@ibm-watson/natural-language-classifier-demo
v1.2.0
Published
Natural Language Classifier sample application
Downloads
37
Readme
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
- Sign up for an IBM Cloud account.
- Download the IBM Cloud CLI.
- 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 theusername
andpassword
values if your service instance doesn't provide anapikey
. - Copy the
url
value.
Configuring the application
- 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 haveusername
andpassword
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
.
In the application folder, copy the .env.example file and create a file called .env
cp .env.example .env
Open the .env file and add the service credentials that you obtained in the previous step.
Example .env file that configures the
apikey
andurl
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
andpassword
credentials, add theNATURAL_LANGUAGE_CLASSIFIER_USERNAME
andNATURAL_LANGUAGE_CLASSIFIER_PASSWORD
variables to the .env file.
Example .env file that configures the
username
,password
, andurl
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
- If your service instance uses
Add the
CLASSIFIER_ID
to the previous propertiesCLASSIFIER_ID=522be-7b41-ab44-dec3-g1eab2ha73c6
Running locally
Install the dependencies
npm install
Run the application
npm start
View the application in a browser at
localhost:3000
Deploying to IBM Cloud as a Cloud Foundry Application
Login to IBM Cloud with the IBM Cloud CLI
ibmcloud login
Target a Cloud Foundry organization and space.
ibmcloud target --cf
Edit the manifest.yml file. Change the name field to something unique.
For example,- name: my-app-name
.Deploy the application
ibmcloud app push
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.