replay-rec 0.20.0rc0__tar.gz → 0.20.1__tar.gz

{replay_rec-0.20.0rc0 → replay_rec-0.20.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: replay-rec
-Version: 0.20.0rc0
+Version: 0.20.1
 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 (>=1.13.1,<1.14)
 Requires-Dist: setuptools
-Requires-Dist: torch (>=1.8,<3.0.0)
+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

{replay_rec-0.20.0rc0 → replay_rec-0.20.1}/pyproject.toml

@@ -40,19 +40,19 @@ dependencies = [
     "scikit-learn (>=1.6.1,<1.7.0)",
     "pyarrow (<22.0)",
     "tqdm (>=4.67,<5)",
-    "torch (>=1.8,<3.0.0)",
-    "lightning (>=2.0.2,<=2.4.0)",
-    "pytorch-optimizer (>=3.8.0,<4)",
-    "lightautoml (>=0.4.1,<0.5)",
-    "numba (>=0.50,<1)",
-    "sb-obp (>=0.5.10,<0.6)",
-    "d3rlpy (>=2.8.1,<2.9)",
-    "implicit (>=0.7.2,<0.8)",
-    "pyspark (>=3.0,<3.5)",
-    "psutil (<=7.0.0)",
+    "pyspark (>=3.0,<3.5); extra == 'spark'",
+    "psutil (<=7.0.0); extra == 'spark'",
+    "torch (>=1.8, <3.0.0); extra == 'torch' or extra == 'torch-cpu'",
+    "pytorch-optimizer (>=3.8.0,<3.9.0); extra == 'torch' or extra == 'torch-cpu'",
+    "lightning (<2.6.0); extra == 'torch' or extra == 'torch-cpu'",
 ]
 dynamic = ["dependencies"]
-version = "0.20.0.preview"
+version = "0.20.1"
+
+[project.optional-dependencies]
+spark = ["pyspark", "psutil"]
+torch = ["torch", "pytorch-optimizer", "lightning"]
+torch-cpu = ["torch", "pytorch-optimizer", "lightning"]
 
 [project.urls]
 homepage = "https://sb-ai-lab.github.io/RePlay/"
@@ -66,6 +66,13 @@ target-version = ["py39", "py310", "py311", "py312"]
 packages = [{include = "replay"}]
 exclude = [
     "replay/conftest.py",
+    "replay/experimental",
+]
+
+[tool.poetry.dependencies]
+torch = [
+    {markers = "extra == 'torch-cpu' and extra !='torch'", source = "torch-cpu-mirror"},
+    {markers = "extra == 'torch' and extra !='torch-cpu'", source = "PyPI"},
 ]
 
 [tool.poetry.group.dev.dependencies]
@@ -88,9 +95,14 @@ docutils = "0.16"
 data-science-types = "0.2.23"
 filelock = "~3.14.0"
 
+[[tool.poetry.source]]
+name = "torch-cpu-mirror"
+url = "https://download.pytorch.org/whl/cpu"
+priority = "explicit"
+
 [tool.poetry-dynamic-versioning]
 enable = false
-format-jinja = """0.20.0{{ env['PACKAGE_SUFFIX'] }}"""
+format-jinja = """0.20.1{{ env['PACKAGE_SUFFIX'] }}"""
 vcs = "git"
 
 [tool.ruff]

{replay_rec-0.20.0rc0 → replay_rec-0.20.1}/replay/__init__.py

@@ -4,4 +4,4 @@
 # functionality removed in Python 3.12 is used in downstream packages (like lightfm)
 import setuptools as _
 
-__version__ = "0.20.0.preview"
+__version__ = "0.20.1"

{replay_rec-0.20.0rc0 → replay_rec-0.20.1}/replay/data/nn/sequence_tokenizer.py

@@ -15,7 +15,6 @@ from replay.data import Dataset, FeatureHint, FeatureSchema, FeatureSource, Feat
 from replay.data.dataset_utils import DatasetLabelEncoder
 from replay.preprocessing import LabelEncoder, LabelEncodingRule
 from replay.preprocessing.label_encoder import HandleUnknownStrategies
-from replay.utils import deprecation_warning
 
 if TYPE_CHECKING:
     from .schema import TensorFeatureInfo, TensorFeatureSource, TensorSchema
@@ -406,7 +405,6 @@ class SequenceTokenizer:
             tensor_feature._set_cardinality(dataset_feature.cardinality)
 
     @classmethod
-    @deprecation_warning("with `use_pickle` equals to `True` will be deprecated in future versions")
     def load(cls, path: str, use_pickle: bool = False, **kwargs) -> "SequenceTokenizer":
         """
         Load tokenizer object from the given path.
@@ -450,12 +448,16 @@ class SequenceTokenizer:
             tokenizer._encoder._features_columns = encoder_features_columns
             tokenizer._encoder._encoding_rules = tokenizer_dict["encoder"]["encoding_rules"]
         else:
+            warnings.warn(
+                "with `use_pickle` equals to `True` will be deprecated in future versions",
+                DeprecationWarning,
+                stacklevel=2,
+            )
             with open(path, "rb") as file:
                 tokenizer = pickle.load(file)
 
         return tokenizer
 
-    @deprecation_warning("with `use_pickle` equals to `True` will be deprecated in future versions")
     def save(self, path: str, use_pickle: bool = False) -> None:
         """
         Save the tokenizer to the given path.
@@ -496,6 +498,11 @@ class SequenceTokenizer:
             with open(base_path / "init_args.json", "w+") as file:
                 json.dump(tokenizer_dict, file)
         else:
+            warnings.warn(
+                "with `use_pickle` equals to `True` will be deprecated in future versions",
+                DeprecationWarning,
+                stacklevel=2,
+            )
             with open(path, "wb") as file:
                 pickle.dump(self, file)
 

{replay_rec-0.20.0rc0 → replay_rec-0.20.1}/replay/data/nn/sequential_dataset.py

@@ -110,17 +110,27 @@ class SequentialDataset(abc.ABC):
 
         sequential_dict = {}
         sequential_dict["_class_name"] = self.__class__.__name__
-        self._sequences.reset_index().to_json(base_path / "sequences.json")
+
+        df = SequentialDataset._convert_array_to_list(self._sequences)
+        df.reset_index().to_parquet(base_path / "sequences.parquet")
         sequential_dict["init_args"] = {
             "tensor_schema": self._tensor_schema._get_object_args(),
             "query_id_column": self._query_id_column,
             "item_id_column": self._item_id_column,
-            "sequences_path": "sequences.json",
+            "sequences_path": "sequences.parquet",
         }
 
         with open(base_path / "init_args.json", "w+") as file:
             json.dump(sequential_dict, file)
 
+    @staticmethod
+    def _convert_array_to_list(df):
+        return df.map(lambda x: x.tolist() if isinstance(x, np.ndarray) else x)
+
+    @staticmethod
+    def _convert_list_to_array(df):
+        return df.map(lambda x: np.array(x) if isinstance(x, list) else x)
+
 
 class PandasSequentialDataset(SequentialDataset):
     """
@@ -149,7 +159,7 @@ class PandasSequentialDataset(SequentialDataset):
         if sequences.index.name != query_id_column:
             sequences = sequences.set_index(query_id_column)
 
-        self._sequences = sequences
+        self._sequences = SequentialDataset._convert_list_to_array(sequences)
 
     def __len__(self) -> int:
         return len(self._sequences)
@@ -206,7 +216,8 @@ class PandasSequentialDataset(SequentialDataset):
         with open(base_path / "init_args.json") as file:
             sequential_dict = json.loads(file.read())
 
-        sequences = pd.read_json(base_path / sequential_dict["init_args"]["sequences_path"])
+        sequences = pd.read_parquet(base_path / sequential_dict["init_args"]["sequences_path"])
+        sequences = cls._convert_array_to_list(sequences)
         dataset = cls(
             tensor_schema=TensorSchema._create_object_by_args(sequential_dict["init_args"]["tensor_schema"]),
             query_id_column=sequential_dict["init_args"]["query_id_column"],
@@ -258,18 +269,11 @@ class PolarsSequentialDataset(PandasSequentialDataset):
 
     def _convert_polars_to_pandas(self, df: PolarsDataFrame) -> PandasDataFrame:
         pandas_df = PandasDataFrame(df.to_dict(as_series=False))
-
-        for column in pandas_df.select_dtypes(include="object").columns:
-            if isinstance(pandas_df[column].iloc[0], list):
-                pandas_df[column] = pandas_df[column].apply(lambda x: np.array(x))
-
+        pandas_df = SequentialDataset._convert_list_to_array(pandas_df)
         return pandas_df
 
     def _convert_pandas_to_polars(self, df: PandasDataFrame) -> PolarsDataFrame:
-        for column in df.select_dtypes(include="object").columns:
-            if isinstance(df[column].iloc[0], np.ndarray):
-                df[column] = df[column].apply(lambda x: x.tolist())
-
+        df = SequentialDataset._convert_array_to_list(df)
         return pl.from_dict(df.to_dict("list"))
 
     @classmethod
@@ -290,7 +294,7 @@ class PolarsSequentialDataset(PandasSequentialDataset):
         with open(base_path / "init_args.json") as file:
             sequential_dict = json.loads(file.read())
 
-        sequences = pl.DataFrame(pd.read_json(base_path / sequential_dict["init_args"]["sequences_path"]))
+        sequences = pl.from_pandas(pd.read_parquet(base_path / sequential_dict["init_args"]["sequences_path"]))
         dataset = cls(
             tensor_schema=TensorSchema._create_object_by_args(sequential_dict["init_args"]["tensor_schema"]),
             query_id_column=sequential_dict["init_args"]["query_id_column"],

{replay_rec-0.20.0rc0 → replay_rec-0.20.1}/replay/data/nn/torch_sequential_dataset.py

@@ -1,3 +1,4 @@
+import warnings
 from collections.abc import Generator, Sequence
 from typing import TYPE_CHECKING, NamedTuple, Optional, Union, cast
 
@@ -5,8 +6,6 @@ import numpy as np
 import torch
 from torch.utils.data import Dataset as TorchDataset
 
-from replay.utils import deprecation_warning
-
 if TYPE_CHECKING:
     from .schema import TensorFeatureInfo, TensorMap, TensorSchema
     from .sequential_dataset import SequentialDataset
@@ -29,16 +28,12 @@ class TorchSequentialDataset(TorchDataset):
     Torch dataset for sequential recommender models
     """
 
-    @deprecation_warning(
-        "`padding_value` parameter will be removed in future versions. "
-        "Instead, you should specify `padding_value` for each column in TensorSchema"
-    )
     def __init__(
         self,
         sequential: "SequentialDataset",
         max_sequence_length: int,
         sliding_window_step: Optional[int] = None,
-        padding_value: int = 0,
+        padding_value: Optional[int] = None,
     ) -> None:
         """
         :param sequential: sequential dataset
@@ -53,6 +48,15 @@ class TorchSequentialDataset(TorchDataset):
         self._sequential = sequential
         self._max_sequence_length = max_sequence_length
         self._sliding_window_step = sliding_window_step
+        if padding_value is not None:
+            warnings.warn(
+                "`padding_value` parameter will be removed in future versions. "
+                "Instead, you should specify `padding_value` for each column in TensorSchema",
+                DeprecationWarning,
+                stacklevel=2,
+            )
+        else:
+            padding_value = 0
         self._padding_value = padding_value
         self._index2sequence_map = self._build_index2sequence_map()
 
@@ -177,17 +181,13 @@ class TorchSequentialValidationDataset(TorchDataset):
     Torch dataset for sequential recommender models that additionally stores ground truth
     """
 
-    @deprecation_warning(
-        "`padding_value` parameter will be removed in future versions. "
-        "Instead, you should specify `padding_value` for each column in TensorSchema"
-    )
     def __init__(
         self,
         sequential: "SequentialDataset",
         ground_truth: "SequentialDataset",
         train: "SequentialDataset",
         max_sequence_length: int,
-        padding_value: int = 0,
+        padding_value: Optional[int] = None,
         sliding_window_step: Optional[int] = None,
         label_feature_name: Optional[str] = None,
     ):

{replay_rec-0.20.0rc0 → replay_rec-0.20.1}/replay/models/lin_ucb.py

@@ -1,5 +1,6 @@
 import warnings
-from typing import Union
+from os.path import join
+from typing import Optional, Union
 
 import numpy as np
 import pandas as pd
@@ -8,7 +9,11 @@ from tqdm import tqdm
 
 from replay.data.dataset import Dataset
 from replay.utils import SparkDataFrame
-from replay.utils.spark_utils import convert2spark
+from replay.utils.spark_utils import (
+    convert2spark,
+    load_pickled_from_parquet,
+    save_picklable_to_parquet,
+)
 
 from .base_rec import HybridRecommender
 
@@ -177,6 +182,7 @@ class LinUCB(HybridRecommender):
     _study = None  # field required for proper optuna's optimization
     linucb_arms: list[Union[DisjointArm, HybridArm]]  # initialize only when working within fit method
     rel_matrix: np.array  # matrix with relevance scores from predict method
+    _num_items: int  # number of items/arms
 
     def __init__(
         self,
@@ -195,7 +201,7 @@ class LinUCB(HybridRecommender):
 
     @property
     def _init_args(self):
-        return {"is_hybrid": self.is_hybrid}
+        return {"is_hybrid": self.is_hybrid, "eps": self.eps, "alpha": self.alpha}
 
     def _verify_features(self, dataset: Dataset):
         if dataset.query_features is None:
@@ -230,6 +236,7 @@ class LinUCB(HybridRecommender):
         self._num_items = item_features.shape[0]
         self._user_dim_size = user_features.shape[1] - 1
         self._item_dim_size = item_features.shape[1] - 1
+        self._user_idxs_list = set(user_features[feature_schema.query_id_column].values)
 
         # now initialize an arm object for each potential arm instance
         if self.is_hybrid:
@@ -248,11 +255,14 @@ class LinUCB(HybridRecommender):
             ]
 
             for i in tqdm(range(self._num_items)):
-                B = log.loc[log[feature_schema.item_id_column] == i]  # noqa: N806
-                idxs_list = B[feature_schema.query_id_column].values
-                rel_list = B[feature_schema.interactions_rating_column].values
+                B = log.loc[  # noqa: N806
+                    (log[feature_schema.item_id_column] == i)
+                    & (log[feature_schema.query_id_column].isin(self._user_idxs_list))
+                ]
                 if not B.empty:
                     # if we have at least one user interacting with the hand i
+                    idxs_list = B[feature_schema.query_id_column].values
+                    rel_list = B[feature_schema.interactions_rating_column].values
                     cur_usrs = scs.csr_matrix(
                         user_features.query(f"{feature_schema.query_id_column} in @idxs_list")
                         .drop(columns=[feature_schema.query_id_column])
@@ -284,11 +294,14 @@ class LinUCB(HybridRecommender):
             ]
 
             for i in range(self._num_items):
-                B = log.loc[log[feature_schema.item_id_column] == i]  # noqa: N806
-                idxs_list = B[feature_schema.query_id_column].values  # noqa: F841
-                rel_list = B[feature_schema.interactions_rating_column].values
+                B = log.loc[  # noqa: N806
+                    (log[feature_schema.item_id_column] == i)
+                    & (log[feature_schema.query_id_column].isin(self._user_idxs_list))
+                ]
                 if not B.empty:
                     # if we have at least one user interacting with the hand i
+                    idxs_list = B[feature_schema.query_id_column].values  # noqa: F841
+                    rel_list = B[feature_schema.interactions_rating_column].values
                     cur_usrs = user_features.query(f"{feature_schema.query_id_column} in @idxs_list").drop(
                         columns=[feature_schema.query_id_column]
                     )
@@ -318,8 +331,10 @@ class LinUCB(HybridRecommender):
         user_features = dataset.query_features
         item_features = dataset.item_features
         big_k = min(oversample * k, item_features.shape[0])
+        self._user_idxs_list = set(user_features[feature_schema.query_id_column].values)
 
         users = users.toPandas()
+        users = users[users[feature_schema.query_id_column].isin(self._user_idxs_list)]
         num_user_pred = users.shape[0]
         rel_matrix = np.zeros((num_user_pred, self._num_items), dtype=float)
 
@@ -404,3 +419,34 @@ class LinUCB(HybridRecommender):
         warnings.warn(warn_msg)
         dataset.to_spark()
         return convert2spark(res_df)
+
+    def _save_model(self, path: str, additional_params: Optional[dict] = None):
+        super()._save_model(path, additional_params)
+
+        save_picklable_to_parquet(self.linucb_arms, join(path, "linucb_arms.dump"))
+
+        if self.is_hybrid:
+            linucb_hybrid_shared_params = {
+                "A_0": self.A_0,
+                "A_0_inv": self.A_0_inv,
+                "b_0": self.b_0,
+                "beta": self.beta,
+            }
+            save_picklable_to_parquet(
+                linucb_hybrid_shared_params,
+                join(path, "linucb_hybrid_shared_params.dump"),
+            )
+
+    def _load_model(self, path: str):
+        super()._load_model(path)
+
+        loaded_linucb_arms = load_pickled_from_parquet(join(path, "linucb_arms.dump"))
+        self.linucb_arms = loaded_linucb_arms
+        self._num_items = len(loaded_linucb_arms)
+
+        if self.is_hybrid:
+            loaded_linucb_hybrid_shared_params = load_pickled_from_parquet(
+                join(path, "linucb_hybrid_shared_params.dump")
+            )
+            for param, value in loaded_linucb_hybrid_shared_params.items():
+                setattr(self, param, value)

{replay_rec-0.20.0rc0 → replay_rec-0.20.1}/replay/models/nn/sequential/bert4rec/dataset.py

@@ -12,7 +12,6 @@ from replay.data.nn import (
     TorchSequentialDataset,
     TorchSequentialValidationDataset,
 )
-from replay.utils import deprecation_warning
 
 
 class Bert4RecTrainingBatch(NamedTuple):
@@ -89,10 +88,6 @@ class Bert4RecTrainingDataset(TorchDataset):
     Dataset that generates samples to train BERT-like model
     """
 
-    @deprecation_warning(
-        "`padding_value` parameter will be removed in future versions. "
-        "Instead, you should specify `padding_value` for each column in TensorSchema"
-    )
     def __init__(
         self,
         sequential: SequentialDataset,
@@ -101,7 +96,7 @@ class Bert4RecTrainingDataset(TorchDataset):
         sliding_window_step: Optional[int] = None,
         label_feature_name: Optional[str] = None,
         custom_masker: Optional[Bert4RecMasker] = None,
-        padding_value: int = 0,
+        padding_value: Optional[int] = None,
     ) -> None:
         """
         :param sequential: Sequential dataset with training data.
@@ -181,15 +176,11 @@ class Bert4RecPredictionDataset(TorchDataset):
     Dataset that generates samples to infer BERT-like model
     """
 
-    @deprecation_warning(
-        "`padding_value` parameter will be removed in future versions. "
-        "Instead, you should specify `padding_value` for each column in TensorSchema"
-    )
     def __init__(
         self,
         sequential: SequentialDataset,
         max_sequence_length: int,
-        padding_value: int = 0,
+        padding_value: Optional[int] = None,
     ) -> None:
         """
         :param sequential: Sequential dataset with data to make predictions at.
@@ -239,17 +230,13 @@ class Bert4RecValidationDataset(TorchDataset):
     Dataset that generates samples to infer and validate BERT-like model
     """
 
-    @deprecation_warning(
-        "`padding_value` parameter will be removed in future versions. "
-        "Instead, you should specify `padding_value` for each column in TensorSchema"
-    )
     def __init__(
         self,
         sequential: SequentialDataset,
         ground_truth: SequentialDataset,
         train: SequentialDataset,
         max_sequence_length: int,
-        padding_value: int = 0,
+        padding_value: Optional[int] = None,
         label_feature_name: Optional[str] = None,
     ):
         """

{replay_rec-0.20.0rc0 → replay_rec-0.20.1}/replay/models/nn/sequential/postprocessors/postprocessors.py

@@ -51,7 +51,7 @@ class RemoveSeenItems(BasePostProcessor):
 
     def _compute_scores(self, query_ids: torch.LongTensor, scores: torch.Tensor) -> torch.Tensor:
         flat_seen_item_ids = self._get_flat_seen_item_ids(query_ids)
-        return self._fill_item_ids(scores, flat_seen_item_ids, -np.inf)
+        return self._fill_item_ids(scores.clone(), flat_seen_item_ids, -np.inf)
 
     def _fill_item_ids(
         self,

{replay_rec-0.20.0rc0 → replay_rec-0.20.1}/replay/models/nn/sequential/sasrec/dataset.py

@@ -10,7 +10,6 @@ from replay.data.nn import (
     TorchSequentialDataset,
     TorchSequentialValidationDataset,
 )
-from replay.utils import deprecation_warning
 
 
 class SasRecTrainingBatch(NamedTuple):
@@ -31,17 +30,13 @@ class SasRecTrainingDataset(TorchDataset):
     Dataset that generates samples to train SasRec-like model
     """
 
-    @deprecation_warning(
-        "`padding_value` parameter will be removed in future versions. "
-        "Instead, you should specify `padding_value` for each column in TensorSchema"
-    )
     def __init__(
         self,
         sequential: SequentialDataset,
         max_sequence_length: int,
         sequence_shift: int = 1,
         sliding_window_step: Optional[None] = None,
-        padding_value: int = 0,
+        padding_value: Optional[int] = None,
         label_feature_name: Optional[str] = None,
     ) -> None:
         """
@@ -127,15 +122,11 @@ class SasRecPredictionDataset(TorchDataset):
     Dataset that generates samples to infer SasRec-like model
     """
 
-    @deprecation_warning(
-        "`padding_value` parameter will be removed in future versions. "
-        "Instead, you should specify `padding_value` for each column in TensorSchema"
-    )
     def __init__(
         self,
         sequential: SequentialDataset,
         max_sequence_length: int,
-        padding_value: int = 0,
+        padding_value: Optional[int] = None,
     ) -> None:
         """
         :param sequential: Sequential dataset with data to make predictions at.
@@ -179,17 +170,13 @@ class SasRecValidationDataset(TorchDataset):
     Dataset that generates samples to infer and validate SasRec-like model
     """
 
-    @deprecation_warning(
-        "`padding_value` parameter will be removed in future versions. "
-        "Instead, you should specify `padding_value` for each column in TensorSchema"
-    )
     def __init__(
         self,
         sequential: SequentialDataset,
         ground_truth: SequentialDataset,
         train: SequentialDataset,
         max_sequence_length: int,
-        padding_value: int = 0,
+        padding_value: Optional[int] = None,
         label_feature_name: Optional[str] = None,
     ):
         """

{replay_rec-0.20.0rc0 → replay_rec-0.20.1}/replay/utils/__init__.py

@@ -15,4 +15,3 @@ from .types import (
     PolarsDataFrame,
     SparkDataFrame,
 )
-from .warnings import deprecation_warning

replay_rec-0.20.0rc0/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