Minor fixes

doc/source/data/creating-datasets.rst

@@ -168,7 +168,7 @@ Supported File Formats
 
   This function stores image data in single-column
   `Arrow Table <https://arrow.apache.org/docs/python/generated/pyarrow.Table.html>`__
-  blocks using our 
+  blocks using the 
   :class:`tensor extension type <ray.data.extensions.tensor_extension.ArrowTensorType>`.
   For more information on working with tensors in Datasets, read the 
   :ref:`tensor data guide <datasets_tensor_support>`.

doc/source/data/doc_code/creating_datasets.py

@@ -156,23 +156,13 @@
 #            schema={__value__: ArrowTensorType(shape=(32, 32, 3), dtype=uint8)})
 
 ds.take(1)
-# -> [{'image':
-#         array([[[ 92,  71,  57],
-#                 [107,  87,  72],
-#                 ...,
-#                 [141, 161, 185],
-#                 [139, 158, 184]],
-#
-#                ...,
-#
-#                [[135, 135, 109],
-#                 [135, 135, 108],
-#                 ...,
-#                 [167, 150,  89],
-#                 [165, 146,  90]]], dtype=uint8),
-#      'label': 'cat',
-#     }]
-# __read_images_end__
+# -> [array([[[ 88,  70,  68],
+#            [103,  88,  85],
+#            [112,  96,  97],
+#            ...,
+#            [168, 151,  81],
+#            [167, 149,  83],
+#            [166, 148,  82]]], dtype=uint8)]
 # fmt: on
 
 # fmt: off

doc/source/data/doc_code/tensor.py

@@ -199,22 +199,13 @@ def cast_udf(block: pa.Table) -> pa.Table:
 #            schema={__value__: ArrowTensorType(shape=(32, 32, 3), dtype=uint8)})
 
 ds.take(1)
-# -> [{'image':
-#         array([[[ 92,  71,  57],
-#                 [107,  87,  72],
-#                 ...,
-#                 [141, 161, 185],
-#                 [139, 158, 184]],
-#
-#                ...,
-#
-#                [[135, 135, 109],
-#                 [135, 135, 108],
-#                 ...,
-#                 [167, 150,  89],
-#                 [165, 146,  90]]], dtype=uint8),
-#      'label': 'cat',
-#     }]
+# -> [array([[[ 88,  70,  68],
+#            [103,  88,  85],
+#            [112,  96,  97],
+#            ...,
+#            [168, 151,  81],
+#            [167, 149,  83],
+#            [166, 148,  82]]], dtype=uint8)]
 # __create_images_end__
 
 

python/ray/data/read_api.py

@@ -423,7 +423,7 @@ def read_images(
         >>> path = "s3://air-example-data-2/movie-image-small-filesize-1GB"
         >>> ds = ray.data.read_images(path)
         >>> ds
-        Dataset(num_blocks=200, num_rows=41979, schema=<class 'numpy.ndarray'>)
+        Dataset(num_blocks=200, num_rows=41979, schema={__value__: ArrowTensorType(shape=(386, 256, 3), dtype=uint8)})
 
         If your images are arranged like:
 
@@ -468,8 +468,9 @@ def read_images(
             `Pillow <https://pillow.readthedocs.io/en/stable/index.html>`_.
 
     Returns:
-        A :class:`~ray.data.Dataset` containing ``np.ndarray`` objects constructed from
-        the images at the specified paths.
+        A :class:`~ray.data.Dataset` containing tensors that represent the images at
+        the specified paths. For information on working with tensors, read the
+        :ref:`tensor data guide <datasets_tensor_support>`.
 
     Raises:
         ValueError: if ``size`` contains non-positive numbers.