Fixed dynamic functionality in all models

Author: x-tabdeveloping

turftopic/dynamic.py

@@ -314,7 +314,7 @@ def plot_topics_over_time(self, top_k: int = 6):
                     continue
                 high = high[np.argsort(-values)]
                 name_over_time.append(", ".join(vocab[high]))
-            times = self.time_bin_edges[1:]
+            times = self.time_bin_edges[:-1]
             fig.add_trace(
                 go.Scatter(
                     x=times,

turftopic/models/_keynmf.py

@@ -254,7 +254,7 @@ def fit_transform_dynamic(
         time_bin_edges: list[datetime],
     ) -> np.ndarray:
         self.time_bin_edges = time_bin_edges
-        n_bins = len(time_bin_edges) + 1
+        n_bins = len(time_bin_edges) - 1
         document_term_matrix = self.vectorize(keywords, fitting=True)
         check_non_negative(document_term_matrix, "NMF (input X)")
         document_topic_matrix, H = _initialize_nmf(

turftopic/models/cluster.py

@@ -12,7 +12,7 @@
 from sklearn.preprocessing import label_binarize
 
 from turftopic.base import ContextualModel, Encoder
-from turftopic.dynamic import DynamicTopicModel, bin_timestamps
+from turftopic.dynamic import DynamicTopicModel
 from turftopic.feature_importance import (
     cluster_centroid_distance,
     ctf_idf,
@@ -335,20 +335,26 @@ def fit_transform_dynamic(
         embeddings: Optional[np.ndarray] = None,
         bins: Union[int, list[datetime]] = 10,
     ):
-        time_labels, self.time_bin_edges = bin_timestamps(timestamps, bins)
-        temporal_components = []
-        temporal_importances = []
+        time_labels, self.time_bin_edges = self.bin_timestamps(
+            timestamps, bins
+        )
+        n_comp, n_vocab = self.components_.shape
+        n_bins = len(self.time_bin_edges) - 1
+        if hasattr(self, "components_"):
+            doc_topic_matrix = label_binarize(
+                self.labels_, classes=self.classes_
+            )
+        else:
+            doc_topic_matrix = self.fit_transform(
+                raw_documents, embeddings=embeddings
+            )
+        self.temporal_components = np.zeros(
+            (n_bins, n_comp, n_vocab), dtype=doc_topic_matrix.dtype
+        )
+        self.temporal_importance_ = np.zeros((n_bins, n_comp))
         if embeddings is None:
             embeddings = self.encoder_.encode(raw_documents)
-        for i_timebin in np.arange(len(self.time_bin_edges) - 1):
-            if hasattr(self, "components_"):
-                doc_topic_matrix = label_binarize(
-                    self.labels_, classes=self.classes_
-                )
-            else:
-                doc_topic_matrix = self.fit_transform(
-                    raw_documents, embeddings=embeddings
-                )
+        for i_timebin in np.unique(time_labels):
             topic_importances = doc_topic_matrix[time_labels == i_timebin].sum(
                 axis=0
             )
@@ -382,8 +388,6 @@ def fit_transform_dynamic(
                 mask_terms = t_doc_term_matrix.sum(axis=0).astype(np.float64)
                 mask_terms[mask_terms == 0] = np.nan
                 components *= mask_terms
-            temporal_components.append(components)
-            temporal_importances.append(topic_importances)
-        self.temporal_components_ = np.stack(temporal_components)
-        self.temporal_importance_ = np.stack(temporal_importances)
+            self.temporal_components_[i_timebin] = components
+            self.temporal_importance_[i_timebin].append(topic_importances)
         return doc_topic_matrix

turftopic/models/gmm.py

@@ -10,7 +10,7 @@
 from sklearn.pipeline import Pipeline, make_pipeline
 
 from turftopic.base import ContextualModel, Encoder
-from turftopic.dynamic import DynamicTopicModel, bin_timestamps
+from turftopic.dynamic import DynamicTopicModel
 from turftopic.feature_importance import soft_ctf_idf
 from turftopic.vectorizer import default_vectorizer
 
@@ -168,7 +168,9 @@ def fit_transform_dynamic(
         embeddings: Optional[np.ndarray] = None,
         bins: Union[int, list[datetime]] = 10,
     ):
-        time_labels, self.time_bin_edges = bin_timestamps(timestamps, bins)
+        time_labels, self.time_bin_edges = self.bin_timestamps(
+            timestamps, bins
+        )
         if hasattr(self, "components_"):
             doc_topic_matrix = self.transform(
                 raw_documents, embeddings=embeddings
@@ -178,9 +180,13 @@ def fit_transform_dynamic(
                 raw_documents, embeddings=embeddings
             )
         document_term_matrix = self.vectorizer.transform(raw_documents)
-        temporal_components = []
-        temporal_importances = []
-        for i_timebin in np.arange(len(self.time_bin_edges) - 1):
+        n_comp, n_vocab = self.components_.shape
+        n_bins = len(self.time_bin_edges) - 1
+        self.temporal_components = np.zeros(
+            (n_bins, n_comp, n_vocab), dtype=document_term_matrix.dtype
+        )
+        self.temporal_importance_ = np.zeros((n_bins, n_comp))
+        for i_timebin in np.unique(time_labels):
             topic_importances = doc_topic_matrix[time_labels == i_timebin].sum(
                 axis=0
             )
@@ -190,8 +196,6 @@ def fit_transform_dynamic(
                 doc_topic_matrix[time_labels == i_timebin],
                 document_term_matrix[time_labels == i_timebin],  # type: ignore
             )
-            temporal_components.append(components)
-            temporal_importances.append(topic_importances)
-        self.temporal_components_ = np.stack(temporal_components)
-        self.temporal_importance_ = np.stack(temporal_importances)
+            self.temporal_components_[i_timebin] = components
+            self.temporal_importance_[i_timebin].append(topic_importances)
         return doc_topic_matrix

turftopic/models/keynmf.py

@@ -9,7 +9,7 @@
 
 from turftopic.base import ContextualModel, Encoder
 from turftopic.data import TopicData
-from turftopic.dynamic import DynamicTopicModel, bin_timestamps
+from turftopic.dynamic import DynamicTopicModel
 from turftopic.models._keynmf import KeywordExtractor, KeywordNMF
 
 
@@ -300,7 +300,7 @@ def partial_fit_dynamic(
                 )
             else:
                 self.time_bin_edges = bins
-        time_labels, self.time_bin_edges = bin_timestamps(
+        time_labels, self.time_bin_edges = self.bin_timestamps(
             timestamps, self.time_bin_edges
         )
         if keywords is None: