Documentation of Recommenders

[miguelgfierro]

Description

Documentation of recommenders

I think the best way to review this is by compiling the documentation locally (see the README).

I put there the basic info. Maybe we want to add more information to the pages. Feel free to directly push to this branch if you want to add comments in any module.

Related Issues

#817
#651

Checklist:

• I have followed the contribution guidelines and code style for this project.
• I have added tests covering my contributions.
• I have updated the documentation accordingly.

[review-notebook-app]

Check out this pull request on ReviewNB: https://app.reviewnb.com/microsoft/recommenders/pull/859

You'll be able to see visual diffs and write comments on notebook cells. Powered by ReviewNB.

[yueguoguo]

This is good 👍 One dummy question, in the PR how can we render it to html and view it?

[gramhagen]

This is good 👍 One dummy question, in the PR how can we render it to html and view it?

instructions in readme: https://github.com/microsoft/recommenders/blob/documentation/docs/README.md

[yueguoguo]

Just noticed that - thanks @gramhagen for pointing it out!

[gramhagen]

love it!

[miguelgfierro]

I ended up hosting the documentation in prometheus http://prometheus.europe.corp.microsoft.com/recommenders/, in case anyone wants to take a look, this is probably quicker

[yueguoguo]

@miguelgfierro I still have issue accessing the site, even in the corp net...

[miguelgfierro]

can you try again now?

[miguelgfierro]

there is this error:

tests\unit\test_wide_deep_utils.py F                                     [100%]

================================== FAILURES ===================================
_______________________________ test_wide_deep ________________________________

pd_df = (   userID  itemID   itemFeat  rating
0       1       1  [1, 1, 1]       5
1       1       2  [2, 2, 2]       4
2     ...4, 4, 4]       5
5       2       5  [5, 5, 5]       3, array([1, 2], dtype=int64), array([1, 2, 3, 4, 5], dtype=int64))
tmp = 'C:\\Users\\recocat\\AppData\\Local\\Temp\\pytest-of-recocat\\pytest-10\\tmp6u7o6a6o'

    @pytest.mark.gpu
    def test_wide_deep(pd_df, tmp):
        """Test `build_feature_columns` and `build_model`"""
        data, users, items = pd_df
    
        # Test wide model
        # Test if wide column has two original features and one crossed feature
        wide_columns, _ = build_feature_columns(
            users, items, model_type='wide', crossed_feat_dim=10
        )
        assert len(wide_columns) == 3
        # Check crossed feature dimension
>       assert wide_columns[2].hash_bucket_size == 10
E       AssertionError: assert 1000 == 10
E        +  where 1000 = _CrossedColumn(keys=(_VocabularyListCategoricalColumn(key='userID', vocabulary_list=(1, 2), dtype=tf.int64, default_va...lary_list=(1, 2, 3, 4, 5), dtype=tf.int64, default_value=-1, num_oov_buckets=0)), hash_bucket_size=1000, hash_key=None).hash_bucket_size

tests\unit\test_wide_deep_utils.py:58: AssertionError

not sure whether it is something that I touch ...