Merlin-models

What’s Changed

⚠ Breaking Changes

- Remove masking for now marcromeyn (557)
- Removing Queue-based negative-sampling for now marcromeyn (558)

🐜 Bug Fixes

- Add signature checks for various models like two-tower & DLRM marcromeyn (588)
- Keep Dataloader lazy when using map operations oliverholworthy (572)
- Enable serialization of TensorInitializer oliverholworthy (549)
- EmbeddingFeatures - Move embedding table creation from build to __init__ oliverholworthy (532)
- Handle ParallelBlock in Model.from_block oliverholworthy (517)
- Propagate schema to branches if needed in ParallelBlock marcromeyn (478)

🚀 Features

- Hashed cross timmy00 (587)
- Update UniformNegativeSampling to handle targets and add optional control for testing oliverholworthy (583)
- Allow for blocks in the Model to transform the targets marcromeyn (554)
- Add In-Batch Negative Sampling Block for positive-only batches oliverholworthy (560)
- Add functionality to set activation as a list in MLPBlock rvk007 (548)
- Add Cond Layer to tensorflow combinators oliverholworthy (552)
- Adding AsRaggedTensors transformation marcromeyn (556)
- Breaking out BaseModel to support sub-classing marcromeyn (518)
- Add new block EmbeddingTable oliverholworthy (541)
- Adding pre & post to Model marcromeyn (542)
- XGBoost - Add evals argument to fit to support eval on datasets other than training oliverholworthy (538)
- XGBoost - Train/eval with features from schema passed in to the constructor oliverholworthy (531)
- XGBoost - Use DaskDeviceQuantileDMatrix with GPU Training oliverholworthy (528)
- Use standard Keras embedding layers inside `EmbeddingFeatures` block karlhigley (472)
- Refactored top-k metrics and created TopKMetricsAggregator for optimized metrics computation gabrielspmoreira (514)

📄 Documentation

- Attribute source of MF image mikemckiernan (568)
- add xgboost example radekosmulski (522)
- add usecase with pretrained embeddings radekosmulski (508)
- Update URLs to Criteo datasets mikemckiernan (516)

🔧 Maintenance

- Adding the last 2 major TF versions to our CPU-tests marcromeyn (573)
- Add Keras layer_test function to testing_utils oliverholworthy (584)
- Attempt to remove docs dependencies mikemckiernan (586)
- Integration Tests for Retrieval models gabrielspmoreira (537)
- Move data-augmentation transformations into the new data_augmentation package marcromeyn (566)
- Moving tf/core/blocks to tf/core marcromeyn (565)
- Replace usage of tensorflow.python.keras with tensorflow.keras oliverholworthy (555)
- Make blocks part of Model and not of SequentialBlock marcromeyn (551)
- Adding schema's to manifest marcromeyn (539)
- Add tests for train_metrics_steps ensuring we can control the frequency of computing metrics oliverholworthy (519)
- Add tests for calling filter block when output returns empty oliverholworthy (481)

What’s Changed

- Quick fix to simplify DLRM when there are no continuous features marcromeyn (479)
- Move Input-blocks marcromeyn (471)
- Fixing the inconsistency when exporting embeddings to cudf DataFrame gabrielspmoreira (452)
- Remove the `mask` variable from the `ModelContext` karlhigley (449)
- Move masking into the `FeatureContext` karlhigley (443)
- Create `FeatureContext` and pass it to model layers with `call_layer` karlhigley (428)
- Rename "mask schema" to "mask" or "feature mask" karlhigley (425)
- Rename `BlockContext` to `ModelContext` karlhigley (417)
- Create `FeatureCollection` as a way to pass input features to blocks karlhigley (418)
- Added TensorInitializer that can be used to initialize variables/embeddings with pretrained weights gabrielspmoreira (357)

⚠ Breaking Changes

- Remove `Block.to_model` benfred (501)
- Moving loss- and metrics-calculation to model instead of the predicti… marcromeyn (431)
- Make Model creation explicit karlhigley (432)

🐜 Bug Fixes

- Fixes computing metrics each N steps during training and adding regularization_loss metric gabrielspmoreira (511)
- Fix to pass shuffle argument to dataloader benfred (493)
- fix broken links in the 04-Exporting-ranking-models.ipynb nb rnyak (490)
- Fixes errors on retrieval models evaluation in graph mode gabrielspmoreira (488)
- Fixes and improvements in ranking metrics gabrielspmoreira (475)
- Fixes and improves masking (for both Causal LM and Masked LM) and adds SequenceAggregation.MASKED_MEAN (used by YouTubeDNN) gabrielspmoreira (464)
- Replace use of removeprefix function which requires Python 3.9+ oliverholworthy (465)
- Parametrize base-model-tests to run in both graph- and eager-mode marcromeyn (456)
- Add validation for movielens variant and fix docstring oliverholworthy (434)
- Use collections.abc for Sequence import oliverholworthy (427)

🚀 Features

- XGBoost - Switch to dask API oliverholworthy (466)
- Fixes and improves masking (for both Causal LM and Masked LM) and adds SequenceAggregation.MASKED_MEAN (used by YouTubeDNN) gabrielspmoreira (464)
- Moving loss- and metrics-calculation to model instead of the predicti… marcromeyn (431)
- XGBoost - Change group_columns to qid_column oliverholworthy (462)
- First sketch of XGBoost integration with Merlin Dataset oliverholworthy (433)
- Getting rid of feature-variables in ModelContext marcromeyn (455)
- Adding the missing logQ correction to sampled softmax gabrielspmoreira (457)
- Making YoutubeDNNRetrievalModel more configurable gabrielspmoreira (447)
- Making EmbeddingOptions.embedding_dims to have priority over .inferred_embedding_dims gabrielspmoreira (398)

📄 Documentation

- Update to refer to merlin-tensorflow container mikemckiernan (512)
- Fix prediction task documentation benfred (505)
- Fix dataloader docstring benfred (492)
- Add common release-drafter workflow mikemckiernan (439)
- Add common release-drafter configuration mikemckiernan (435)
- Adding container info to notebook 01, 02 and 06 bschifferer (424)

🔧 Maintenance

- Fix pytest marker for integration tests. oliverholworthy (510)
- Add a GA workflow that requires labels on PR's benfred (506)
- Use shared implementation of triage workflow benfred (504)
- remove unnecessary line radekosmulski (494)
- Adding automatic branch pruning to ParallelBlock marcromeyn (477)
- Move tabular tests from test_core to test_tabular marcromeyn (476)
- Remove tf.test.is_gpu_available call benfred (470)
- Update setup.py to include only the merlin namespace oliverholworthy (469)
- Add labels to PRs for change log mikemckiernan (453)
- Make use of model_test for all ranking- and benchmark-models marcromeyn (440)
- Move tests to tests/unit or tests/integration jperez999 (445)
- Creating generic model_test marcromeyn (430)
- Create separate a Github-workflow for each backend marcromeyn (423)
- rm git pull cmd in test unit jperez999 (438)
- Adding CI for notebooks 03, 04, 05 and 06 bschifferer (414)

Known Issues
* model.evaluate() gives much higher acc value for small batch size when we set validation_data int the model.fit() https://github.com/NVIDIA-Merlin/models/issues/373

What's Changed
* Fixing MF by applying L2-norm in the towers individually by gabrielspmoreira in https://github.com/NVIDIA-Merlin/models/pull/353
* Ensure inferred embedding dim from feature cardinality is multiple of 8 by gabrielspmoreira in https://github.com/NVIDIA-Merlin/models/pull/355
* Update advanced_example notebook by sararb in https://github.com/NVIDIA-Merlin/models/pull/360
* Refactoring the evaluation of RetrievalModel by marcromeyn in https://github.com/NVIDIA-Merlin/models/pull/352
* First design of popularity correction by sararb in https://github.com/NVIDIA-Merlin/models/pull/362
* Fixes and improvements in embeddings export for MatrixFactorizationModel and TwoTowerModel by gabrielspmoreira in https://github.com/NVIDIA-Merlin/models/pull/365
* Adding AlphaDropout support, which is recommended by selu activation by gabrielspmoreira in https://github.com/NVIDIA-Merlin/models/pull/369
* Simplified TopKIndexBlock implementation and fixed intermittent inconsistency on retrieval models eval by gabrielspmoreira in https://github.com/NVIDIA-Merlin/models/pull/370
* Evaluation metrics of a top-k recommender by sararb in https://github.com/NVIDIA-Merlin/models/pull/371
* Adding unttests for example notebooks by bschifferer in https://github.com/NVIDIA-Merlin/models/pull/377
* Adding option for embeddings_l2_reg, which is in particular critical for MF by gabrielspmoreira in https://github.com/NVIDIA-Merlin/models/pull/381
* Creating a reg_factor for PopularityLogitsCorrection by gabrielspmoreira in https://github.com/NVIDIA-Merlin/models/pull/386
* Adding unittests for Notebook 04 and 05 by bschifferer in https://github.com/NVIDIA-Merlin/models/pull/385
* fix accessing item-id embeddings table based on IntDomain name by sararb in https://github.com/NVIDIA-Merlin/models/pull/376
* Fix top-k recommender to return correct top-k relevant items. by sararb in https://github.com/NVIDIA-Merlin/models/pull/389
* Update `testbook` tests to use absolute notebook paths by karlhigley in https://github.com/NVIDIA-Merlin/models/pull/394
* Add missing features to Ali-ccp data generator by rnyak in https://github.com/NVIDIA-Merlin/models/pull/399
* Fixes error with fit() with validation data by gabrielspmoreira in https://github.com/NVIDIA-Merlin/models/pull/402
* Update README.rst by bschifferer in https://github.com/NVIDIA-Merlin/models/pull/401
* Add unit test for 03_exploring_different_models by rnyak in https://github.com/NVIDIA-Merlin/models/pull/405
* remove unneeded packages by jperez999 in https://github.com/NVIDIA-Merlin/models/pull/412
* Use shuffle_df from merlin-core by benfred in https://github.com/NVIDIA-Merlin/models/pull/413
* Adding CI for movielens notebooks by bschifferer in https://github.com/NVIDIA-Merlin/models/pull/411
* Remove `.python-version` file by karlhigley in https://github.com/NVIDIA-Merlin/models/pull/416
* Update the tags selection from the schema by excluding the target variable by sararb in https://github.com/NVIDIA-Merlin/models/pull/397
* Create a basic conda recipe by benfred in https://github.com/NVIDIA-Merlin/models/pull/420
* docs: Use sphinx-ext-toc to control examples by mikemckiernan in https://github.com/NVIDIA-Merlin/models/pull/404


**Full Changelog**: https://github.com/NVIDIA-Merlin/models/compare/v0.3.0...v0.4.0

What's Changed
* fix for tf when creating cpu dataloader by jperez999 in https://github.com/NVIDIA-Merlin/models/pull/222
* Create the necessary blocks/methods for ItemRetrieval evaluation by sararb in https://github.com/NVIDIA-Merlin/models/pull/189
* Adding wrap_as_model to Block by marcromeyn in https://github.com/NVIDIA-Merlin/models/pull/209
* chore: add PR doc previews by mikemckiernan in https://github.com/NVIDIA-Merlin/models/pull/229
* Refactors and optimizes evaluation with ranking metrics by gabrielspmoreira in https://github.com/NVIDIA-Merlin/models/pull/226
* Dataloader/targets by marcromeyn in https://github.com/NVIDIA-Merlin/models/pull/195
* Break up core.py by marcromeyn in https://github.com/NVIDIA-Merlin/models/pull/227
* Improvements in two-tower model and DCN by gabrielspmoreira in https://github.com/NVIDIA-Merlin/models/pull/237
* Adding NCFModel as benchmark by sararb in https://github.com/NVIDIA-Merlin/models/pull/230
* fix: Typo in workflow script by mikemckiernan in https://github.com/NVIDIA-Merlin/models/pull/248
* Updates container testing by albert17 in https://github.com/NVIDIA-Merlin/models/pull/234
* Specify encoding when reading csv file for ml-100k by benfred in https://github.com/NVIDIA-Merlin/models/pull/249
* chore: Trigger on closed pull requests by mikemckiernan in https://github.com/NVIDIA-Merlin/models/pull/251
* docs: Incremental improvements by mikemckiernan in https://github.com/NVIDIA-Merlin/models/pull/193
* Set up automated docstring coverage checks by karlhigley in https://github.com/NVIDIA-Merlin/models/pull/257
* Automatic setting of retrieval model top-k evaluation by sararb in https://github.com/NVIDIA-Merlin/models/pull/238
* Fixing MLPBlock saving with regularizers by marcromeyn in https://github.com/NVIDIA-Merlin/models/pull/264
* Check if valid data is merlin.io.dataset and then convert to BatchedDataset by rnyak in https://github.com/NVIDIA-Merlin/models/pull/269
* Fix mypy issues & make MF return a RetrievalModel by marcromeyn in https://github.com/NVIDIA-Merlin/models/pull/266
* Update Dataset schema when schema is passed in BatchedDataset by marcromeyn in https://github.com/NVIDIA-Merlin/models/pull/265
* Fix small bug when shuffle is passed in .fit by marcromeyn in https://github.com/NVIDIA-Merlin/models/pull/272
* Moving RetrievalModel._ensure_unique to utils by marcromeyn in https://github.com/NVIDIA-Merlin/models/pull/267
* Fix bug in tower saving where all features were required by marcromeyn in https://github.com/NVIDIA-Merlin/models/pull/275
* Move interrogate docstring coverage settings to pyproject.toml by karlhigley in https://github.com/NVIDIA-Merlin/models/pull/276
* Fix MatrixFactorizationModel bug by sararb in https://github.com/NVIDIA-Merlin/models/pull/280
* Implementation of DeepFM model by sararb in https://github.com/NVIDIA-Merlin/models/pull/271
* Add intersphinx mapping for merlin-core by benfred in https://github.com/NVIDIA-Merlin/models/pull/281
* Examples for Getting Started and Schema File by bschifferer in https://github.com/NVIDIA-Merlin/models/pull/253
* Explore different ranking models by rnyak in https://github.com/NVIDIA-Merlin/models/pull/256
* Item retrieval evaluation fixes by gabrielspmoreira in https://github.com/NVIDIA-Merlin/models/pull/279
* [Doc] a hyperlink missing by rhdong in https://github.com/NVIDIA-Merlin/models/pull/286
* docs: Add API documentation by mikemckiernan in https://github.com/NVIDIA-Merlin/models/pull/212
* Exclude additional directories from docstring coverage req't by karlhigley in https://github.com/NVIDIA-Merlin/models/pull/293
* fix evaluation loss equal to zero and add docstrings by sararb in https://github.com/NVIDIA-Merlin/models/pull/294
* docs: Add nightly multi-version build by mikemckiernan in https://github.com/NVIDIA-Merlin/models/pull/298
* fix: Do not rebuild on PR close by mikemckiernan in https://github.com/NVIDIA-Merlin/models/pull/299
* Retrieval models (ALI-CCP)- Two-Tower model example by rnyak in https://github.com/NVIDIA-Merlin/models/pull/262
* docs: Revise API page by mikemckiernan in https://github.com/NVIDIA-Merlin/models/pull/305
* Exporting ranking models by rnyak in https://github.com/NVIDIA-Merlin/models/pull/300
* Small fixes on Matrix Factorization by gabrielspmoreira in https://github.com/NVIDIA-Merlin/models/pull/306
* first draft of advanced example notebook by sararb in https://github.com/NVIDIA-Merlin/models/pull/295
* Fix default int64 dtype in index.py to avoid dtype errors in Retrieval model validation step by rnyak in https://github.com/NVIDIA-Merlin/models/pull/307
* Specify encoding when reading csv file for ml-1m by benfred in https://github.com/NVIDIA-Merlin/models/pull/310
* Example Readme by bschifferer in https://github.com/NVIDIA-Merlin/models/pull/296
* fix categorical-ohe block by sararb in https://github.com/NVIDIA-Merlin/models/pull/314
* Improving handling of data in examples + tests by marcromeyn in https://github.com/NVIDIA-Merlin/models/pull/309
* quick fix in aliccp schema by sararb in https://github.com/NVIDIA-Merlin/models/pull/323
* fix binary tag in Ali-CCP workflow by sararb in https://github.com/NVIDIA-Merlin/models/pull/325
* updates from readme bash by sararb in https://github.com/NVIDIA-Merlin/models/pull/303
* Pairwise losses fixes by gabrielspmoreira in https://github.com/NVIDIA-Merlin/models/pull/317
* Upgrading black + enabling black on notebooks by marcromeyn in https://github.com/NVIDIA-Merlin/models/pull/326
* docs: Add redirect page by mikemckiernan in https://github.com/NVIDIA-Merlin/models/pull/329
* Fix the evaluation of sampled softmax-based tasks by sararb in https://github.com/NVIDIA-Merlin/models/pull/315
* Fixing synthetic data-generation for aliccp-raw by marcromeyn in https://github.com/NVIDIA-Merlin/models/pull/327
* Adding codespell + flake8-nb to pre-commit by marcromeyn in https://github.com/NVIDIA-Merlin/models/pull/331
* remove barchart from example_utils by rnyak in https://github.com/NVIDIA-Merlin/models/pull/334
* Fix 03-03-05 nbs wrt bug bash by rnyak in https://github.com/NVIDIA-Merlin/models/pull/333
* Merlin models examples fixes by gabrielspmoreira in https://github.com/NVIDIA-Merlin/models/pull/313
* Update NVTabular and merlin-core requirements for the release by benfred in https://github.com/NVIDIA-Merlin/models/pull/347
* Report skipped tests in blossom CI by benfred in https://github.com/NVIDIA-Merlin/models/pull/348
* Fixing error on retrieval model evaluation when using mixed_precision by gabrielspmoreira in https://github.com/NVIDIA-Merlin/models/pull/337
* Automate pushing package to pypi by benfred in https://github.com/NVIDIA-Merlin/models/pull/349

New Contributors
* rhdong made their first contribution in https://github.com/NVIDIA-Merlin/models/pull/286

**Full Changelog**: https://github.com/NVIDIA-Merlin/models/compare/v0.2.0...v0.3.0

What's Changed
* Fix TARGET tag typo in dataloader and `sampler` initialization in ItemRetrievalTask() by rnyak in https://github.com/NVIDIA-Merlin/models/pull/176
* Pointwise, Pairwise and Listwise Losses by gabrielspmoreira in https://github.com/NVIDIA-Merlin/models/pull/166
* Add download, convert and etl util func for movielens dataset by rnyak in https://github.com/NVIDIA-Merlin/models/pull/155
* Copying Github templates from T4Rec by marcromeyn in https://github.com/NVIDIA-Merlin/models/pull/165
* [REVIEW] docs: initial commit for Sphinx docs by mikemckiernan in https://github.com/NVIDIA-Merlin/models/pull/174
* fix references to item-id column by sararb in https://github.com/NVIDIA-Merlin/models/pull/180
* Activates GPU CI System by albert17 in https://github.com/NVIDIA-Merlin/models/pull/186
* quick fix of setting dtypes from sparse inputs by sararb in https://github.com/NVIDIA-Merlin/models/pull/183
* Adding some basic doc-strings by marcromeyn in https://github.com/NVIDIA-Merlin/models/pull/185
* Introducing TupleAggregator & use it for CosineSimilarity + ElementWiseMultiply by marcromeyn in https://github.com/NVIDIA-Merlin/models/pull/164
* Unified Schema by benfred in https://github.com/NVIDIA-Merlin/models/pull/184
* Adding models by marcromeyn in https://github.com/NVIDIA-Merlin/models/pull/187
* Fix SyntheticData.read_schema with proto text files by benfred in https://github.com/NVIDIA-Merlin/models/pull/191
* Adding batch-predict by marcromeyn in https://github.com/NVIDIA-Merlin/models/pull/145
* Move to 'merlin' namespace by benfred in https://github.com/NVIDIA-Merlin/models/pull/198
* Fix ItemRetrieval assertion and output errors by rnyak in https://github.com/NVIDIA-Merlin/models/pull/200
* Adds initializers and regularizers options to MLPBlock by gabrielspmoreira in https://github.com/NVIDIA-Merlin/models/pull/206
* Update merlin core version by benfred in https://github.com/NVIDIA-Merlin/models/pull/213
* Assume 'merlin' is a first party package for isort by benfred in https://github.com/NVIDIA-Merlin/models/pull/216
* Implemented support for TF mixed precision (mixed_float16) by gabrielspmoreira in https://github.com/NVIDIA-Merlin/models/pull/217
* Add shim to adapt the implicit library by benfred in https://github.com/NVIDIA-Merlin/models/pull/218
* Add a helper function to get the movielens dataset by benfred in https://github.com/NVIDIA-Merlin/models/pull/207
* Add shim to adapt the lightfm library by benfred in https://github.com/NVIDIA-Merlin/models/pull/219

New Contributors
* mikemckiernan made their first contribution in https://github.com/NVIDIA-Merlin/models/pull/174

**Full Changelog**: https://github.com/NVIDIA-Merlin/models/compare/v0.1.0...v0.2.0

Initial public release