`DataIterator` provides iterators over the dataset. This class combines some data sets and provides a batch iterator over them. For example::

`ProxyEvaluator` is the interface to evaluate models. `ProxyEvaluator` contains various evaluation protocols: * **First**, evaluation metric

Cpp implementation `UniEvaluator` for item ranking task. Evaluation metrics of `UniEvaluator` are configurable and can automatically fit both

Retriever combining embedding similarity with recency.

Wraps another sampler to yield a mini-batch of indices.

`GroupedEvaluator` evaluates models in user groups. This class evaluates the ranking performance of models in user groups, which are split ac

`Logger` is a simple encapsulation of python logger. This class can show a message on standard output and write it into the file named `filen

Samples elements randomly, without replacement.

Samples elements sequentially, always in the same order.

Iterates once over the dataset, as specified by the sampler.

Pack the given data to one dataset. Args: data (list or tuple): a list of 'data'.

Base class for all evaluator.

Configuration for this pydantic object.

A configurator class. This class can read arguments from ini-style configuration file and parse arguments from command line simultaneously. T

Base class for all Samplers. Every Sampler subclass has to provide an __iter__ method, providing a way to iterate over indices of dataset ele

Python implementation `UniEvaluator` for item ranking task. Evaluation metrics of `UniEvaluator` are configurable and can automatically fit b