replay-rec 0.17.1rc0__py3-none-any.whl → 0.18.0rc0__py3-none-any.whl

replay/__init__.py

@@ -1,2 +1,3 @@
 """ RecSys library """
-__version__ = "0.17.1.preview"
+
+__version__ = "0.18.0.preview"

replay/data/dataset.py

@@ -1,6 +1,7 @@
 """
 ``Dataset`` universal dataset class for manipulating interactions and feed data to models.
 """
+
 from __future__ import annotations
 
 import json
@@ -606,7 +607,7 @@ class Dataset:
         if self.is_pandas:
             min_id = data[column].min()
         elif self.is_spark:
-            min_id = data.agg(sf.min(column).alias("min_index")).collect()[0][0]
+            min_id = data.agg(sf.min(column).alias("min_index")).first()[0]
         else:
             min_id = data[column].min()
         if min_id < 0:
@@ -616,7 +617,7 @@ class Dataset:
         if self.is_pandas:
             max_id = data[column].max()
         elif self.is_spark:
-            max_id = data.agg(sf.max(column).alias("max_index")).collect()[0][0]
+            max_id = data.agg(sf.max(column).alias("max_index")).first()[0]
         else:
             max_id = data[column].max()
 

replay/data/dataset_utils/dataset_label_encoder.py

@@ -4,6 +4,7 @@ Contains classes for encoding categorical data
 ``LabelEncoderTransformWarning`` new category of warning for DatasetLabelEncoder.
 ``DatasetLabelEncoder`` to encode categorical features in `Dataset` objects.
 """
+
 import warnings
 from typing import Dict, Iterable, Iterator, Optional, Sequence, Set, Union
 

replay/data/nn/schema.py

@@ -418,11 +418,11 @@ class TensorSchema(Mapping[str, TensorFeatureInfo]):
                 "feature_type": feature.feature_type.name,
                 "is_seq": feature.is_seq,
                 "feature_hint": feature.feature_hint.name if feature.feature_hint else None,
-                "feature_sources": [
-                    {"source": x.source.name, "column": x.column, "index": x.index} for x in feature.feature_sources
-                ]
-                if feature.feature_sources
-                else None,
+                "feature_sources": (
+                    [{"source": x.source.name, "column": x.column, "index": x.index} for x in feature.feature_sources]
+                    if feature.feature_sources
+                    else None
+                ),
                 "cardinality": feature.cardinality if feature.feature_type == FeatureType.CATEGORICAL else None,
                 "embedding_dim": feature.embedding_dim if feature.feature_type == FeatureType.CATEGORICAL else None,
                 "tensor_dim": feature.tensor_dim if feature.feature_type == FeatureType.NUMERICAL else None,

replay/experimental/metrics/__init__.py

@@ -47,6 +47,7 @@ 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

replay/experimental/metrics/base_metric.py

@@ -1,6 +1,7 @@
 """
 Base classes for quality and diversity metrics.
 """
+
 import logging
 from abc import ABC, abstractmethod
 from typing import Dict, List, Optional, Union

replay/experimental/models/base_rec.py

@@ -86,8 +86,8 @@ class BaseRecommender(RecommenderCommons, IsSavable, ABC):
         self.fit_items = sf.broadcast(items)
         self._num_users = self.fit_users.count()
         self._num_items = self.fit_items.count()
-        self._user_dim_size = self.fit_users.agg({"user_idx": "max"}).collect()[0][0] + 1
-        self._item_dim_size = self.fit_items.agg({"item_idx": "max"}).collect()[0][0] + 1
+        self._user_dim_size = self.fit_users.agg({"user_idx": "max"}).first()[0] + 1
+        self._item_dim_size = self.fit_items.agg({"item_idx": "max"}).first()[0] + 1
         self._fit(log, user_features, item_features)
 
     @abstractmethod
@@ -122,7 +122,7 @@ class BaseRecommender(RecommenderCommons, IsSavable, ABC):
         # count maximal number of items seen by users
         max_seen = 0
         if num_seen.count() > 0:
-            max_seen = num_seen.select(sf.max("seen_count")).collect()[0][0]
+            max_seen = num_seen.select(sf.max("seen_count")).first()[0]
 
         # crop recommendations to first k + max_seen items for each user
         recs = recs.withColumn(
@@ -335,7 +335,7 @@ class BaseRecommender(RecommenderCommons, IsSavable, ABC):
             setattr(
                 self,
                 f"_{entity}_dim_size",
-                getattr(self, f"fit_{entity}s").agg({f"{entity}_idx": "max"}).collect()[0][0] + 1,
+                getattr(self, f"fit_{entity}s").agg({f"{entity}_idx": "max"}).first()[0] + 1,
             )
         return getattr(self, f"_{entity}_dim_size")
 
@@ -1088,7 +1088,7 @@ class NonPersonalizedRecommender(Recommender, ABC):
         Calculating a fill value a the minimal relevance
         calculated during model training multiplied by weight.
         """
-        return item_popularity.select(sf.min("relevance")).collect()[0][0] * weight
+        return item_popularity.select(sf.min("relevance")).first()[0] * weight
 
     @staticmethod
     def _check_relevance(log: SparkDataFrame):
@@ -1113,7 +1113,7 @@ class NonPersonalizedRecommender(Recommender, ABC):
         max_hist_len = (
             (log.join(users, on="user_idx").groupBy("user_idx").agg(sf.countDistinct("item_idx").alias("items_count")))
             .select(sf.max("items_count"))
-            .collect()[0][0]
+            .first()[0]
         )
         # all users have empty history
         if max_hist_len is None:
@@ -1146,7 +1146,7 @@ class NonPersonalizedRecommender(Recommender, ABC):
             users = users.join(user_to_num_items, on="user_idx", how="left")
             users = users.fillna(0, "num_items")
             # 'selected_item_popularity' truncation by k + max_seen
-            max_seen = users.select(sf.coalesce(sf.max("num_items"), sf.lit(0))).collect()[0][0]
+            max_seen = users.select(sf.coalesce(sf.max("num_items"), sf.lit(0))).first()[0]
             selected_item_popularity = selected_item_popularity.filter(sf.col("rank") <= k + max_seen)
             return users.join(selected_item_popularity, on=(sf.col("rank") <= k + sf.col("num_items")), how="left")
 

replay/experimental/models/cql.py

@@ -1,6 +1,7 @@
 """
 Using CQL implementation from `d3rlpy` package.
 """
+
 import io
 import logging
 import tempfile
@@ -402,6 +403,7 @@ class MdpDatasetBuilder:
         top_k (int): the number of top user items to learn predicting.
         action_randomization_scale (float): the scale of action randomization gaussian noise.
     """
+
     logger: logging.Logger
     top_k: int
     action_randomization_scale: float

replay/experimental/models/ddpg.py

@@ -704,13 +704,15 @@ class DDPG(Recommender):
         :param data: pandas DataFrame
         """
         data = data[["user_idx", "item_idx", "relevance"]]
-        train_data = data.values.tolist()
+        users = data["user_idx"].values.tolist()
+        items = data["item_idx"].values.tolist()
+        scores = data["relevance"].values.tolist()
 
-        user_num = data["user_idx"].max() + 1
-        item_num = data["item_idx"].max() + 1
+        user_num = max(users) + 1
+        item_num = max(items) + 1
 
         train_mat = defaultdict(float)
-        for user, item, rel in train_data:
+        for user, item, rel in zip(users, items, scores):
             train_mat[user, item] = rel
         train_matrix = sp.dok_matrix((user_num, item_num), dtype=np.float32)
         dict.update(train_matrix, train_mat)

replay/experimental/models/lightfm_wrap.py

@@ -98,12 +98,12 @@ class LightFMWrap(HybridRecommender):
         fit_dim = getattr(self, f"_{entity}_dim")
         matrix_height = max(
             fit_dim,
-            log_ids_list.select(sf.max(idx_col_name)).collect()[0][0] + 1,
+            log_ids_list.select(sf.max(idx_col_name)).first()[0] + 1,
         )
         if not feature_table.rdd.isEmpty():
             matrix_height = max(
                 matrix_height,
-                feature_table.select(sf.max(idx_col_name)).collect()[0][0] + 1,
+                feature_table.select(sf.max(idx_col_name)).first()[0] + 1,
             )
 
         features_np = (

replay/experimental/models/mult_vae.py

@@ -2,6 +2,7 @@
 MultVAE implementation
 (Variational Autoencoders for Collaborative Filtering)
 """
+
 from typing import Optional, Tuple
 
 import numpy as np

replay/experimental/models/neuromf.py

@@ -3,6 +3,7 @@ Generalized Matrix Factorization (GMF),
 Multi-Layer Perceptron (MLP),
 Neural Matrix Factorization (MLP + GMF).
 """
+
 from typing import List, Optional
 
 import numpy as np

replay/experimental/models/scala_als.py

@@ -115,7 +115,7 @@ class ALSWrap(Recommender, ItemVectorModel):
                     .groupBy("user_idx")
                     .agg(sf.count("user_idx").alias("num_seen"))
                     .select(sf.max("num_seen"))
-                    .collect()[0][0]
+                    .first()[0]
                 )
                 max_seen = max_seen_in_log if max_seen_in_log is not None else 0
 
@@ -280,7 +280,7 @@ class ScalaALSWrap(ALSWrap, ANNMixin):
                 .groupBy("user_idx")
                 .agg(sf.count("user_idx").alias("num_seen"))
                 .select(sf.max("num_seen"))
-                .collect()[0][0]
+                .first()[0]
             )
             max_seen = max_seen_in_log if max_seen_in_log is not None else 0
 

replay/experimental/preprocessing/data_preparator.py

@@ -6,6 +6,7 @@ Contains classes for data preparation and categorical features transformation.
 ``ToNumericFeatureTransformer`` leaves only numerical features
 by one-hot encoding of some features and deleting the others.
 """
+
 import json
 import logging
 import string
@@ -699,7 +700,7 @@ if PYSPARK_AVAILABLE:
                 return
 
             cat_feat_values_dict = {
-                name: (spark_df.select(sf.collect_set(sf.col(name))).collect()[0][0]) for name in self.cat_cols_list
+                name: (spark_df.select(sf.collect_set(sf.col(name))).first()[0]) for name in self.cat_cols_list
             }
             self.expressions_list = [
                 sf.when(sf.col(col_name) == cur_name, 1)

replay/experimental/preprocessing/padder.py

@@ -179,7 +179,7 @@ class Padder:
         self, df_transformed: SparkDataFrame, col: str, pad_value: Union[str, float, List, None]
     ) -> SparkDataFrame:
         if self.array_size == -1:
-            max_array_size = df_transformed.agg(sf.max(sf.size(col)).alias("max_array_len")).collect()[0][0]
+            max_array_size = df_transformed.agg(sf.max(sf.size(col)).alias("max_array_len")).first()[0]
         else:
             max_array_size = self.array_size
 

replay/experimental/scenarios/two_stages/two_stages_scenario.py

@@ -383,7 +383,7 @@ class TwoStagesScenario(HybridRecommender):
                 log_to_filter_cached.groupBy("user_idx")
                 .agg(sf.count("item_idx").alias("num_positives"))
                 .select(sf.max("num_positives"))
-                .collect()[0][0]
+                .first()[0]
             )
 
         pred = model._predict(

replay/experimental/utils/model_handler.py

@@ -170,8 +170,13 @@ def load_indexer(path: str) -> Indexer:
 
     indexer = Indexer(**args)
 
-    indexer.user_type = getattr(st, user_type)()
-    indexer.item_type = getattr(st, item_type)()
+    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"))

replay/metrics/__init__.py

@@ -42,6 +42,7 @@ 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 .base_metric import Metric
 from .categorical_diversity import CategoricalDiversity
 from .coverage import Coverage

replay/models/als.py

@@ -115,7 +115,7 @@ class ALSWrap(Recommender, ItemVectorModel):
                     .groupBy(self.query_column)
                     .agg(sf.count(self.query_column).alias("num_seen"))
                     .select(sf.max("num_seen"))
-                    .collect()[0][0]
+                    .first()[0]
                 )
                 max_seen = max_seen_in_interactions if max_seen_in_interactions is not None else 0
 

replay/models/base_rec.py

@@ -401,8 +401,8 @@ class BaseRecommender(RecommenderCommons, IsSavable, ABC):
         self.fit_items = sf.broadcast(items)
         self._num_queries = self.fit_queries.count()
         self._num_items = self.fit_items.count()
-        self._query_dim_size = self.fit_queries.agg({self.query_column: "max"}).collect()[0][0] + 1
-        self._item_dim_size = self.fit_items.agg({self.item_column: "max"}).collect()[0][0] + 1
+        self._query_dim_size = self.fit_queries.agg({self.query_column: "max"}).first()[0] + 1
+        self._item_dim_size = self.fit_items.agg({self.item_column: "max"}).first()[0] + 1
         self._fit(dataset)
 
     @abstractmethod
@@ -431,7 +431,7 @@ class BaseRecommender(RecommenderCommons, IsSavable, ABC):
         # count maximal number of items seen by queries
         max_seen = 0
         if num_seen.count() > 0:
-            max_seen = num_seen.select(sf.max("seen_count")).collect()[0][0]
+            max_seen = num_seen.select(sf.max("seen_count")).first()[0]
 
         # crop recommendations to first k + max_seen items for each query
         recs = recs.withColumn(
@@ -708,7 +708,7 @@ class BaseRecommender(RecommenderCommons, IsSavable, ABC):
             setattr(
                 self,
                 dim_size,
-                fit_entities.agg({column: "max"}).collect()[0][0] + 1,
+                fit_entities.agg({column: "max"}).first()[0] + 1,
             )
         return getattr(self, dim_size)
 
@@ -1426,7 +1426,7 @@ class NonPersonalizedRecommender(Recommender, ABC):
         Calculating a fill value a the minimal rating
         calculated during model training multiplied by weight.
         """
-        return item_popularity.select(sf.min(rating_column)).collect()[0][0] * weight
+        return item_popularity.select(sf.min(rating_column)).first()[0] * weight
 
     @staticmethod
     def _check_rating(dataset: Dataset):
@@ -1460,7 +1460,7 @@ class NonPersonalizedRecommender(Recommender, ABC):
                 .agg(sf.countDistinct(item_column).alias("items_count"))
             )
             .select(sf.max("items_count"))
-            .collect()[0][0]
+            .first()[0]
         )
         # all queries have empty history
         if max_hist_len is None:
@@ -1495,7 +1495,7 @@ class NonPersonalizedRecommender(Recommender, ABC):
             queries = queries.join(query_to_num_items, on=self.query_column, how="left")
             queries = queries.fillna(0, "num_items")
             # 'selected_item_popularity' truncation by k + max_seen
-            max_seen = queries.select(sf.coalesce(sf.max("num_items"), sf.lit(0))).collect()[0][0]
+            max_seen = queries.select(sf.coalesce(sf.max("num_items"), sf.lit(0))).first()[0]
             selected_item_popularity = selected_item_popularity.filter(sf.col("rank") <= k + max_seen)
             return queries.join(selected_item_popularity, on=(sf.col("rank") <= k + sf.col("num_items")), how="left")
 

replay/models/extensions/ann/index_inferers/nmslib_filter_index_inferer.py

@@ -32,9 +32,9 @@ class NmslibFilterIndexInferer(IndexInferer):
             index = index_store.load_index(
                 init_index=lambda: create_nmslib_index_instance(index_params),
                 load_index=lambda index, path: index.loadIndex(path, load_data=True),
-                configure_index=lambda index: index.setQueryTimeParams({"efSearch": index_params.ef_s})
-                if index_params.ef_s
-                else None,
+                configure_index=lambda index: (
+                    index.setQueryTimeParams({"efSearch": index_params.ef_s}) if index_params.ef_s else None
+                ),
             )
 
             # max number of items to retrieve per batch

replay/models/extensions/ann/index_inferers/nmslib_index_inferer.py

@@ -30,9 +30,9 @@ class NmslibIndexInferer(IndexInferer):
             index = index_store.load_index(
                 init_index=lambda: create_nmslib_index_instance(index_params),
                 load_index=lambda index, path: index.loadIndex(path, load_data=True),
-                configure_index=lambda index: index.setQueryTimeParams({"efSearch": index_params.ef_s})
-                if index_params.ef_s
-                else None,
+                configure_index=lambda index: (
+                    index.setQueryTimeParams({"efSearch": index_params.ef_s}) if index_params.ef_s else None
+                ),
             )
 
             user_vectors = get_csr_matrix(user_idx, vector_items, vector_ratings)

replay/models/nn/sequential/bert4rec/model.py

@@ -1,7 +1,7 @@
 import contextlib
 import math
 from abc import ABC, abstractmethod
-from typing import Dict, Optional, Tuple, Union, cast
+from typing import Dict, Optional, Union
 
 import torch
 
@@ -115,13 +115,10 @@ class Bert4RecModel(torch.nn.Module):
         # (B x L x E)
         x = self.item_embedder(inputs, token_mask)
 
-        # (B x 1 x L x L)
-        pad_mask_for_attention = self._get_attention_mask_from_padding(pad_mask)
-
         # Running over multiple transformer blocks
         for transformer in self.transformer_blocks:
             for _ in range(self.num_passes_over_block):
-                x = transformer(x, pad_mask_for_attention)
+                x = transformer(x, pad_mask)
 
         return x
 
@@ -147,11 +144,6 @@ class Bert4RecModel(torch.nn.Module):
         """
         return self.forward_step(inputs, pad_mask, token_mask)[:, -1, :]
 
-    def _get_attention_mask_from_padding(self, pad_mask: torch.BoolTensor) -> torch.BoolTensor:
-        # (B x L) -> (B x 1 x L x L)
-        pad_mask_for_attention = pad_mask.unsqueeze(1).repeat(1, self.max_len, 1).unsqueeze(1)
-        return cast(torch.BoolTensor, pad_mask_for_attention)
-
     def _init(self) -> None:
         for _, param in self.named_parameters():
             with contextlib.suppress(ValueError):
@@ -456,7 +448,7 @@ class TransformerBlock(torch.nn.Module):
         :param dropout: Dropout rate.
         """
         super().__init__()
-        self.attention = MultiHeadedAttention(h=attn_heads, d_model=hidden_size, dropout=dropout)
+        self.attention = torch.nn.MultiheadAttention(hidden_size, attn_heads, dropout=dropout, batch_first=True)
         self.attention_dropout = torch.nn.Dropout(dropout)
         self.attention_norm = LayerNorm(hidden_size)
 
@@ -479,7 +471,8 @@ class TransformerBlock(torch.nn.Module):
         """
         # Attention + skip-connection
         x_norm = self.attention_norm(x)
-        y = x + self.attention_dropout(self.attention(x_norm, x_norm, x_norm, mask))
+        attent_emb, _ = self.attention(x_norm, x_norm, x_norm, key_padding_mask=~mask, need_weights=False)
+        y = x + self.attention_dropout(attent_emb)
 
         # PFF + skip-connection
         z = y + self.pff_dropout(self.pff(self.pff_norm(y)))
@@ -487,106 +480,6 @@ class TransformerBlock(torch.nn.Module):
         return self.dropout(z)
 
 
-class Attention(torch.nn.Module):
-    """
-    Compute Scaled Dot Product Attention
-    """
-
-    def __init__(self, dropout: float) -> None:
-        """
-        :param dropout: Dropout rate.
-        """
-        super().__init__()
-        self.dropout = torch.nn.Dropout(p=dropout)
-
-    def forward(
-        self, query: torch.Tensor, key: torch.Tensor, value: torch.Tensor, mask: torch.BoolTensor
-    ) -> Tuple[torch.Tensor, torch.Tensor]:
-        """
-        :param query: Query feature vector.
-        :param key: Key feature vector.
-        :param value: Value feature vector.
-        :param mask: Mask where 0 - <MASK>, 1 - otherwise.
-
-        :returns: Tuple of scaled dot product attention
-                and attention logits for each element.
-        """
-        scores = torch.matmul(query, key.transpose(-2, -1)) / math.sqrt(query.size(-1))
-
-        scores = scores.masked_fill(mask == 0, -1e9)
-        p_attn = torch.nn.functional.softmax(scores, dim=-1)
-        p_attn = self.dropout(p_attn)
-
-        return torch.matmul(p_attn, value), p_attn
-
-
-class MultiHeadedAttention(torch.nn.Module):
-    """
-    Take in model size and number of heads.
-    """
-
-    def __init__(self, h: int, d_model: int, dropout: float = 0.1) -> None:
-        """
-        :param h: Head sizes of multi-head attention.
-        :param d_model: Embedding dimension.
-        :param dropout: Dropout rate.
-            Default: ``0.1``.
-        """
-        super().__init__()
-        assert d_model % h == 0
-
-        # We assume d_v always equals d_k
-        self.d_k = d_model // h
-        self.h = h
-
-        # 3 linear projections for Q, K, V
-        self.qkv_linear_layers = torch.nn.ModuleList([torch.nn.Linear(d_model, d_model) for _ in range(3)])
-
-        # 2 linear projections for P -> P_q, P_k
-        self.pos_linear_layers = torch.nn.ModuleList([torch.nn.Linear(d_model, d_model) for _ in range(2)])
-
-        self.output_linear = torch.nn.Linear(d_model, d_model)
-
-        self.attention = Attention(dropout)
-
-    def forward(
-        self,
-        query: torch.Tensor,
-        key: torch.Tensor,
-        value: torch.Tensor,
-        mask: torch.BoolTensor,
-    ) -> torch.Tensor:
-        """
-        :param query: Query feature vector.
-        :param key: Key feature vector.
-        :param value: Value feature vector.
-        :param mask: Mask where 0 - <MASK>, 1 - otherwise.
-
-        :returns: Attention outputs.
-        """
-        batch_size = query.size(0)
-
-        # B - batch size
-        # L - sequence length (max_len)
-        # E - embedding size for tokens fed into transformer
-        # K - max relative distance
-        # H - attention head count
-
-        # Do all the linear projections in batch from d_model => h x d_k
-        # (B x L x E) -> (B x H x L x (E / H))
-        query, key, value = [
-            layer(x).view(batch_size, -1, self.h, self.d_k).transpose(1, 2)
-            for layer, x in zip(self.qkv_linear_layers, (query, key, value))
-        ]
-
-        x, _ = self.attention(query, key, value, mask)
-
-        # Concat using a view and apply a final linear.
-        x = x.transpose(1, 2).contiguous().view(batch_size, -1, self.h * self.d_k)
-
-        return self.output_linear(x)
-
-
 class LayerNorm(torch.nn.Module):
     """
     Construct a layernorm module (See citation for details).

replay/models/nn/sequential/sasrec/model.py

@@ -401,7 +401,12 @@ class SasRecLayers(torch.nn.Module):
         """
         super().__init__()
         self.attention_layers = self._layers_stacker(
-            num_blocks, torch.nn.MultiheadAttention, hidden_size, num_heads, dropout
+            num_blocks,
+            torch.nn.MultiheadAttention,
+            hidden_size,
+            num_heads,
+            dropout,
+            batch_first=True,
         )
         self.attention_layernorms = self._layers_stacker(num_blocks, torch.nn.LayerNorm, hidden_size, eps=1e-8)
         self.forward_layers = self._layers_stacker(num_blocks, SasRecPointWiseFeedForward, hidden_size, dropout)
@@ -422,11 +427,9 @@ class SasRecLayers(torch.nn.Module):
         """
         length = len(self.attention_layers)
         for i in range(length):
-            seqs = torch.transpose(seqs, 0, 1)
             query = self.attention_layernorms[i](seqs)
-            attent_emb, _ = self.attention_layers[i](query, seqs, seqs, attn_mask=attention_mask)
+            attent_emb, _ = self.attention_layers[i](query, seqs, seqs, attn_mask=attention_mask, need_weights=False)
             seqs = query + attent_emb
-            seqs = torch.transpose(seqs, 0, 1)
 
             seqs = self.forward_layernorms[i](seqs)
             seqs = self.forward_layers[i](seqs)
@@ -492,7 +495,7 @@ class SasRecPointWiseFeedForward(torch.nn.Module):
 
         :returns: Output tensors.
         """
-        outputs = self.dropout2(self.conv2(self.relu(self.dropout1(self.conv1(inputs.transpose(-1, -2))))))
+        outputs = self.dropout2(self.conv2(self.dropout1(self.relu(self.conv1(inputs.transpose(-1, -2))))))
         outputs = outputs.transpose(-1, -2)
         outputs += inputs
 

replay/optimization/optuna_objective.py

@@ -1,6 +1,7 @@
 """
 This class calculates loss function for optimization process
 """
+
 import collections
 import logging
 from functools import partial

replay/preprocessing/converter.py

@@ -102,6 +102,6 @@ class CSRConverter:
         row_count = self.row_count if self.row_count is not None else _get_max(rows_data) + 1
         col_count = self.column_count if self.column_count is not None else _get_max(cols_data) + 1
         return csr_matrix(
-            (data, (rows_data, cols_data)),
+            (data.tolist(), (rows_data.tolist(), cols_data.tolist())),
             shape=(row_count, col_count),
         )

replay/preprocessing/filters.py

@@ -1,6 +1,7 @@
 """
 Select or remove data by some criteria
 """
+
 from abc import ABC, abstractmethod
 from datetime import datetime, timedelta
 from typing import Callable, Optional, Tuple, Union
@@ -355,8 +356,8 @@ class NumInteractionsFilter(_BaseFilter):
     >>> log_pd = pd.DataFrame({"user_id": ["u1", "u2", "u2", "u3", "u3", "u3"],
     ...                     "item_id": ["i1", "i2","i3", "i1", "i2","i3"],
     ...                     "rating": [1., 0.5, 3, 1, 0, 1],
-    ...                     "timestamp": ["2020-01-01 23:59:59", "2020-02-01",
-    ...                                   "2020-02-01", "2020-01-01 00:04:15",
+    ...                     "timestamp": ["2020-01-01 23:59:59", "2020-02-01 00:00:00",
+    ...                                   "2020-02-01 00:00:01", "2020-01-01 00:04:15",
     ...                                   "2020-01-02 00:04:14", "2020-01-05 23:59:59"]},
     ...             )
     >>> log_pd["timestamp"] = pd.to_datetime(log_pd["timestamp"], format="ISO8601")
@@ -367,7 +368,7 @@ class NumInteractionsFilter(_BaseFilter):
     +-------+-------+------+-------------------+
     |     u1|     i1|   1.0|2020-01-01 23:59:59|
     |     u2|     i2|   0.5|2020-02-01 00:00:00|
-    |     u2|     i3|   3.0|2020-02-01 00:00:00|
+    |     u2|     i3|   3.0|2020-02-01 00:00:01|
     |     u3|     i1|   1.0|2020-01-01 00:04:15|
     |     u3|     i2|   0.0|2020-01-02 00:04:14|
     |     u3|     i3|   1.0|2020-01-05 23:59:59|
@@ -393,7 +394,7 @@ class NumInteractionsFilter(_BaseFilter):
     |user_id|item_id|rating|          timestamp|
     +-------+-------+------+-------------------+
     |     u1|     i1|   1.0|2020-01-01 23:59:59|
-    |     u2|     i2|   0.5|2020-02-01 00:00:00|
+    |     u2|     i3|   3.0|2020-02-01 00:00:01|
     |     u3|     i3|   1.0|2020-01-05 23:59:59|
     +-------+-------+------+-------------------+
     <BLANKLINE>
@@ -403,7 +404,7 @@ class NumInteractionsFilter(_BaseFilter):
     |user_id|item_id|rating|          timestamp|
     +-------+-------+------+-------------------+
     |     u1|     i1|   1.0|2020-01-01 23:59:59|
-    |     u2|     i3|   3.0|2020-02-01 00:00:00|
+    |     u2|     i3|   3.0|2020-02-01 00:00:01|
     |     u3|     i3|   1.0|2020-01-05 23:59:59|
     +-------+-------+------+-------------------+
     <BLANKLINE>
@@ -482,7 +483,7 @@ class NumInteractionsFilter(_BaseFilter):
 
         return (
             interactions.sort(sorting_columns, descending=descending)
-            .with_columns(pl.col(self.query_column).cumcount().over(self.query_column).alias("temp_rank"))
+            .with_columns(pl.col(self.query_column).cum_count().over(self.query_column).alias("temp_rank"))
             .filter(pl.col("temp_rank") <= self.num_interactions)
             .drop("temp_rank")
         )
@@ -497,8 +498,8 @@ class EntityDaysFilter(_BaseFilter):
     >>> log_pd = pd.DataFrame({"user_id": ["u1", "u2", "u2", "u3", "u3", "u3"],
     ...                     "item_id": ["i1", "i2","i3", "i1", "i2","i3"],
     ...                     "rating": [1., 0.5, 3, 1, 0, 1],
-    ...                     "timestamp": ["2020-01-01 23:59:59", "2020-02-01",
-    ...                                   "2020-02-01", "2020-01-01 00:04:15",
+    ...                     "timestamp": ["2020-01-01 23:59:59", "2020-02-01 00:00:00",
+    ...                                   "2020-02-01 00:00:01", "2020-01-01 00:04:15",
     ...                                   "2020-01-02 00:04:14", "2020-01-05 23:59:59"]},
     ...             )
     >>> log_pd["timestamp"] = pd.to_datetime(log_pd["timestamp"], format="ISO8601")
@@ -509,7 +510,7 @@ class EntityDaysFilter(_BaseFilter):
     +-------+-------+------+-------------------+
     |     u1|     i1|   1.0|2020-01-01 23:59:59|
     |     u2|     i2|   0.5|2020-02-01 00:00:00|
-    |     u2|     i3|   3.0|2020-02-01 00:00:00|
+    |     u2|     i3|   3.0|2020-02-01 00:00:01|
     |     u3|     i1|   1.0|2020-01-01 00:04:15|
     |     u3|     i2|   0.0|2020-01-02 00:04:14|
     |     u3|     i3|   1.0|2020-01-05 23:59:59|
@@ -524,7 +525,7 @@ class EntityDaysFilter(_BaseFilter):
     +-------+-------+------+-------------------+
     |     u1|     i1|   1.0|2020-01-01 23:59:59|
     |     u2|     i2|   0.5|2020-02-01 00:00:00|
-    |     u2|     i3|   3.0|2020-02-01 00:00:00|
+    |     u2|     i3|   3.0|2020-02-01 00:00:01|
     |     u3|     i1|   1.0|2020-01-01 00:04:15|
     |     u3|     i2|   0.0|2020-01-02 00:04:14|
     +-------+-------+------+-------------------+
@@ -539,7 +540,7 @@ class EntityDaysFilter(_BaseFilter):
     |     u1|     i1|   1.0|2020-01-01 23:59:59|
     |     u3|     i1|   1.0|2020-01-01 00:04:15|
     |     u2|     i2|   0.5|2020-02-01 00:00:00|
-    |     u2|     i3|   3.0|2020-02-01 00:00:00|
+    |     u2|     i3|   3.0|2020-02-01 00:00:01|
     +-------+-------+------+-------------------+
     <BLANKLINE>
     """
@@ -636,8 +637,8 @@ class GlobalDaysFilter(_BaseFilter):
     >>> log_pd = pd.DataFrame({"user_id": ["u1", "u2", "u2", "u3", "u3", "u3"],
     ...                     "item_id": ["i1", "i2","i3", "i1", "i2","i3"],
     ...                     "rating": [1., 0.5, 3, 1, 0, 1],
-    ...                     "timestamp": ["2020-01-01 23:59:59", "2020-02-01",
-    ...                                   "2020-02-01", "2020-01-01 00:04:15",
+    ...                     "timestamp": ["2020-01-01 23:59:59", "2020-02-01 00:00:00",
+    ...                                   "2020-02-01 00:00:01", "2020-01-01 00:04:15",
     ...                                   "2020-01-02 00:04:14", "2020-01-05 23:59:59"]},
     ...             )
     >>> log_pd["timestamp"] = pd.to_datetime(log_pd["timestamp"], format="ISO8601")
@@ -648,7 +649,7 @@ class GlobalDaysFilter(_BaseFilter):
     +-------+-------+------+-------------------+
     |     u1|     i1|   1.0|2020-01-01 23:59:59|
     |     u2|     i2|   0.5|2020-02-01 00:00:00|
-    |     u2|     i3|   3.0|2020-02-01 00:00:00|
+    |     u2|     i3|   3.0|2020-02-01 00:00:01|
     |     u3|     i1|   1.0|2020-01-01 00:04:15|
     |     u3|     i2|   0.0|2020-01-02 00:04:14|
     |     u3|     i3|   1.0|2020-01-05 23:59:59|
@@ -670,7 +671,7 @@ class GlobalDaysFilter(_BaseFilter):
     |user_id|item_id|rating|          timestamp|
     +-------+-------+------+-------------------+
     |     u2|     i2|   0.5|2020-02-01 00:00:00|
-    |     u2|     i3|   3.0|2020-02-01 00:00:00|
+    |     u2|     i3|   3.0|2020-02-01 00:00:01|
     +-------+-------+------+-------------------+
     <BLANKLINE>
     """
@@ -738,8 +739,8 @@ class TimePeriodFilter(_BaseFilter):
     >>> log_pd = pd.DataFrame({"user_id": ["u1", "u2", "u2", "u3", "u3", "u3"],
     ...                     "item_id": ["i1", "i2","i3", "i1", "i2","i3"],
     ...                     "rating": [1., 0.5, 3, 1, 0, 1],
-    ...                     "timestamp": ["2020-01-01 23:59:59", "2020-02-01",
-    ...                                   "2020-02-01", "2020-01-01 00:04:15",
+    ...                     "timestamp": ["2020-01-01 23:59:59", "2020-02-01 00:00:00",
+    ...                                   "2020-02-01 00:00:01", "2020-01-01 00:04:15",
     ...                                   "2020-01-02 00:04:14", "2020-01-05 23:59:59"]},
     ...             )
     >>> log_pd["timestamp"] = pd.to_datetime(log_pd["timestamp"], format="ISO8601")
@@ -750,7 +751,7 @@ class TimePeriodFilter(_BaseFilter):
     +-------+-------+------+-------------------+
     |     u1|     i1|   1.0|2020-01-01 23:59:59|
     |     u2|     i2|   0.5|2020-02-01 00:00:00|
-    |     u2|     i3|   3.0|2020-02-01 00:00:00|
+    |     u2|     i3|   3.0|2020-02-01 00:00:01|
     |     u3|     i1|   1.0|2020-01-01 00:04:15|
     |     u3|     i2|   0.0|2020-01-02 00:04:14|
     |     u3|     i3|   1.0|2020-01-05 23:59:59|

replay/preprocessing/history_based_fp.py

@@ -179,8 +179,8 @@ class LogStatFeaturesProcessor(EmptyFeatureProcessor):
         abnormality_aggs = [sf.mean(sf.col("abnormality")).alias("abnormality")]
 
         # Abnormality CR:
-        max_std = item_features.select(sf.max("i_std")).collect()[0][0]
-        min_std = item_features.select(sf.min("i_std")).collect()[0][0]
+        max_std = item_features.select(sf.max("i_std")).first()[0]
+        min_std = item_features.select(sf.min("i_std")).first()[0]
         if max_std - min_std != 0:
             abnormality_df = abnormality_df.withColumn(
                 "controversy",
@@ -201,15 +201,15 @@ class LogStatFeaturesProcessor(EmptyFeatureProcessor):
          :param log: input SparkDataFrame ``[user_idx, item_idx, timestamp, relevance]``
         """
         self.calc_timestamp_based = (isinstance(log.schema["timestamp"].dataType, TimestampType)) & (
-            log.select(sf.countDistinct(sf.col("timestamp"))).collect()[0][0] > 1
+            log.select(sf.countDistinct(sf.col("timestamp"))).first()[0] > 1
         )
-        self.calc_relevance_based = log.select(sf.countDistinct(sf.col("relevance"))).collect()[0][0] > 1
+        self.calc_relevance_based = log.select(sf.countDistinct(sf.col("relevance"))).first()[0] > 1
 
         user_log_features = log.groupBy("user_idx").agg(*self._create_log_aggregates(agg_col="user_idx"))
         item_log_features = log.groupBy("item_idx").agg(*self._create_log_aggregates(agg_col="item_idx"))
 
         if self.calc_timestamp_based:
-            last_date = log.select(sf.max("timestamp")).collect()[0][0]
+            last_date = log.select(sf.max("timestamp")).first()[0]
             user_log_features = self._add_ts_based(features=user_log_features, max_log_date=last_date, prefix="u")
 
             item_log_features = self._add_ts_based(features=item_log_features, max_log_date=last_date, prefix="i")

replay/preprocessing/label_encoder.py

@@ -5,6 +5,7 @@ Contains classes for encoding categorical data
     Recommended to use together with the LabelEncoder.
 ``LabelEncoder`` to apply multiple LabelEncodingRule to dataframe.
 """
+
 import abc
 import warnings
 from typing import Dict, List, Literal, Mapping, Optional, Sequence, Union

replay/scenarios/__init__.py

@@ -1,4 +1,5 @@
 """
 Scenarios are a series of actions for recommendations
 """
+
 from .fallback import Fallback

replay/splitters/last_n_splitter.py

@@ -193,7 +193,7 @@ class LastNSplitter(Splitter):
 
     def _add_time_partition_to_polars(self, interactions: PolarsDataFrame) -> PolarsDataFrame:
         res = interactions.sort(self.timestamp_column).with_columns(
-            pl.col(self.divide_column).cumcount().over(pl.col(self.divide_column)).alias("row_num")
+            pl.col(self.divide_column).cum_count().over(pl.col(self.divide_column)).alias("row_num")
         )
 
         return res

replay/splitters/time_splitter.py

@@ -193,7 +193,7 @@ class TimeSplitter(Splitter):
             )
             test_start = int(dates.count() * (1 - threshold)) + 1
             test_start = (
-                dates.filter(sf.col("_row_number_by_ts") == test_start).select(self.timestamp_column).collect()[0][0]
+                dates.filter(sf.col("_row_number_by_ts") == test_start).select(self.timestamp_column).first()[0]
             )
             res = interactions.withColumn("is_test", sf.col(self.timestamp_column) >= test_start)
         else:

replay/splitters/two_stage_splitter.py

@@ -1,8 +1,10 @@
 """
 This splitter split data by two columns.
 """
+
 from typing import Optional, Tuple
 
+import numpy as np
 import polars as pl
 
 from replay.utils import PYSPARK_AVAILABLE, DataFrameLike, PandasDataFrame, PolarsDataFrame, SparkDataFrame
@@ -124,15 +126,15 @@ class TwoStageSplitter(Splitter):
         :return: DataFrame with single column `first_divide_column`
         """
         if isinstance(interactions, SparkDataFrame):
-            all_values = interactions.select(self.first_divide_column).distinct()
+            all_values = interactions.select(self.first_divide_column).distinct().sort(self.first_divide_column)
             user_count = all_values.count()
         elif isinstance(interactions, PandasDataFrame):
             all_values = PandasDataFrame(
-                interactions[self.first_divide_column].unique(), columns=[self.first_divide_column]
+                np.sort(interactions[self.first_divide_column].unique()), columns=[self.first_divide_column]
             )
             user_count = len(all_values)
         else:
-            all_values = interactions.select(self.first_divide_column).unique()
+            all_values = interactions.select(self.first_divide_column).unique().sort(self.first_divide_column)
             user_count = len(all_values)
 
         value_error = False
@@ -152,7 +154,7 @@ class TwoStageSplitter(Splitter):
         if isinstance(interactions, SparkDataFrame):
             test_users = (
                 all_values.withColumn("_rand", sf.rand(self.seed))
-                .withColumn("_row_num", sf.row_number().over(Window.orderBy("_rand")))
+                .withColumn("_row_num", sf.row_number().over(Window.partitionBy(sf.lit(0)).orderBy("_rand")))
                 .filter(f"_row_num <= {test_user_count}")
                 .drop("_rand", "_row_num")
             )
@@ -240,10 +242,10 @@ class TwoStageSplitter(Splitter):
         res = res.fill_null(False)
 
         train = res.filter((pl.col("_frac") > self.second_divide_size) | (~pl.col("is_test"))).drop(
-            "_rand", "_row_num", "count", "_frac", "is_test"
+            "_row_num", "count", "_frac", "is_test"
         )
         test = res.filter((pl.col("_frac") <= self.second_divide_size) & pl.col("is_test")).drop(
-            "_rand", "_row_num", "count", "_frac", "is_test"
+            "_row_num", "count", "_frac", "is_test"
         )
 
         return train, test

replay/utils/distributions.py

@@ -1,4 +1,5 @@
 """Distribution calculations"""
+
 from .types import PYSPARK_AVAILABLE, DataFrameLike, PandasDataFrame
 
 if PYSPARK_AVAILABLE:

replay/utils/session_handler.py

@@ -48,10 +48,10 @@ def get_spark_session(
             path_to_replay_jar = (
                 "https://repo1.maven.org/maven2/io/github/sb-ai-lab/replay_2.12/3.1.3/replay_2.12-3.1.3.jar"
             )
-        elif pyspark_version.startswith(("3.2", "3.3")):
+        elif pyspark_version.startswith(("3.2", "3.3")):  # pragma: no cover
             path_to_replay_jar = "https://repo1.maven.org/maven2/io/github/sb-ai-lab/replay_2.12/3.2.0_als_metrics/replay_2.12-3.2.0_als_metrics.jar"
         elif pyspark_version.startswith("3.4"):  # pragma: no cover
-            path_to_replay_jar = "https://repo1.maven.org/maven2/io/github/sb-ai-lab/replay_2.12/3.4.0_als_metrics/replay_2.12-3.4.0_als_metrics.jar"
+            path_to_replay_jar = "https://repo1.maven.org/maven2/io/github/sb-ai-lab/replay_after_fix_2.12/0.1/replay_after_fix_2.12-0.1.jar"
         else:  # pragma: no cover
             path_to_replay_jar = (
                 "https://repo1.maven.org/maven2/io/github/sb-ai-lab/replay_2.12/3.1.3/replay_2.12-3.1.3.jar"
@@ -83,7 +83,7 @@ def get_spark_session(
         .config("spark.driver.maxResultSize", "4g")
         .config("spark.driver.bindAddress", "127.0.0.1")
         .config("spark.driver.host", "localhost")
-        .config("spark.sql.execution.arrow.pyspark.enabled", "true")
+        .config("spark.sql.execution.arrow.enabled", "true")
         .config("spark.kryoserializer.buffer.max", "256m")
         .config("spark.files.overwrite", "true")
         .master(f"local[{'*' if core_count == -1 else core_count}]")

replay/utils/spark_utils.py

@@ -459,8 +459,8 @@ def fallback(
     if base.count() == 0:
         return get_top_k_recs(fill, k, query_column=query_column, rating_column=rating_column)
     margin = 0.1
-    min_in_base = base.agg({rating_column: "min"}).collect()[0][0]
-    max_in_fill = fill.agg({rating_column: "max"}).collect()[0][0]
+    min_in_base = base.agg({rating_column: "min"}).first()[0]
+    max_in_fill = fill.agg({rating_column: "max"}).first()[0]
     diff = max_in_fill - min_in_base
     fill = fill.withColumnRenamed(rating_column, "relevance_fallback")
     if diff >= 0:

{replay_rec-0.17.1rc0.dist-info → replay_rec-0.18.0rc0.dist-info}/METADATA

@@ -1,11 +1,11 @@
 Metadata-Version: 2.1
 Name: replay-rec
-Version: 0.17.1rc0
+Version: 0.18.0rc0
 Summary: RecSys Library
 Home-page: https://sb-ai-lab.github.io/RePlay/
 License: Apache-2.0
 Author: AI Lab
-Requires-Python: >=3.8.1,<3.11
+Requires-Python: >=3.8.1,<3.12
 Classifier: Development Status :: 4 - Beta
 Classifier: Environment :: Console
 Classifier: Intended Audience :: Developers
@@ -16,32 +16,34 @@ Classifier: Operating System :: Unix
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
 Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Provides-Extra: all
 Provides-Extra: spark
 Provides-Extra: torch
 Requires-Dist: d3rlpy (>=2.0.4,<3.0.0)
+Requires-Dist: fixed-install-nmslib (==2.1.2)
 Requires-Dist: gym (>=0.26.0,<0.27.0)
-Requires-Dist: hnswlib (==0.7.0)
+Requires-Dist: hnswlib (>=0.7.0,<0.8.0)
 Requires-Dist: implicit (>=0.7.0,<0.8.0)
 Requires-Dist: lightautoml (>=0.3.1,<0.4.0)
 Requires-Dist: lightfm (==1.17)
-Requires-Dist: lightning (>=2.0.2,<3.0.0) ; extra == "torch" or extra == "all"
+Requires-Dist: lightning (>=2.0.2,<=2.4.0) ; extra == "torch" or extra == "all"
 Requires-Dist: llvmlite (>=0.32.1)
-Requires-Dist: nmslib (==2.1.1)
 Requires-Dist: numba (>=0.50)
 Requires-Dist: numpy (>=1.20.0)
 Requires-Dist: optuna (>=3.2.0,<3.3.0)
 Requires-Dist: pandas (>=1.3.5,<=2.2.2)
-Requires-Dist: polars (>=0.20.7,<0.21.0)
-Requires-Dist: psutil (>=5.9.5,<5.10.0)
+Requires-Dist: polars (>=1.0.0,<1.1.0)
+Requires-Dist: psutil (>=6.0.0,<6.1.0)
 Requires-Dist: pyarrow (>=12.0.1)
-Requires-Dist: pyspark (>=3.0,<3.5) ; extra == "spark" or extra == "all"
+Requires-Dist: pyspark (>=3.0,<3.5) ; (python_full_version >= "3.8.1" and python_version < "3.11") and (extra == "spark" or extra == "all")
+Requires-Dist: pyspark (>=3.4,<3.5) ; (python_version >= "3.11" and python_version < "3.12") and (extra == "spark" or extra == "all")
 Requires-Dist: pytorch-ranger (>=0.1.1,<0.2.0) ; extra == "torch" or extra == "all"
-Requires-Dist: sb-obp (>=0.5.7,<0.6.0)
+Requires-Dist: sb-obp (>=0.5.8,<0.6.0)
 Requires-Dist: scikit-learn (>=1.0.2,<2.0.0)
-Requires-Dist: scipy (>=1.8.1,<1.9.0)
-Requires-Dist: torch (>=1.8,<2.0) ; extra == "torch" or extra == "all"
+Requires-Dist: scipy (>=1.8.1,<2.0.0)
+Requires-Dist: torch (>=1.8,<=2.4.0) ; extra == "torch" or extra == "all"
 Project-URL: Repository, https://github.com/sb-ai-lab/RePlay
 Description-Content-Type: text/markdown
 

{replay_rec-0.17.1rc0.dist-info → replay_rec-0.18.0rc0.dist-info}/RECORD

@@ -1,10 +1,10 @@
-replay/__init__.py,sha256=_PQ2zFERSGjgeThzFv3t6MPODgutry1eR82biGhB98o,54
+replay/__init__.py,sha256=8QXsQRY27Ie9xmwimwzqKYG4KTLnxtZW0ns89LKKtUU,55
 replay/data/__init__.py,sha256=g5bKRyF76QL_BqlED-31RnS8pBdcyj9loMsx5vAG_0E,301
-replay/data/dataset.py,sha256=cSStvCqIc6WAJNtbmsxncSpcQZ1KfULMsrmf_V0UdPw,29490
+replay/data/dataset.py,sha256=FnvsFeIcCMlq94_NDQRY3-jgpVvKN-4FdivABWVr8Pk,29481
 replay/data/dataset_utils/__init__.py,sha256=9wUvG8ZwGUvuzLU4zQI5FDcH0WVVo5YLN2ey3DterP0,55
-replay/data/dataset_utils/dataset_label_encoder.py,sha256=TEx2zLw5rJdIz1SRBEznyVv5x_Cs7o6QQbzMk-M1LU0,9598
+replay/data/dataset_utils/dataset_label_encoder.py,sha256=o8p7XvQewKuqYY8anrUhuY8gTau1FbpPjnNSAwbDZTY,9599
 replay/data/nn/__init__.py,sha256=WxLsi4rgOuuvGYHN49xBPxP2Srhqf3NYgfBDVH-ZvBo,1122
-replay/data/nn/schema.py,sha256=pO4N7RgmgrqfD1-2d95OTeihKHTZ-5y2BG7CX_wBFi4,16198
+replay/data/nn/schema.py,sha256=N6lBWC1Q_kX1s6oVdOaxxAYE2pWqwbkDK7LmLL8N1Ts,16208
 replay/data/nn/sequence_tokenizer.py,sha256=Ambrp3CMOp3JP68PiwmVh0m-_zNXiWzxxVreHkEwOyY,32592
 replay/data/nn/sequential_dataset.py,sha256=jCWxC0Pm1eQ5p8Y6_Bmg4fSEvPaecLrqz1iaWzaICdI,11014
 replay/data/nn/torch_sequential_dataset.py,sha256=BqrK_PtkhpsaY1zRIWGk4EgwPL31a7IWCc0hLDuwDQc,10984
@@ -12,8 +12,8 @@ replay/data/nn/utils.py,sha256=YKE9gkIHZDDiwv4THqOWL4PzsdOujnPuM97v79Mwq0E,2769
 replay/data/schema.py,sha256=F_cv6sYb6l23yuX5xWnbqoJ9oSeUT2NpIM19u8Lf2jA,15606
 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=W6S9YTGCezLORyTKCqL4Y_PniC1k3Bu5XWIM3WVHg2Q,2860
-replay/experimental/metrics/base_metric.py,sha256=aYmKZ_336dRrlslBzYsgsOzmed54BNjNXsRcpzB5gyM,22648
+replay/experimental/metrics/__init__.py,sha256=bdQogGbEDVAeH7Ejbb6vpw7bP6CYhftTu_DQuoFRuCA,2861
+replay/experimental/metrics/base_metric.py,sha256=mWbkRGdHTF3ZHq9WSqTGGAX2XJtOSzwcefjSu1Mdl0Y,22649
 replay/experimental/metrics/coverage.py,sha256=3kVBAUhIEOuD8aJ6DShH2xh_1F61dcLZb001VCkmeJk,3154
 replay/experimental/metrics/experiment.py,sha256=Bd_XB9zbngcAwf5JLZKVPsFWQoz9pEGlPEUbkiR_MDc,7343
 replay/experimental/metrics/hitrate.py,sha256=TfWJrUyZXabdMr4tn8zqUPGDcYy2yphVCzXmLSHCxY0,675
@@ -29,10 +29,10 @@ replay/experimental/metrics/unexpectedness.py,sha256=JQQXEYHtQM8nqp7X2He4E9ZYwbp
 replay/experimental/models/__init__.py,sha256=R284PXgSxt-JWWwlSTLggchash0hrLfy4b2w-ySaQf4,588
 replay/experimental/models/admm_slim.py,sha256=Oz-x0aQAnGFN9z7PB7MiKfduBasc4KQrBT0JwtYdwLY,6581
 replay/experimental/models/base_neighbour_rec.py,sha256=pRcffr0cdRNZRVpzWb2Qv-UIsLkhbs7K1GRAmrSqPSM,7506
-replay/experimental/models/base_rec.py,sha256=rj2r7r_mmJdzKAkg5CHG1eqJhOpUHAETPe0NwfibFjU,49606
+replay/experimental/models/base_rec.py,sha256=eTHQdjEaS_5e-8y7xB6tHlSObD0cbD66_NfFZJK2NxU,49571
 replay/experimental/models/base_torch_rec.py,sha256=oDkCxVFQjIHSWKlCns6mU3ECWbQW3mQZWvBHBxJQdwc,8111
-replay/experimental/models/cql.py,sha256=9ONDMblfxUgol5Pb2UInfSHVRbB2Ma15zAZC6valhtk,19628
-replay/experimental/models/ddpg.py,sha256=sZrGgwj_kKeUnwwT9qooc4Cxz2oVGkNfUwUe1N7mreI,31982
+replay/experimental/models/cql.py,sha256=3IBQEqWfyHmvGxCvWtIbLgjuRWfd_8mySg8bVaI4KHQ,19630
+replay/experimental/models/ddpg.py,sha256=uqWk235-YZ2na-NPN4TxUM9ZhogpLZEjivt1oSC2rtI,32080
 replay/experimental/models/dt4rec/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 replay/experimental/models/dt4rec/dt4rec.py,sha256=ZIHYonDubStN7Gb703csy86R7Q3_1fZc4zJf98HYFe4,5895
 replay/experimental/models/dt4rec/gpt1.py,sha256=T3buFtYyF6Fh6sW6f9dUZFcFEnQdljItbRa22CiKb0w,14044
@@ -41,15 +41,15 @@ replay/experimental/models/dt4rec/utils.py,sha256=jbCx2Xc85VtjQx-caYhJFfVuj1Wf86
 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=dKSVCMXWRB7IUnpEK_QNhSEuUSVcG793E8MT_AGXneY,25890
 replay/experimental/models/implicit_wrap.py,sha256=8F-f-CaStmlNHwphu-yu8o4Aft08NKDD_SqqH0zp1Uo,4655
-replay/experimental/models/lightfm_wrap.py,sha256=a2ctIEoZf7I0C_awiQI1lE4RGJ7ISs60znysgHRXZCw,11337
-replay/experimental/models/mult_vae.py,sha256=FdJ-GL6Jj2l5-38edKp_jsNfwFNGPxMHXKn8cG2tGJs,11607
-replay/experimental/models/neuromf.py,sha256=QRu--zIyOSQIp8R5Ksgiw7o0s5yOhQpuAX9YshKJs4w,14391
-replay/experimental/models/scala_als.py,sha256=PVf0YA3ii4iRwGqpYg6nStgaauyrm9QTzLtK_4f1En0,10985
+replay/experimental/models/lightfm_wrap.py,sha256=8nuTpiBuddKlMFFpbUpRt5k_JiBGRjPpF_hNbKdLP4Q,11327
+replay/experimental/models/mult_vae.py,sha256=BnnlUHPlNuvh7EFA8bjITRW_m8JQANRD6zvsNQ1SUXM,11608
+replay/experimental/models/neuromf.py,sha256=Hr9qEKv1shkwAqCVCxfews1Pk3F6yni2WIZUGS2tNCE,14392
+replay/experimental/models/scala_als.py,sha256=-sMZ8P_XbmVi-hApuS46MpaosVIXRED05cgsOI3ojvQ,10975
 replay/experimental/nn/data/__init__.py,sha256=5EAF-FNd7xhkUpTq_5MyVcPXBD81mJCwYrcbhdGOWjE,48
 replay/experimental/nn/data/schema_builder.py,sha256=5PphL9kK-tVm30nWdTjHUzqVOnTwKiU_MlxGdL5HJ8Y,1736
 replay/experimental/preprocessing/__init__.py,sha256=uMyeyQ_GKqjLhVGwhrEk3NLhhzS0DKi5xGo3VF4WkiA,130
-replay/experimental/preprocessing/data_preparator.py,sha256=fQ8Blo_uzA-2eC-_ViVeU26Tqj5lxLTCBoDJfEmiqUo,35968
-replay/experimental/preprocessing/padder.py,sha256=o7S_Zk-ne_jria3QhWCKkYa6bEqhCdtvCA-R0MjOvU4,9569
+replay/experimental/preprocessing/data_preparator.py,sha256=SLyk4HWurLmUHuev5L_GmI3oVU-58lCflOExHJ7zCGw,35964
+replay/experimental/preprocessing/padder.py,sha256=ROKnGA0136C9W9Qkky-1V5klcMxvwos5KL4_jMLOgwY,9564
 replay/experimental/preprocessing/sequence_generator.py,sha256=E1_0uZJLv8V_n6YzRlgUWtcrHIdjNwPeBN-BMbz0e-A,9053
 replay/experimental/scenarios/__init__.py,sha256=gWFLCkLyOmOppvbRMK7C3UMlMpcbIgiGVolSH6LPgWA,91
 replay/experimental/scenarios/obp_wrapper/__init__.py,sha256=rsRyfsTnVNp20LkTEugwoBrV9XWbIhR8tOqec_Au6dY,450
@@ -58,12 +58,12 @@ replay/experimental/scenarios/obp_wrapper/replay_offline.py,sha256=A6TPBFHj_UUL0
 replay/experimental/scenarios/obp_wrapper/utils.py,sha256=-ioWTb73NmHWxVxw4BdSolctqeeGIyjKtydwc45nrrk,3271
 replay/experimental/scenarios/two_stages/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 replay/experimental/scenarios/two_stages/reranker.py,sha256=tJtWhbHRNV4sJZ9RZzqIfylTplKh9QVwTIBhEGGnXq8,4244
-replay/experimental/scenarios/two_stages/two_stages_scenario.py,sha256=ZgflnQ6xuxDFphdKX6Q0jtXidHS7c2YvDaccoaL78Qo,29846
+replay/experimental/scenarios/two_stages/two_stages_scenario.py,sha256=frwsST85YGMGEZPf4DZFp3kPKPEcVgaxOCEdtZywpkw,29841
 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=0ksSm5bJ1bL32VV5HI-KPe0a1EAzzOhMtmSYaM_zRrE,6271
+replay/experimental/utils/model_handler.py,sha256=Rfj57E1R_XMEEigHNZa9a-rzEsyLWSDsgKfXoRzWWdg,6426
 replay/experimental/utils/session_handler.py,sha256=076TLpTOcnh13BznNTtJW6Zhrqvm9Ee1mlpP5YMD4No,1313
-replay/metrics/__init__.py,sha256=KDkxVnKa4ks9K9GmlrdTx1pkIl-MAmm78ZASsp2ZndE,2812
+replay/metrics/__init__.py,sha256=j0PGvUehaPEZMNo9SQwJsnvzrS4bam9eHrRMQFLnMjY,2813
 replay/metrics/base_metric.py,sha256=uleW5vLrdA3iRx72tFyW0cxe6ne_ugQ1XaY_ZTcnAOo,15960
 replay/metrics/categorical_diversity.py,sha256=OYsF-Ng-WrF9CC-sKgQKngrA779NO8MtgRvvAyC8MXM,10781
 replay/metrics/coverage.py,sha256=wE1Y_TgKOzf_9ixeas-vsxANAHeHSGPuGrzKk8DklaY,8843
@@ -82,10 +82,10 @@ replay/metrics/surprisal.py,sha256=wj9Q5mAdECpl0LfykJWt8jgN3_CUSlai2fhiFgJr_Vw,7
 replay/metrics/torch_metrics_builder.py,sha256=2gcCcb0A-TVpYcBIYGhXrggyFX-M_T7Q1pQUiMpxEZE,13845
 replay/metrics/unexpectedness.py,sha256=cfDnkpK6nPeawwHDVNQAkUtsW0SvAttI84k4M5ttkyo,6888
 replay/models/__init__.py,sha256=_4gNsauyrVMYEoFDihPYY9kGuBGGFyy1krvxF7oEYjk,808
-replay/models/als.py,sha256=dpBwyg1ZBqtdgrFluHaq5nuPQT---fmA-N2TspJAM0U,6232
+replay/models/als.py,sha256=eGiMok_zu5ZUKXU9i9feCP4RGMqSnlIGHjks6MqKzHw,6227
 replay/models/association_rules.py,sha256=cp4myXvMqro6zLMjJzJMb0DZ5DQFQEZvhqf5OBgBw8Y,14659
 replay/models/base_neighbour_rec.py,sha256=zMORSm4uMQSNj12v0n_6w8fVHgSYjeiqyYE9rrWgSfU,7887
-replay/models/base_rec.py,sha256=iF0eMlNQVcd-nb3aCRG3ObpmEi7P4-jP_5mKjwc6anc,66407
+replay/models/base_rec.py,sha256=NFz_xcarDwhaB3fSa-5uLBa6tyATOwOQLD_yR445m5U,66372
 replay/models/cat_pop_rec.py,sha256=tzI1UMlC3kEOrtDZ1UPpCP13tX8CeDJP7PHwQKl9Mmo,11922
 replay/models/cluster.py,sha256=9JcpGnbfgFa4UsyxPAa4WMuJFa3rsuAxiKoy-s_UfyE,4970
 replay/models/extensions/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -106,8 +106,8 @@ replay/models/extensions/ann/index_inferers/__init__.py,sha256=47DEQpj8HBSa-_TIm
 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=1bpBjRhj4J_ecaORRhkhEke7ImJcxVTFRmmGK2wISB4,3120
-replay/models/extensions/ann/index_inferers/nmslib_index_inferer.py,sha256=TqyunbjMQp1bWltbouvqK2kr2cnER6_d75NuCTVB3O0,2195
+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
@@ -125,7 +125,7 @@ replay/models/nn/sequential/__init__.py,sha256=CI2n0cxs_amqJrwBMq6n0Z_uBOu7CGXfa
 replay/models/nn/sequential/bert4rec/__init__.py,sha256=JfZqHOGxcvOkICl5cWmZbZhaKXpkIvua-Wj57VWWEhw,399
 replay/models/nn/sequential/bert4rec/dataset.py,sha256=sCnYGF-sQ1YlLq7vofQo2GIIlc59YlbUgmW7bHI6MPg,10324
 replay/models/nn/sequential/bert4rec/lightning.py,sha256=TqO0V-g0JA0D-L2t08AgAIQgBkDtLUgl4xqekSiDWJ4,22605
-replay/models/nn/sequential/bert4rec/model.py,sha256=tiAiKOUwk3iPPYWyWkfOF23IzfL1NbeaF-8kNt9uZlU,21303
+replay/models/nn/sequential/bert4rec/model.py,sha256=lZJwJbWPjrcvQCpD2LULMva-nXaTL8PgZHkZ-8z9okU,17758
 replay/models/nn/sequential/callbacks/__init__.py,sha256=Q7mSZ_RB6iyD7QZaBL_NJ0uh8cRfgxq7gtPHbkSyhoo,282
 replay/models/nn/sequential/callbacks/prediction_callbacks.py,sha256=H4MZ87_N0hCKtHbsTuN-Cq_SJ-n9TSkvv2okuGnwo3M,9045
 replay/models/nn/sequential/callbacks/validation_callback.py,sha256=6TNl3NN9oahK1J7DT44461xqBuUCblCsLzUi2svlhF4,5825
@@ -135,7 +135,7 @@ replay/models/nn/sequential/postprocessors/postprocessors.py,sha256=V32xMyNPztJ5
 replay/models/nn/sequential/sasrec/__init__.py,sha256=c6130lRpPkcbuGgkM7slagBIgH7Uk5zUtSzFDEwAsik,250
 replay/models/nn/sequential/sasrec/dataset.py,sha256=ReGNc6t9jjXxMZJp0WqFj1jatJFHnWOrkK3W8lwBNIs,7036
 replay/models/nn/sequential/sasrec/lightning.py,sha256=DtLnNikTNvqroCzaVFw7u-QZpZdvwiYbCwJLE7FkHms,21397
-replay/models/nn/sequential/sasrec/model.py,sha256=DE9kaqlcL22v07kpi2IzIwZ4-3AXNBVTZCnfuTS5usg,27775
+replay/models/nn/sequential/sasrec/model.py,sha256=EBAfDP3WHZC-Pyb8dm0mr3gpxhrCOFQDHbZ2itFPWmk,27780
 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
@@ -145,36 +145,36 @@ replay/models/ucb.py,sha256=X98ulD8L3gWR3VA7rbQkXFqQyzWc-Nt12lp_gbLTfLQ,6964
 replay/models/wilson.py,sha256=o7aUWjq3648dAfgGBoWD5Gu-HzdyobPMaH2lzCLijiA,4558
 replay/models/word2vec.py,sha256=MgoRIS5vqW9cH1HKAGa2xsLLnTH6XC1EXk4Dzvn5lXA,9171
 replay/optimization/__init__.py,sha256=az6U10rF7X6rPRUUPwLyiM1WFNJ_6kl0imA5xLVWFLs,120
-replay/optimization/optuna_objective.py,sha256=Z-8X0_FT3BicVWj0UhxoLrvZAck3Dhn7jHDGo0i0hxA,7653
+replay/optimization/optuna_objective.py,sha256=OUYlC3wQj4GmrSbE_z5IPPS6OEEPUoeRCWFJnIR1Na8,7654
 replay/preprocessing/__init__.py,sha256=TtBysFqYeDy4kZAEnWEaNSwPvbffYdfMkEs71YG51fM,411
-replay/preprocessing/converter.py,sha256=DczqsVLrwFi6EFhK2HR8rGiIxGCwXeY7QNgWorjA41g,4390
-replay/preprocessing/filters.py,sha256=wsXWQoZ-2aAecunLkaTxeLWi5ow4e3FAGcElx0iNx0w,41669
-replay/preprocessing/history_based_fp.py,sha256=tfgKJPKm53LSNqM6VmMXYsVrRDc-rP1Tbzn8s3mbziQ,18751
-replay/preprocessing/label_encoder.py,sha256=MLBavPD-dB644as0E9ZJSE9-8QxGCB_IHek1w3xtqDI,27040
+replay/preprocessing/converter.py,sha256=JQ-4u5x0eXtswl1iH-bZITBXQov1nebnZ6XcvpD8Twk,4417
+replay/preprocessing/filters.py,sha256=4Lk3gnNwksPscdW6a47qJ_r8QEpbYRuNqTPJ9-bvSRo,41743
+replay/preprocessing/history_based_fp.py,sha256=Wb2DXHawE2dYghm1ARr05_5opd_TLfthZ7h5e0zbDjY,18726
+replay/preprocessing/label_encoder.py,sha256=JrVNP93NVt630OFmacQ6MlkH7rTLIPog05-0vyBuQtQ,27041
 replay/preprocessing/sessionizer.py,sha256=G6i0K3FwqtweRxvcSYraJ-tBWAT2HnV-bWHHlIZJF-s,12217
-replay/scenarios/__init__.py,sha256=kw2wRkPPinw0IBA20D83XQ3xeSudk3KuYAAA1Wdr8xY,93
+replay/scenarios/__init__.py,sha256=XXAKEQPTLlve-0O6NPwFgahFrb4oGcIq3HaYaaGxG2E,94
 replay/scenarios/fallback.py,sha256=EeBmIR-5igzKR2m55bQRFyhxTkpJez6ZkCW449n8hWs,7130
 replay/splitters/__init__.py,sha256=DnqVMelrzLwR8fGQgcWN_8FipGs8T4XGSPOMW-L_x2g,454
 replay/splitters/base_splitter.py,sha256=hj9_GYDWllzv3XnxN6WHu1JKRRVjXo77vZEOLbF9v-s,7761
 replay/splitters/cold_user_random_splitter.py,sha256=gVwBVdn_0IOaLGT_UzJoS9AMaPhelZy-FpC5JQS1PhA,4136
 replay/splitters/k_folds.py,sha256=WH02_DP18A2ae893ysonmfLPB56_i1ETllTAwaCYekg,6218
-replay/splitters/last_n_splitter.py,sha256=r9kdq2JPi508C9ywjwc68an-iq27KsigMfHWLz0YohE,15346
+replay/splitters/last_n_splitter.py,sha256=ITq8yzd7PrbAi3yp5XJlBehq0E0boiPyTEn72sXZEOA,15347
 replay/splitters/new_users_splitter.py,sha256=bv_QCPkL7KFxJIovAXQbP3Rlty3My48YNTqrj-2ucFQ,9167
 replay/splitters/random_splitter.py,sha256=mbOcxeF0B9WQ9OSxK8CHkPtO8UzKCZJt3rRyFhn-hyQ,2996
 replay/splitters/ratio_splitter.py,sha256=8zvuCn16Icc4ntQPKXJ5ArAWuJzCZ9NHZtgWctKyBVY,17519
-replay/splitters/time_splitter.py,sha256=iXhuafjBx7dWyJSy-TEVy1IUQBwMpA1gAiF4-GtRe2g,9031
-replay/splitters/two_stage_splitter.py,sha256=PWozxjjgjrVzdz6Sm9dcDTeH0bOA24reFzkk_N_TgbQ,17734
+replay/splitters/time_splitter.py,sha256=tsoK3Qg_pcYHDxBlv2xC8ohAikoIqac3fRGBvCb-QRo,9026
+replay/splitters/two_stage_splitter.py,sha256=U90l1wfJnMAAW1j4YpJSd8zWvWB-LDUKFCifnanXraU,17830
 replay/utils/__init__.py,sha256=vDJgOWq81fbBs-QO4ZDpdqR4KDyO1kMOOxBRi-5Gp7E,253
 replay/utils/common.py,sha256=s4Pro3QCkPeVBsj-s0vrbhd_pkJD-_-2M_sIguxGzQQ,5411
 replay/utils/dataframe_bucketizer.py,sha256=LipmBBQkdkLGroZpbP9i7qvTombLdMxo2dUUys1m5OY,3748
-replay/utils/distributions.py,sha256=kGGq2KzQZ-yhTuw_vtOsKFXVpXUOQ2l4aIFBcaDufZ8,1202
+replay/utils/distributions.py,sha256=UuhaC9HI6HnUXW97fEd-TsyDk4JT8t7k1T_6l5FpOMs,1203
 replay/utils/model_handler.py,sha256=V-mHDh8_UexjVSsMBBRA9yrjS_5MPHwYOwv_UrI-Zfs,6466
-replay/utils/session_handler.py,sha256=ijTvDSNAe1D9R1e-dhtd-r80tFNiIBsFdWZLgw-gLEo,5153
-replay/utils/spark_utils.py,sha256=k5lUFM2C9QZKQON3dqhgfswyUF4tsgJOn0U2wCKimqM,26901
+replay/utils/session_handler.py,sha256=RYzQvvOnukundccEBnH4ghEdyUgiGB9etz5e3Elvfgw,5157
+replay/utils/spark_utils.py,sha256=LBzS8PJc6Mq8q7S_f6BbQZkeOEW49briAdp--pwFWbs,26891
 replay/utils/time.py,sha256=J8asoQBytPcNw-BLGADYIsKeWhIoN1H5hKiX9t2AMqo,9376
 replay/utils/types.py,sha256=5sw0A7NG4ZgQKdWORnBy0wBZ5F98sP_Ju8SKQ6zbDS4,651
-replay_rec-0.17.1rc0.dist-info/LICENSE,sha256=rPmcA7UrHxBChEAAlJyE24qUWKKl9yLQXxFsKeg_LX4,11344
-replay_rec-0.17.1rc0.dist-info/METADATA,sha256=FgZduBS6AVq1qSNahVyNFCJILLPdVLVosbxjUxN7WkQ,10890
-replay_rec-0.17.1rc0.dist-info/NOTICE,sha256=k0bo4KHiHLRax5K3XKTTrf2Fi8V91mJ-R3FMdh6Reg0,2002
-replay_rec-0.17.1rc0.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-replay_rec-0.17.1rc0.dist-info/RECORD,,
+replay_rec-0.18.0rc0.dist-info/LICENSE,sha256=rPmcA7UrHxBChEAAlJyE24qUWKKl9yLQXxFsKeg_LX4,11344
+replay_rec-0.18.0rc0.dist-info/METADATA,sha256=u_aqIEAypmp3QkU8Jgt0knTsyUbgxcF2lBGz2evOdIg,11164
+replay_rec-0.18.0rc0.dist-info/NOTICE,sha256=k0bo4KHiHLRax5K3XKTTrf2Fi8V91mJ-R3FMdh6Reg0,2002
+replay_rec-0.18.0rc0.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+replay_rec-0.18.0rc0.dist-info/RECORD,,