spelling

xadupre · xadupre · commit f0f7589f9ecc · 2025-03-24T14:46:33.000+01:00
diff --git a/.github/workflows/spell-check.yml b/.github/workflows/spell-check.yml
@@ -0,0 +1,26 @@
+ame: Spell Check
+
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+
+jobs:
+  spell-check:
+    runs-on: ubuntu-latest
+
+    steps:
+      # Checkout the repository
+      - name: Checkout code
+        uses: actions/checkout@v3
+
+      # Install codespell
+      - name: Install codespell
+        run: |
+          pip install codespell
+
+      # Run codespell
+      - name: Run codespell
+        run: |
+          codespell --skip="*.png,*.jpg,*.jpeg,*.gif,*.svg,*.ico,*.pdf,*.js" --ignore-words-list="nd,te,OT" --check-filenames
diff --git a/README.rst b/README.rst
@@ -99,4 +99,4 @@ Snapshot of usefuls tools
 
 **max_diff**
 
-Returns the maximum discrancies accross nested containers containing tensors.
+Returns the maximum discrancies across nested containers containing tensors.
diff --git a/_doc/examples/plot_export_tiny_llm.py b/_doc/examples/plot_export_tiny_llm.py
@@ -4,7 +4,7 @@
 Steel method forward to guess the dynamic shapes
 ================================================
 
-Inputs are always dynamic with LLMs that is why dyanmic shapes
+Inputs are always dynamic with LLMs that is why dynamic shapes
 needs to be specified when a LLM is exported with:func:`torch.export.export`.
 Most of the examples on :epkg:`HuggingFace` use method
 :meth:`transformers.GenerationMixin.generate` but we only want to
@@ -15,7 +15,7 @@
 
 We focus on the model
 `Tiny-LLM <https://huggingface.co/arnir0/Tiny-LLM>`_.
-To avoid downloading any weigths, we write a function creating a
+To avoid downloading any weights, we write a function creating a
 random model based on the same architecture.
 
 Steel the forward method
diff --git a/_doc/examples/plot_export_with_dynamic_cache.py b/_doc/examples/plot_export_with_dynamic_cache.py
@@ -54,9 +54,9 @@ def forward(self, x, y):
 pprint.pprint(ds)
 
 # %%
-# The function returns a tuple with two objets.
+# The function returns a tuple with two objects.
 # The first one for the positional arguments, the other one
-# for the named arguments. There is no named argements. We
+# for the named arguments. There is no named arguments. We
 # we used the first result to export.
 
 ep = torch.export.export(model, (x, y), dynamic_shapes=ds[0])
@@ -66,7 +66,7 @@ def forward(self, x, y):
 # kwargs
 # ++++++
 #
-# We do the same with named argments.
+# We do the same with named arguments.
 
 
 class Model(torch.nn.Module):
diff --git a/_doc/examples/plot_export_with_dynamic_shapes_auto.py b/_doc/examples/plot_export_with_dynamic_shapes_auto.py
@@ -4,7 +4,7 @@
 Use DYNAMIC or AUTO when exporting if dynamic shapes has constraints
 ====================================================================
 
-Settings the dynamic shapes is not always easy.
+Setting the dynamic shapes is not always easy.
 Here are a few tricks to make it work.
 
 dx + dy not allowed?
diff --git a/_doc/examples/plot_failing_model_extract.py b/_doc/examples/plot_failing_model_extract.py
@@ -39,7 +39,7 @@
             oh.make_node("Cast", ["C"], ["X999"], to=999, name="failing"),
             oh.make_node("CastLike", ["X999", "Y"], ["Z"], name="n4"),
         ],
-        "nd",
+        "-nd-",
         [
             oh.make_tensor_value_info("X", TFLOAT, ["a", "b", "c"]),
             oh.make_tensor_value_info("Y", TFLOAT, ["a", "b", "c"]),
diff --git a/_doc/examples/plot_failing_onnxruntime_evaluator.py b/_doc/examples/plot_failing_onnxruntime_evaluator.py
@@ -8,7 +8,7 @@
 how to run a python runtime on a model but it may very slow sometimes
 and it could show some discrepancies if the only provider is not CPU.
 Let's use :class:`OnnxruntimeEvaluator <onnx_diagnostic.reference.OnnxruntimeEvaluator>`.
-It splits the model into node and runs them independantly until it succeeds
+It splits the model into node and runs them independently until it succeeds
 or fails. This class converts every node into model based on the types
 discovered during the execution. It relies on :class:`InferenceSessionForTorch
 <onnx_diagnostic.ort_session.InferenceSessionForTorch>` or
@@ -43,7 +43,7 @@
             oh.make_node("Cast", ["C"], ["X999"], to=999, name="failing"),
             oh.make_node("CastLike", ["X999", "Y"], ["Z"], name="n4"),
         ],
-        "nd",
+        "-nd-",
         [
             oh.make_tensor_value_info("X", TBFLOAT16, ["a", "b", "c"]),
             oh.make_tensor_value_info("Y", TBFLOAT16, ["a", "b", "c"]),
@@ -100,7 +100,7 @@
 # %%
 # We can see it run until it reaches `Cast` and stops.
 # The error message is not always obvious to interpret.
-# It gets improved everytime from time to time.
+# It gets improved every time from time to time.
 # This runtime is useful when it fails for a numerical reason.
 # It is possible to insert prints in the python code to print
 # more information or debug if needed.
diff --git a/_doc/examples/plot_failing_reference_evaluator.py b/_doc/examples/plot_failing_reference_evaluator.py
@@ -33,7 +33,7 @@
             oh.make_node("Cast", ["C"], ["X999"], to=999, name="failing"),
             oh.make_node("CastLike", ["X999", "Y"], ["Z"], name="n4"),
         ],
-        "nd",
+        "-nd-",
         [
             oh.make_tensor_value_info("X", TFLOAT, ["a", "b", "c"]),
             oh.make_tensor_value_info("Y", TFLOAT, ["a", "b", "c"]),
@@ -75,7 +75,7 @@
 # %%
 # We can see it run until it reaches `Cast` and stops.
 # The error message is not always obvious to interpret.
-# It gets improved everytime from time to time.
+# It gets improved every time from time to time.
 # This runtime is useful when it fails for a numerical reason.
 # It is possible to insert prints in the python code to print
 # more information or debug if needed.
diff --git a/_doc/index.rst b/_doc/index.rst
@@ -18,7 +18,7 @@ onnx-diagnostic: investigate onnx models
 .. image:: https://codecov.io/gh/sdpython/onnx-diagnostic/branch/main/graph/badge.svg?token=Wb9ZGDta8J 
     :target: https://codecov.io/gh/sdpython/onnx-diagnostic
 
-**onnx-diagnostic** helps investgating onnx models, exporting models into onnx.
+**onnx-diagnostic** helps investigating onnx models, exporting models into onnx.
 It implements tools used to understand issues.
 
 Source are `sdpython/onnx-diagnostic
diff --git a/_unittests/ut_xrun_doc/test_helpers.py b/_unittests/ut_xrun_doc/test_helpers.py
@@ -87,7 +87,7 @@ def test_pretty_onnx(self):
                     oh.make_node("Mul", ["Y", "sy"], ["ysy"]),
                     oh.make_node("Mul", ["X", "ysy"], ["final"]),
                 ],
-                "nd",
+                "-nd-",
                 [
                     oh.make_tensor_value_info("X", TFLOAT, [1, "b", "c"]),
                     oh.make_tensor_value_info("Y", TFLOAT, ["a", "b", "c"]),
@@ -111,7 +111,7 @@ def test_print_pretty_onnx(self):
                     oh.make_node("Mul", ["Y", "sy"], ["ysy"]),
                     oh.make_node("Mul", ["X", "ysy"], ["final"]),
                 ],
-                "nd",
+                "-nd-",
                 [
                     oh.make_tensor_value_info("X", TFLOAT, [1, "b", "c"]),
                     oh.make_tensor_value_info("Y", TFLOAT, ["a", "b", "c"]),
@@ -136,7 +136,7 @@ def test_get_onnx_signature(self):
                     oh.make_node("Mul", ["Y", "sy"], ["ysy"]),
                     oh.make_node("Mul", ["X", "ysy"], ["final"]),
                 ],
-                "nd",
+                "-nd-",
                 [
                     oh.make_tensor_value_info("X", TFLOAT, [1, "b", "c"]),
                     oh.make_tensor_value_info("Y", TFLOAT, ["a", "b", "c"]),
diff --git a/onnx_diagnostic/export/dynamic_shapes.py b/onnx_diagnostic/export/dynamic_shapes.py
@@ -144,7 +144,7 @@ def __init__(
         ), f"unexpected type for model={type(model)}, it must be a torch.nn.Module"
         assert name, (
             f"name={name!r} cannot be empty this string is used to "
-            f"display meaningfull error messages"
+            f"display meaningful error messages"
         )
         self.name = name
         self.model = model
@@ -195,7 +195,7 @@ def process_inputs(
         """
         if not isinstance(inputs, list):
             raise ValueError(
-                f"inputs should be specifed as a list of sets of "
+                f"inputs should be specified as a list of sets of "
                 f"inputs but type(inputs) is {type(inputs)}"
             )
         new_inputs = []
diff --git a/onnx_diagnostic/ext_test_case.py b/onnx_diagnostic/ext_test_case.py
@@ -179,7 +179,7 @@ def measure_time(
         real measurement
     :param div_by_number: divide by the number of executions
     :param max_time: execute the statement until the total goes
-        beyond this time (approximatively), *repeat* is ignored,
+        beyond this time (approximately), *repeat* is ignored,
         *div_by_number* must be set to True
     :return: dictionary
 
@@ -678,7 +678,7 @@ def requires_cuda(msg: str = "", version: str = "", memory: int = 0):
 
     :param msg: to overwrite the message
     :param version: minimum version
-    :param memory: minimun number of Gb to run the test
+    :param memory: minimum number of Gb to run the test
     """
     import torch
 
@@ -1073,9 +1073,11 @@ def statistics_on_folder(
     """
     if isinstance(folder, list):
         rows = []
-        for fo in folder:
-            last = fo.replace("\\", "/").split("/")[-1]
-            r = statistics_on_folder(fo, pattern=pattern, aggregation=max(aggregation - 1, 0))
+        for fold in folder:
+            last = fold.replace("\\", "/").split("/")[-1]
+            r = statistics_on_folder(
+                fold, pattern=pattern, aggregation=max(aggregation - 1, 0)
+            )
             if aggregation == 0:
                 rows.extend(r)
                 continue
diff --git a/onnx_diagnostic/helpers.py b/onnx_diagnostic/helpers.py
@@ -1210,7 +1210,7 @@ def max_diff(
         allow a comparison between a single tensor and a list of one tensor
     :return: dictionary with many values
 
-    * abs: max abolute error
+    * abs: max absolute error
     * rel: max relative error
     * sum: sum of the errors
     * n: number of outputs values, if there is one
diff --git a/onnx_diagnostic/onnx_tools.py b/onnx_diagnostic/onnx_tools.py
@@ -101,7 +101,7 @@ def onnx_unlighten(
     The model is modified inplace.
 
     :param onx: model
-    :param stats: statics, can be None if onx is a file,
+    :param stats: statistics, can be None if onx is a file,
         then it loads the file ``<filename>.stats``,
         it assumes it is json format
     :param verbose: verbosity
diff --git a/onnx_diagnostic/reference/ort_evaluator.py b/onnx_diagnostic/reference/ort_evaluator.py
@@ -24,7 +24,7 @@ class OnnxruntimeEvaluator:
     This class loads an onnx model and the executes one by one the nodes
     with onnxruntime. This class is mostly meant for debugging.
 
-    :param proto: proto or filaname
+    :param proto: proto or filename
     :param session_options: options
     :param providers: providers
     :param nvtx: enable nvidia events
@@ -37,7 +37,7 @@ class OnnxruntimeEvaluator:
     :param use_training_api: use onnxruntime-traning API
     :param verbose: verbosity
     :param local_functions: additional local function
-    :param ir_version: ir verions to use when unknown
+    :param ir_version: ir version to use when unknown
     :param opsets: opsets to use when unknown
     """
 
diff --git a/onnx_diagnostic/torch_export_patches/onnx_export_errors.py b/onnx_diagnostic/torch_export_patches/onnx_export_errors.py
@@ -123,7 +123,7 @@ def _unregister(cls: type, verbose: int = 0):
         torch.utils._pytree._deregister_pytree_node(cls)
     optree.unregister_pytree_node(cls, namespace="torch")
     assert cls not in torch.utils._pytree.SUPPORTED_NODES, (
-        f"{cls} was not successfull unregistered "
+        f"{cls} was not successful unregistered "
         f"from torch.utils._pytree.SUPPORTED_NODES="
         f"{pprint.pformat(list(torch.utils._pytree.SUPPORTED_NODES))}"
     )
@@ -201,8 +201,8 @@ def bypass_export_some_errors(
     * ``torch._subclasses.fake_impls.infer_size``
     * fix missing method ``name`` for ``sympy.S.IntegerConstant``
     * ``AttentionMaskConverter._make_causal_mask``
-    * Serialialization of ``MambaCache`` (in :epkg:`transformers`)
-    * Serialialization of ``DynamicCache`` (in :epkg:`transformers`)
+    * Serialization of ``MambaCache`` (in :epkg:`transformers`)
+    * Serialization of ``DynamicCache`` (in :epkg:`transformers`)
     * reduce errors due to shape inference
     * replaces :class:`transformers.cache_utils.DynamicCache` with
       :class:`patched_DynamicCache
diff --git a/onnx_diagnostic/torch_test_helper.py b/onnx_diagnostic/torch_test_helper.py
@@ -11,7 +11,7 @@
 
 def to_numpy(tensor: "torch.Tensor"):  # noqa: F821
     """
-    Convets a torch tensor to numy.
+    Converts a torch tensor to numy.
     """
     try:
         return tensor.numpy()

Original file line number	Diff line number	Diff line change
`@@ -99,4 +99,4 @@ Snapshot of usefuls tools`
`99`	`99`
`100`	`100`	`max_diff`
`101`	`101`
`102`		`-Returns the maximum discrancies accross nested containers containing tensors.`
	`102`	`+Returns the maximum discrancies across nested containers containing tensors.`
Original file line number	Diff line number	Diff line change
`@@ -39,7 +39,7 @@`
`39`	`39`	`oh.make_node("Cast", ["C"], ["X999"], to=999, name="failing"),`
`40`	`40`	`oh.make_node("CastLike", ["X999", "Y"], ["Z"], name="n4"),`
`41`	`41`	`],`
`42`		`- "nd",`
	`42`	`+ "-nd-",`
`43`	`43`	`[`
`44`	`44`	`oh.make_tensor_value_info("X", TFLOAT, ["a", "b", "c"]),`
`45`	`45`	`oh.make_tensor_value_info("Y", TFLOAT, ["a", "b", "c"]),`