Add pyspelling config and workflow (#2274)

Pipeline is:
 - Filter python comments
 - Remove encoding comment and one `:: figure:` rst 
 - Convert markup to html
 - Remove code sections from converted rst (important: for markup to properly recognize something as code-section it must have correct indentation)

Add non-standard words to `tutorials-worldlist.txt`
So far only covers `data_loading_tutorial.py`

Author: malfet

.github/workflows/spelling.yml

@@ -0,0 +1,20 @@
+name: Check spelling
+
+on:
+  pull_request:
+  push:
+    branches:
+      - main
+jobs:
+  pyspelling:
+    runs-on: ubuntu-20.04
+    steps:
+      - uses: actions/checkout@v3
+      - uses: actions/setup-python@v4
+        with:
+          python-version: '3.9'
+          cache: 'pip'
+      - run: pip install pyspelling
+      - run: sudo apt-get install aspell aspell-en
+      - run: pyspelling
+

.pyspelling.yml

@@ -0,0 +1,25 @@
+spellchecker: aspell
+matrix:
+- name: beginner
+  sources:
+    - beginner_source/data_loading_tutorial.py
+  dictionary:
+    wordlists:
+      - tutorials-wordlist.txt
+  pipeline:
+  - pyspelling.filters.python:
+      group_comments: true
+  - pyspelling.filters.context:
+      context_visible_first: true
+      delimiters:
+        # Exclude figure rST tags
+        - open: '\.\.\s+(figure|literalinclude|)::'
+          close: '\n'
+        # Exclude Python coding directives
+        - open: '-\*- coding:'
+          close: '\n'
+  - pyspelling.filters.markdown:
+  - pyspelling.filters.html:
+      ignores:
+        - code
+        - pre

beginner_source/data_loading_tutorial.py

@@ -124,7 +124,7 @@ class FaceLandmarksDataset(Dataset):
 
     def __init__(self, csv_file, root_dir, transform=None):
         """
-        Args:
+        Arguments:
             csv_file (string): Path to the csv file with annotations.
             root_dir (string): Directory with all the images.
             transform (callable, optional): Optional transform to be applied
@@ -197,7 +197,7 @@ def __getitem__(self, idx):
 #    swap axes).
 #
 # We will write them as callable classes instead of simple functions so
-# that parameters of the transform need not be passed everytime it's
+# that parameters of the transform need not be passed every time it's
 # called. For this, we just need to implement ``__call__`` method and
 # if required, ``__init__`` method. We can then use a transform like this:
 #
@@ -291,12 +291,12 @@ def __call__(self, sample):
         image = image.transpose((2, 0, 1))
         return {'image': torch.from_numpy(image),
                 'landmarks': torch.from_numpy(landmarks)}
-    
+
 ######################################################################
 # .. note::
 #     In the example above, `RandomCrop` uses an external library's random number generator 
-#     (in this case, Numpy's `np.random.int`). This can result in unexpected behavior with `DataLoader` 
-#     (see https://pytorch.org/docs/stable/notes/faq.html#my-data-loader-workers-return-identical-random-numbers). 
+#     (in this case, Numpy's `np.random.int`). This can result in unexpected behavior with `DataLoader`
+#     (see `here <https://pytorch.org/docs/stable/notes/faq.html#my-data-loader-workers-return-identical-random-numbers>`_).
 #     In practice, it is safer to stick to PyTorch's random number generator, e.g. by using `torch.randint` instead.
 
 ######################################################################
@@ -404,7 +404,7 @@ def show_landmarks_batch(sample_batched):
         plt.title('Batch from dataloader')
 
 # if you are using Windows, uncomment the next line and indent the for loop.
-# you might need to go back and change "num_workers" to 0. 
+# you might need to go back and change ``num_workers`` to 0.
 
 # if __name__ == '__main__':
 for i_batch, sample_batched in enumerate(dataloader):
@@ -444,21 +444,21 @@ def show_landmarks_batch(sample_batched):
 # which operate on ``PIL.Image`` like  ``RandomHorizontalFlip``, ``Scale``,
 # are also available. You can use these to write a dataloader like this: ::
 #
-#   import torch
-#   from torchvision import transforms, datasets
-#
-#   data_transform = transforms.Compose([
-#           transforms.RandomSizedCrop(224),
-#           transforms.RandomHorizontalFlip(),
-#           transforms.ToTensor(),
-#           transforms.Normalize(mean=[0.485, 0.456, 0.406],
-#                                std=[0.229, 0.224, 0.225])
-#       ])
-#   hymenoptera_dataset = datasets.ImageFolder(root='hymenoptera_data/train',
-#                                              transform=data_transform)
-#   dataset_loader = torch.utils.data.DataLoader(hymenoptera_dataset,
-#                                                batch_size=4, shuffle=True,
-#                                                num_workers=4)
+#    import torch
+#    from torchvision import transforms, datasets
+#
+#    data_transform = transforms.Compose([
+#            transforms.RandomSizedCrop(224),
+#            transforms.RandomHorizontalFlip(),
+#            transforms.ToTensor(),
+#            transforms.Normalize(mean=[0.485, 0.456, 0.406],
+#                                 std=[0.229, 0.224, 0.225])
+#        ])
+#    hymenoptera_dataset = datasets.ImageFolder(root='hymenoptera_data/train',
+#                                               transform=data_transform)
+#    dataset_loader = torch.utils.data.DataLoader(hymenoptera_dataset,
+#                                                 batch_size=4, shuffle=True,
+#                                                 num_workers=4)
 #
 # For an example with training code, please see
 # :doc:`transfer_learning_tutorial`.

tutorials-wordlist.txt

@@ -0,0 +1,23 @@
+csv
+DataLoaders
+dataloader
+dataset
+datasets
+dir
+imagenet
+io
+jpg
+ndarrays
+Numpy's
+numpy
+preprocess
+preprocessing
+pytorch
+rescale
+runtime
+th
+subclasses
+submodule
+tanh
+torchvision
+uncomment