deeplotx 0.2.20__tar.gz → 0.2.21__tar.gz

{deeplotx-0.2.20 → deeplotx-0.2.21}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: deeplotx
-Version: 0.2.20
+Version: 0.2.21
 Summary: Easy-2-use long text classifier trainers.
 Requires-Python: >=3.10
 Description-Content-Type: text/markdown
@@ -21,13 +21,19 @@ Dynamic: license-file
 - Install with pip
 
     ```
-    pip install git+https://github.com/vortezwohl/DeepLoTX.git
+    pip install -U deeplotx
     ```
 
 - Install with uv
 
     ```
-    uv add git+https://github.com/vortezwohl/DeepLoTX.git
+    uv add -U deeplotx
+    ```
+  
+- Install from github
+
+    ```
+    pip install -U git+https://github.com/vortezwohl/DeepLoTX.git
     ```
 
 ## Quick Start

{deeplotx-0.2.20 → deeplotx-0.2.21}/README.md

@@ -5,13 +5,19 @@
 - Install with pip
 
     ```
-    pip install git+https://github.com/vortezwohl/DeepLoTX.git
+    pip install -U deeplotx
     ```
 
 - Install with uv
 
     ```
-    uv add git+https://github.com/vortezwohl/DeepLoTX.git
+    uv add -U deeplotx
+    ```
+  
+- Install from github
+
+    ```
+    pip install -U git+https://github.com/vortezwohl/DeepLoTX.git
     ```
 
 ## Quick Start

{deeplotx-0.2.20 → deeplotx-0.2.21}/deeplotx/encoder/bert_encoder.py

@@ -13,19 +13,20 @@ class BertEncoder(nn.Module):
     def __init__(self, model_name_or_path: str = DEFAULT_BERT):
         super().__init__()
         self.tokenizer = BertTokenizer.from_pretrained(pretrained_model_name_or_path=model_name_or_path,
-                                                       cache_dir=CACHE_PATH)
+                                                       cache_dir=CACHE_PATH, _from_auto=True)
         self.bert = BertModel.from_pretrained(pretrained_model_name_or_path=model_name_or_path,
-                                              cache_dir=CACHE_PATH)
+                                              cache_dir=CACHE_PATH, _from_auto=True)
+        self.embed_dim = self.bert.config.max_position_embeddings
 
-    def forward(self, input_ids, attention_mask: torch.Tensor) -> torch.Tensor:
+    def forward(self, input_ids: torch.Tensor, attention_mask: torch.Tensor) -> torch.Tensor:
         def _encoder(_input_tup: tuple[torch.Tensor, torch.Tensor]) -> torch.Tensor:
             return self.bert.forward(_input_tup[0], attention_mask=_input_tup[1]).last_hidden_state[:, 0, :]
 
-        num_chunks = math.ceil(input_ids.shape[-1] / 512)
+        num_chunks = math.ceil(input_ids.shape[-1] / self.embed_dim)
         chunks = chunk_results = []
         for i in range(num_chunks):
-            start_idx = i * 512
-            end_idx = min(start_idx + 512, input_ids.shape[-1])
+            start_idx = i * self.embed_dim
+            end_idx = min(start_idx + self.embed_dim, input_ids.shape[-1])
             chunks.append((input_ids[:, start_idx: end_idx], attention_mask[:, start_idx: end_idx]))
         ori_mode = self.bert.training
         self.bert.eval()

{deeplotx-0.2.20 → deeplotx-0.2.21}/deeplotx/encoder/long_text_encoder.py

@@ -24,7 +24,7 @@ class LongTextEncoder(BertEncoder):
         return input_tup[0], super().forward(input_tup[1], attention_mask=input_tup[2])
 
     @override
-    def encode(self, text: str) -> torch.Tensor:
+    def encode(self, text: str, use_cache: bool = True) -> torch.Tensor:
         _text_to_show = text.replace("\n", str())
         logger.debug(f'Embedding \"{_text_to_show if len(_text_to_show) < 128 else _text_to_show[:128] + "..."}\".')
         # read cache
@@ -58,5 +58,6 @@ class LongTextEncoder(BertEncoder):
             fin_emb_tensor = torch.cat((fin_emb_tensor.detach().clone(), emb.detach().clone()), dim=-1)
         fin_emb_tensor = fin_emb_tensor.squeeze()
         # write cache
-        self._cache[_text_hash] = fin_emb_tensor
+        if use_cache:
+            self._cache[_text_hash] = fin_emb_tensor
         return fin_emb_tensor

deeplotx-0.2.21/deeplotx/encoder/longformer_encoder.py

@@ -0,0 +1,30 @@
+import torch
+from torch import nn
+from transformers import LongformerTokenizer, LongformerModel
+
+from deeplotx import __ROOT__
+
+CACHE_PATH = f'{__ROOT__}\\.cache'
+DEFAULT_LONGFORMER = 'allenai/longformer-base-4096'
+
+
+class LongformerEncoder(nn.Module):
+    def __init__(self, model_name_or_path: str = DEFAULT_LONGFORMER):
+        super().__init__()
+        self.tokenizer = LongformerTokenizer.from_pretrained(pretrained_model_name_or_path=model_name_or_path,
+                                                             cache_dir=CACHE_PATH, _from_auto=True)
+        self.bert = LongformerModel.from_pretrained(pretrained_model_name_or_path=model_name_or_path,
+                                                    cache_dir=CACHE_PATH, _from_auto=True)
+
+    def forward(self, input_ids: torch.Tensor, attention_mask: torch.Tensor) -> torch.Tensor:
+        ori_mode = self.bert.training
+        self.bert.eval()
+        with torch.no_grad():
+            res = self.bert.forward(input_ids, attention_mask=attention_mask).last_hidden_state[:, 0, :]
+        self.bert.train(mode=ori_mode)
+        return res
+
+    def encode(self, text: str) -> torch.Tensor:
+        _input_ids = torch.tensor([self.tokenizer.encode(text)], dtype=torch.long)
+        _att_mask = torch.tensor([[1] * _input_ids.shape[-1]], dtype=torch.int)
+        return self.forward(_input_ids, _att_mask).squeeze()

{deeplotx-0.2.20 → deeplotx-0.2.21}/deeplotx/nn/base_neural_network.py

@@ -1,3 +1,5 @@
+from abc import abstractmethod
+
 import torch
 from torch import nn
 
@@ -28,6 +30,7 @@ class BaseNeuralNetwork(nn.Module):
     def elastic_net(self, alpha: float = 1e-4, rho: float = 0.5) -> torch.Tensor:
         return alpha * (rho * self.l1(_lambda=1.) + (1 - rho) * self.l2(_lambda=1.))
 
+    @abstractmethod
     def forward(self, x) -> torch.Tensor: ...
 
     def predict(self, x) -> torch.Tensor:

{deeplotx-0.2.20 → deeplotx-0.2.21}/deeplotx.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: deeplotx
-Version: 0.2.20
+Version: 0.2.21
 Summary: Easy-2-use long text classifier trainers.
 Requires-Python: >=3.10
 Description-Content-Type: text/markdown
@@ -21,13 +21,19 @@ Dynamic: license-file
 - Install with pip
 
     ```
-    pip install git+https://github.com/vortezwohl/DeepLoTX.git
+    pip install -U deeplotx
     ```
 
 - Install with uv
 
     ```
-    uv add git+https://github.com/vortezwohl/DeepLoTX.git
+    uv add -U deeplotx
+    ```
+  
+- Install from github
+
+    ```
+    pip install -U git+https://github.com/vortezwohl/DeepLoTX.git
     ```
 
 ## Quick Start

{deeplotx-0.2.20 → deeplotx-0.2.21}/deeplotx.egg-info/SOURCES.txt

@@ -10,6 +10,7 @@ deeplotx.egg-info/top_level.txt
 deeplotx/encoder/__init__.py
 deeplotx/encoder/bert_encoder.py
 deeplotx/encoder/long_text_encoder.py
+deeplotx/encoder/longformer_encoder.py
 deeplotx/nn/__init__.py
 deeplotx/nn/base_neural_network.py
 deeplotx/nn/linear_regression.py

{deeplotx-0.2.20 → deeplotx-0.2.21}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "deeplotx"
-version = "0.2.20"
+version = "0.2.21"
 description = "Easy-2-use long text classifier trainers."
 readme = "README.md"
 requires-python = ">=3.10"