (For better performance, select a higher hardware configuration.) For software, select DO + NLP Runtime 22.1 on Python 3.9. Finally, click Create.
Switch to the Access control tab on the left, then select Access tokens and click New access token +.
Enter a Name for the access token, and select Editor in the Access role. Then, click Create. Now the access token is created for you and you can use it in the notebook.
Set an environment for a notebook. Click on the Assets tab, and find the notebook that you want to work with among the assets. Click the ellipsis (the three dots) to the right of the notebook name to open a drop-down menu. Within this menu, click Change environment.
Select the environment template that you created previously, and click Change.
Run the notebook by clicking the ellipsis and selecting Edit.
Your notebook loads. You can follow the instructions in your notebook to complete the tutorials on Watson NLP.

Conclusion

This tutorial walked you through the steps to set up your Python environment so that you can use the IBM Watson NLP library. The tutorial is a prerequisite to the Use the Watson NLP library to perform sentiment analysis and Use the Watson NLP library to perform emotion classification tutorials and any other tutorial that uses Watson NLP library for NLP tasks.

Set up your IBM Watson NLP environment

Set up your IBM Watson NLP environment