replay-rec 0.20.2__py3-none-any.whl → 0.20.3rc0__py3-none-any.whl

replay/experimental/utils/logger.py

@@ -0,0 +1,24 @@
+import logging
+
+
+def get_logger(
+    name,
+    level=logging.INFO,
+    format_str="%(asctime)s [%(pathname)s:%(lineno)s - %(levelname)s ] %(message)s",
+    date_format="%Y-%m-%d %H:%M:%S",
+    file=False,
+):
+    """
+    Get python logger instance
+    """
+    logger = logging.getLogger(name)
+    logger.setLevel(level)
+
+    if not logger.hasHandlers():
+        handler = logging.StreamHandler() if not file else logging.FileHandler(name)
+        handler.setLevel(level)
+        formatter = logging.Formatter(fmt=format_str, datefmt=date_format)
+        handler.setFormatter(formatter)
+        logger.addHandler(handler)
+
+    return logger

replay/experimental/utils/model_handler.py

@@ -0,0 +1,186 @@
+import json
+from inspect import getfullargspec
+from os.path import join
+from pathlib import Path
+from typing import Union
+
+from replay.experimental.models.base_rec import BaseRecommender
+from replay.experimental.preprocessing import Indexer
+from replay.utils import PYSPARK_AVAILABLE
+from replay.utils.session_handler import State
+from replay.utils.spark_utils import load_pickled_from_parquet, save_picklable_to_parquet
+
+if PYSPARK_AVAILABLE:
+    import pyspark.sql.types as st
+    from pyspark.ml.feature import IndexToString, StringIndexerModel
+    from pyspark.sql import SparkSession
+
+    from replay.utils.model_handler import get_fs
+
+    def get_list_of_paths(spark: SparkSession, dir_path: str):
+        """
+        Returns list of paths to files in the `dir_path`
+
+        :param spark: spark session
+        :param dir_path: path to dir in hdfs or local disk
+        :return: list of paths to files
+        """
+        fs = get_fs(spark)
+        statuses = fs.listStatus(spark._jvm.org.apache.hadoop.fs.Path(dir_path))
+        return [str(f.getPath()) for f in statuses]
+
+
+def save(model: BaseRecommender, path: Union[str, Path], overwrite: bool = False):
+    """
+    Save fitted model to disk as a folder
+
+    :param model: Trained recommender
+    :param path: destination where model files will be stored
+    :return:
+    """
+    if isinstance(path, Path):
+        path = str(path)
+
+    spark = State().session
+
+    fs = get_fs(spark)
+    if not overwrite:
+        is_exists = fs.exists(spark._jvm.org.apache.hadoop.fs.Path(path))
+        if is_exists:
+            msg = f"Path '{path}' already exists. Mode is 'overwrite = False'."
+            raise FileExistsError(msg)
+
+    fs.mkdirs(spark._jvm.org.apache.hadoop.fs.Path(path))
+    model._save_model(join(path, "model"))
+
+    init_args = model._init_args
+    init_args["_model_name"] = str(model)
+    sc = spark.sparkContext
+    df = spark.read.json(sc.parallelize([json.dumps(init_args)]))
+    df.coalesce(1).write.mode("overwrite").option("ignoreNullFields", "false").json(join(path, "init_args.json"))
+
+    dataframes = model._dataframes
+    df_path = join(path, "dataframes")
+    for name, df in dataframes.items():
+        if df is not None:
+            df.write.mode("overwrite").parquet(join(df_path, name))
+
+    if hasattr(model, "fit_users"):
+        model.fit_users.write.mode("overwrite").parquet(join(df_path, "fit_users"))
+    if hasattr(model, "fit_items"):
+        model.fit_items.write.mode("overwrite").parquet(join(df_path, "fit_items"))
+    if hasattr(model, "study"):
+        save_picklable_to_parquet(model.study, join(path, "study"))
+
+
+def load(path: str, model_type=None) -> BaseRecommender:
+    """
+    Load saved model from disk
+
+    :param path: path to model folder
+    :return: Restored trained model
+    """
+    spark = State().session
+    args = spark.read.json(join(path, "init_args.json")).first().asDict(recursive=True)
+    name = args["_model_name"]
+    del args["_model_name"]
+
+    model_class = model_type if model_type is not None else globals()[name]
+    if name == "CQL":
+        for a in args:
+            if isinstance(args[a], dict) and "type" in args[a] and args[a]["type"] == "none":
+                args[a]["params"] = {}
+    init_args = getfullargspec(model_class.__init__).args
+    init_args.remove("self")
+    extra_args = set(args) - set(init_args)
+    if len(extra_args) > 0:
+        extra_args = {key: args[key] for key in args}
+        init_args = {key: args[key] for key in init_args}
+    else:
+        init_args = args
+        extra_args = {}
+
+    model = model_class(**init_args)
+    for arg in extra_args:
+        model.arg = extra_args[arg]
+
+    dataframes_paths = get_list_of_paths(spark, join(path, "dataframes"))
+    for dataframe_path in dataframes_paths:
+        df = spark.read.parquet(dataframe_path)
+        attr_name = dataframe_path.split("/")[-1]
+        setattr(model, attr_name, df)
+
+    model._load_model(join(path, "model"))
+    fs = get_fs(spark)
+    model.study = (
+        load_pickled_from_parquet(join(path, "study"))
+        if fs.exists(spark._jvm.org.apache.hadoop.fs.Path(join(path, "study")))
+        else None
+    )
+
+    return model
+
+
+def save_indexer(indexer: Indexer, path: Union[str, Path], overwrite: bool = False):
+    """
+    Save fitted indexer to disk as a folder
+
+    :param indexer: Trained indexer
+    :param path: destination where indexer files will be stored
+    """
+    if isinstance(path, Path):
+        path = str(path)
+
+    spark = State().session
+
+    if not overwrite:
+        fs = get_fs(spark)
+        is_exists = fs.exists(spark._jvm.org.apache.hadoop.fs.Path(path))
+        if is_exists:
+            msg = f"Path '{path}' already exists. Mode is 'overwrite = False'."
+            raise FileExistsError(msg)
+
+    init_args = indexer._init_args
+    init_args["user_type"] = str(indexer.user_type)
+    init_args["item_type"] = str(indexer.item_type)
+    sc = spark.sparkContext
+    df = spark.read.json(sc.parallelize([json.dumps(init_args)]))
+    df.coalesce(1).write.mode("overwrite").json(join(path, "init_args.json"))
+
+    indexer.user_indexer.write().overwrite().save(join(path, "user_indexer"))
+    indexer.item_indexer.write().overwrite().save(join(path, "item_indexer"))
+    indexer.inv_user_indexer.write().overwrite().save(join(path, "inv_user_indexer"))
+    indexer.inv_item_indexer.write().overwrite().save(join(path, "inv_item_indexer"))
+
+
+def load_indexer(path: str) -> Indexer:
+    """
+    Load saved indexer from disk
+
+    :param path: path to folder
+    :return: restored Indexer
+    """
+    spark = State().session
+    args = spark.read.json(join(path, "init_args.json")).first().asDict()
+
+    user_type = args["user_type"]
+    del args["user_type"]
+    item_type = args["item_type"]
+    del args["item_type"]
+
+    indexer = Indexer(**args)
+
+    if user_type.endswith("()"):
+        user_type = user_type[:-2]
+        item_type = item_type[:-2]
+    user_type = getattr(st, user_type)
+    item_type = getattr(st, item_type)
+    indexer.user_type = user_type()
+    indexer.item_type = item_type()
+
+    indexer.user_indexer = StringIndexerModel.load(join(path, "user_indexer"))
+    indexer.item_indexer = StringIndexerModel.load(join(path, "item_indexer"))
+    indexer.inv_user_indexer = IndexToString.load(join(path, "inv_user_indexer"))
+    indexer.inv_item_indexer = IndexToString.load(join(path, "inv_item_indexer"))
+
+    return indexer

replay/experimental/utils/session_handler.py

@@ -0,0 +1,44 @@
+from typing import Optional
+
+import torch
+
+from replay.utils.session_handler import Borg, get_spark_session, logger_with_settings
+from replay.utils.types import PYSPARK_AVAILABLE, MissingImport
+
+if PYSPARK_AVAILABLE:
+    from pyspark.sql import SparkSession
+else:
+    SparkSession = MissingImport
+
+
+class State(Borg):
+    """
+    All modules look for Spark session via this class. You can put your own session here.
+
+    Other parameters are stored here too: ``default device`` for ``pytorch`` (CPU/CUDA)
+    """
+
+    def __init__(
+        self,
+        session: Optional[SparkSession] = None,
+        device: Optional[torch.device] = None,
+    ):
+        Borg.__init__(self)
+        if not hasattr(self, "logger_set"):
+            self.logger = logger_with_settings()
+            self.logger_set = True
+
+        if session is None:
+            if not hasattr(self, "session"):
+                self.session = get_spark_session()
+        else:
+            self.session = session
+
+        if device is None:
+            if not hasattr(self, "device"):
+                if torch.cuda.is_available():
+                    self.device = torch.device(f"cuda:{torch.cuda.current_device()}")
+                else:
+                    self.device = torch.device("cpu")
+        else:
+            self.device = device

{replay_rec-0.20.2.dist-info → replay_rec-0.20.3rc0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: replay-rec
-Version: 0.20.2
+Version: 0.20.3rc0
 Summary: RecSys Library
 License-Expression: Apache-2.0
 License-File: LICENSE
@@ -14,29 +14,23 @@ Classifier: Intended Audience :: Developers
 Classifier: Intended Audience :: Science/Research
 Classifier: Natural Language :: English
 Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
-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: 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)
 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) ; extra == "spark"
-Requires-Dist: psutil ; extra == "spark"
+Requires-Dist: psutil (<=7.0.0)
 Requires-Dist: pyarrow (<22.0)
-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: pyspark (>=3.0,<3.5)
+Requires-Dist: pytorch-optimizer (>=3.8.0,<4)
+Requires-Dist: sb-obp (>=0.5.10,<0.6)
 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) ; extra == "torch" or extra == "torch-cpu"
-Requires-Dist: torch ; extra == "torch"
-Requires-Dist: torch ; extra == "torch-cpu"
+Requires-Dist: torch (>=1.8,<2.9.0)
 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-0.20.2.dist-info → replay_rec-0.20.3rc0.dist-info}/RECORD

@@ -1,4 +1,4 @@
-replay/__init__.py,sha256=EMBA8TgTenz2iXuIiy5uFEcdJ7OduVzd_qSIBcgPfP4,225
+replay/__init__.py,sha256=UO9-zAzQ0Zw6zeU2AwtbXyTUIsneXgvNK-oTutQNSEc,233
 replay/data/__init__.py,sha256=g5bKRyF76QL_BqlED-31RnS8pBdcyj9loMsx5vAG_0E,301
 replay/data/dataset.py,sha256=yQDc8lfphQYfHpm_T1MhnG8_GyM4ONyxJoFc1rUgdJ8,30755
 replay/data/dataset_utils/__init__.py,sha256=9wUvG8ZwGUvuzLU4zQI5FDcH0WVVo5YLN2ey3DterP0,55
@@ -6,11 +6,66 @@ replay/data/dataset_utils/dataset_label_encoder.py,sha256=bxuJPhShFZBok7bQZYGNMV
 replay/data/nn/__init__.py,sha256=nj2Ep-tduuQkc-TnBkvN8-rDnFbcWO2oZrfcXl9M3C8,1122
 replay/data/nn/schema.py,sha256=h1KgaNV-hgN9Vpt24c92EmeMpm_8W0s9a2M0wLxJHYk,17101
 replay/data/nn/sequence_tokenizer.py,sha256=_9fBF-84jdn8Pa3pFKIr6prUjNYCc6BVzwRl9VSleKQ,37419
-replay/data/nn/sequential_dataset.py,sha256=qthp87SQ44VpgoH3RKsqm6CxCeQyApn58l7_16txAZM,11303
+replay/data/nn/sequential_dataset.py,sha256=JNmPjVrrBhModj-yrkExl28oCm1gbdU8z4nMfB5PQko,11565
 replay/data/nn/torch_sequential_dataset.py,sha256=QSh4IM2vzAF095_ZMC1gMqZj9slHXos9gfx_R_DlpGM,11545
 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/experimental/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+replay/experimental/metrics/__init__.py,sha256=bdQogGbEDVAeH7Ejbb6vpw7bP6CYhftTu_DQuoFRuCA,2861
+replay/experimental/metrics/base_metric.py,sha256=0ro9VoSnPtPAximnlcgmQaMNg9zoUN2AHAH_2WgfZiQ,22663
+replay/experimental/metrics/coverage.py,sha256=UqYm-WtAlBFZ3kqv8PyLo4qqKiIXmR_CQFAl6H_YdqA,3150
+replay/experimental/metrics/experiment.py,sha256=pD2Dyyg4PM1HjbrNrhAspZJP3B-i2So205qBChRGwwc,7337
+replay/experimental/metrics/hitrate.py,sha256=TfWJrUyZXabdMr4tn8zqUPGDcYy2yphVCzXmLSHCxY0,675
+replay/experimental/metrics/map.py,sha256=S4dKiMpYR0_pu0bqioGMT0kIC1s2aojFP4rddBqMPtM,921
+replay/experimental/metrics/mrr.py,sha256=q6I1Cndlwr716mMuYtTMu0lN8Rrp9khxhb49OM2IpV8,530
+replay/experimental/metrics/ncis_precision.py,sha256=yrErOhBZvZdNpQPx_AXyktDJatqdWRIHNMyei0QDJtQ,1088
+replay/experimental/metrics/ndcg.py,sha256=q3KTsyZCrfvcpEjEnR_kWVB9ZaTFRxnoNRAr2WD0TrU,1538
+replay/experimental/metrics/precision.py,sha256=U9pD9yRGeT8uH32BTyQ-W5qsAnbFWu-pqy4XfkcXfCM,664
+replay/experimental/metrics/recall.py,sha256=5xRPGxfbVoDFEI5E6dVlZpT4RvnDlWzaktyoqh3a8mc,774
+replay/experimental/metrics/rocauc.py,sha256=yq4vW2_bXO8HCjREBZVrHMKeZ054LYvjJmLJTXWPfQA,1675
+replay/experimental/metrics/surprisal.py,sha256=CK4_zed2bSMDwC7ZBCS8d8RwGEqt8bh3w3fTpjKiK6Y,3052
+replay/experimental/metrics/unexpectedness.py,sha256=JQQXEYHtQM8nqp7X2He4E9ZYwbpdENaK8oQG7sUQT3s,2621
+replay/experimental/models/__init__.py,sha256=yeu0PAkqWNqNLDnUYpg0_vpkWT8tG8KmRMybodVFkZ4,1709
+replay/experimental/models/admm_slim.py,sha256=dDg2c_5Lk8acykirtsv38Jg1l6kgAoBhRvPHPv5Vfis,8654
+replay/experimental/models/base_neighbour_rec.py,sha256=Q2C4rle9FeVIncqgMuhLV6qZbPj2Bz8W_Ao8iQu31TU,7387
+replay/experimental/models/base_rec.py,sha256=AmN6-PgIaNzD-sMIndMuRA3TJ0WZBbowCjaSTTgiYrY,54150
+replay/experimental/models/base_torch_rec.py,sha256=mwbbsR-sQuQAFC1d8X2k0zP3iJeEP-X5nAaR3IV7Sqg,8105
+replay/experimental/models/cql.py,sha256=ItTukqhH3V-PItVPawET9zO9tG4D8R4xKzz3tqKMjSc,19619
+replay/experimental/models/ddpg.py,sha256=bzX4KvkuIecYA4bkFB1BnLKE3zqteujhpvsxAXEnKoM,32266
+replay/experimental/models/dt4rec/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+replay/experimental/models/dt4rec/dt4rec.py,sha256=zcxn2MjrJg8eYqfGwfK80UjH2-uwNDg4PBbmQZz7Le0,5895
+replay/experimental/models/dt4rec/gpt1.py,sha256=T3buFtYyF6Fh6sW6f9dUZFcFEnQdljItbRa22CiKb0w,14044
+replay/experimental/models/dt4rec/trainer.py,sha256=YeaJ8mnoYZqnPwm1P9qOYb8GzgFC5At-JeSDcvG2V2o,3859
+replay/experimental/models/dt4rec/utils.py,sha256=UF--cukjFB3uwzqaVHdCS3ik2qTtw97tzbSFGPkDfE8,8153
+replay/experimental/models/extensions/spark_custom_models/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+replay/experimental/models/extensions/spark_custom_models/als_extension.py,sha256=R9Xj5Yew5eH3dMJ9qfIyhBg4NeMv-wXVEISgzCwFQz0,25846
+replay/experimental/models/hierarchical_recommender.py,sha256=BqnEFBppKawt8Xx5lzBWk6qnmdCrZ7c2hpKj3mi1GvU,11441
+replay/experimental/models/implicit_wrap.py,sha256=8F-f-CaStmlNHwphu-yu8o4Aft08NKDD_SqqH0zp1Uo,4655
+replay/experimental/models/lightfm_wrap.py,sha256=rA9T2vGjrbt_GJV1XccYYsrs9qtgDtqVJCWBHFYrm4k,11329
+replay/experimental/models/mult_vae.py,sha256=l-6g-2fIs80vxBl9VGY4FrJannAXrzsQOyGNuHU8tDs,11601
+replay/experimental/models/neural_ts.py,sha256=oCqStgGg5CpGFAv1dC-3ODmK9nI05evzJ3XKBDQhgAo,42535
+replay/experimental/models/neuromf.py,sha256=acC50kxYlctriNGqyOEkq57Iu4icUvZasyWFeRUJans,14386
+replay/experimental/models/scala_als.py,sha256=6aMl8hUFR2J_nI5U8Z_-5BxfeATiWnC8zdj1C0AFbm4,10751
+replay/experimental/models/u_lin_ucb.py,sha256=-gu6meOYeSwP6N8ILtwasWYj4Mbs6EJEFQXUHE8N_lY,3750
+replay/experimental/nn/data/__init__.py,sha256=5EAF-FNd7xhkUpTq_5MyVcPXBD81mJCwYrcbhdGOWjE,48
+replay/experimental/nn/data/schema_builder.py,sha256=nfE0-bVgYUwzyhNTTcXUWhfNBAZQLHWenM6-zEglqps,3301
+replay/experimental/preprocessing/__init__.py,sha256=uMyeyQ_GKqjLhVGwhrEk3NLhhzS0DKi5xGo3VF4WkiA,130
+replay/experimental/preprocessing/data_preparator.py,sha256=-yqWZT06iEYsY7rCSGRAgLcp6o7jvlsU431HspHQ2o4,35940
+replay/experimental/preprocessing/padder.py,sha256=uxE6WlmYNd9kbACMEidxG1L19G5Rk0gQbvpN_TosMZ4,9558
+replay/experimental/preprocessing/sequence_generator.py,sha256=vFtLkq9MuLGThPsa67103qlcMLYLfnAkR_HI1FXPwjw,9047
+replay/experimental/scenarios/__init__.py,sha256=gWFLCkLyOmOppvbRMK7C3UMlMpcbIgiGVolSH6LPgWA,91
+replay/experimental/scenarios/obp_wrapper/__init__.py,sha256=ZOJgpjRsmhXTpzGumk3AALKmstNBachtu_hOXUIPY5s,434
+replay/experimental/scenarios/obp_wrapper/obp_optuna_objective.py,sha256=swwcot05a8GzIVhEKpfmjG16CuciItVuddPaOjCKo9o,2543
+replay/experimental/scenarios/obp_wrapper/replay_offline.py,sha256=9ZP17steBiTh_KO37NnXWyN5LuPpABPhL_QG4JJHf7I,9622
+replay/experimental/scenarios/obp_wrapper/utils.py,sha256=Uv_fqyJDt69vIdrw-Y9orLLzyHG0ko8svza0Hs_a87Q,3233
+replay/experimental/scenarios/two_stages/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+replay/experimental/scenarios/two_stages/reranker.py,sha256=NQhooA3OXLAh_PwydBNU2DGRRGPq2j2R0SSHtDM7hlg,4238
+replay/experimental/scenarios/two_stages/two_stages_scenario.py,sha256=u41ymdhx0MS1I08VDjJ2UhXpSqsfTA1x9Hbz1tOaWLY,29822
+replay/experimental/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+replay/experimental/utils/logger.py,sha256=UwLowaeOG17sDEe32LiZel8MnjSTzeW7J3uLG1iwLuA,639
+replay/experimental/utils/model_handler.py,sha256=Rfj57E1R_XMEEigHNZa9a-rzEsyLWSDsgKfXoRzWWdg,6426
+replay/experimental/utils/session_handler.py,sha256=H0C-Q2pqrs_5aDvoAkRMZuS5qu07uhu6g5FEL3NJiic,1305
 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
@@ -131,8 +186,8 @@ replay/utils/session_handler.py,sha256=fQo2wseow8yuzKnEXT-aYAXcQIgRbTTXp0v7g1VVi
 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-0.20.2.dist-info/METADATA,sha256=p6_RHj2GamGz9NJpmIQW3mRKn_kbBaKyYkQXgOnSYEg,13562
-replay_rec-0.20.2.dist-info/WHEEL,sha256=zp0Cn7JsFoX2ATtOhtaFYIiE2rmFAD4OcMhtUki8W3U,88
-replay_rec-0.20.2.dist-info/licenses/LICENSE,sha256=rPmcA7UrHxBChEAAlJyE24qUWKKl9yLQXxFsKeg_LX4,11344
-replay_rec-0.20.2.dist-info/licenses/NOTICE,sha256=k0bo4KHiHLRax5K3XKTTrf2Fi8V91mJ-R3FMdh6Reg0,2002
-replay_rec-0.20.2.dist-info/RECORD,,
+replay_rec-0.20.3rc0.dist-info/METADATA,sha256=LCtP5r4PZP-jTKxRCFkk1mYq6qqUNS4rgjcDfmF3by8,13155
+replay_rec-0.20.3rc0.dist-info/WHEEL,sha256=zp0Cn7JsFoX2ATtOhtaFYIiE2rmFAD4OcMhtUki8W3U,88
+replay_rec-0.20.3rc0.dist-info/licenses/LICENSE,sha256=rPmcA7UrHxBChEAAlJyE24qUWKKl9yLQXxFsKeg_LX4,11344
+replay_rec-0.20.3rc0.dist-info/licenses/NOTICE,sha256=k0bo4KHiHLRax5K3XKTTrf2Fi8V91mJ-R3FMdh6Reg0,2002
+replay_rec-0.20.3rc0.dist-info/RECORD,,