valor-lite 0.34.0__py3-none-any.whl → 0.34.1__py3-none-any.whl

valor_lite/classification/computation.py

@@ -9,7 +9,7 @@ def _compute_rocauc(
     n_labels: int,
     mask_matching_labels: NDArray[np.bool_],
     pd_labels: NDArray[np.int32],
-):
+) -> tuple[NDArray[np.float64], float]:
     """
     Compute ROCAUC and mean ROCAUC.
     """
@@ -56,12 +56,12 @@ def _compute_rocauc(
     np.maximum.accumulate(tpr, axis=1, out=tpr)
 
     # compute rocauc
-    rocauc = np.trapz(x=fpr, y=tpr, axis=1)  # type: ignore - numpy will be switching to `trapezoid` in the future.
+    rocauc = np.trapezoid(x=fpr, y=tpr, axis=1)
 
     # compute mean rocauc
     mean_rocauc = rocauc.mean()
 
-    return rocauc, mean_rocauc
+    return rocauc, mean_rocauc  # type: ignore[reportReturnType]
 
 
 def compute_precision_recall_rocauc(

valor_lite/object_detection/computation.py

@@ -560,12 +560,12 @@ def compute_precion_recall(
     )
 
     return (
-        ap_results,
+        ap_results,  # type: ignore[reportReturnType]
         ar_results,
         accuracy,
         counts,
         pr_curve,
-    )  # type: ignore[reportReturnType]
+    )
 
 
 def _count_with_examples(

valor_lite/object_detection/manager.py

@@ -195,8 +195,8 @@ class Evaluator:
 
     def compute_precision_recall(
         self,
-        iou_thresholds: list[float] = [0.5, 0.75, 0.9],
-        score_thresholds: list[float] = [0.5],
+        iou_thresholds: list[float],
+        score_thresholds: list[float],
         filter_: Filter | None = None,
     ) -> dict[MetricType, list[Metric]]:
         """
@@ -240,9 +240,9 @@ class Evaluator:
 
     def compute_confusion_matrix(
         self,
-        iou_thresholds: list[float] = [0.5, 0.75, 0.9],
-        score_thresholds: list[float] = [0.5],
-        number_of_examples: int = 0,
+        iou_thresholds: list[float],
+        score_thresholds: list[float],
+        number_of_examples: int,
         filter_: Filter | None = None,
     ) -> list[Metric]:
         """
@@ -254,7 +254,7 @@ class Evaluator:
             A list of IOU thresholds to compute metrics over.
         score_thresholds : list[float]
             A list of score thresholds to compute metrics over.
-        number_of_examples : int, default=0
+        number_of_examples : int
             Maximum number of annotation examples to return in ConfusionMatrix.
         filter_ : Filter, optional
             An optional filter object.
@@ -295,7 +295,7 @@ class Evaluator:
 
     def evaluate(
         self,
-        iou_thresholds: list[float] = [0.5, 0.75, 0.9],
+        iou_thresholds: list[float] = [0.1, 0.5, 0.75],
         score_thresholds: list[float] = [0.5],
         number_of_examples: int = 0,
         filter_: Filter | None = None,
@@ -305,9 +305,9 @@ class Evaluator:
 
         Parameters
         ----------
-        iou_thresholds : list[float]
+        iou_thresholds : list[float], default=[0.1, 0.5, 0.75]
             A list of IOU thresholds to compute metrics over.
-        score_thresholds : list[float]
+        score_thresholds : list[float], default=[0.5]
             A list of score thresholds to compute metrics over.
         number_of_examples : int, default=0
             Maximum number of annotation examples to return in ConfusionMatrix.

valor_lite/text_generation/computation.py

@@ -1,7 +1,3 @@
-import evaluate
-from nltk.tokenize import RegexpTokenizer
-from nltk.translate import bleu_score
-
 from valor_lite.text_generation.llm.generation import (
     generate_answer_correctness_verdicts,
     generate_answer_relevance_verdicts,
@@ -551,6 +547,8 @@ def calculate_rouge_scores(
     use_stemmer: bool, default=False
         If True, uses Porter stemmer to strip word suffixes. Defaults to False.
     """
+    import evaluate
+
     rouge = evaluate.load("rouge")
 
     metrics = rouge.compute(
@@ -589,6 +587,9 @@ def calculate_sentence_bleu(
         higher/lower order ngrams, use customized weights. Example: when accounting
         for up to 5-grams with uniform weights (this is called BLEU-5) use [1/5]*5
     """
+    from nltk.tokenize import RegexpTokenizer
+    from nltk.translate import bleu_score
+
     if len(weights) == 0:
         raise ValueError("At least one weight should be defined.")
 

{valor_lite-0.34.0.dist-info → valor_lite-0.34.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: valor-lite
-Version: 0.34.0
+Version: 0.34.1
 Summary: Evaluate machine learning models.
 Project-URL: homepage, https://www.striveworks.com
 Requires-Python: >=3.10
@@ -8,17 +8,14 @@ Description-Content-Type: text/markdown
 Requires-Dist: numpy
 Requires-Dist: tqdm
 Requires-Dist: shapely
-Requires-Dist: evaluate
-Requires-Dist: nltk
-Requires-Dist: rouge_score
+Provides-Extra: nlp
+Requires-Dist: evaluate; extra == "nlp"
+Requires-Dist: nltk; extra == "nlp"
+Requires-Dist: rouge_score; extra == "nlp"
 Provides-Extra: mistral
 Requires-Dist: mistralai>=1.0; extra == "mistral"
 Provides-Extra: openai
 Requires-Dist: openai; extra == "openai"
-Provides-Extra: test
-Requires-Dist: pytest; extra == "test"
-Requires-Dist: coverage; extra == "test"
-Requires-Dist: pre-commit; extra == "test"
 Provides-Extra: docs
 Requires-Dist: mkdocs; extra == "docs"
 Requires-Dist: mkdocs-material; extra == "docs"
@@ -26,8 +23,14 @@ Requires-Dist: mkdocstrings; extra == "docs"
 Requires-Dist: mkdocstrings-python; extra == "docs"
 Requires-Dist: mkdocs-include-dir-to-nav; extra == "docs"
 Requires-Dist: mkdocs-swagger-ui-tag; extra == "docs"
+Provides-Extra: test
+Requires-Dist: pytest; extra == "test"
+Requires-Dist: coverage; extra == "test"
+Requires-Dist: pre-commit; extra == "test"
+Provides-Extra: benchmark
+Requires-Dist: requests; extra == "benchmark"
 Provides-Extra: dev
-Requires-Dist: valor-lite[docs,mistral,openai,test]; extra == "dev"
+Requires-Dist: valor-lite[benchmark,docs,mistral,nlp,openai,test]; extra == "dev"
 
 # valor-lite: Fast, local machine learning evaluation.
 

{valor_lite-0.34.0.dist-info → valor_lite-0.34.1.dist-info}/RECORD

@@ -4,14 +4,14 @@ valor_lite/profiling.py,sha256=TLIROA1qccFw9NoEkMeQcrvvGGO75c4K5yTIWoCUix8,11746
 valor_lite/schemas.py,sha256=pB0MrPx5qFLbwBWDiOUUm-vmXdWvbJLFCBmKgbcbI5g,198
 valor_lite/classification/__init__.py,sha256=8MI8bGwCxYGqRP7KxG7ezhYv4qQ5947XGvvlF8WPM5g,392
 valor_lite/classification/annotation.py,sha256=0aUOvcwBAZgiNOJuyh-pXyNTG7vP7r8CUfnU3OmpUwQ,1113
-valor_lite/classification/computation.py,sha256=dOcq1xxarwwwtHya1Wl8KZXE-PoGafOAYK0LQqxGphY,12191
+valor_lite/classification/computation.py,sha256=y0xU2M1vCEJ5P7meiZRSGowKg0tD1zrqO2LzMLTekPg,12194
 valor_lite/classification/manager.py,sha256=cZ6-DKao59QqF0JF_U26tBoydpCElAAH8rRyX_Kc6bc,16618
 valor_lite/classification/metric.py,sha256=_mW3zynmpW8jUIhK2OeX4usdftHgHM9_l7EAbEe2N3w,12288
 valor_lite/classification/utilities.py,sha256=eG-Qhd213uf2GXuuqsPxCgBRBFV-z_ADbzneF1kE368,6964
 valor_lite/object_detection/__init__.py,sha256=Ql8rju2q7y0Zd9zFvtBJDRhgQFDm1RSYkTsyH3ZE6pA,648
 valor_lite/object_detection/annotation.py,sha256=x9bsl8b75yvkMByXXiIYI9d9T03olDqtykSvKJc3aFw,7729
-valor_lite/object_detection/computation.py,sha256=Q9sFMQhRupseZmGZzA7uEpqpeo9XpmSIkeKGMNEZfP4,28345
-valor_lite/object_detection/manager.py,sha256=wjjMvzCoWs5oavtSj1NT-o4QFT5Sqf79WIb_OO64y1o,23071
+valor_lite/object_detection/computation.py,sha256=zfVTl_TDK3rho3282VcruTvBK6DqbxduP7tE7esMFUY,28345
+valor_lite/object_detection/manager.py,sha256=uo9o0gWBQUkTTgwTluhXk0ouVDW8qiyrqTwJD6PJDKE,23043
 valor_lite/object_detection/metric.py,sha256=npK2sxiwCUTKlRlFym1AlZTvP9herf9lakbsBDwljGM,24901
 valor_lite/object_detection/utilities.py,sha256=42RRyP6L3eWtDY_f7qs7f0WTjhcibmUBu2I4yAwupF0,16456
 valor_lite/semantic_segmentation/__init__.py,sha256=BhTUbwbdJa1FdS4ZA3QSIZ8TuJmdGGLGCd5hX6SzKa4,297
@@ -23,7 +23,7 @@ valor_lite/semantic_segmentation/metric.py,sha256=T9RfPJf4WgqGQTXYvSy08vJG5bjXXJ
 valor_lite/semantic_segmentation/utilities.py,sha256=UD0X-iCWMR8Rmw2YaP4HM3lxwhYwo-yNGzF-taAJ8RA,2959
 valor_lite/text_generation/__init__.py,sha256=pGhpWCSZjLM0pPHCtPykAfos55B8ie3mi9EzbNxfj-U,356
 valor_lite/text_generation/annotation.py,sha256=O5aXiwCS4WjA-fqn4ly-O0MsTHoIOmqxqCaAp9IeI3M,1270
-valor_lite/text_generation/computation.py,sha256=vdZTajB0OuGEwoKWxKkq3lWxlPaUsrp_X5-ZgjkYLhg,18639
+valor_lite/text_generation/computation.py,sha256=hGDkPfzWY9SDTdozd-nArexJ3ZSNlCIWqHGoD8vO2Cc,18652
 valor_lite/text_generation/manager.py,sha256=C4QwvronGHXmYSkaRmUGy7TN0C0aeyDx9Hb-ClNYXK4,24810
 valor_lite/text_generation/metric.py,sha256=C9gbWejjOJ23JVLecuUhYW5rkx30NUCfRtgsM46uMds,10409
 valor_lite/text_generation/llm/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -33,7 +33,7 @@ valor_lite/text_generation/llm/instructions.py,sha256=fz2onBZZWcl5W8iy7zEWkPGU9N
 valor_lite/text_generation/llm/integrations.py,sha256=-rTfdAjq1zH-4ixwYuMQEOQ80pIFzMTe0BYfroVx3Pg,6974
 valor_lite/text_generation/llm/utilities.py,sha256=bjqatGgtVTcl1PrMwiDKTYPGJXKrBrx7PDtzIblGSys,1178
 valor_lite/text_generation/llm/validators.py,sha256=Wzr5RlfF58_2wOU-uTw7C8skan_fYdhy4Gfn0jSJ8HM,2700
-valor_lite-0.34.0.dist-info/METADATA,sha256=2l5zKt0RkVHbdYmC1kLF71rG_dKZnZQ-XyuAQGf7dTg,4908
-valor_lite-0.34.0.dist-info/WHEEL,sha256=PZUExdf71Ui_so67QXpySuHtCi3-J3wvF4ORK6k_S8U,91
-valor_lite-0.34.0.dist-info/top_level.txt,sha256=9ujykxSwpl2Hu0_R95UQTR_l07k9UUTSdrpiqmq6zc4,11
-valor_lite-0.34.0.dist-info/RECORD,,
+valor_lite-0.34.1.dist-info/METADATA,sha256=1CDSurHwdrTJMTHvcKF_-JUoztcCSPJTrXuL6DpMDBQ,5062
+valor_lite-0.34.1.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
+valor_lite-0.34.1.dist-info/top_level.txt,sha256=9ujykxSwpl2Hu0_R95UQTR_l07k9UUTSdrpiqmq6zc4,11
+valor_lite-0.34.1.dist-info/RECORD,,

{valor_lite-0.34.0.dist-info → valor_lite-0.34.1.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (75.6.0)
+Generator: setuptools (78.1.0)
 Root-Is-Purelib: true
 Tag: py3-none-any