codestyle

Author: voorhs

autointent/modules/scoring/_bert.py

@@ -76,7 +76,7 @@ def _initialize_model(self) -> Any:  # noqa: ANN401
         label2id = {i: i for i in range(self._n_classes)}
         id2label = {i: i for i in range(self._n_classes)}
 
-        return AutoModelForSequenceClassification.from_pretrained( # type: ignore[no-untyped-call]
+        return AutoModelForSequenceClassification.from_pretrained(  # type: ignore[no-untyped-call]
             self.classification_model_config.model_name,
             trust_remote_code=self.classification_model_config.trust_remote_code,
             num_labels=self._n_classes,

autointent/modules/scoring/_cnn/textcnn.py

@@ -52,21 +52,13 @@ def __init__(
 
         if pretrained_embs is not None:
             _, embed_dim = pretrained_embs.shape
-            self.embedding = nn.Embedding.from_pretrained(pretrained_embs, freeze=True) # type: ignore[no-untyped-call]
+            self.embedding = nn.Embedding.from_pretrained(pretrained_embs, freeze=True)  # type: ignore[no-untyped-call]
         else:
-            self.embedding = nn.Embedding(
-                num_embeddings=vocab_size,
-                embedding_dim=embed_dim,
-                padding_idx=padding_idx
-            )
-
-        self.convs = nn.ModuleList([
-            nn.Conv1d(
-                in_channels=embed_dim,
-                out_channels=num_filters,
-                kernel_size=k
-            ) for k in kernel_sizes
-        ])
+            self.embedding = nn.Embedding(num_embeddings=vocab_size, embedding_dim=embed_dim, padding_idx=padding_idx)
+
+        self.convs = nn.ModuleList(
+            [nn.Conv1d(in_channels=embed_dim, out_channels=num_filters, kernel_size=k) for k in kernel_sizes]
+        )
         self.dropout = nn.Dropout(dropout)
         self.fc = nn.Linear(num_filters * len(kernel_sizes), n_classes)
 
@@ -77,7 +69,7 @@ def forward(self, x: torch.Tensor) -> torch.Tensor:
         conved: list[torch.Tensor] = [F.relu(conv(embedded)).max(dim=2)[0] for conv in self.convs]
         concatenated: torch.Tensor = torch.cat(conved, dim=1)
         dropped: torch.Tensor = self.dropout(concatenated)
-        return self.fc(dropped) # type: ignore[no-any-return]
+        return self.fc(dropped)  # type: ignore[no-any-return]
 
     def dump(self, path: Path) -> None:
         metadata = {
@@ -87,7 +79,7 @@ def dump(self, path: Path) -> None:
             "kernel_sizes": self.kernel_sizes,
             "num_filters": self.num_filters,
             "dropout": self.dropout_rate,
-            "padding_idx": self.padding_idx
+            "padding_idx": self.padding_idx,
         }
         with (path / self._metadata_dict_name).open("w") as file:
             json.dump(metadata, file, indent=4)

tests/modules/scoring/test_cnn.py

@@ -21,7 +21,7 @@ def test_cnn_prediction(dataset):
         embed_dim=128,
         kernel_sizes=(3, 4, 5),
         num_filters=100,
-        dropout=0.1
+        dropout=0.1,
     )
     scorer.fit(data_handler.train_utterances(0), data_handler.train_labels(0))
 
@@ -57,12 +57,7 @@ def test_cnn_cache_clearing(dataset):
     """Test that the CNN model properly handles cache clearing."""
     data_handler = DataHandler(dataset)
 
-    scorer = CNNScorer(
-        max_seq_length=50,
-        num_train_epochs=1,
-        batch_size=8,
-        learning_rate=5e-5
-    )
+    scorer = CNNScorer(max_seq_length=50, num_train_epochs=1, batch_size=8, learning_rate=5e-5)
     scorer.fit(data_handler.train_utterances(0), data_handler.train_labels(0))
 
     test_data = ["test text"]
@@ -86,12 +81,7 @@ def test_cnn_scorer_dump_load(dataset):
     data_handler = DataHandler(dataset)
 
     # Create and train scorer
-    scorer = CNNScorer(
-        max_seq_length=50,
-        num_train_epochs=1,
-        batch_size=8,
-        learning_rate=5e-5
-    )
+    scorer = CNNScorer(max_seq_length=50, num_train_epochs=1, batch_size=8, learning_rate=5e-5)
     scorer.fit(data_handler.train_utterances(0), data_handler.train_labels(0))
 
     # Test data
@@ -110,12 +100,7 @@ def test_cnn_scorer_dump_load(dataset):
         scorer.dump(str(temp_dir_path))
 
         # Create a new scorer and load saved model
-        scorer_loaded = CNNScorer(
-            max_seq_length=50,
-            num_train_epochs=1,
-            batch_size=8,
-            learning_rate=5e-5
-        )
+        scorer_loaded = CNNScorer(max_seq_length=50, num_train_epochs=1, batch_size=8, learning_rate=5e-5)
         scorer_loaded = scorer_loaded.load(str(temp_dir_path))
 
         # Verify model is loaded