v3.1.8

src/streamsight/algorithms/__init__.py

@@ -31,7 +31,7 @@
     Random
     RecentPopularity
     DecayPopularity
-    MostPop
+    MostPopular
 
 Item Similarity Algorithms
 ----------------------------
@@ -69,17 +69,11 @@
     TARSItemKNNDing
 """
 
-from streamsight.algorithms.base import Algorithm
-from streamsight.algorithms.decay_popularity import DecayPopularity
-from streamsight.algorithms.itemknn import ItemKNN
-from streamsight.algorithms.itemknn_incremental import ItemKNNIncremental
-from streamsight.algorithms.itemknn_incremental_movielens import ItemKNNIncrementalMovieLens100K
-from streamsight.algorithms.itemknn_rolling import ItemKNNRolling
-from streamsight.algorithms.itemknn_static import ItemKNNStatic
-from streamsight.algorithms.most_pop import MostPop
-from streamsight.algorithms.random import Random
-from streamsight.algorithms.recent_popularity import RecentPopularity
-from streamsight.algorithms.time_aware_item_knn import (
+from .base import Algorithm
+from .baseline import MostPopular, Random, RecentPopularity
+from .baseline.decay_popularity import DecayPopularity
+from .itemknn import ItemKNN, ItemKNNIncremental, ItemKNNIncrementalMovieLens100K, ItemKNNRolling, ItemKNNStatic
+from .time_aware_item_knn import (
     TARSItemKNN,
     TARSItemKNNDing,
     TARSItemKNNLiu,
@@ -95,7 +89,7 @@
     "ItemKNNIncrementalMovieLens100K",
     "ItemKNNRolling",
     "ItemKNNStatic",
-    "MostPop",
+    "MostPopular",
     "Random",
     "RecentPopularity",
     "TARSItemKNN",

src/streamsight/algorithms/base.py

@@ -11,8 +11,8 @@
 from sklearn.utils.validation import check_is_fitted
 
 from streamsight.matrix import InteractionMatrix, ItemUserBasedEnum, PredictionMatrix, to_csr_matrix
-from streamsight.utils.util import add_columns_to_csr_matrix, add_rows_to_csr_matrix
 from ..models import BaseModel, ParamMixin
+from ..utils import add_columns_to_csr_matrix, add_rows_to_csr_matrix
 
 
 logger = logging.getLogger(__name__)
@@ -331,7 +331,6 @@ class TopKAlgorithm(Algorithm):
     def __init__(self, K: int = 10) -> None:
         super().__init__()
         self.K = K
-        self.similarity_matrix_: csr_matrix
 
 
 class TopKItemSimilarityMatrixAlgorithm(TopKAlgorithm):

src/streamsight/algorithms/baseline/__init__.py

@@ -0,0 +1,10 @@
+from .most_popular import MostPopular
+from .random import Random
+from .recent_popularity import RecentPopularity
+
+
+__all__ = [
+    "MostPopular",
+    "Random",
+    "RecentPopularity",
+]

src/streamsight/algorithms/decay_popularity.py → src/streamsight/algorithms/baseline/decay_popularity.py

@@ -3,8 +3,8 @@
 import numpy as np
 from scipy.sparse import csr_matrix, lil_matrix
 
-from streamsight.matrix import InteractionMatrix
-from .base import Algorithm
+from ...matrix import InteractionMatrix
+from ..base import Algorithm
 
 
 class DecayPopularity(Algorithm):

src/streamsight/algorithms/baseline/most_popular.py

@@ -0,0 +1,72 @@
+import logging
+from typing import Self
+
+import numpy as np
+from scipy.sparse import csr_matrix, hstack, vstack
+
+from ...matrix import PredictionMatrix
+from ..base import PopularityPaddingMixin, TopKAlgorithm
+
+
+logger = logging.getLogger(__name__)
+
+
+class MostPopular(TopKAlgorithm, PopularityPaddingMixin):
+    """A popularity-based algorithm that considers all historical data."""
+
+    IS_BASE: bool = False
+    X_: csr_matrix | None = None  # Store all historical training data
+
+    def _append_training_data(self, X: csr_matrix) -> None:
+        """Append a new interaction matrix to the historical data.
+
+        Args:
+            X (csr_matrix): Interaction matrix to append
+        """
+        if self.X_ is None:
+            raise ValueError("No existing training data to append to.")
+        X_prev: csr_matrix = self.X_.copy()
+        new_num_rows = max(X_prev.shape[0], X.shape[0])
+        new_num_cols = max(X_prev.shape[1], X.shape[1])
+        # Pad the previous matrix
+        if X_prev.shape[0] < new_num_rows:  # Pad rows
+            row_padding = csr_matrix((new_num_rows - X_prev.shape[0], X_prev.shape[1]))
+            X_prev = vstack([X_prev, row_padding])
+        if X_prev.shape[1] < new_num_cols:  # Pad columns
+            col_padding = csr_matrix((X_prev.shape[0], new_num_cols - X_prev.shape[1]))
+            X_prev = hstack([X_prev, col_padding])
+
+        # Pad the current matrix
+        if X.shape[0] < new_num_rows:  # Pad rows
+            row_padding = csr_matrix((new_num_rows - X.shape[0], X.shape[1]))
+            X = vstack([X, row_padding])
+        if X.shape[1] < new_num_cols:  # Pad columns
+            col_padding = csr_matrix((X.shape[0], new_num_cols - X.shape[1]))
+            X = hstack([X, col_padding])
+
+        # Merge data
+        self.X_ = X_prev + X
+
+    def _fit(self, X: csr_matrix) -> Self:
+        if self.X_ is not None:
+            self._append_training_data(X)
+        else:
+            self.X_ = X.copy()
+
+        if not isinstance(self.X_, csr_matrix):
+            raise ValueError("Training data is not initialized properly.")
+
+        if self.X_.shape[1] < self.K:
+            logger.warning("K is larger than the number of items.", UserWarning)
+
+        self.sorted_scores_ = self.get_popularity_scores(self.X_)
+        return self
+
+    def _predict(self, X: PredictionMatrix) -> csr_matrix:
+        intended_shape = (X.get_prediction_data().num_interactions, X.user_item_shape[1])
+
+        # Vectorized: repeat the sorted scores for each prediction row
+        data = np.tile(self.sorted_scores_, (intended_shape[0], 1))
+        X_pred = csr_matrix(data)
+
+        return X_pred

src/streamsight/algorithms/random.py → src/streamsight/algorithms/baseline/random.py

@@ -4,9 +4,9 @@
 import pandas as pd
 from scipy.sparse import csr_matrix
 
-from ..matrix import PredictionMatrix
-from .base import TopKAlgorithm
-from .utils import get_top_K_values
+from ...matrix import PredictionMatrix
+from ..base import TopKAlgorithm
+from ..utils import get_top_K_values
 
 
 class Random(TopKAlgorithm):

src/streamsight/algorithms/baseline/recent_popularity.py

@@ -0,0 +1,34 @@
+
+import logging
+from typing import Self
+
+import numpy as np
+from scipy.sparse import csr_matrix
+
+from ...matrix import PredictionMatrix
+from ..base import PopularityPaddingMixin, TopKAlgorithm
+
+
+logger = logging.getLogger(__name__)
+
+
+class RecentPopularity(TopKAlgorithm, PopularityPaddingMixin):
+    """A popularity-based algorithm which only considers popularity of the latest train data."""
+
+    IS_BASE: bool = False
+
+    def _fit(self, X: csr_matrix) -> Self:
+        self.sorted_scores_ = self.get_popularity_scores(X)
+        return self
+
+    def _predict(self, X: PredictionMatrix) -> csr_matrix:
+        """
+        Predict the K most popular item for each user using only data from the latest window.
+        """
+        intended_shape = (X.get_prediction_data().num_interactions, X.user_item_shape[1])
+
+        # Vectorized: repeat the sorted scores for each prediction row
+        data = np.tile(self.sorted_scores_, (intended_shape[0], 1))
+        X_pred = csr_matrix(data)
+
+        return X_pred

src/streamsight/algorithms/itemknn/__init__.py

@@ -0,0 +1,14 @@
+from .itemknn import ItemKNN
+from .itemknn_incremental import ItemKNNIncremental
+from .itemknn_incremental_movielens import ItemKNNIncrementalMovieLens100K
+from .itemknn_rolling import ItemKNNRolling
+from .itemknn_static import ItemKNNStatic
+
+
+__all__ = [
+    "ItemKNN",
+    "ItemKNNIncremental",
+    "ItemKNNIncrementalMovieLens100K",
+    "ItemKNNRolling",
+    "ItemKNNStatic",
+]

src/streamsight/algorithms/itemknn.py → src/streamsight/algorithms/itemknn/itemknn.py

@@ -5,8 +5,8 @@
 from sklearn.metrics.pairwise import cosine_similarity
 
 from streamsight.matrix import ItemUserBasedEnum, PredictionMatrix
-from .base import PopularityPaddingMixin, TopKItemSimilarityMatrixAlgorithm
-from .utils import get_top_K_values
+from ..base import PopularityPaddingMixin, TopKItemSimilarityMatrixAlgorithm
+from ..utils import get_top_K_values
 
 
 logger = logging.getLogger(__name__)

src/streamsight/algorithms/itemknn_incremental.py → src/streamsight/algorithms/itemknn/itemknn_incremental.py

@@ -3,7 +3,7 @@
 
 from scipy.sparse import csr_matrix, hstack, vstack
 
-from .base import PopularityPaddingMixin, TopKItemSimilarityMatrixAlgorithm
+from ..base import PopularityPaddingMixin, TopKItemSimilarityMatrixAlgorithm
 from .itemknn import ItemKNN
 
 

src/streamsight/algorithms/itemknn_incremental_movielens.py → src/streamsight/algorithms/itemknn/itemknn_incremental_movielens.py

@@ -2,12 +2,12 @@
 
 import numpy as np
 import pandas as pd
-from scipy.sparse import csr_matrix, hstack, vstack
+from scipy.sparse import csr_matrix
 from sklearn.metrics.pairwise import cosine_similarity
 from sklearn.preprocessing import OneHotEncoder
 
-from streamsight.matrix import InteractionMatrix
-from streamsight.utils.util import add_rows_to_csr_matrix
+from ...matrix import InteractionMatrix
+from ...utils import add_rows_to_csr_matrix
 from .itemknn_incremental import ItemKNNIncremental