deeplotx 0.2.21__tar.gz → 0.3.2__tar.gz

{deeplotx-0.2.21 → deeplotx-0.3.2}/PKG-INFO

@@ -1,11 +1,11 @@
 Metadata-Version: 2.4
 Name: deeplotx
-Version: 0.2.21
+Version: 0.3.2
 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-0.2.21 → deeplotx-0.3.2}/deeplotx/__init__.py

@@ -3,7 +3,7 @@ import os
 
 __ROOT__ = os.path.dirname(os.path.abspath(__file__))
 
-from .encoder import BertEncoder, LongTextEncoder
+from .encoder import BertEncoder, LongTextEncoder, LongformerEncoder
 from .nn import LinearRegression, LogisticRegression, SoftmaxRegression
 from .trainer import TextBinaryClassifierTrainer
 

{deeplotx-0.2.21 → deeplotx-0.3.2}/deeplotx/encoder/__init__.py

@@ -1,2 +1,3 @@
 from .bert_encoder import BertEncoder
 from .long_text_encoder import LongTextEncoder
+from .longformer_encoder import LongformerEncoder

deeplotx-0.3.2/deeplotx/similarity/__init__.py

@@ -0,0 +1,17 @@
+import numpy as np
+import torch
+
+bias = 1e-12
+
+
+def ndarray_adapter(*args) -> tuple | np.ndarray:
+    args = list(args)
+    for i, arg in enumerate(args):
+        match arg.__class__:
+            case torch.Tensor:
+                args[i] = arg.detach().cpu().numpy()
+            case List:
+                args[i] = np.asarray(arg)
+    if len(args) > 1:
+        return tuple(args)
+    return args[0]

deeplotx-0.3.2/deeplotx/similarity/distribution.py

@@ -0,0 +1,32 @@
+import numpy as np
+import torch
+
+from deeplotx.similarity import bias, ndarray_adapter
+
+
+def cross_entropy(p: torch.Tensor | np.ndarray, q: torch.Tensor | np.ndarray) -> np.float32:
+    p, q = ndarray_adapter(p, q)
+    q = np.clip(q, bias, 1 - bias)
+    return -1 * (np.sum(p * np.log(q)) / p.shape[0])
+
+
+def kl_divergence(p: torch.Tensor | np.ndarray, q: torch.Tensor | np.ndarray) -> np.float32:
+    p, q = ndarray_adapter(p, q)
+    q = np.where(q == 0, bias, q)
+    p = p / np.sum(p)
+    q = q / np.sum(q)
+    return np.sum(p * np.log(p / q))
+
+
+def js_divergence(p: torch.Tensor | np.ndarray, q: torch.Tensor | np.ndarray) -> np.float32:
+    p, q = ndarray_adapter(p, q)
+    m = (p + q) / 2
+    return (kl_divergence(p, m) + kl_divergence(q, m)) / 2
+
+
+def hellinger_distance(p: torch.Tensor | np.ndarray, q: torch.Tensor | np.ndarray) -> np.float32:
+    p, q = ndarray_adapter(p, q)
+    p = p / np.sum(p)
+    q = q / np.sum(q)
+    squared_diff = (np.sqrt(p) - np.sqrt(q)) ** 2
+    return np.sqrt(np.sum(squared_diff)) / np.sqrt(2)

deeplotx-0.3.2/deeplotx/similarity/set.py

@@ -0,0 +1,19 @@
+from deeplotx.similarity import bias
+
+
+def jaccard_similarity(set1: set, set2: set) -> float:
+    return (len(set1.intersection(set2)) + bias) / (len(set1.union(set2)) + bias)
+
+
+def overlap_coefficient(set1: set, set2: set) -> float:
+    return (len(set1.intersection(set2)) + bias) / (min(len(set1), len(set2)) + bias)
+
+
+def dice_coefficient(set1: set, set2: set) -> float:
+    return (2 * len(set1.intersection(set2)) + bias) / (len(set1) + len(set2) + bias)
+
+
+def ochiai_similarity(set1: set, set2: set) -> float:
+    intersection = len(set1.intersection(set2))
+    product = len(set1) ** 0.5 * len(set2) ** 0.5
+    return (intersection + bias) / (product + bias)

deeplotx-0.3.2/deeplotx/similarity/vector.py

@@ -0,0 +1,36 @@
+import numpy as np
+import torch
+
+from deeplotx.similarity import ndarray_adapter
+
+
+def l2_normalize(x: torch.Tensor | np.ndarray) -> np.ndarray:
+    x = ndarray_adapter(x)
+    return x / np.sqrt(np.sum(np.multiply(x, x)))
+
+
+def z_score_normalize(x: torch.Tensor | np.ndarray) -> np.ndarray:
+    x = ndarray_adapter(x)
+    mean = np.mean(x)
+    std_dev = np.std(x)
+    return (x - mean) / std_dev
+
+
+def euclidean_similarity(p: torch.Tensor | np.ndarray, q: torch.Tensor | np.ndarray) -> np.float32:
+    p, q = ndarray_adapter(p, q)
+    distance = p - q
+    distance = np.sum(np.multiply(distance, distance))
+    return np.sqrt(distance)
+
+
+def cosine_similarity(p: torch.Tensor | np.ndarray, q: torch.Tensor | np.ndarray) -> np.float32:
+    p, q = ndarray_adapter(p, q)
+    a = np.matmul(np.transpose(p), q)
+    b = np.sum(np.multiply(p, p))
+    c = np.sum(np.multiply(q, q))
+    return 1 - (a / (np.sqrt(b) * np.sqrt(c)))
+
+
+def chebyshev_similarity(p: torch.Tensor | np.ndarray, q: torch.Tensor | np.ndarray) -> np.float32:
+    p, q = ndarray_adapter(p, q)
+    return np.max(np.abs(p - q))

{deeplotx-0.2.21 → deeplotx-0.3.2}/deeplotx.egg-info/PKG-INFO

@@ -1,11 +1,11 @@
 Metadata-Version: 2.4
 Name: deeplotx
-Version: 0.2.21
+Version: 0.3.2
 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-0.2.21 → deeplotx-0.3.2}/deeplotx.egg-info/SOURCES.txt

@@ -16,6 +16,10 @@ deeplotx/nn/base_neural_network.py
 deeplotx/nn/linear_regression.py
 deeplotx/nn/logistic_regression.py
 deeplotx/nn/softmax_regression.py
+deeplotx/similarity/__init__.py
+deeplotx/similarity/distribution.py
+deeplotx/similarity/set.py
+deeplotx/similarity/vector.py
 deeplotx/trainer/__init__.py
 deeplotx/trainer/base_trainer.py
 deeplotx/trainer/text_binary_classification_trainer.py

{deeplotx-0.2.21 → deeplotx-0.3.2}/deeplotx.egg-info/requires.txt

@@ -1,4 +1,4 @@
-huggingface-hub[hf-xet]>=0.30.2
+hf-xet>=1.0.5
 jupyter>=1.1.1
 numpy>=2.2.5
 python-dotenv>=1.1.0

{deeplotx-0.2.21 → deeplotx-0.3.2}/pyproject.toml

@@ -1,15 +1,15 @@
-[project]
-name = "deeplotx"
-version = "0.2.21"
-description = "Easy-2-use long text classifier trainers."
-readme = "README.md"
-requires-python = ">=3.10"
-dependencies = [
-    "huggingface-hub[hf-xet]>=0.30.2",
-    "jupyter>=1.1.1",
-    "numpy>=2.2.5",
-    "python-dotenv>=1.1.0",
-    "torch>=2.7.0",
-    "transformers>=4.51.3",
-    "typing-extensions>=4.13.2",
-]
+[project]
+name = "deeplotx"
+version = "0.3.2"
+description = "Easy-2-use long text classifier trainers."
+readme = "README.md"
+requires-python = ">=3.10"
+dependencies = [
+    "hf-xet>=1.0.5",
+    "jupyter>=1.1.1",
+    "numpy>=2.2.5",
+    "python-dotenv>=1.1.0",
+    "torch>=2.7.0",
+    "transformers>=4.51.3",
+    "typing-extensions>=4.13.2",
+]