@ibm-watson/natural-language-classifier-demo

🚀 Natural Language Classifier Sample Application

This Node.js app demonstrates some of the Natural Language Classifier service features.

The IBM Watson™ Natural Language Classifier service applies deep learning techniques to make predictions about the best predefined classes for short sentences or phrases. The classes can trigger a corresponding action in an application, such as directing a request to a location or person, or answering a question. After training, the service returns information for texts that it hasn't seen before. The response includes the name of the top classes and confidence values.

You can view a demo of this app.

Prerequisites

1. Sign up for an IBM Cloud account.
2. Download the IBM Cloud CLI.
3. Create an instance of the Natural Language Classifier service and get your credentials:
   • Go to the Natural Language Classifier page in the IBM Cloud Catalog.
   • Log in to your IBM Cloud account.
   • Click Create.
   • Click Show to view the service credentials.
   • Copy the apikey value, or copy the username and password values if your service instance doesn't provide an apikey.
   • Copy the url value.

Configuring the application

1. The Natural Language Classifier service must be trained before you can successfully use this application. The training data is provided in the file training/weather_data_train.csv.
   If you have username and password credentials, train a classifier by using the following command:

curl -i -u "<username>":"<password>" \
-F training_data=@training/weather_data_train.csv \
-F training_metadata="{\"language\":\"en\",\"name\":\"TutorialClassifier\"}" \
"<url>/v1/classifiers"

Make sure to replace <username>, <password> and <url>.
If you have apikey credentials, use the word "apikey" as your username and your apikey as the password.
After running the command, copy the value for classifier_id.

1. In the application folder, copy the .env.example file and create a file called .env

   cp .env.example .env
   

2. Open the .env file and add the service credentials that you obtained in the previous step.

   Example .env file that configures the apikey and url for a Natural Language Classifier service instance hosted in the US East region:

   NATURAL_LANGUAGE_CLASSIFIER_IAM_APIKEY=X4rbi8vwZmKpXfowaS3GAsA7vdy17Qh7km5D6EzKLHL2
   NATURAL_LANGUAGE_CLASSIFIER_URL=https://gateway.watsonplatform.net/natural-language-classifier/api
   

   • If your service instance uses username and password credentials, add the NATURAL_LANGUAGE_CLASSIFIER_USERNAME and NATURAL_LANGUAGE_CLASSIFIER_PASSWORD variables to the .env file.

   Example .env file that configures the username, password, and url for a Natural Language Classifier service instance hosted in the Sydney region:

   NATURAL_LANGUAGE_CLASSIFIER_USERNAME=522be-7b41-ab44-dec3-g1eab2ha73c6
   NATURAL_LANGUAGE_CLASSIFIER_PASSWORD=A4Z5BdGENrwu8
   NATURAL_LANGUAGE_CLASSIFIER_URL=https://gateway-syd.watsonplatform.net/natural-language-classifier/api
   

3. Add the CLASSIFIER_ID to the previous properties

   CLASSIFIER_ID=522be-7b41-ab44-dec3-g1eab2ha73c6
   

Running locally

1. Install the dependencies

   npm install
   

2. Run the application

   npm start
   

3. View the application in a browser at localhost:3000

Deploying to IBM Cloud as a Cloud Foundry Application

1. Login to IBM Cloud with the IBM Cloud CLI

   ibmcloud login
   

2. Target a Cloud Foundry organization and space.

   ibmcloud target --cf
   

3. Edit the manifest.yml file. Change the name field to something unique.
   For example, - name: my-app-name.

4. Deploy the application

   ibmcloud app push
   

5. View the application online at the app URL.
   For example: https://my-app-name.mybluemix.net

Directory structure

.
├── app.js                      // express routes
├── config                      // express configuration
│   ├── error-handler.js
│   ├── express.js
│   └── security.js
├── manifest.yml
├── package.json
├── public                      // static resources
├── server.js                   // entry point
├── test                        // unit tests
├── training
│   └── weather_data_train.csv  // training file
└── views                       // react components

License

This sample code is licensed under Apache 2.0.
Full license text is available in LICENSE.

Contributing

See CONTRIBUTING.

Open Source @ IBM

Find more open source projects on the IBM Github Page.