replay-rec 0.17.1rc0__tar.gz → 0.18.0__tar.gz

{replay_rec-0.17.1rc0 → replay_rec-0.18.0}/PKG-INFO

@@ -1,11 +1,11 @@
 Metadata-Version: 2.1
 Name: replay-rec
-Version: 0.17.1rc0
+Version: 0.18.0
 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 +16,26 @@ 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: gym (>=0.26.0,<0.27.0)
-Requires-Dist: hnswlib (==0.7.0)
-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: llvmlite (>=0.32.1)
-Requires-Dist: nmslib (==2.1.1)
-Requires-Dist: numba (>=0.50)
+Requires-Dist: fixed-install-nmslib (==2.1.2)
+Requires-Dist: hnswlib (>=0.7.0,<0.8.0)
+Requires-Dist: lightning (>=2.0.2,<=2.4.0) ; extra == "torch" or extra == "all"
 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,<3.6) ; (python_full_version >= "3.8.1" and python_version < "3.11") and (extra == "spark" or extra == "all")
+Requires-Dist: pyspark (>=3.4,<3.6) ; (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: 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 → replay_rec-0.18.0}/pyproject.toml

@@ -7,7 +7,7 @@ build-backend = "poetry_dynamic_versioning.backend"
 
 [tool.black]
 line-length = 120
-target-versions = ["py38", "py39", "py310"]
+target-versions = ["py38", "py39", "py310", "py311"]
 
 [tool.poetry]
 name = "replay-rec"
@@ -39,33 +39,29 @@ classifiers = [
 ]
 exclude = [
     "replay/conftest.py",
+    "replay/experimental",
 ]
-version = "0.17.1.preview"
+version = "0.18.0"
 
 [tool.poetry.dependencies]
-python = ">=3.8.1, <3.11"
+python = ">=3.8.1, <3.12"
 numpy = ">=1.20.0"
-pandas = ">=1.3.5,<=2.2.2"
-polars = "~0.20.7"
+pandas = ">=1.3.5, <=2.2.2"
+polars = "~1.0.0"
 optuna = "~3.2.0"
-scipy = "~1.8.1"
-psutil = "~5.9.5"
-pyspark = {version = ">=3.0,<3.5", optional = true}
+scipy = "^1.8.1"
+psutil = "~6.0.0"
 scikit-learn = "^1.0.2"
 pyarrow = ">=12.0.1"
-nmslib = "2.1.1"
-hnswlib = "0.7.0"
-torch = "^1.8"
-lightning = "^2.0.2"
-pytorch-ranger = "^0.1.1"
-lightfm = "1.17"
-lightautoml = "~0.3.1"
-numba = ">=0.50"
-llvmlite = ">=0.32.1"
-sb-obp = "^0.5.7"
-d3rlpy = "^2.0.4"
-implicit = "~0.7.0"
-gym = "^0.26.0"
+pyspark = [
+    {version = ">=3.4,<3.6", python = ">=3.11,<3.12", optional = true},
+    {version = ">=3.0,<3.6", python = ">=3.8.1,<3.11", optional = true},
+]
+torch = {version = ">=1.8, <=2.4.0", optional = true}
+lightning = {version = ">=2.0.2, <=2.4.0", optional = true}
+pytorch-ranger = {version = "^0.1.1", optional = true}
+fixed-install-nmslib = "2.1.2"
+hnswlib = "^0.7.0"
 
 [tool.poetry.extras]
 spark = ["pyspark"]
@@ -77,7 +73,7 @@ jupyter = "~1.0.0"
 jupyterlab = "^3.6.0"
 pytest = ">=7.1.0"
 pytest-cov = ">=3.0.0"
-statsmodels = "~0.13.5"
+statsmodels = "~0.14.0"
 black = ">=23.3.0"
 ruff = ">=0.0.261"
 toml-sort = "^0.23.0"
@@ -92,7 +88,7 @@ data-science-types = "0.2.23"
 
 [tool.poetry-dynamic-versioning]
 enable = false
-format-jinja = """0.17.1{{ env['PACKAGE_SUFFIX'] }}"""
+format-jinja = """0.18.0{{ env['PACKAGE_SUFFIX'] }}"""
 vcs = "git"
 
 [tool.ruff]

replay_rec-0.18.0/replay/__init__.py

@@ -0,0 +1,3 @@
+""" RecSys library """
+
+__version__ = "0.18.0"

{replay_rec-0.17.1rc0 → replay_rec-0.18.0}/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_rec-0.17.1rc0 → replay_rec-0.18.0}/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_rec-0.17.1rc0 → replay_rec-0.18.0}/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_rec-0.17.1rc0 → replay_rec-0.18.0}/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_rec-0.17.1rc0 → replay_rec-0.18.0}/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_rec-0.17.1rc0 → replay_rec-0.18.0}/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_rec-0.17.1rc0 → replay_rec-0.18.0}/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_rec-0.17.1rc0 → replay_rec-0.18.0}/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_rec-0.17.1rc0 → replay_rec-0.18.0}/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_rec-0.17.1rc0 → replay_rec-0.18.0}/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_rec-0.17.1rc0 → replay_rec-0.18.0}/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_rec-0.17.1rc0 → replay_rec-0.18.0}/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_rec-0.17.1rc0 → replay_rec-0.18.0}/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|