deeplotx 0.3.1__py3-none-any.whl → 0.4.1__py3-none-any.whl

deeplotx/nn/__init__.py

@@ -1,3 +1,5 @@
 from .linear_regression import LinearRegression
 from .logistic_regression import LogisticRegression
 from .softmax_regression import SoftmaxRegression
+from .recursive_sequential import RecursiveSequential
+from .auto_regression import AutoRegression

deeplotx/nn/auto_regression.py

@@ -0,0 +1,9 @@
+from deeplotx.nn import RecursiveSequential
+
+
+class AutoRegression(RecursiveSequential):
+    def __init__(self, feature_dim: int, hidden_dim: int | None = None,
+                 recursive_layers: int = 2, model_name: str | None = None):
+        super().__init__(input_dim=feature_dim, output_dim=feature_dim,
+                         hidden_dim=hidden_dim, recursive_layers=recursive_layers,
+                         model_name=model_name)

deeplotx/nn/base_neural_network.py

@@ -31,7 +31,7 @@ class BaseNeuralNetwork(nn.Module):
         return alpha * (rho * self.l1(_lambda=1.) + (1 - rho) * self.l2(_lambda=1.))
 
     @abstractmethod
-    def forward(self, x) -> torch.Tensor: ...
+    def forward(self, *args, **kwargs) -> torch.Tensor: ...
 
     def predict(self, x) -> torch.Tensor:
         __train = self.training

deeplotx/nn/recursive_sequential.py

@@ -0,0 +1,30 @@
+from typing_extensions import override
+
+import torch
+from torch import nn
+
+from deeplotx.nn.base_neural_network import BaseNeuralNetwork
+from deeplotx.nn import LinearRegression
+
+
+class RecursiveSequential(BaseNeuralNetwork):
+    def __init__(self, input_dim: int, output_dim: int,
+                 hidden_dim: int | None = None, recursive_layers: int = 2,
+                 model_name: str | None = None):
+        super().__init__(model_name=model_name)
+        if hidden_dim is None:
+            hidden_dim = input_dim
+        self.lstm = nn.LSTM(input_size=input_dim, hidden_size=hidden_dim,
+                            num_layers=recursive_layers, batch_first=True,
+                            bias=True, bidirectional=True)
+        self.regressive_head = LinearRegression(input_dim=hidden_dim * 2, output_dim=output_dim)
+
+    def initial_state(self, batch_size: int = 1) -> tuple[torch.Tensor, torch.Tensor]:
+        zeros = torch.zeros(self.lstm.num_layers * 2, batch_size, self.lstm.hidden_size)
+        return zeros, zeros
+
+    @override
+    def forward(self, x, state: tuple[torch.Tensor, torch.Tensor]) -> tuple[torch.Tensor, tuple[torch.Tensor, torch.Tensor]]:
+        x, (hidden_state, cell_state) = self.lstm(x, state)
+        x = self.regressive_head(x[:, -1, :])
+        return x, (hidden_state, cell_state)

{deeplotx-0.3.1.dist-info → deeplotx-0.4.1.dist-info}/METADATA

@@ -1,11 +1,11 @@
 Metadata-Version: 2.4
 Name: deeplotx
-Version: 0.3.1
+Version: 0.4.1
 Summary: Easy-2-use long text classifier trainers.
 Requires-Python: >=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: huggingface-hub[hf-xet]>=0.30.2
+Requires-Dist: hf-xet>=1.0.5
 Requires-Dist: jupyter>=1.1.1
 Requires-Dist: numpy>=2.2.5
 Requires-Dist: python-dotenv>=1.1.0

{deeplotx-0.3.1.dist-info → deeplotx-0.4.1.dist-info}/RECORD

@@ -3,10 +3,12 @@ deeplotx/encoder/__init__.py,sha256=EM-xrTsHoGaiiFpj-iFAxilMHXC_sQKWYrcq1qCnI3U,
 deeplotx/encoder/bert_encoder.py,sha256=A-B7Gj94xv6UhvsFTBH7tnkAdGHRhfUZA2QjSnTKB6c,1970
 deeplotx/encoder/long_text_encoder.py,sha256=V6VxaHW6bMMaZHgU1UZ8n19UfSIV2f2sarWXquiFffQ,3018
 deeplotx/encoder/longformer_encoder.py,sha256=mZpC5TrGHQo98-ydGtVQQ9KRHgCGl1sRoxcQs7r4SSo,1409
-deeplotx/nn/__init__.py,sha256=9gh8rhKqVWtJyvryU_wHPTLEQIorwOBhAQRc0DtNamM,153
-deeplotx/nn/base_neural_network.py,sha256=Rkwu58mXXcuusf-59yLX89MywQx-EvTsSXOvlzUptRE,1621
+deeplotx/nn/__init__.py,sha256=oQ-vYXyuaGelfCOs2im_gZXAiiBlCCVXh1uw9yjvRMs,253
+deeplotx/nn/auto_regression.py,sha256=o82C9TREZbhGdj2knSVGTXhjJne0LGEqc7BllByJJWE,449
+deeplotx/nn/base_neural_network.py,sha256=xWKG4FX6Jzdlrfc1HOW1aO9uh0Af3D-dB5Jl7eCxsAk,1635
 deeplotx/nn/linear_regression.py,sha256=D4mEWVOq6q1Fm2otm57rgZ_E06HJLZBV5k636PprAf4,1520
 deeplotx/nn/logistic_regression.py,sha256=QAtZp2oyqOW8-1pJWVcahsSM83bzfA68EHObg-wSHHY,463
+deeplotx/nn/recursive_sequential.py,sha256=Nj5B4iPAq7SUCKepextZbHWvGPxHo3w9UXEsEg_nFi4,1352
 deeplotx/nn/softmax_regression.py,sha256=eUn3mVNlye9ewVdw3McPHZuKbUvvaamsUgFIJMVMgBU,487
 deeplotx/similarity/__init__.py,sha256=JA1om2zeDcQVS1R04nDMdP6yegxdLJ14WF63pSTL3oo,418
 deeplotx/similarity/distribution.py,sha256=wQGouuuW531pZeBRKBujXsdsoz4fDnPw7_GW81jwepc,1066
@@ -18,8 +20,8 @@ deeplotx/trainer/text_binary_classification_trainer.py,sha256=5O-5dwVMCj5EDX9gjJ
 deeplotx/util/__init__.py,sha256=JxqAK_WOOHcYVSTHBT1-WuBwWrPEVDTV3titeVWvNUM,74
 deeplotx/util/hash.py,sha256=wwsC6kOQvbpuvwKsNQOARd78_wePmW9i3oaUuXRUnpc,352
 deeplotx/util/read_file.py,sha256=ptzouvEQeeW8KU5BrWNJlXw-vFXVrpS9SkAUxsu6A8A,612
-deeplotx-0.3.1.dist-info/licenses/LICENSE,sha256=IwGE9guuL-ryRPEKi6wFPI_zOhg7zDZbTYuHbSt_SAk,35823
-deeplotx-0.3.1.dist-info/METADATA,sha256=GzIi1llGFDTLvHDLF3GOQ4G6MafM10M-7IeosZwZlaY,1616
-deeplotx-0.3.1.dist-info/WHEEL,sha256=DnLRTWE75wApRYVsjgc6wsVswC54sMSJhAEd4xhDpBk,91
-deeplotx-0.3.1.dist-info/top_level.txt,sha256=hKg4pVDXZ-WWxkRfJFczRIll1Sv7VyfKCmzHLXbuh1U,9
-deeplotx-0.3.1.dist-info/RECORD,,
+deeplotx-0.4.1.dist-info/licenses/LICENSE,sha256=IwGE9guuL-ryRPEKi6wFPI_zOhg7zDZbTYuHbSt_SAk,35823
+deeplotx-0.4.1.dist-info/METADATA,sha256=0Y3sfxpnTZgN8Edk_AIt8bphP9TQ6UScSn2k0tyThj0,1598
+deeplotx-0.4.1.dist-info/WHEEL,sha256=DnLRTWE75wApRYVsjgc6wsVswC54sMSJhAEd4xhDpBk,91
+deeplotx-0.4.1.dist-info/top_level.txt,sha256=hKg4pVDXZ-WWxkRfJFczRIll1Sv7VyfKCmzHLXbuh1U,9
+deeplotx-0.4.1.dist-info/RECORD,,