Dicee

We're happy to announce the 0.0.9 release.

You can install it with `pip install dicee==0.0.9`

Features
1. An [AbstractCallback](https://github.com/dice-group/dice-embeddings/blob/b891508412b318ea50f1af809462506ef7ed667c/core/abstracts.py#L591) class is implemented. Few callback classes are created to print info related to training, to save the model paramaters and apply polyak parameter ensemble model [PrintCallback](https://github.com/dice-group/dice-embeddings/blob/b891508412b318ea50f1af809462506ef7ed667c/core/callbacks.py#L35), [KGESaveCallback](https://github.com/dice-group/dice-embeddings/blob/b891508412b318ea50f1af809462506ef7ed667c/core/callbacks.py#L65), [PPE](https://github.com/dice-group/dice-embeddings/blob/b891508412b318ea50f1af809462506ef7ed667c/core/callbacks.py#L149).
2. Pandas, Modin and Polars can be used as a [backend](https://github.com/dice-group/dice-embeddings/tree/b891508412b318ea50f1af809462506ef7ed667c/core/read_preprocess_save_load_kg). Reading, preprocessing, saving and loading can be done in a parallel fashion.
3. [AccumulateEpochLossCallback](https://github.com/dice-group/dice-embeddings/blob/b891508412b318ea50f1af809462506ef7ed667c/core/callbacks.py#L12)
5. Gradient Accumulation is implemented.

Applications
1. A [function](https://github.com/dice-group/dice-embeddings/blob/main/core/knowledge_graph_embeddings.py#L26) for predicting conjunctive queries over knowledge graph is implemented.
2. A [function](https://github.com/dice-group/dice-embeddings/blob/b891508412b318ea50f1af809462506ef7ed667c/core/knowledge_graph_embeddings.py#L92) to detect missing triples is implemented.

Features
1. KvsSample technique implemented. KvsSample is KvsAll with selected tail entities. This technique reduces the memory usage during training as we can select the number of tail entities.
2. [Sharded Training tested](https://pytorch-lightning.readthedocs.io/en/stable/advanced/model_parallel.html#sharded-training)

Maintenance
1. Use Python 3.9
2. More tests are added
3. ReadMe is structured

Todos for the next release
1. Explicit Class Kronecker Decomposition at retriving embeddings

Features
Self-supervised Learning module: Pseudo-Labelling and [Conformal Credal Self-Supervised Learning](https://arxiv.org/abs/2205.15239) implemented.

Maintenance
1. Documentation & Instrations are improved.
2. Use Python 3.10 due to [PEP 635](https://peps.python.org/pep-0635/)

Todos for the next release
2. Consider using [Weights & Biases](https://wandb.ai/site)
3. Study [[Raymond Hettinger](https://twitter.com/raymondh)](https://twitter.com/raymondh/status/1533369936739016705) 's talk about Structural Pattern Matching in the Real World: New tooling, real code, problems solved.
4. Explicit Class Kronecker Decomposition at retriving embeddings

Features

Batch Relaxation training strategy started.
Seed selection for the computation is available.
Input KG size reduction: Entities that do not occur X times can be removed.
Lower memory usage through selecting most efficient index type.
swifter is included to do dataframe().apply() via using all CPUs
_QMult with 11.4 B on DBpedia is succesfuly trained and deployed._

Maintenance

The title of the repo. has been changed.
Repo name has been changed.
Testing with three pytest setting is documented
Regression tests are extended.
More functions and classes are documented.

Todos for the next release
1. Use Python 3.10 to use [PEP 635](https://peps.python.org/pep-0635/)
2. Use Python 3.10 to benefit [from 10% performance increase](https://mail.python.org/pipermail/python-dev/2016-January/142945.html) and https://bugs.python.org/issue42093 <3
3. Consider using [Weights & Biases](https://wandb.ai/site)

We're happy to announce the 0.1.4 release. You can install it with `pip install dicee`


What's Changed
* Version by Demirrr in https://github.com/dice-group/dice-embeddings/pull/231
* Functionnal embedings. by Louis-Mozart in https://github.com/dice-group/dice-embeddings/pull/225
* refactoring by Louis-Mozart in https://github.com/dice-group/dice-embeddings/pull/233
* Fixing torch and pykeen versions by Demirrr in https://github.com/dice-group/dice-embeddings/pull/234
* Develop by Demirrr in https://github.com/dice-group/dice-embeddings/pull/235
* Documentation workflow added by alkidbaci in https://github.com/dice-group/dice-embeddings/pull/236
* DeCal test added by Demirrr in https://github.com/dice-group/dice-embeddings/pull/237
* Develop by Demirrr in https://github.com/dice-group/dice-embeddings/pull/238
* Continual Training and Downloading Pretrained models by Demirrr in https://github.com/dice-group/dice-embeddings/pull/239
* DualE implemented within the dice framework. by Louis-Mozart in https://github.com/dice-group/dice-embeddings/pull/241
* Docstring added to DualE and DeCaL for documentation by Louis-Mozart in https://github.com/dice-group/dice-embeddings/pull/242
* Prep for the new release by Demirrr in https://github.com/dice-group/dice-embeddings/pull/248

New Contributors
* Louis-Mozart made their first contribution in https://github.com/dice-group/dice-embeddings/pull/225
* alkidbaci made their first contribution in https://github.com/dice-group/dice-embeddings/pull/236

**Full Changelog**: https://github.com/dice-group/dice-embeddings/compare/v1.0.1.3.2...v1.0.1.4