replay-rec 0.20.3rc0__py3-none-any.whl → 0.21.0__py3-none-any.whl

replay/splitters/random_next_n_splitter.py

@@ -0,0 +1,224 @@
+from typing import Optional
+
+import numpy as np
+import pandas as pd
+import polars as pl
+
+from replay.utils import (
+    PYSPARK_AVAILABLE,
+    DataFrameLike,
+    PandasDataFrame,
+    PolarsDataFrame,
+    SparkDataFrame,
+)
+
+from .base_splitter import Splitter
+
+if PYSPARK_AVAILABLE:
+    import pyspark.sql.functions as sf
+    from pyspark.sql import Window
+
+
+class RandomNextNSplitter(Splitter):
+    """
+    Split interactions by a random position in the user sequence.
+    For each user, a random cut index is sampled and the target part consists of
+    the next ``N`` interactions starting from this cut; the train part contains
+    all interactions before the cut. Interactions after the target window are
+    discarded.
+
+    Note: by changing the ``seed`` attribute on an existing splitter instance,
+    you can obtain different splits without recreating the object. This is useful
+    when you need to generate multiple randomized splits of the same dataset.
+
+    >>> from datetime import datetime
+    >>> import pandas as pd
+    >>> columns = ["query_id", "item_id", "timestamp"]
+    >>> data = [
+    ...     (1, 1, "01-01-2020"),
+    ...     (1, 2, "02-01-2020"),
+    ...     (1, 3, "03-01-2020"),
+    ...     (2, 1, "06-01-2020"),
+    ...     (2, 2, "07-01-2020"),
+    ...     (2, 3, "08-01-2020"),
+    ... ]
+    >>> dataset = pd.DataFrame(data, columns=columns)
+    >>> dataset["timestamp"] = pd.to_datetime(dataset["timestamp"], format="%d-%m-%Y")
+    >>> splitter = RandomNextNSplitter(
+    ...     N=2,
+    ...     divide_column="query_id",
+    ...     seed=42,
+    ...     query_column="query_id",
+    ...     item_column="item_id",
+    ... )
+    >>> train, test = splitter.split(dataset)
+    """
+
+    _init_arg_names = [
+        "N",
+        "divide_column",
+        "seed",
+        "drop_cold_users",
+        "drop_cold_items",
+        "query_column",
+        "item_column",
+        "timestamp_column",
+        "session_id_column",
+        "session_id_processing_strategy",
+    ]
+
+    def __init__(
+        self,
+        N: Optional[int] = 1,  # noqa: N803
+        divide_column: str = "query_id",
+        seed: Optional[int] = None,
+        query_column: str = "query_id",
+        drop_cold_users: bool = False,
+        drop_cold_items: bool = False,
+        item_column: str = "item_id",
+        timestamp_column: str = "timestamp",
+        session_id_column: Optional[str] = None,
+        session_id_processing_strategy: str = "test",
+    ):
+        """
+        :param N: Optional window size. If None, the test set contains all interactions
+            from the cut to the end; otherwise the next ``N`` interactions. Must be >= 1.
+            Default: 1.
+        :param divide_column: Name of the column used to group interactions
+            for random cut sampling, default: ``query_id``.
+        :param seed: Random seed used to sample cut indices, default: ``None``.
+        :param query_column: Name of query interaction column.
+        :param drop_cold_users: Drop users from test DataFrame which are not in
+            the train DataFrame, default: ``False``.
+        :param drop_cold_items: Drop items from test DataFrame which are not in
+            the train DataFrame, default: ``False``.
+        :param item_column: Name of item interaction column.
+            If ``drop_cold_items`` is ``False``, then you can omit this
+            parameter. Default: ``item_id``.
+        :param timestamp_column: Name of time column, default: ``timestamp``.
+        :param session_id_column: Name of session id column whose values cannot
+            be split between train/test, default: ``None``.
+        :param session_id_processing_strategy: Strategy to process a session if
+            it crosses the boundary: ``train`` or ``test``. ``train`` means the
+            whole session goes to train, ``test`` — the whole session goes to
+            test. Default: ``test``.
+        """
+
+        super().__init__(
+            drop_cold_users=drop_cold_users,
+            drop_cold_items=drop_cold_items,
+            query_column=query_column,
+            item_column=item_column,
+            timestamp_column=timestamp_column,
+            session_id_column=session_id_column,
+            session_id_processing_strategy=session_id_processing_strategy,
+        )
+        self.N = N
+        if self.N is not None and self.N < 1:
+            msg = "N must be >= 1"
+            raise ValueError(msg)
+        self.divide_column = divide_column
+        self.seed = seed
+
+    def _sample_cuts(self, counts: np.ndarray) -> np.ndarray:
+        rng = np.random.RandomState(self.seed)
+        return rng.randint(0, counts)
+
+    def _partial_split_pandas(
+        self,
+        interactions: PandasDataFrame,
+    ) -> tuple[PandasDataFrame, PandasDataFrame]:
+        df = interactions.sort_values([self.divide_column, self.timestamp_column])
+        df["_event_rank"] = df.groupby(self.divide_column, sort=False).cumcount()
+
+        counts = df.groupby(self.divide_column, sort=False).size()
+        cuts = pd.Series(self._sample_cuts(counts.values), index=counts.index)
+        df["_cut_index"] = df[self.divide_column].map(cuts)
+
+        if self.N is not None:
+            df = df[df["_event_rank"] < df["_cut_index"] + self.N]
+
+        df["is_test"] = df["_event_rank"] >= df["_cut_index"]
+        if self.session_id_column:
+            df = self._recalculate_with_session_id_column(df)
+
+        train = df[~df["is_test"]][interactions.columns]
+        test = df[df["is_test"]][interactions.columns]
+
+        return train, test
+
+    def _partial_split_polars(
+        self,
+        interactions: PolarsDataFrame,
+    ) -> tuple[PolarsDataFrame, PolarsDataFrame]:
+        df = interactions.sort([self.divide_column, self.timestamp_column]).with_columns(
+            (pl.col(self.divide_column).cum_count().over(self.divide_column) - 1).alias("_event_rank")
+        )
+
+        counts = df.group_by(self.divide_column).len()
+        r_values = self._sample_cuts(counts["len"].to_numpy())
+        cuts_df = pl.DataFrame(
+            {
+                self.divide_column: counts[self.divide_column],
+                "_cut_index": r_values,
+            }
+        )
+        df = df.join(cuts_df, on=self.divide_column, how="left")
+
+        if self.N is not None:
+            df = df.filter(pl.col("_event_rank") < pl.col("_cut_index") + self.N)
+
+        df = df.with_columns((pl.col("_event_rank") >= pl.col("_cut_index")).alias("is_test"))
+        if self.session_id_column:
+            df = self._recalculate_with_session_id_column(df)
+
+        train = df.filter(~pl.col("is_test")).select(interactions.columns)
+        test = df.filter(pl.col("is_test")).select(interactions.columns)
+
+        return train, test
+
+    def _partial_split_spark(
+        self,
+        interactions: SparkDataFrame,
+    ) -> tuple[SparkDataFrame, SparkDataFrame]:
+        w = Window.partitionBy(self.divide_column).orderBy(self.timestamp_column)
+        df = interactions.withColumn("_event_rank", sf.row_number().over(w) - sf.lit(1))
+
+        counts = df.groupBy(self.divide_column).agg(sf.count(sf.lit(1)).alias("_count"))
+        seed_lit = sf.lit(self.seed) if self.seed is not None else sf.lit(0)
+        cuts = counts.select(
+            self.divide_column,
+            sf.pmod(
+                sf.xxhash64(sf.col(self.divide_column), seed_lit).cast("long"),
+                sf.col("_count").cast("long"),
+            )
+            .cast("long")
+            .alias("_cut_index"),
+        )
+
+        df = df.join(cuts, on=self.divide_column, how="left")
+
+        if self.N is not None:
+            df = df.filter(sf.col("_event_rank") < sf.col("_cut_index") + sf.lit(self.N))
+
+        df = df.withColumn("is_test", sf.col("_event_rank") >= sf.col("_cut_index"))
+        if self.session_id_column:
+            df = self._recalculate_with_session_id_column(df)
+
+        train = df.filter(~sf.col("is_test")).select(interactions.columns)
+        test = df.filter(sf.col("is_test")).select(interactions.columns)
+
+        return train, test
+
+    def _partial_split(self, interactions: DataFrameLike) -> tuple[DataFrameLike, DataFrameLike]:
+        if isinstance(interactions, PandasDataFrame):
+            return self._partial_split_pandas(interactions)
+        if isinstance(interactions, PolarsDataFrame):
+            return self._partial_split_polars(interactions)
+        if isinstance(interactions, SparkDataFrame):
+            return self._partial_split_spark(interactions)
+        msg = f"{self} is not implemented for {type(interactions)}"
+        raise NotImplementedError(msg)
+
+    def _core_split(self, interactions: DataFrameLike) -> tuple[DataFrameLike, DataFrameLike]:
+        return self._partial_split(interactions)

replay/utils/common.py

@@ -2,9 +2,10 @@ import functools
 import inspect
 import json
 from pathlib import Path
-from typing import Any, Callable, Union
+from typing import Any, Callable, TypeVar, Union
 
 from polars import from_pandas as pl_from_pandas
+from typing_extensions import ParamSpec
 
 from replay.data.dataset import Dataset
 from replay.preprocessing import (
@@ -16,6 +17,7 @@ from replay.splitters import (
     KFolds,
     LastNSplitter,
     NewUsersSplitter,
+    RandomNextNSplitter,
     RandomSplitter,
     RatioSplitter,
     TimeSplitter,
@@ -37,6 +39,7 @@ SavableObject = Union[
     KFolds,
     LastNSplitter,
     NewUsersSplitter,
+    RandomNextNSplitter,
     RandomSplitter,
     RatioSplitter,
     TimeSplitter,
@@ -56,6 +59,9 @@ if TORCH_AVAILABLE:
         PolarsSequentialDataset,
     ]
 
+P = ParamSpec("P")
+R = TypeVar("R")
+
 
 def save_to_replay(obj: SavableObject, path: Union[str, Path]) -> None:
     """
@@ -87,10 +93,10 @@ def _check_if_dataframe(var: Any):
         raise ValueError(msg)
 
 
-def check_if_dataframe(*args_to_check: str) -> Callable[..., Any]:
-    def decorator_func(func: Callable[..., Any]) -> Callable[..., Any]:
+def check_if_dataframe(*args_to_check: str) -> Callable[P, R]:
+    def decorator_func(func: Callable[P, R]) -> Callable[P, R]:
         @functools.wraps(func)
-        def wrap_func(*args: Any, **kwargs: Any) -> Any:
+        def wrap_func(*args: P.args, **kwargs: P.kwargs) -> R:
             extended_kwargs = {}
             extended_kwargs.update(kwargs)
             extended_kwargs.update(dict(zip(inspect.signature(func).parameters.keys(), args)))

{replay_rec-0.20.3rc0.dist-info → replay_rec-0.21.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: replay-rec
-Version: 0.20.3rc0
+Version: 0.21.0
 Summary: RecSys Library
 License-Expression: Apache-2.0
 License-File: LICENSE
@@ -14,23 +14,29 @@ Classifier: Intended Audience :: Developers
 Classifier: Intended Audience :: Science/Research
 Classifier: Natural Language :: English
 Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
-Requires-Dist: d3rlpy (>=2.8.1,<2.9)
-Requires-Dist: implicit (>=0.7.2,<0.8)
-Requires-Dist: lightautoml (>=0.4.1,<0.5)
-Requires-Dist: lightning (>=2.0.2,<=2.4.0)
-Requires-Dist: numba (>=0.50,<1)
+Provides-Extra: spark
+Provides-Extra: torch
+Provides-Extra: torch-cpu
+Requires-Dist: lightning (<2.6.0) ; extra == "torch" or extra == "torch-cpu"
+Requires-Dist: lightning ; extra == "torch"
+Requires-Dist: lightning ; extra == "torch-cpu"
 Requires-Dist: numpy (>=1.20.0,<2)
 Requires-Dist: pandas (>=1.3.5,<2.4.0)
 Requires-Dist: polars (<2.0)
-Requires-Dist: psutil (<=7.0.0)
+Requires-Dist: psutil (<=7.0.0) ; extra == "spark"
+Requires-Dist: psutil ; extra == "spark"
 Requires-Dist: pyarrow (<22.0)
-Requires-Dist: pyspark (>=3.0,<3.5)
-Requires-Dist: pytorch-optimizer (>=3.8.0,<4)
-Requires-Dist: sb-obp (>=0.5.10,<0.6)
+Requires-Dist: pyspark (>=3.0,<3.5) ; extra == "spark"
+Requires-Dist: pyspark ; extra == "spark"
+Requires-Dist: pytorch-optimizer (>=3.8.0,<3.9.0) ; extra == "torch" or extra == "torch-cpu"
+Requires-Dist: pytorch-optimizer ; extra == "torch"
+Requires-Dist: pytorch-optimizer ; extra == "torch-cpu"
 Requires-Dist: scikit-learn (>=1.6.1,<1.7.0)
 Requires-Dist: scipy (>=1.8.1,<2.0.0)
 Requires-Dist: setuptools
-Requires-Dist: torch (>=1.8,<2.9.0)
+Requires-Dist: torch (>=1.8,<3.0.0) ; extra == "torch" or extra == "torch-cpu"
+Requires-Dist: torch ; extra == "torch"
+Requires-Dist: torch ; extra == "torch-cpu"
 Requires-Dist: tqdm (>=4.67,<5)
 Project-URL: Homepage, https://sb-ai-lab.github.io/RePlay/
 Project-URL: Repository, https://github.com/sb-ai-lab/RePlay
@@ -231,7 +237,7 @@ pip install optuna
 
 2) Model compilation via OpenVINO:
 ```bash
-pip install openvino onnx
+pip install openvino onnx onnxscript
 ```
 
 3) Vector database and hierarchical search support:

replay_rec-0.21.0.dist-info/RECORD

@@ -0,0 +1,223 @@
+replay/__init__.py,sha256=v3mrDhnKFg0X1ZQBAAyAMlOgyZDPiRd01VsfpkOu9bo,225
+replay/data/__init__.py,sha256=g5bKRyF76QL_BqlED-31RnS8pBdcyj9loMsx5vAG_0E,301
+replay/data/dataset.py,sha256=yBl-yJVIokgN4prFY949tHe2UVJC_j5xdaulIoSPvQI,31252
+replay/data/dataset_utils/__init__.py,sha256=9wUvG8ZwGUvuzLU4zQI5FDcH0WVVo5YLN2ey3DterP0,55
+replay/data/dataset_utils/dataset_label_encoder.py,sha256=bxuJPhShFZBok7bQZYGNMV1etCLNTJUpyKO5MIwWack,9823
+replay/data/nn/__init__.py,sha256=Dpso6tN10moj92_NrXCVWBEAMhnGXewGC12H9fTCg0E,1228
+replay/data/nn/parquet/__init__.py,sha256=e6FDBPzlv9SMduGJOtn2EarxPXk3_wHKWConS__SmWk,786
+replay/data/nn/parquet/collate.py,sha256=tOArGUnJCILdAHEHELW7o3iuKCVD4w8BEbxNYXv7yJc,984
+replay/data/nn/parquet/constants/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+replay/data/nn/parquet/constants/batches.py,sha256=2VJwk_W9wOk6C1P4IMvlO5bWuP1i14TCFGHaL487TkI,271
+replay/data/nn/parquet/constants/device.py,sha256=EV25_HKMiPyAx7pops1Vr3YVR-9CmW_cpmxlymmyg9Q,51
+replay/data/nn/parquet/constants/filesystem.py,sha256=v23OWKtTDFnCqCYuhL4d9o-PDjihfYIMVkatWzhqoiQ,67
+replay/data/nn/parquet/constants/metadata.py,sha256=UQdTtnMPwGkpwgogrIij5C9G_HdKCZXKoGur0KFIdCM,133
+replay/data/nn/parquet/fixed_batch_dataset.py,sha256=SFfyUkFaleZ4W_oskrl_6ws8f10Dkqo71U7C6g7yuD8,5150
+replay/data/nn/parquet/impl/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+replay/data/nn/parquet/impl/array_1d_column.py,sha256=HgjJ4Dz1za_X_WfqrrXbjV_pPo5B_P3OJ3NXw8cjcBY,4823
+replay/data/nn/parquet/impl/array_2d_column.py,sha256=2pjjmlF8Kbqi11uTtMYa29mWR1Aiieajvx3w96YrW50,5633
+replay/data/nn/parquet/impl/column_protocol.py,sha256=Tjcbo3b2I834OMsaVz312AzvFMAiSydWDtN7_uMNzc0,340
+replay/data/nn/parquet/impl/indexing.py,sha256=_ETICbsn-q70iEvUAIwgoZFqrIB2UxQVvqQ4kD3F8DY,4945
+replay/data/nn/parquet/impl/masking.py,sha256=NBq6klPCAUO-Zm-VvCf1t6E_yLGbo03KvAq7Bl64ZsI,627
+replay/data/nn/parquet/impl/named_columns.py,sha256=LUlI7tsh-6kfcVAAKjpPnZvGUwaCvHOj-Zqgqh73A14,3117
+replay/data/nn/parquet/impl/numeric_column.py,sha256=A1jKct3YJegzzu8BoHHcypAgZUPFM3QR03FkdMQfxnI,3940
+replay/data/nn/parquet/impl/utils.py,sha256=MqZcSC4fQnRrrxHFg21ukrntTQkASpEh6SKftOP20Ds,446
+replay/data/nn/parquet/info/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+replay/data/nn/parquet/info/distributed_info.py,sha256=po7pl0m24pqjzlWKlfrdDWKZ4w0FEPoYLfW0KqqFCVY,850
+replay/data/nn/parquet/info/partitioning.py,sha256=2XuiRlHaQbiRHrmPrmn2JNogiHvknmvIHB8IIK3pf78,4525
+replay/data/nn/parquet/info/replicas.py,sha256=L2YnD6nvp_hjqhtptzq5KLdm8WlUskFnxbvL_06_AYQ,2480
+replay/data/nn/parquet/info/worker_info.py,sha256=sIqBqHSeFdO00dDg_Mc_6UNXDQXGcu0iQVinRy84RUE,947
+replay/data/nn/parquet/iterable_dataset.py,sha256=mQe2xvrpOU3vrVdy_tCxaFk45fqJv8mnQQS48-sQcqU,4246
+replay/data/nn/parquet/iterator.py,sha256=X5KXtjdY_uSfMlP9IXBqMzSimBqlAZbYX_Y483q_3U8,2577
+replay/data/nn/parquet/metadata/__init__.py,sha256=UZX60ANtjo6zX0p43hU9q8fBldVJNCEmGzXjHqz0MJQ,341
+replay/data/nn/parquet/metadata/metadata.py,sha256=jJOL8mieXhX18FO9lgaP95MOtO1l7tY63ldxoOAvzwA,3459
+replay/data/nn/parquet/parquet_dataset.py,sha256=pKthRppp0MstfNwOk9wMrE6wFvDecCtbTKWIri4HGr0,8017
+replay/data/nn/parquet/parquet_module.py,sha256=g53lgb-bydDg5P27I4MODnnMcRi1qjpvAw3_QQ9UgxQ,8208
+replay/data/nn/parquet/partitioned_iterable_dataset.py,sha256=BZEh2EiBKMZxi822-doyTbjDkZQQ62SxAp_NhZVZdmk,1938
+replay/data/nn/parquet/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+replay/data/nn/parquet/utils/compute_length.py,sha256=VWabulpRICy-_Z0ZBXpEmhAIlpXVwTwe9kX2L2XCdbE,2492
+replay/data/nn/schema.py,sha256=vLSDj4ZprOL9aurdcpOZ78KgNRXXuwt4wuTq5feiAvA,17115
+replay/data/nn/sequence_tokenizer.py,sha256=zh026PRsTzPhUhW1SqPOvAZOdrIDbDyBRwdkgwtvTh0,37745
+replay/data/nn/sequential_dataset.py,sha256=BcLkM_w3yF7F0EgPK5_jcreurh8k0fVJBoA9KJpp1fM,11800
+replay/data/nn/torch_sequential_dataset.py,sha256=VQ3l3SQBFxIuXKr5FpVJNE-As3MgJ7SAa4Aeb0S2yNA,11874
+replay/data/nn/utils.py,sha256=Ic3G4yZRIzBYXLmwP1VstlZXPNR7AYGCc5EyZAERp5c,3297
+replay/data/schema.py,sha256=JmYLCrNgBS5oq4O_PT724Gr1pDurHEykcqV8Xaj0XTw,15922
+replay/data/spark_schema.py,sha256=4o0Kn_fjwz2-9dBY3q46F9PL0F3E7jdVpIlX7SG3OZI,1111
+replay/data/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+replay/data/utils/batching.py,sha256=jBNhRC5jqNe2pVVlmvFLvjTo86Ud0e_Lj2P0W2yNcKY,2268
+replay/data/utils/typing/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+replay/data/utils/typing/dtype.py,sha256=QJigLH7fv-xIb_s-R_70KTZxOgl2ZJkhEhf_txziRAY,1590
+replay/metrics/__init__.py,sha256=j0PGvUehaPEZMNo9SQwJsnvzrS4bam9eHrRMQFLnMjY,2813
+replay/metrics/base_metric.py,sha256=ejtwFHktN4J8Fi1HIM3w0zlMAd8nO7-XpFi2D1iHXUQ,16010
+replay/metrics/categorical_diversity.py,sha256=3tp8n457Ob4gjM-UTB5N19u9WAF7fLDkWKk-Mth-Vzc,10769
+replay/metrics/coverage.py,sha256=e6vPItrRlI-mLNuOT5uoo5lMAAzkYGKZRxvupi21dMk,8528
+replay/metrics/descriptors.py,sha256=BHORyGKfJgPeUjgLO0u2urSTe16UQbb-HHh8soqnwDE,3893
+replay/metrics/experiment.py,sha256=6Sw8PyItn3E2R-BBa_YwrmtBV3n0uAGHHOvkhHYgMz4,8125
+replay/metrics/hitrate.py,sha256=LcOJLMs3_Dq4_pbKx95qdCdjGrX52dyWyuWUFXCyaDw,2314
+replay/metrics/map.py,sha256=dIZcmUxd2XnNC7d_d7gmq0cjNaI1hlNMaJTSHGCokQE,2572
+replay/metrics/mrr.py,sha256=qM8tVMSoyYR-kTx0mnBGppoC53SxNlZKm7JKMUmSv9U,2163
+replay/metrics/ndcg.py,sha256=izajmD243ZIK3KLm9M-NtLwxb9N3Ktj58__AAfwF6Vc,3110
+replay/metrics/novelty.py,sha256=j3p1fbUVi2QQgEre42jeQx73PYYDUhy5gYlrL4BL5b8,5488
+replay/metrics/offline_metrics.py,sha256=f_U4Tk3Ke5sR0_OYvoE2_nD6wrOCveg3DM3B9pStVUI,20454
+replay/metrics/precision.py,sha256=DRlsgY_b4bJCOSZjCA58N41REMiDt-dbagRSXxfXyvY,2256
+replay/metrics/recall.py,sha256=fzpASDiH88zcpXJZTbStQ3nuzzSdhd9k1wjF27rM4wc,2447
+replay/metrics/rocauc.py,sha256=1vaVEK7DQTL8BX-i7A64hTFWyO38aNycscPGrdWKwbA,3282
+replay/metrics/surprisal.py,sha256=HkmYrOuw3jydxFrkidjdcpAcKz2DeOnMsKqwB2g9pwY,7526
+replay/metrics/torch_metrics_builder.py,sha256=mnHrmRTOKZ_edrTrTKs7IPzKt5DkQYRd2B_8b3bB9yU,14071
+replay/metrics/unexpectedness.py,sha256=LSi-z50l3_yrvLnmToHQzm6Ygf2QpNt_zhk6jdg7QUo,6882
+replay/models/__init__.py,sha256=kECYluQZ83zRUWaHVvnt7Tg3BerHrJy9v8XfRxsqyYY,1123
+replay/models/als.py,sha256=1MFAbcx64tv0MX1wE9CM1NxKD3F3ZDhZUrmt6dvHu74,6220
+replay/models/association_rules.py,sha256=shBNsKjlii0YK-XA6bSl5Ov0ZFTnjxZbgKJU9PFYptY,14507
+replay/models/base_neighbour_rec.py,sha256=SdGb2ejpYjHmxFNTk5zwEo0RWdfPAj1vKGP_oj7IrQo,7783
+replay/models/base_rec.py,sha256=aNIEbSy8G5q92NOpDlSJbp0Z-lAkazFLa9eDAajl1wI,56067
+replay/models/cat_pop_rec.py,sha256=ed1X1PDQY41hFJ1cO3Q5OWy0rXhV5_n23hJ-QHWONtE,11968
+replay/models/cluster.py,sha256=9JcpGnbfgFa4UsyxPAa4WMuJFa3rsuAxiKoy-s_UfyE,4970
+replay/models/common.py,sha256=rFmfwwzWCWED2HaDVuSN7ZUAgaNPGPawUudgn4IApbo,2121
+replay/models/extensions/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+replay/models/extensions/ann/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+replay/models/extensions/ann/ann_mixin.py,sha256=Ua1fuwrvtISNDQ8iPV-ln8S1LDKz8-rIU2UYsMExAiU,7782
+replay/models/extensions/ann/entities/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+replay/models/extensions/ann/entities/base_hnsw_param.py,sha256=5GRdcQj4-zhNXfJ7ko2WHGHgRuXCzSHCRcRxljl1V4c,776
+replay/models/extensions/ann/entities/hnswlib_param.py,sha256=j3V4JXM_yfR6s2TjYakIXMg-zS1-MrP6an930DEIWGM,2104
+replay/models/extensions/ann/entities/nmslib_hnsw_param.py,sha256=WeEhRR4jKqgvWK_zDK8fx6kEqc2e_bc0kubvqK3iV8c,2162
+replay/models/extensions/ann/index_builders/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+replay/models/extensions/ann/index_builders/base_index_builder.py,sha256=Ul25G0FaNLOXUjrDXxZDTg7tLXlv1N6wR8kWjWICtZ0,2110
+replay/models/extensions/ann/index_builders/driver_hnswlib_index_builder.py,sha256=U8-3lRahyWmWkZ7tYuO-Avd1jX-lGh7JukC140wJ-WQ,1600
+replay/models/extensions/ann/index_builders/driver_nmslib_index_builder.py,sha256=1NLWyAJGYgp46uUBhUYQyd0stmG6DhLh7U4JEne5TFw,1308
+replay/models/extensions/ann/index_builders/executor_hnswlib_index_builder.py,sha256=cf3LhBCRRN-lBYGlJbv8vnY-KVeHAleN5cVjvd58Ibs,2476
+replay/models/extensions/ann/index_builders/executor_nmslib_index_builder.py,sha256=0DPJ3WAt0cZ5dmtZv87fmMEgYXWf8rM35f7CA_DgWZY,2618
+replay/models/extensions/ann/index_builders/nmslib_index_builder_mixin.py,sha256=AIkVnobesnTM5lrBSWf9gd0CySwFQ0vH_DjemfLS4Cs,1925
+replay/models/extensions/ann/index_inferers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+replay/models/extensions/ann/index_inferers/base_inferer.py,sha256=I39aqEc2somfndrCd-KC3XYZnYSrJ2hGpR9y6wO93NA,2524
+replay/models/extensions/ann/index_inferers/hnswlib_filter_index_inferer.py,sha256=JjT4l_XAjzUOsTAE7OS88zAgPd_h_O44oUnn2kVr8E0,2477
+replay/models/extensions/ann/index_inferers/hnswlib_index_inferer.py,sha256=CoY_oMfdcwnh87ceuSpHXu4Czle9xxeMisO8XJUuJLE,1717
+replay/models/extensions/ann/index_inferers/nmslib_filter_index_inferer.py,sha256=tjuqbkztWBU4K6qp5LPFU_GOGJf2f4oXneExtUEVUzw,3128
+replay/models/extensions/ann/index_inferers/nmslib_index_inferer.py,sha256=S5eCBZlTXxEAeX6yeZGC7j56gOcJ7lMNb4Cs_5PEj9E,2203
+replay/models/extensions/ann/index_inferers/utils.py,sha256=6IST2FPSY3nuYu5KqzRpd4FgdaV3GnQRQlxp9LN_yyA,641
+replay/models/extensions/ann/index_stores/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+replay/models/extensions/ann/index_stores/base_index_store.py,sha256=u4l2ybAXX92ZMGK7NqqosbKF75QgFqhAMVadd5ePj6Y,910
+replay/models/extensions/ann/index_stores/hdfs_index_store.py,sha256=0zDq9PdDOiD6HvtZlfjTbuJHfeTOWBTQ_HiuqZmoxtA,3090
+replay/models/extensions/ann/index_stores/shared_disk_index_store.py,sha256=thl4T1uYU4Gtk4nBao_qK8CbFBdX1xmXNishxgfCd-I,2030
+replay/models/extensions/ann/index_stores/spark_files_index_store.py,sha256=QP_8mE7EIBbePIe0AB-IWuJLRA5MR3wswCEt8oHzn-0,3617
+replay/models/extensions/ann/index_stores/utils.py,sha256=6r2GP_EFCaCguolW857pb4lRS8rh6_Nv_Edso9_j5no,3756
+replay/models/extensions/ann/utils.py,sha256=AgQvThi_DvEtakQeTno9hVZVWiWMFHKTjRcQ2wLa5vk,1222
+replay/models/kl_ucb.py,sha256=L6vC2KsTBTTx4ckmGhWybOiLa5Wt54N7cgl7jS2FQRg,6731
+replay/models/knn.py,sha256=HEiGHHQg9pV1_EIWZHfK-XD0BNAm1bj1c0ND9rYnj3k,8992
+replay/models/lin_ucb.py,sha256=iAR3PbbaQKqmisOKEx9ZyfpxnxcZomr6YauG4mvSakU,18800
+replay/models/nn/__init__.py,sha256=AT3o1qXaxUq4_QIGlcGuSs54ZpueOo-SbpZwuGI-6os,41
+replay/models/nn/loss/__init__.py,sha256=s3iO9QTZvLz_ony2b5K0hEmDmitrXQnAe9j6BRxLpR4,53
+replay/models/nn/loss/sce.py,sha256=mRJZYmwQNT-kMi66pXrE1-OdM7y_YEQFHzC37odnEo4,5165
+replay/models/nn/optimizer_utils/__init__.py,sha256=9aiEk662v9-qJgzi8TZYaaqQSiZWr4ZleFHwcLOZX14,219
+replay/models/nn/optimizer_utils/optimizer_factory.py,sha256=OJPX4XD_uG0iZKzxmhzT60uS66swGtpZnAV5A98vcgs,3439
+replay/models/nn/sequential/__init__.py,sha256=CI2n0cxs_amqJrwBMq6n0Z_uBOu7CGXfagqvE4Jlmjw,128
+replay/models/nn/sequential/bert4rec/__init__.py,sha256=JfZqHOGxcvOkICl5cWmZbZhaKXpkIvua-Wj57VWWEhw,399
+replay/models/nn/sequential/bert4rec/dataset.py,sha256=Y63LESZYqKDG3OSvrWRy4Tgkib24VKJ9c9qJsGarr5k,12110
+replay/models/nn/sequential/bert4rec/lightning.py,sha256=vxAf1H1VfLqgZhOz9fxEMmw4L3wfOr_wFnWHn_vPE34,28351
+replay/models/nn/sequential/bert4rec/model.py,sha256=C1AKcQ8KF0XMXERwrFneW9kg7hzc-9FIqhCc-t91F7o,17469
+replay/models/nn/sequential/callbacks/__init__.py,sha256=Q7mSZ_RB6iyD7QZaBL_NJ0uh8cRfgxq7gtPHbkSyhoo,282
+replay/models/nn/sequential/callbacks/prediction_callbacks.py,sha256=UtEzO9_f5Jwku9dbz7twr4o2_cV3L-viC4lQuce5l1c,10808
+replay/models/nn/sequential/callbacks/validation_callback.py,sha256=ydcNkUhaFD78ogqZWySzzKg4BaPyEkaRqmLiD4qFDzM,6583
+replay/models/nn/sequential/compiled/__init__.py,sha256=eSVcCaUH5cDJQRbC7K99X7uMNR-Z-KR4TmYOGKWWJCI,531
+replay/models/nn/sequential/compiled/base_compiled_model.py,sha256=f4AuTyx5tufQOtOWUSEgj1cWvMZzSL7YN2Z-PtURgTY,10478
+replay/models/nn/sequential/compiled/bert4rec_compiled.py,sha256=woGI3qk4J2Rb5FyaDwpSCuG-AMfyH34F6Bt5pV-wqk0,6798
+replay/models/nn/sequential/compiled/sasrec_compiled.py,sha256=eCRpxPdu94KyvczYJx2jgt6xaTZ3RpNYvcfyyyTYuiA,6170
+replay/models/nn/sequential/postprocessors/__init__.py,sha256=89LGzkNHukcuC2-rfpiz7vmv1zyk6MNY-8zaXrvtn0M,164
+replay/models/nn/sequential/postprocessors/_base.py,sha256=Pi8vWcaiqj3XddaxbiOYd5ME7ZfIkk0GPoCgpFKdO0g,1300
+replay/models/nn/sequential/postprocessors/postprocessors.py,sha256=fclLmGkJbWAnNBw-Rvc_kKQsw0rUF2jfJ7s6VF8ge4I,8021
+replay/models/nn/sequential/sasrec/__init__.py,sha256=c6130lRpPkcbuGgkM7slagBIgH7Uk5zUtSzFDEwAsik,250
+replay/models/nn/sequential/sasrec/dataset.py,sha256=Le_rG-MoCpWoSKdrEJOyLo3S617FLMEMI8Ix51YEQx0,9452
+replay/models/nn/sequential/sasrec/lightning.py,sha256=nJthkJvgp-nBy6mtt_5PvzUFihArXYTnZdAih85F01U,27067
+replay/models/nn/sequential/sasrec/model.py,sha256=xLPz2HvPkDGMaXiWcyug7auQgBG-ai37OPFb7_jvorU,27876
+replay/models/optimization/__init__.py,sha256=N8xCuzu0jQGwHrIBjuTRf-ZcZuBJ6FB0d9C5a7izJQU,338
+replay/models/optimization/optuna_mixin.py,sha256=pKu-Vw9l2LsDycubpdJiLkC1eE4pKrDG0T2lhUgRUB4,11960
+replay/models/optimization/optuna_objective.py,sha256=UHWOJwBngPA3IRz9yAMEWPg00oyb7Wq9PXuRPYHIiLE,7538
+replay/models/pop_rec.py,sha256=Ju9y2rU2vW_jFU9-W15fbbr5_ZzYGihSjSxsqKsAf0Q,4964
+replay/models/query_pop_rec.py,sha256=UNsHtf3eQpJom73ZmEO5us4guI4SnCLJYTfuUpRgqes,4086
+replay/models/random_rec.py,sha256=9SC012_X3sNzrAjDG1CPGhjisZb6gnv4VCW7yIMSNpk,8066
+replay/models/slim.py,sha256=OAdTS64bObZujzHkq8vfP1kkoLMSWxk1KLg6lCCA0N8,4551
+replay/models/thompson_sampling.py,sha256=gcjlVl1mPiEVt70y8frA762O-eCZzd3SVg1lnDRCEHk,1939
+replay/models/ucb.py,sha256=b2qFgvOAZcyv5triPk18duqF_jt-ty7mypenjRLNWwQ,6952
+replay/models/wilson.py,sha256=o7aUWjq3648dAfgGBoWD5Gu-HzdyobPMaH2lzCLijiA,4558
+replay/models/word2vec.py,sha256=atfj6GjR_L-TdurRFr1yi7B3BicJ3ZdFxixW9RfojJs,8882
+replay/nn/__init__.py,sha256=Bd_Xi9s5g1zWSjMwk50ztG9oezhs37r2L4-mfB-gEsg,256
+replay/nn/agg.py,sha256=JneTgVlo00cEg5FxzIp6NvNVOXqvL45e9vsXPP_5ztg,3799
+replay/nn/attention.py,sha256=RR_KsqvnrZ1ZYr51KTBA9q5gB-0sqhmakjH1JdIo9dE,7812
+replay/nn/embedding.py,sha256=xY_zPpC055cTXAZ8TShUYP3ZrBUA2HQwn4dkOCKXYJ0,11876
+replay/nn/ffn.py,sha256=ivOFu14289URepyEFxYov_XNYMUrINjU-2rEqoXxbnU,4618
+replay/nn/head.py,sha256=csjwQrcA7M7FebgSL1tKDbjfaoni52CymQR0Zt8RhWg,2084
+replay/nn/lightning/__init__.py,sha256=jHiwtYuboGUY4Of18zrkvdWD0xXJ_zuo83-XgiqxSfY,36
+replay/nn/lightning/callback/__init__.py,sha256=ImNEJeIK-wJnqdkZgP8tWTDQHaS9xYqzTEf3FEM0XAw,253
+replay/nn/lightning/callback/metrics_callback.py,sha256=dIu1wDtqjXH6ogFGsh2L-dpkgz7OKjtTrVbBLrI4pjg,6986
+replay/nn/lightning/callback/predictions_callback.py,sha256=e9PeXNyyGz-m46FEaafgCToPEVC9T5Cb8Q4sFArnpLY,11347
+replay/nn/lightning/module.py,sha256=jFvevwiriY9alZMBw6KAiRMsJv-dJ8fEVrenVRiuWeI,5246
+replay/nn/lightning/optimizer.py,sha256=1tXhz9RIBHLpEQtZ1PUzCAc4mn6Q_E38zR0nf5km6U8,1778
+replay/nn/lightning/postprocessor/__init__.py,sha256=LhUeOWDD5vRBDXF2tQEjvPKH1rNIlrf5KPbcV66AdtQ,77
+replay/nn/lightning/postprocessor/_base.py,sha256=X0LtYItmxlXt4Sxk3cOdyIK3FG5dijQzyh5Kv6s5FjE,1592
+replay/nn/lightning/postprocessor/seen_items.py,sha256=h-sfD3vmNCdS7lYvqCfqw9oPqutmaSIuZ0CIidG0Y30,2922
+replay/nn/lightning/scheduler.py,sha256=CUuynPTFrKBrkpmbWR-xpfAkHZ0Vfz_THUDo3uoZi8k,2714
+replay/nn/loss/__init__.py,sha256=YXAXQIN0coj8MxeK5isTGXgvMxhH5pUO6j1D3d7jl3A,471
+replay/nn/loss/base.py,sha256=oD1vATWoQDi45zG9EPjg3hgDrfpr4ue_rQFfArn1dFs,8871
+replay/nn/loss/bce.py,sha256=cPlxdJTBZ0b22K6V9ve4qo7xkp99CjEsnl3_vVGphqs,8373
+replay/nn/loss/ce.py,sha256=jOmhLtKD_E0jX8tUfXpsmaaQVHKKiwXW9USB_GyN3ZU,13218
+replay/nn/loss/login_ce.py,sha256=NER_Hbs_H3IXn_bkgwG25VQNQ6ZjjDcxq-aMI7pC2eM,16498
+replay/nn/loss/logout_ce.py,sha256=KhcYyCnUzLZR1sFpxM6_QliLoxmC6MJoLkPOgf_ZYzU,10306
+replay/nn/mask.py,sha256=Jbx7sulGZYfasNaD9CZzJma0cEVaDlxdpzs295507II,3329
+replay/nn/normalization.py,sha256=Z86t5WCr4KfVR9qCCe-EIAwwomnIIxb11PP88WHA1JI,187
+replay/nn/output.py,sha256=6uecMOMN4FGoQ-NzKGacZnlrk_9TwQswpC-x3G_DMTY,1291
+replay/nn/sequential/__init__.py,sha256=jet_ueMz5Bm087JDph7ln87NID7DbCb0WENj-tjoOGg,229
+replay/nn/sequential/sasrec/__init__.py,sha256=8crj-JL8xeP-cCOCnxCSVF_-R6feKhj0YRHOcaMsqrU,213
+replay/nn/sequential/sasrec/agg.py,sha256=e-IkIO-MMbei2UGxTUopWvloguJoVaZiN31sXkdUVag,2004
+replay/nn/sequential/sasrec/diff_transformer.py,sha256=4ehM5EMizajmWBAzmcj3CYSFl21V1R2b7RDRJlx3O4Q,4790
+replay/nn/sequential/sasrec/model.py,sha256=sQ2FvfDyZ3G6PjbNME--fMboqUt66z9J8t8YYlJ9J6Q,14803
+replay/nn/sequential/sasrec/transformer.py,sha256=sJf__IPnhbJWDPuFTPSbBGSSntznQtS-hJtJo3iFBkw,4037
+replay/nn/sequential/twotower/__init__.py,sha256=-rEASPqKCbS55MTTgeDZ5irfWfM9or1vNTHZnJN2AcU,124
+replay/nn/sequential/twotower/model.py,sha256=VxUUjldHndCkDjrXGqmxGnTi5fh8vmnr7XNBpYjsqW8,28659
+replay/nn/sequential/twotower/reader.py,sha256=j4mlKx5Lf3hFnSgaxMLkuqWLZd3dkLchDI4JEuZHLGY,3674
+replay/nn/transform/__init__.py,sha256=9PeaDHmftb0s1gEEgJRNWw6Bl2wfE_-lImatipaHUQ0,705
+replay/nn/transform/copy.py,sha256=ZfNXbMJYTwXDMJ5T8ib9Dh5XOGLjj7gGB4NbBExFZiM,1302
+replay/nn/transform/grouping.py,sha256=XOJoVBk234DI6x05Kqr7KOjLetDaLp2NMAJWHecQcsI,1384
+replay/nn/transform/negative_sampling.py,sha256=R5di5-IuNtpbjcjHYcBTZYd6Lk2R5_I77PVioaL5s5w,7475
+replay/nn/transform/next_token.py,sha256=UONG8_J-UxZdRCOEcz7fvU40k-hvE_h7ff014L9Ukpg,4491
+replay/nn/transform/rename.py,sha256=_uD2e1UmtBRyOTVpHUnZ5xhePmClaGQsc0g7Es-rupE,1026
+replay/nn/transform/reshape.py,sha256=sgswIogWHUwOVp02k13Qopn84LofqLoA4M7U1GAfmio,1359
+replay/nn/transform/sequence_roll.py,sha256=7jf42SgWHU1L7SirqQWXx0h9a6VQQ29kehE4LmdUt9o,1531
+replay/nn/transform/template/__init__.py,sha256=lYzAekZUXwncGR66Nq8YypplGOtL00GFfm0PalGiY5g,106
+replay/nn/transform/template/sasrec.py,sha256=FoOhroe-S0JPaxIQ3Ba-3_gyslgj47RoLL2geOxNAO4,1906
+replay/nn/transform/template/twotower.py,sha256=BIlbqTfKEMcyx2Ksr4qzAD0h0mdhiTLa1xcmZ2e8Ksc,896
+replay/nn/transform/token_mask.py,sha256=WcalZkY2UCoNiq2mBtu8fqYFOUfqCh21XyDMgvIpeB4,2529
+replay/nn/transform/trim.py,sha256=mPn6LPxu3c3yE14heMSRsDEU4h94tkFiRr62mOa3lKg,1608
+replay/nn/utils.py,sha256=GumtN-QRP9ljXYti3YvuNk13e0Q92xvkYuCJBhaViCI,801
+replay/preprocessing/__init__.py,sha256=c6wFPAc6lATyp0lE-ZDjHMsXyEMPKX7Usuqylv6H5XQ,597
+replay/preprocessing/converter.py,sha256=JQ-4u5x0eXtswl1iH-bZITBXQov1nebnZ6XcvpD8Twk,4417
+replay/preprocessing/discretizer.py,sha256=jzYqvoSVmiL-oS-ri9Om0vSDoU8bCQimjUoe7FiPfLU,27024
+replay/preprocessing/filters.py,sha256=cCX8BikKNqcAGFpJkYssQkR_6tUjjktSlpZOxK1ezUw,49930
+replay/preprocessing/history_based_fp.py,sha256=oEu1CkCz7xcGbPdSTHfhTe1NimnFo50Arn8qngRBgE8,18702
+replay/preprocessing/label_encoder.py,sha256=puedlFGitjI_yi4uxRIR6L4Wz6oZ93gIEPeylC-jCtI,41459
+replay/preprocessing/sessionizer.py,sha256=G6i0K3FwqtweRxvcSYraJ-tBWAT2HnV-bWHHlIZJF-s,12217
+replay/preprocessing/utils.py,sha256=e-JRoadbeTe3Qvp_NXMZNQkmgedeR6iJLyO_82xKPd0,7109
+replay/scenarios/__init__.py,sha256=XXAKEQPTLlve-0O6NPwFgahFrb4oGcIq3HaYaaGxG2E,94
+replay/scenarios/fallback.py,sha256=dO3s9jqYup4rbgMaY6Z6HGm1r7SXkm7jOvNZDr5zm_U,7138
+replay/splitters/__init__.py,sha256=9vhrZ8nCgq_NYJkv4wn0JYqhKURZH6Z8IyRNN1BX6AI,510
+replay/splitters/base_splitter.py,sha256=zvYVEHBYrK8Y2qPv3kYachfLFwR9-kUAiU1UJSNGS8A,7749
+replay/splitters/cold_user_random_splitter.py,sha256=32VgAHiwk9Emkofu1KqwGZrrFiyrYtSQ3YPdt5p_XoQ,4423
+replay/splitters/k_folds.py,sha256=RDDL3gE6M5qfK5Ig-pxxJeq3O4uxsWJjLFQRRzQ2Ssg,6211
+replay/splitters/last_n_splitter.py,sha256=hMWIGYFg17LioT08VBXut5Ic-w9oXsKd739cy2xuwYs,15368
+replay/splitters/new_users_splitter.py,sha256=NksAdl_wL9zwHj3cY5NqrrnkOajgyUDloSsRZ9HUE48,9160
+replay/splitters/random_next_n_splitter.py,sha256=aRqRe1jll7o5Hj-si-jyr341T4nXLfpX39crwVpLl-Y,8713
+replay/splitters/random_splitter.py,sha256=0DO0qulT0jp_GXswmFh3BMJ7utS-z9e-r5jIrmTKGC4,2989
+replay/splitters/ratio_splitter.py,sha256=rFWN-nKBYx1qKrmtYzjYf08DWFiKOCo5ZRUz-NHJFfs,17506
+replay/splitters/time_splitter.py,sha256=0ZAMK26b--1wjrfzCuNVBh7gMPTa8SGf4LMEgACiUxA,9013
+replay/splitters/two_stage_splitter.py,sha256=8Zn6BTJmZg04CD4l2jmil2dEu6xtglJaSS5mkotIXRc,17823
+replay/utils/__init__.py,sha256=3Skc9bUISEPPMMxdUCCT_S1q-i7cAT3KT0nExe-VMrw,343
+replay/utils/common.py,sha256=_sBKR1hlZavXll8NN0hyGDIEdLakccPofu8JskHpBgk,5488
+replay/utils/dataframe_bucketizer.py,sha256=LipmBBQkdkLGroZpbP9i7qvTombLdMxo2dUUys1m5OY,3748
+replay/utils/distributions.py,sha256=UuhaC9HI6HnUXW97fEd-TsyDk4JT8t7k1T_6l5FpOMs,1203
+replay/utils/model_handler.py,sha256=6WRyd39B-UXTtKTHWD_ssYN1vMmkjd417bwKb50uqJY,5754
+replay/utils/session_handler.py,sha256=fQo2wseow8yuzKnEXT-aYAXcQIgRbTTXp0v7g1VVi0w,5138
+replay/utils/spark_utils.py,sha256=GbRp-MuUoO3Pc4chFvlmo9FskSlRLeNlC3Go5pEJ6Ok,27411
+replay/utils/time.py,sha256=J8asoQBytPcNw-BLGADYIsKeWhIoN1H5hKiX9t2AMqo,9376
+replay/utils/types.py,sha256=rD9q9CqEXgF4yy512Hv2nXclvwcnfodOnhBZ1HSUI4c,1260
+replay_rec-0.21.0.dist-info/METADATA,sha256=9KaxfPOyxMV7l4O3L3qy59ACnvB1-ZbhwynJGKKlXzw,13573
+replay_rec-0.21.0.dist-info/WHEEL,sha256=zp0Cn7JsFoX2ATtOhtaFYIiE2rmFAD4OcMhtUki8W3U,88
+replay_rec-0.21.0.dist-info/licenses/LICENSE,sha256=rPmcA7UrHxBChEAAlJyE24qUWKKl9yLQXxFsKeg_LX4,11344
+replay_rec-0.21.0.dist-info/licenses/NOTICE,sha256=k0bo4KHiHLRax5K3XKTTrf2Fi8V91mJ-R3FMdh6Reg0,2002
+replay_rec-0.21.0.dist-info/RECORD,,

replay/experimental/metrics/__init__.py

@@ -1,62 +0,0 @@
-"""
-Most metrics require dataframe with recommendations
-and dataframe with ground truth values —
-which objects each user interacted with.
-
-- recommendations (Union[pandas.DataFrame, spark.DataFrame]):
-    predictions of a recommender system,
-    DataFrame with columns ``[user_id, item_id, relevance]``
-- ground_truth (Union[pandas.DataFrame, spark.DataFrame]):
-    test data, DataFrame with columns
-    ``[user_id, item_id, timestamp, relevance]``
-
-Metric is calculated for all users, presented in ``ground_truth``
-for accurate metric calculation in case when the recommender system generated
-recommendation not for all users.  It is assumed, that all users,
-we want to calculate metric for, have positive interactions.
-
-But if we have users, who observed the recommendations, but have not responded,
-those users will be ignored and metric will be overestimated.
-For such case we propose additional optional parameter ``ground_truth_users``,
-the dataframe with all users, which should be considered during the metric calculation.
-
-- ground_truth_users (Optional[Union[pandas.DataFrame, spark.DataFrame]]):
-    full list of users to calculate metric for, DataFrame with ``user_id`` column
-
-Every metric is calculated using top ``K`` items for each user.
-It is also possible to calculate metrics
-using multiple values for ``K`` simultaneously.
-In this case the result will be a dictionary and not a number.
-
-Make sure your recommendations do not contain user-item duplicates
-as duplicates could lead to the wrong calculation results.
-
-- k (Union[Iterable[int], int]):
-    a single number or a list, specifying the
-    truncation length for recommendation list for each user
-
-By default, metrics are averaged by users,
-but you can alternatively use method ``metric.median``.
-Also, you can get the lower bound
-of ``conf_interval`` for a given ``alpha``.
-
-Diversity metrics require extra parameters on initialization stage,
-but do not use ``ground_truth`` parameter.
-
-For each metric, a formula for its calculation is given, because this is
-important for the correct comparison of algorithms, as mentioned in our
-`article <https://arxiv.org/abs/2206.12858>`_.
-"""
-
-from replay.experimental.metrics.base_metric import Metric, NCISMetric
-from replay.experimental.metrics.coverage import Coverage
-from replay.experimental.metrics.hitrate import HitRate
-from replay.experimental.metrics.map import MAP
-from replay.experimental.metrics.mrr import MRR
-from replay.experimental.metrics.ncis_precision import NCISPrecision
-from replay.experimental.metrics.ndcg import NDCG
-from replay.experimental.metrics.precision import Precision
-from replay.experimental.metrics.recall import Recall
-from replay.experimental.metrics.rocauc import RocAuc
-from replay.experimental.metrics.surprisal import Surprisal
-from replay.experimental.metrics.unexpectedness import Unexpectedness