fix some doctests

Author: voorhs

autointent/modules/retrieval/_vectordb.py

@@ -32,12 +32,20 @@ class VectorDBModule(RetrievalModule):
 
     Examples
     --------
+    .. testsetup::
+
+        db_dir = "doctests-db"
+
     .. testcode::
 
         from autointent.modules.retrieval import VectorDBModule
         utterances = ["bye", "how are you?", "good morning"]
         labels = [0, 1, 1]
-        vector_db = VectorDBModule(k=2, embedder_name="sergeyzh/rubert-tiny-turbo")
+        vector_db = VectorDBModule(
+            k=2,
+            embedder_name="sergeyzh/rubert-tiny-turbo",
+            db_dir=db_dir,
+        )
         vector_db.fit(utterances, labels)
         predictions = vector_db.predict(["how is the weather today?"])
         print(predictions)
@@ -46,6 +54,11 @@ class VectorDBModule(RetrievalModule):
 
         ([[1, 1]], [[0.1525942087173462, 0.18616724014282227]], [['good morning', 'how are you?']])
 
+    .. testcleanup::
+
+        import shutil
+        shutil.rmtree(db_dir)
+
     """
 
     vector_index: VectorIndex

autointent/modules/scoring/_description/description.py

@@ -40,35 +40,6 @@ class DescriptionScorer(ScoringModule):
     :ivar db_dir: Directory path where the vector database is stored.
     :ivar name: Name of the scorer, defaults to "description".
 
-    Examples
-    --------
-    .. testsetup::
-
-        db_dir = "doctests-db"
-
-    .. testcode::
-
-        from autointent.modules import DescriptionScorer
-        utterances = ["what is your name?", "how old are you?"]
-        labels = [0, 1]
-        descriptions = ["greeting", "age-related question"]
-        scorer = DescriptionScorer(
-            embedder_name="sergeyzh/rubert-tiny-turbo",
-            db_dir=db_dir
-        )
-        scorer.fit(utterances, labels, descriptions)
-        scores = scorer.predict(["tell me about your age?"])
-        print(scores)  # Outputs similarity scores for the utterance against all descriptions
-
-    .. testoutput::
-
-        [[0.47210786 0.5278922 ]]
-
-    .. testcleanup::
-
-        import shutil
-        shutil.rmtree(db_dir)
-
     """
 
     weights_file_name: str = "description_vectors.npy"

autointent/modules/scoring/_linear.py

@@ -48,14 +48,20 @@ class LinearScorer(ScoringModule):
     .. testcode::
 
         from autointent.modules import LinearScorer
-        from autointent import Dataset
-        dataset = Dataset.from_datasets("AutoIntent/banking77")
         scorer = LinearScorer(
-            embedder_name="sergeyzh/rubert-tiny-turbo",
+            embedder_name="sergeyzh/rubert-tiny-turbo", cv=2
         )
-        scorer.fit(dataset["train"]["utterance"], dataset["train"]["label"])
-        test_utterances = ["Hello!", "What's up?"]
+        utterances = ["hello", "goodbye", "allo", "sayonara"]
+        labels = [0, 1, 0, 1]
+        scorer.fit(utterances, labels)
+        test_utterances = ["hi", "bye"]
         probabilities = scorer.predict(test_utterances)
+        print(probabilities)
+
+    .. testoutput::
+
+        [[0.50000032 0.49999968]
+         [0.50000032 0.49999968]]
 
     """