Fix OSS predict-py API

[hudeven]

Motivation and Context

OSS predict-py API(load PyTorch model and predict for a row of json) is broken. It requires pass a valid label in json, which doesn't make sense during inference. With this diff, only columns/tensorizers with is_input=True are required during inference

How Has This Been Tested

Added unit test:
$ pytest tests/main_test.py

Test in command line
$ pytext predict-py --model-file /tmp/model.pt <<< '{"text": "create an alarm for 1:30 pm"}'

Types of changes

• Docs change / refactoring / dependency upgrade
• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to change)

Checklist

• My code follows the code style of this project.
• My change requires a change to the documentation.
• I have updated the documentation accordingly.
• I have read the CONTRIBUTING document.
• I have completed my CLA (see CONTRIBUTING)
• I have added tests to cover my changes.
• All new and existing tests passed.

[facebook-github-bot]

@hudeven has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator.

[facebook-github-bot]

@hudeven merged this pull request in cb8e2c5.