refactor: merge all channel-specific attributes of the Image class #1191
Conversation
WalkthroughThe pull request introduces significant changes to the Changes
Possibly related PRs
Poem
Thank you for using CodeRabbit. We offer it for free to the OSS community and would appreciate your support in helping us grow. If you find it useful, would you consider giving us a shout-out on your favorite social media? TipsChatThere are 3 ways to chat with CodeRabbit:
Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments. CodeRabbit Commands (Invoked using PR comments)
Other keywords and placeholders
CodeRabbit Configuration File (
|
Codecov ReportAttention: Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## develop #1191 +/- ##
===========================================
+ Coverage 93.08% 93.12% +0.03%
===========================================
Files 210 210
Lines 32974 33105 +131
===========================================
+ Hits 30694 30828 +134
+ Misses 2280 2277 -3 ☔ View full report in Codecov by Sentry. |
Czaki
changed the title
Czaki
changed the title
Czaki
changed the title
Reviewer's Guide by SourceryThis pull request refactors the Image class in the PartSegImage package, merging all channel-specific attributes and making most arguments keyword-only. The changes aim to improve the class's structure and usage. File-Level Changes
Tips
|
![sourcery-ai[bot]](https://avatars.githubusercontent.com/in/48477?s=60&v=4){kind=small}
There was a problem hiding this comment.
Hey @Czaki - I've reviewed your changes and they look great!
Here's what I looked at during the review
- 🟡 General issues: 2 issues found
- 🟢 Security: all looks good
- 🟡 Testing: 5 issues found
- 🟢 Complexity: all looks good
- 🟢 Documentation: all looks good
Help me be more useful! Please click 👍 or 👎 on each comment to tell me if it was helpful.
| self.metadata = dict(metadata_dict) if metadata_dict is not None else {} | ||
|
|
||
| @staticmethod | ||
| def _adjust_channel_info( |
There was a problem hiding this comment.
suggestion: Consider a more robust approach for default color assignment
The use of cycle for default colors could lead to unexpected behavior with a large number of channels. A modulo operation on a fixed list of colors might ensure more consistent and predictable color assignment.
@staticmethod
def _adjust_channel_info(
channel_info: list[ChannelInfo | ChannelInfoFull] | None,
channel_array: list[np.ndarray],
default_colors: list[str] = ['red', 'green', 'blue', 'yellow', 'cyan', 'magenta']
) -> list[ChannelInfoFull]:
| return _fun | ||
|
|
||
|
|
||
| def merge_into_channel_info(fun): |
There was a problem hiding this comment.
suggestion (performance): Optimize merge_into_channel_info decorator for performance
The decorator performs several operations on every function call, which could impact performance for frequently called methods. Consider moving the deprecation warning and merging logic to the init method to perform these operations only once during object creation.
def merge_into_channel_info(fun):
def wrapper(self, *args, **kwargs):
if not hasattr(self, '_merged_channel_info'):
self._merged_channel_info = self._merge_channel_info()
return fun(self, *args, **kwargs)
return wraps(fun)(wrapper)
| with pytest.raises(ValueError, match="Wrong array shape"): | ||
| self.image_class( | ||
| np.zeros(data_shape), | ||
| (5, 5, 5), | ||
| spacing=(5, 5, 5), | ||
| mask=np.zeros(data_shape[:-2] + (40,)), | ||
| axes_order=self.image_class.axis_order, | ||
| ) |
There was a problem hiding this comment.
suggestion (testing): Update test to use new 'spacing' parameter and 'channel_info' instead of 'channel_names'
The test has been updated to use the new 'spacing' parameter and 'channel_info' instead of 'channel_names'. This change reflects the refactoring in the main code. Verify that all tests in this file are updated to use these new parameters consistently.
| with pytest.raises(ValueError, match="Wrong array shape"): | |
| self.image_class( | |
| np.zeros(data_shape), | |
| (5, 5, 5), | |
| spacing=(5, 5, 5), | |
| mask=np.zeros(data_shape[:-2] + (40,)), | |
| axes_order=self.image_class.axis_order, | |
| ) | |
| def test_image_mask_exception(self): | |
| with pytest.raises(ValueError, match="Wrong array shape"): | |
| self.image_class( | |
| np.zeros(data_shape), | |
| spacing=(5, 5, 5), | |
| mask=np.zeros(data_shape[:-2] + (40,)), | |
| axes_order=self.image_class.axis_order, | |
| channel_info=[{"name": f"Channel {i}"} for i in range(data_shape[-1])] | |
| ) |
| axes_order="ZYXC", | ||
| channel_names=["a", "b"], | ||
| channel_info=[ChannelInfo("a"), ChannelInfo("b")], | ||
| shift=(10, 9, 8), | ||
| name="Test", | ||
| ) |
There was a problem hiding this comment.
suggestion (testing): Update test to use new 'spacing' parameter and 'channel_info' instead of 'channel_names'
The test has been updated to use the new 'spacing' parameter and 'channel_info' instead of 'channel_names'. This change is consistent with the refactoring in the main code. Ensure that all other tests in this file are updated similarly.
def test_ome_save(tmp_path, bundle_test_dir, ome_xml, z_size):
data = np.zeros((z_size, 20, 20, 2), dtype=np.uint8)
spacing = (27e-6, 6e-6, 6e-6)
channel_info = [ChannelInfo("a"), ChannelInfo("b")]
image = Image(
data,
spacing=spacing,
axes_order="ZYXC",
channel_info=channel_info,
shift=(10, 9, 8),
name="Test",
)
|
|
||
| @staticmethod | ||
| def _adjust_channel_info( | ||
| channel_info: list[ChannelInfo | ChannelInfoFull] | None, channel_array: list[np.ndarray] |
There was a problem hiding this comment.
issue (code-quality): We've found these issues:
- Convert for loop into list comprehension (
list-comprehension) - Replace a for append loop with list extend (
for-append-to-extend)
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 4
Outside diff range and nitpick comments (4)
package/tests/test_PartSegImage/test_image.py (1)
365-367: Adjust spacing to match 2D image dimensionsThe image is 2D, but the
spacingis specified as a 3-tuple(1, 1, 1). Consider adjusting thespacingto a 2-tuple(1, 1)to match the dimensions of the image more accurately.Apply this diff to adjust the spacing:
-image = self.image_class( - np.zeros((1, 1, 20, 30, 3), np.uint8), spacing=(1, 1, 1), file_path="", axes_order="TZYXC" -) +image = self.image_class( + np.zeros((1, 1, 20, 30, 3), np.uint8), spacing=(1, 1), file_path="", axes_order="TZYXC" +)package/PartSegImage/image.py (3)
26-31: Consider adding docstrings toChannelInfodataclass.Including a docstring for the
ChannelInfoclass would enhance code readability and provide clear documentation of its purpose and usage.
33-38: Consider adding docstrings toChannelInfoFulldataclass.Adding a docstring to the
ChannelInfoFullclass would improve maintainability by explaining its role and how it differs fromChannelInfo.
136-167: Simplify conditional checks inmerge_into_channel_infofor clarity.Reordering the checks for
Nonebefore type checking enhances readability and avoids unnecessary type checks onNonevalues.Apply this diff to simplify the conditional checks:
channel_names = kwargs.pop("channel_names", []) default_coloring = kwargs.pop("default_coloring", []) ranges = kwargs.pop("ranges", []) if any([channel_names, default_coloring, ranges]): + if channel_names is None: + channel_names = [] if isinstance(channel_names, str): channel_names = [channel_names] - if channel_names is None: - channel_names = [] if default_coloring is None: default_coloring = [] if ranges is None: ranges = []
Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Files selected for processing (22)
- package/PartSeg/plugins/napari_widgets/simple_measurement_widget.py (1 hunks)
- package/PartSeg/plugins/napari_widgets/utils.py (2 hunks)
- package/PartSegCore/image_transforming/image_projection.py (1 hunks)
- package/PartSegCore/mask/io_functions.py (1 hunks)
- package/PartSegCore/napari_plugins/save_tiff_layer.py (3 hunks)
- package/PartSegImage/init.py (2 hunks)
- package/PartSegImage/image.py (12 hunks)
- package/PartSegImage/image_reader.py (6 hunks)
- package/tests/test_PartSeg/test_base_widgets.py (1 hunks)
- package/tests/test_PartSeg/test_common_backend.py (3 hunks)
- package/tests/test_PartSeg/test_common_gui.py (2 hunks)
- package/tests/test_PartSeg/test_napari_image_view.py (1 hunks)
- package/tests/test_PartSeg/test_settings.py (2 hunks)
- package/tests/test_PartSegCore/test_analysis_batch.py (2 hunks)
- package/tests/test_PartSegCore/test_image_adjustment.py (1 hunks)
- package/tests/test_PartSegCore/test_io.py (3 hunks)
- package/tests/test_PartSegCore/test_mask_create.py (1 hunks)
- package/tests/test_PartSegCore/test_measurements.py (16 hunks)
- package/tests/test_PartSegCore/test_napari_plugins.py (1 hunks)
- package/tests/test_PartSegCore/test_segmentation.py (3 hunks)
- package/tests/test_PartSegImage/test_image.py (20 hunks)
- package/tests/test_PartSegImage/test_image_writer.py (6 hunks)
Additional comments not posted (91)
package/PartSegImage/__init__.py (2)
6-6: LGTM!The import statement has been correctly updated to include the new
ChannelInfoandChannelInfoFullclasses from thePartSegImage.imagemodule.
20-21: LGTM!The
__all__tuple has been correctly updated to include the newChannelInfoandChannelInfoFullclasses, making them part of the public API of the module.package/PartSegCore/napari_plugins/save_tiff_layer.py (2)
18-18: LGTM!The changes to the
Imageconstructor call improve the structure and clarity of the code:
- Replacing
channel_nameswithchannel_infoenhances the structure of channel data being passed to the constructor.- Explicitly naming the
spacingparameter improves code readability.These changes align with the PR objective of refactoring the Image class by merging channel-specific attributes.
Also applies to: 20-20
53-53: LGTM!The changes to the
Imageconstructor call improve the structure and clarity of the code:
- Replacing
channel_nameswithchannel_infoenhances the structure of channel data being passed to the constructor.- Explicitly naming the
spacingparameter improves code readability.These changes align with the PR objective of refactoring the Image class by merging channel-specific attributes.
Also applies to: 55-55
package/PartSegCore/image_transforming/image_projection.py (1)
61-62: Verify the parameter changes in the codebase.The parameter name changes from
image_spacingtospacing, andchannel_namestochannel_infoalign with the PR objective of refactoring the Image class by merging channel-specific attributes. This improves the clarity and organization of the code.Please ensure that all call sites of the
transformmethod have been updated to use the new parameter names.Run the following script to verify the parameter usage:
Verification successful
Approve the parameter changes in the Image class.
The parameter name changes from
image_spacingtospacing, andchannel_namestochannel_infohave been correctly implemented across the codebase. Although these parameters are not directly visible in thetransformmethod ofimage_projection.py, the changes are consistent with the PR objective of refactoring the Image class by merging channel-specific attributes.Key points:
- The
spacingparameter is widely used throughout the codebase, indicating it's a fundamental property of the Image class.channel_infois used to store metadata about image channels, which aligns with the refactoring goal.- In the
transformmethod, these properties are accessed through theimageparameter (e.g.,image.spacing), which is the correct way to use these attributes after the refactoring.The implementation maintains consistency and improves the organization of the Image class while ensuring that existing functionality remains intact.
Scripts executed
The following scripts were executed for the analysis:
Script:
#!/bin/bash # Description: Verify all calls to the `transform` method use the new parameter names. # Test: Search for the method usage. Expect: Only occurrences of the new parameter names. rg --type python -A 5 $'transform\('Length of output: 68
Script:
#!/bin/bash # Description: Verify all calls to the `transform` method use the new parameter names. # Find Python files and search for 'transform(' in them fd -e py -x rg -n -A 5 'transform\(' {} \; # Use ast-grep to find function calls to 'transform' ast-grep --lang python --pattern 'transform($_)'Length of output: 5324
Script:
#!/bin/bash # Description: Search for occurrences of 'spacing' and 'channel_info' in Python files # Search for 'spacing' in Python files echo "Searching for 'spacing':" fd -e py -x rg -n 'spacing' {} \; echo -e "\nSearching for 'channel_info':" fd -e py -x rg -n 'channel_info' {} \; echo -e "\nSearching for 'transform' method implementation in image_projection.py:" rg -n -A 10 'def transform' package/PartSegCore/image_transforming/image_projection.pyLength of output: 45708
package/PartSeg/plugins/napari_widgets/utils.py (3)
15-15: LGTM!The import statement has been correctly updated to include
ChannelInfofromPartSegImage. This aligns with the PR objective of refactoring the Image class to merge channel-specific attributes.
72-72: Verify theImageconstructor usage in the codebase.The change from
data_scaletospacingis a valid refactor that maintains the same functionality. However, ensure that all occurrences of theImageconstructor in the codebase have been updated to use the newspacingparameter.Run the following script to verify the
Imageconstructor usage:Verification successful
Refactoring from 'data_scale' to 'spacing' verified successfully.
The change from 'data_scale' to 'spacing' in the Image constructor has been correctly implemented across the codebase. The single remaining instance of 'data_scale' is used as a variable name to provide the value for the 'spacing' parameter, which is consistent with the refactoring.
- File with remaining 'data_scale' usage: (file name not provided in the output)
- Line: 87
- Context:
image = Image(data_layer.data, spacing=data_scale, axes_order="TZYX"[-data_ndim:])This usage is correct and does not require any further changes.
Scripts executed
The following scripts were executed for the analysis:
Script:
#!/bin/bash # Description: Verify all occurrences of the `Image` constructor use the new `spacing` parameter. # Test: Search for the `Image` constructor usage. Expect: No occurrences of `data_scale`. rg --type python -A 5 $'Image\('Length of output: 64
Script:
#!/bin/bash # Description: Search for Image constructor usage in Python files # Find Python files and search for Image constructor with data_scale or spacing fd '\.py$' --exec rg -n 'Image\(((?!data_scale|spacing).)*(?:data_scale|spacing)' {} -A 5 # Count occurrences of data_scale and spacing in Image constructor echo "Occurrences of 'data_scale' in Image constructor:" fd '\.py$' --exec rg 'Image\(.*data_scale' {} | wc -l echo "Occurrences of 'spacing' in Image constructor:" fd '\.py$' --exec rg 'Image\(.*spacing' {} | wc -lLength of output: 63447
Script:
#!/bin/bash # Description: Locate the remaining 'data_scale' usage in Image constructor # Find the file and line number where 'data_scale' is used in Image constructor echo "Location of 'data_scale' usage in Image constructor:" fd '\.py$' --exec rg -n 'Image\(.*data_scale' {} # Show the context of the 'data_scale' usage echo -e "\nContext of 'data_scale' usage (5 lines before and after):" fd '\.py$' --exec rg -n -C 5 'Image\(.*data_scale' {}Length of output: 1092
74-74: Verify theImageconstructor usage in the codebase.The change from
channel_namestochannel_infoaligns with the PR objective of refactoring the Image class to merge channel-specific attributes. Using a list ofChannelInfoobjects provides a more structured representation of channel information.However, ensure that all occurrences of the
Imageconstructor in the codebase have been updated to use the newchannel_infoparameter with the appropriateChannelInfoobjects.Run the following script to verify the
Imageconstructor usage:package/tests/test_PartSegImage/test_image_writer.py (7)
7-7: LGTM!The import statement for the
ChannelInfoclass is correct and necessary for the subsequent code changes.
19-19: LGTM!The parameter name change from
image_spacingtospacingis consistent with the refactoring goal and does not affect the test functionality.
32-32: LGTM!The parameter name change from
image_spacingtospacingis consistent with the refactoring goal and does not affect the test functionality.
47-49: LGTM!The parameter name changes from
image_spacingtospacingandchannel_namestochannel_info, along with the use of theChannelInfoclass, are consistent with the refactoring goal. These changes improve code clarity and organization without affecting the test functionality.
77-77: LGTM!The parameter name change from
image_spacingtospacingis consistent with the refactoring goal and does not affect the test functionality.
84-84: LGTM!The parameter name change from
image_spacingtospacingis consistent with the refactoring goal and does not affect the test functionality.
107-107: LGTM!The parameter name change from
image_spacingtospacingis consistent with the refactoring goal and does not affect the test functionality.package/tests/test_PartSegCore/test_image_adjustment.py (5)
14-14: LGTM!The change to use the
spacingkeyword argument instead of a tuple for dimensions is consistent with the PR objective and improves code clarity.
20-20: LGTM!The change to use the
spacingkeyword argument instead of a tuple for dimensions is consistent with the PR objective and improves code clarity.
27-27: LGTM!The change to use the
spacingkeyword argument instead of a tuple for dimensions is consistent with the PR objective and improves code clarity.
33-33: LGTM!The change to use the
spacingkeyword argument instead of a tuple for dimensions is consistent with the PR objective and improves code clarity.
39-39: LGTM!The change to use the
spacingkeyword argument instead of a tuple for dimensions is consistent with the PR objective and improves code clarity.package/tests/test_PartSegCore/test_napari_plugins.py (1)
48-48: LGTM!The parameter renaming from
image_spacingtospacingin thePImageinstantiation is consistent with the changes made to thePImageconstructor. The test logic remains unaffected.package/PartSeg/plugins/napari_widgets/simple_measurement_widget.py (1)
87-87: LGTM! The parameter renaming improves clarity.The change from
data_scaletospacingas the keyword argument when instantiating theImageobject is an appropriate update. It improves the clarity and consistency of the parameter naming without altering the functionality.package/tests/test_PartSeg/test_base_widgets.py (1)
196-196: LGTM! Verify theImageconstructor has been updated.The change from
image_spacingtospacingin theImageinstantiation looks good. However, please ensure that theImageconstructor has been updated to accept thespacingparameter instead ofimage_spacing. If not, this test would fail due to an invalid parameter being passed.Run the following script to verify the
Imageconstructor signature:Verification successful
Verified:
spacingparameter is correctly implementedThe change from
image_spacingtospacingin theImageconstructor is correct and properly implemented. TheImageclass inpackage/PartSegImage/image.pyuses a@rename_argumentdecorator to handle this change:@rename_argument("image_spacing", "spacing", "0.15.4") def __init__(self, ..., spacing: Spacing, ...):This implementation ensures that:
- The
spacingparameter is now the preferred name.- For backward compatibility,
image_spacingis still accepted but deprecated since version 0.15.4.Your change in the test file is consistent with this update in the
Imageclass. The test will work correctly with the newspacingparameter.Scripts executed
The following scripts were executed for the analysis:
Script:
#!/bin/bash # Description: Verify the `Image` constructor accepts the `spacing` parameter. # Test: Search for the `Image` constructor definition. # Expect: The constructor should accept the `spacing` parameter. ast-grep --lang python --pattern $'class Image: $$$ def __init__($_, spacing=$_, $$$): $$$ 'Length of output: 101
Script:
#!/bin/bash # Description: Locate the Image class definition and verify its constructor # Step 1: Find Python files that might contain the Image class echo "Searching for files containing 'class Image':" fd -e py | xargs rg "class Image" -l # Step 2: Search for the Image class definition echo -e "\nSearching for Image class definition:" rg "class Image\(" -A 10 # Step 3: Use a more relaxed ast-grep pattern to find the constructor echo -e "\nSearching for Image constructor with spacing parameter:" ast-grep --lang python --pattern 'class Image: $$$ def __init__($$$): $$$ 'Length of output: 889
Script:
#!/bin/bash # Description: Inspect the Image class definition in package/PartSegImage/image.py # Step 1: Display the content of the file echo "Content of package/PartSegImage/image.py:" cat package/PartSegImage/image.py # Step 2: Search for the Image class definition and its constructor echo -e "\nSearching for Image class definition and constructor:" rg "class Image" -A 20 package/PartSegImage/image.py # Step 3: Search specifically for the constructor with the spacing parameter echo -e "\nSearching for Image constructor with spacing parameter:" rg "def __init__.*spacing" package/PartSegImage/image.pyLength of output: 39269
package/tests/test_PartSegCore/test_mask_create.py (1)
412-412: LGTM!The parameter name change from
image_spacingtospacingin theImageconstructor call aligns with the updated interface of theImageclass. This change does not affect the overall logic or functionality of the test.package/tests/test_PartSeg/test_napari_image_view.py (1)
51-51: LGTM!The parameter name has been updated from
image_spacingtospacingwithout affecting the test logic. This change is consistent with the AI-generated summary.package/tests/test_PartSeg/test_settings.py (2)
Line range hint
271-292: LGTM!The test logic for setting and cleaning the ROI on a
BaseSettingsinstance looks correct. The assertions verify the expected behavior of theroi_infoproperties and the image not being set toNone.
306-321: LGTM!The test logic for verifying the behavior of the
verify_imagemethod looks correct. It covers the following scenarios:
- A valid image passes the verification.
- An image with swapped time and stack dimensions raises the expected exception.
- The same image with
silent=Truereturns an image with corrected dimensions.- An image with both time and stack dimensions raises the expected exception.
package/PartSegImage/image_reader.py (8)
8-8: LGTM!The import of
zip_longestfromitertoolsis valid and will be useful for zipping iterables of unequal length.
20-20: LGTM!The import of
ChannelInfofromPartSegImage.imageis valid and will be used to represent channel information.
32-35: LGTM!The
li_if_noutility function provides a concise way to handleNonevalues by returning an empty list instead. It can be useful in scenarios where a list is expected but the value might beNone. The function logic is correct.
328-331: LGTM!Using keyword arguments for
spacingandmetadata_dictwhen constructing an instance ofself.image_classenhances clarity and makes the code more readable. The changes are valid.
382-386: LGTM!The changes in the
readmethod ofCziImageReaderclass are valid and improve the code structure:
- Using keyword arguments for
spacingandmetadata_dictenhances clarity and readability.- The new
channel_infoargument provides channel-specific information using theChannelInfoclass.- The list comprehension creates a
ChannelInfoinstance for each channel name inself.channel_names.
525-530: LGTM!The changes in the creation of
channel_infolist in thereadmethod ofTiffImageReaderclass are valid and improve the code:
zip_longestis used to combineself.channel_names,self.colors, andself.ranges, ensuring they are processed together even if they have different lengths.- The
li_if_nofunction handlesNonevalues gracefully by returning an empty list.ChannelInfoinstances are created using the zipped values, providing channel-specific information.
533-535: LGTM!Using keyword arguments for
spacingandchannel_infowhen constructing an instance ofself.image_classenhances clarity and readability. The changes are consistent with the previous modifications and are valid.
540-540: LGTM!Using a keyword argument for
metadata_dictwhen constructing an instance ofself.image_classenhances clarity and readability. The change is consistent with the previous modifications and is valid.package/PartSegCore/mask/io_functions.py (1)
135-135: LGTM!The change improves code readability by explicitly passing the
spacingparameter as a keyword argument.package/tests/test_PartSeg/test_common_backend.py (5)
260-260: LGTM!The
image_spacingparameter is correctly updated tospacingin theImageinstantiation.
268-268: LGTM!The
image_spacingparameter is correctly updated tospacingin theImageinstantiation.
276-276: LGTM!The
image_spacingparameter is correctly updated tospacingin theImageinstantiation.
713-730: LGTM!The added test cases for the
verify_imagemethod cover various image configurations and seem to be logically correct. The assertions match the expected behavior of the method.
Line range hint
733-750: LGTM!The test case for the path history and last files functionality of the
BaseSettingsclass covers the expected behavior. The assertions match the expected length and content of the path history and last files list.package/tests/test_PartSegCore/test_segmentation.py (7)
38-38: LGTM!The changes to the
Imageconstructor call are correct and consistent with the updated parameter names.
44-44: LGTM!The changes to the
Imageconstructor call are correct and consistent with the updated parameter names.
57-57: LGTM!The changes to the
Imageconstructor call are correct and consistent with the updated parameter names.
62-62: LGTM!The changes to the
Imageconstructor call are correct and consistent with the updated parameter names.
69-69: LGTM!The changes to the
Imageconstructor call are correct and consistent with the updated parameter names.
77-77: LGTM!The changes to the
Imageconstructor call are correct and consistent with the updated parameter names.
659-659: LGTM!The changes to the
Imageconstructor call are correct and consistent with the updated parameter names.package/tests/test_PartSegCore/test_analysis_batch.py (2)
126-126: LGTM!The change from positional to keyword argument for
spacingenhances code readability and maintainability. This is a good practice and unlikely to have any negative impact.
137-137: LGTM!Similar to the previous function, the change from positional to keyword argument for
spacingenhances code readability and maintainability. This is a good practice and unlikely to have any negative impact.package/tests/test_PartSegCore/test_io.py (3)
80-81: LGTM!The changes to the
Imageconstructor call improve code readability by using keyword arguments forspacingandfile_path. The underlying logic remains unaffected.
125-126: Looks good!The
Imageconstructor call has been updated to use keyword arguments, in line with the changes made toanalysis_project. This improves readability while preserving the existing behavior.
505-505: Test updated appropriately.The
Imageconstructor call within thetest_mask_project_tupletest has been updated to use keyword arguments, aligning it with the changes made to the fixture functions. The test remains valid and readable.package/tests/test_PartSeg/test_common_gui.py (2)
155-155: Parameter name update looks good.The change from
image_spacingtospacingaligns with refactoring theImageconstructor parameters for consistency. The random image generation logic is unaffected.
178-178: LGTM!The
image_spacingtospacingparameter name change in theImageconstructor call is consistent with the previous fixture. The rest of the mask project file generation remains the same.package/tests/test_PartSegCore/test_measurements.py (16)
68-68: LGTM!The changes to the
Imageconstructor parameters look good. Theimage_spacingparameter has been correctly replaced withspacing, and thefile_pathparameter has been added.
77-77: LGTM!The changes to the
Imageconstructor parameters look good. Theimage_spacingparameter has been correctly replaced withspacing, and thefile_pathparameter has been added.
93-93: LGTM!The changes to the
Imageconstructor parameters look good. Theimage_spacingparameter has been correctly replaced withspacing, and thefile_pathparameter has been added.
847-847: LGTM!The changes to the
Imageconstructor parameters look good. Theimage_spacingparameter has been correctly replaced withspacing, and thefile_pathparameter has been added.
1258-1258: LGTM!The changes to the
Imageconstructor parameters look good. Theimage_spacingparameter has been correctly replaced withspacing, and thefile_pathparameter has been added.
1470-1470: LGTM!The changes to the
Imageconstructor parameters look good. Theimage_spacingparameter has been correctly replaced withspacing, and thefile_pathparameter has been added.
2164-2164: LGTM!The changes to the
Imageconstructor parameters look good. Theimage_spacingparameter has been correctly replaced withspacing, and thefile_pathparameter has been added.
2179-2179: LGTM!The changes to the
Imageconstructor parameters look good. Theimage_spacingparameter has been correctly replaced withspacing, and thefile_pathparameter has been added.
2199-2199: LGTM!The changes to the
Imageconstructor parameters look good. Theimage_spacingparameter has been correctly replaced withspacing, and thefile_pathparameter has been added.
2221-2221: LGTM!The changes to the
Imageconstructor parameters look good. Theimage_spacingparameter has been correctly replaced withspacing, and thefile_pathparameter has been added.
2236-2236: LGTM!The changes to the
Imageconstructor parameters look good. Theimage_spacingparameter has been correctly replaced withspacing, and thefile_pathparameter has been added.
2247-2247: LGTM!The changes to the
Imageconstructor parameters look good. Theimage_spacingparameter has been correctly replaced withspacing, and thefile_pathparameter has been added.
2262-2262: LGTM!The changes to the
Imageconstructor parameters look good. Theimage_spacingparameter has been correctly replaced withspacing, and thefile_pathparameter has been added.
2278-2278: LGTM!The changes to the
Imageconstructor parameters look good. Theimage_spacingparameter has been correctly replaced withspacing, and thefile_pathparameter has been added.
2316-2316: LGTM!The changes to the
Imageconstructor parameters look good. Theimage_spacingparameter has been correctly replaced withspacing, and thefile_pathparameter has been added.
2397-2397: LGTM!The changes to the
Imageconstructor parameters look good. Theimage_spacingparameter has been correctly replaced withspacing, and thefile_pathparameter has been added.package/tests/test_PartSegImage/test_image.py (13)
8-8: Import statement updated with necessary classesThe import statement now includes
ChannelandChannelInfo, which are required for handling channel information within the tests.
170-170: Correctly raisingValueErrorfor invalid data shapesThe tests appropriately raise a
ValueErrorwhen attempting to create anImageobject with data shapes that do not match the specifiedaxes_order. This ensures that the class properly validates input data.Also applies to: 173-173
178-178: Validation of data shapes andaxes_orderin dimension testsIn the
test_get_dimension_numbermethod, the data shapes align correctly with the providedaxes_order"TZYXC". This ensures accurate determination of the dimensionality of images under various configurations.Also applies to: 184-184, 190-190, 196-196, 202-202, 208-208
215-230: Verification of dimension letters intest_get_dimension_lettersThe tests confirm that the method
get_dimension_lettersreturns the correct letters corresponding to the image dimensions, accounting for variations in the data shape andaxes_order. This is crucial for consistent image processing.
256-258: Proper handling of mask reordering intest_set_mask_reorderThe mask is correctly set with a different
axes_order("XYZ") and the image class handles the reordering properly. This ensures that masks are applied accurately regardless of axis configurations.
306-308: Correct swapping of time and stack axes intest_swap_time_and_stackThe method
swap_time_and_stackcorrectly swaps the time and stack axes of the image, and the test verifies that the new image has the expected number of times and layers.
347-349: Accurate spacing setting and validation intest_spacingThe test appropriately checks that setting the spacing works as expected, including handling invalid inputs. This ensures that the image's spatial metadata is managed reliably.
414-414: Verification of unit conversion intest_get_um_spacingThe tests confirm that the method
get_um_spacingcorrectly converts spacing from meters to micrometers. This ensures that spatial units are handled consistently across different scales.Also applies to: 420-420, 424-424
531-531: Proper exception handling in merging images with different shapesThe test correctly raises a
ValueErrorwhen attempting to merge images with differing shapes intest_merge_fail, ensuring that only compatible images are merged.
595-596: Class consistency when merging differentImagesubclassesWhen merging an
Imageinstance with aChangeChannelPosImageinstance, the resulting image retains the class of the primary image (Imagewhenimage1.merge(image2, "C")). This behavior is appropriate and consistent with expectations.
603-603: Ensuring correct data retrieval intest_get_data_by_axisThe
get_data_by_axismethod is tested with various axis parameters. The returned data shapes are as expected, confirming that the method accurately retrieves data slices along specified axes.
630-630: Verify the inclusion ofmaskandcoloringin string representationsThe tests check the string and repr representations of the
Imageobject for the presence ofmaskandcoloringinformation. Ensure that the__str__and__repr__methods include these details for better readability and debugging.Also applies to: 633-633
62-62: Consistent update toImageinstantiation parametersThroughout the test cases, the instantiation of the
Imageclass has been updated to use the new parametersspacingandfile_path, replacing the deprecatedimage_spacingparameter. This change is consistent with the refactoring objectives and ensures that all tests reflect the updatedImageconstructor.Run the following script to verify that all instances of
Imageuse the updated parameters:Also applies to: 70-70, 84-84, 113-116, 119-122, 126-128, 159-161, 163-165, 236-236, 263-263, 265-267, 269-269, 270-271, 275-277, 279-281, 285-287, 293-295, 306-308, 317-321, 339-341, 347-349, 365-367, 376-378, 414-414, 420-420, 424-424, 435-435, 521-522, 539-540, 551-552, 557-558, 563-564, 575-576, 582-583, 589-590, 595-596
Verification successful
Verification successful:
Imageclass instantiation consistently updatedThe verification process confirms that all instances of
Imageclass instantiation across the codebase now use the updated parametersspacingandfile_path, replacing the deprecatedimage_spacingparameter. This change is consistent throughout multiple test files in the package, including:
- test_common_gui.py
- test_segmentation.py
- test_analysis_batch.py
- test_measurements.py
- test_common_backend.py
The refactoring objectives have been successfully met, ensuring that all tests reflect the updated
Imageconstructor.Scripts executed
The following scripts were executed for the analysis:
Script:
#!/bin/bash # Description: Verify all instantiations of `Image` use `spacing` and `file_path` parameters. # Search for any remaining usage of 'image_spacing' (should find none) rg --type py 'Image\([^\)]*image_spacing' # Confirm that all `Image` instantiations include 'spacing' and 'file_path' rg --type py 'Image\([^\)]*spacing=.*file_path=.*\)'Length of output: 1750
package/PartSegImage/image.py (7)
8-10: Necessary imports added.The addition of
copy,dataclass, andwrapsimports is appropriate for the new functionality introduced in the code.
15-15: ImportingChannelclass for channel handling.The import of
ChannelfromPartSegImage.channel_classis necessary for managing channel-specific operations.
86-102: New decoratorrename_argumentimplemented correctly.The
rename_argumentdecorator effectively handles deprecated arguments by issuing a warning and mapping old argument names to new ones.
104-134: Decoratorpositional_to_namedcorrectly enforces keyword-only arguments.The
positional_to_nameddecorator ensures that all arguments beyond the first two are used as keyword arguments, improving code clarity.
206-214: UpdatedImageconstructor to use keyword-only arguments.By introducing
*in the function signature, all parameters afterdataare now keyword-only, enhancing code clarity and preventing positional argument misuse.
225-226: Ensuringspacingis a tuple for consistency.Converting
spacingto a tuple if it's not already one ensures consistent handling of spacing values throughout the class.
237-238: Initializingchannel_infousing_adjust_channel_info.The assignment of
self._channel_infoensures that channel metadata is correctly processed and stored, which is crucial for channel management.
| @@ -580,7 +618,7 @@ def test_cut_with_roi(): | |||
| mask[0:11, 0:11][diam > 0] = 1 | |||
| mask[6:17, 6:17][diam > 0] = 2 | |||
| mask[12:23, 12:23][diam > 0] = 3 | |||
| image = Image(data, (1, 1), axes_order="CXY") | |||
| image = Image(data, spacing=(1, 1), axes_order="CXY") | |||
There was a problem hiding this comment.
Potential issue with deprecated method _cut_with_roi
The method _cut_with_roi is used in test_cut_with_roi, but leading underscores typically indicate a protected or private method. Confirm whether this method should be used directly in tests or if a public interface is available.
Consider updating the test to use a public method or refactor _cut_with_roi if appropriate.
package/PartSegImage/image.py
Outdated
| channel_info: list[ChannelInfo | ChannelInfoFull] | None, channel_array: list[np.ndarray] | ||
| ) -> list[ChannelInfoFull]: | ||
| default_colors = cycle(["red", "blue", "green", "yellow", "magenta", "cyan"]) | ||
| if channel_info is None: | ||
| ranges = [(np.min(x), np.max(x)) for x in channel_array] | ||
| return [ | ||
| ChannelInfoFull(f"channel {i}", x[0], x[1]) for i, x in enumerate(zip(default_colors, ranges), start=1) | ||
| ] | ||
|
|
||
| channel_info = channel_info[: len(channel_array)] | ||
|
|
||
| res = [] | ||
|
|
||
| for i, ch_inf in enumerate(channel_info): | ||
| res.append( | ||
| ChannelInfoFull( | ||
| name=ch_inf.name or f"channel {i+1}", | ||
| color_map=ch_inf.color_map if ch_inf.color_map is not None else next(default_colors), | ||
| contrast_limits=( | ||
| ch_inf.contrast_limits | ||
| if ch_inf.contrast_limits is not None | ||
| else (np.min(channel_array[i]), np.max(channel_array[i])) | ||
| ), | ||
| ) | ||
| ) | ||
|
|
||
| for i, arr in enumerate(channel_array[len(res) :], start=len(channel_info)): | ||
| res.append(ChannelInfoFull(f"channel {i+1}", next(default_colors), (np.min(arr), np.max(arr)))) | ||
|
|
||
| return res |
There was a problem hiding this comment.
Ensure consistent channel naming in _adjust_channel_info.
There may be inconsistencies in channel numbering when generating default channel names. In the loops starting at lines 248 and 268, channel indices may not align correctly. Consider reviewing the indexing to ensure that channel names are assigned consistently, starting from channel 1.
package/PartSegImage/image.py
Outdated
| if isinstance(color, str): | ||
| if color.startswith("#"): | ||
| color_array = _hex_to_rgb(color) | ||
| else: | ||
| color_array = _name_to_rgb(color) | ||
| res.append(np.array([np.linspace(0, x, num=256) for x in color_array])) |
There was a problem hiding this comment.
Handle exceptions for unknown color names in get_imagej_colors.
When using _name_to_rgb(color), if color is not in _NAMED_COLORS, a KeyError will occur. Adding error handling will provide clearer feedback and prevent unexpected crashes.
Apply this diff to handle unknown color names:
else:
+ try:
color_array = _name_to_rgb(color)
+ except ValueError as e:
+ raise ValueError(f"Invalid color name '{color}': {e}")
res.append(np.array([np.linspace(0, x, num=256) for x in color_array]))Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| if isinstance(color, str): | |
| if color.startswith("#"): | |
| color_array = _hex_to_rgb(color) | |
| else: | |
| color_array = _name_to_rgb(color) | |
| res.append(np.array([np.linspace(0, x, num=256) for x in color_array])) | |
| if isinstance(color, str): | |
| if color.startswith("#"): | |
| color_array = _hex_to_rgb(color) | |
| else: | |
| try: | |
| color_array = _name_to_rgb(color) | |
| except ValueError as e: | |
| raise ValueError(f"Invalid color name '{color}': {e}") | |
| res.append(np.array([np.linspace(0, x, num=256) for x in color_array])) |
There was a problem hiding this comment.
Actionable comments posted: 1
Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Files selected for processing (1)
- package/tests/test_PartSegImage/test_image.py (20 hunks)
Additional comments not posted (12)
package/tests/test_PartSegImage/test_image.py (12)
60-66: LGTM!The test logic is correct, and the changes are consistent with the refactoring.
Line range hint
68-81: LGTM!The test logic is correct, and the changes are consistent with the refactoring.
Line range hint
83-107: LGTM!The test logic is correct, and the changes are consistent with the refactoring.
Line range hint
109-130: LGTM!The test logic is correct, and the changes are consistent with the refactoring.
The past review comment on lines 110-117 is no longer valid as the suggested change has already been made.
Line range hint
132-149: LGTM!The test logic is correct, and the changes are consistent with the refactoring.
The past review comment on lines 135-141 is partially valid. The
spacingchange has been made, butchannel_infois not relevant to this test.
151-157: LGTM!The test logic is correct, and the changes are consistent with the refactoring.
159-167: LGTM!The test logic is correct, and the changes are consistent with the refactoring.
169-174: LGTM!The test logic is correct, and the changes are consistent with the refactoring.
176-213: LGTM!The test logic is correct, and the changes are consistent with the refactoring.
215-233: LGTM!The test logic is correct, and the changes are consistent with the refactoring.
Line range hint
235-254: LGTM!The test logic is correct, and the changes are consistent with the refactoring.
256-261: LGTM!The test logic is correct, and the changes are consistent with the refactoring.
| if "C" not in self.image_class.axis_order: | ||
| pytest.skip("No channel axis") | ||
| image = self.image_class(np.zeros((1, 10, 3, 20, 30), np.uint8), (1, 1, 1), "", axes_order="TZCYX") | ||
| image = self.image_class( | ||
| np.zeros((1, 10, 3, 20, 30), np.uint8), spacing=(1, 1, 1), file_path="", axes_order="TZCYX" | ||
| ) | ||
| assert image.get_image_for_save().shape == (1, 10, 3, 20, 30) | ||
| image = self.image_class(np.zeros((1, 10, 20, 30, 3), np.uint8), (1, 1, 1), "", axes_order="TZYXC") | ||
| image = self.image_class( | ||
| np.zeros((1, 10, 20, 30, 3), np.uint8), spacing=(1, 1, 1), file_path="", axes_order="TZYXC" | ||
| ) | ||
| assert image.get_image_for_save().shape == (1, 10, 3, 20, 30) | ||
|
|
There was a problem hiding this comment.
LGTM, but the conditional in the test should be avoided.
The test logic is correct, and the changes are consistent with the refactoring.
The past review comment on lines 263-264 is still valid. Avoid using conditionals in test functions. Consider moving the conditional logic to a helper function or using parametrized tests.
There was a problem hiding this comment.
This is for skipping, tests and cannot be evaluated using pytest.mark.skipif, as depends on subclass implementation
There was a problem hiding this comment.
@Czaki, thank you for the clarification. I understand that the conditional in the test is necessary due to subclass implementation specifics and cannot be replaced with pytest.mark.skipif.
(_/)
(•.•)?
/ \
Learnings added
Learnt from: Czaki
PR: 4DNucleome/PartSeg#1191
File: package/tests/test_PartSegImage/test_image.py:263-273
Timestamp: 2024-09-21T12:25:43.623Z
Learning: In tests where skipping logic depends on subclass implementations, it's acceptable to use conditionals within test functions instead of `pytest.mark.skipif` since decorators cannot access subclass-specific details.
Note: Learnings are effective only in the context of similar code segments. To apply general coding guidelines, please configure review instructions. You can manage existing learnings in the app.
There was a problem hiding this comment.
Actionable comments posted: 1
Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Files selected for processing (3)
- package/PartSegImage/image.py (11 hunks)
- package/tests/test_PartSegImage/test_image.py (20 hunks)
- package/tests/test_PartSegImage/test_image_writer.py (6 hunks)
Files skipped from review as they are similar to previous changes (2)
- package/tests/test_PartSegImage/test_image.py
- package/tests/test_PartSegImage/test_image_writer.py
Additional comments not posted (13)
package/PartSegImage/image.py (13)
98-113: LGTM!The
rename_argumentdecorator correctly handles argument renaming and raises an appropriate deprecation warning.
116-145: LGTM!The
positional_to_nameddecorator correctly converts positional arguments to keyword arguments and raises an appropriate deprecation warning.
148-178: LGTM!The
merge_into_channel_infodecorator correctly merges the deprecated channel-related arguments into thechannel_infoargument and raises an appropriate deprecation warning.
212-214: LGTM!The changes in the constructor signature and the use of decorators to handle argument renaming, positional to named arguments, and merging channel info look good.
388-390: LGTM!The
channel_infoproperty correctly returns a copy of the_channel_infoattribute to prevent direct modification of the internal state.
392-394: LGTM!The
rangesproperty correctly returns the contrast limits for each channel by extracting them from the_channel_infoattribute.
396-398: LGTM!The
default_coloringproperty correctly returns the color map for each channel by extracting them from the_channel_infoattribute.
Line range hint
400-428: LGTM!The
mergemethod correctly merges another image along a given axis by concatenating the channel arrays and updating the channel names and ranges accordingly.
429-430: LGTM!The
channel_namesproperty correctly returns the names of the channels by extracting them from the_channel_infoattribute.
Line range hint
488-528: LGTM!The
substitutemethod correctly creates a copy of the image with substitutions of provided elements. It uses the current image's attributes as default values and creates newChannelInfoFullinstances for each channel based on the provided or default values.
Line range hint
910-936: LGTM!The
get_imagej_colorsmethod correctly returns the ImageJ colors for each channel. It handles different color formats (string, 1D array, 2D array) and converts them to the appropriate RGB representation with 256 steps per color component.
Line range hint
938-949: LGTM!The
get_colorsmethod correctly returns the colors for each channel. It handles different color formats (string, 1D array, 2D array) and appends them to the resulting list.
Line range hint
218-251: Verify the constructor usage in the codebase.The constructor signature has been updated with the introduction of the
channel_infoargument and the deprecation ofchannel_names,default_coloring, andrangesarguments. Ensure that all the code that instantiates theImageclass has been updated to use the new signature.Run the following script to verify the constructor usage:
Verification successful
Verification successful: Image constructor usage updated correctly
The codebase has been thoroughly checked for usage of the Image constructor. No occurrences of the deprecated arguments (channel_names, default_coloring, ranges) were found in any of the constructor calls. This confirms that the codebase has been successfully updated to use the new constructor signature with the 'channel_info' argument.
Scripts executed
The following scripts were executed for the analysis:
Script:
#!/bin/bash # Description: Verify the usage of the Image constructor in the codebase. # Test: Search for the constructor usage. Expect: No occurrences of the deprecated arguments. rg --type python -A 5 $'Image\(' | rg --type python $'channel_names=|default_coloring=|ranges='Length of output: 157
Script:
#!/bin/bash # Description: Verify the usage of the Image constructor in the codebase. # Find Python files and search for Image constructor usage fd '\.py$' | xargs grep -n 'Image(' | grep -E 'channel_names=|default_coloring=|ranges='Length of output: 90
Script:
#!/bin/bash # Description: Verify the usage of the Image constructor in the codebase. # Step 1: Find Python files and search for any Image constructor usage echo "Searching for Image constructor usage:" fd '\.py$' | xargs grep -n 'Image(' # Step 2: If any results are found, filter for deprecated arguments echo -e "\nFiltering for deprecated arguments:" fd '\.py$' | xargs grep -n 'Image(' | grep -E 'channel_names=|default_coloring=|ranges='Length of output: 20034
package/PartSegImage/image.py
Outdated
| def _adjust_channel_info( | ||
| channel_info: list[ChannelInfo | ChannelInfoFull] | None, channel_array: list[np.ndarray] | ||
| ) -> list[ChannelInfoFull]: | ||
| default_colors = cycle(["red", "blue", "green", "yellow", "magenta", "cyan"]) | ||
| if channel_info is None: | ||
| ranges = [(np.min(x), np.max(x)) for x in channel_array] | ||
| return [ | ||
| ChannelInfoFull(name=f"channel {i}", color_map=x[0], contrast_limits=x[1]) | ||
| for i, x in enumerate(zip(default_colors, ranges), start=1) | ||
| ] | ||
|
|
||
| channel_info = channel_info[: len(channel_array)] | ||
|
|
||
| res = [] | ||
|
|
||
| for i, ch_inf in enumerate(channel_info): | ||
| res.append( | ||
| ChannelInfoFull( | ||
| name=ch_inf.name or f"channel {i+1}", | ||
| color_map=ch_inf.color_map if ch_inf.color_map is not None else next(default_colors), | ||
| contrast_limits=( | ||
| ch_inf.contrast_limits | ||
| if ch_inf.contrast_limits is not None | ||
| else (np.min(channel_array[i]), np.max(channel_array[i])) | ||
| ), | ||
| ) | ||
| ) | ||
|
|
||
| for i, arr in enumerate(channel_array[len(res) :], start=len(channel_info)): | ||
| res.append( | ||
| ChannelInfoFull( | ||
| name=f"channel {i+1}", color_map=next(default_colors), contrast_limits=(np.min(arr), np.max(arr)) | ||
| ) | ||
| ) | ||
|
|
||
| return res |
There was a problem hiding this comment.
Ensure consistent channel naming.
There may be inconsistencies in channel numbering when generating default channel names. In the loops starting at lines 260 and 282, ensure that the channel indices align correctly and the channel names are assigned consistently, starting from channel 1.
Co-authored-by: sourcery-ai[bot] <58596630+sourcery-ai[bot]@users.noreply.github.com> Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
for more information, see https://pre-commit.ci
|
There was a problem hiding this comment.
Actionable comments posted: 0
Outside diff range and nitpick comments (1)
package/PartSegImage/image.py (1)
251-291: LGTM with a minor suggestion!The
_adjust_channel_infomethod correctly handles the adjustment ofchannel_infoand generation ofChannelInfoFullinstances. The logic for handling missing or partialchannel_infois well-implemented.To improve readability, consider extracting the logic for generating default
ChannelInfoFullinstances into a separate method. This will make the_adjust_channel_infomethod more concise and easier to understand.
Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Files selected for processing (2)
- package/PartSegCore/analysis/measurement_calculation.py (2 hunks)
- package/PartSegImage/image.py (11 hunks)
Additional comments not posted (14)
package/PartSegImage/image.py (12)
33-37: LGTM!The
ChannelInfodata class is a good addition to encapsulate channel metadata. The field types and default values are appropriate.
40-48: LGTM!The
ChannelInfoFulldata class is a good addition to encapsulate full channel metadata. The__post_init__method ensures thatcolor_mapis always a string or numpy array, which is a nice touch.
97-112: LGTM!The
rename_argumentdecorator is a good way to handle argument renaming and raise deprecation warnings. The implementation looks correct and should help with backward compatibility.
115-144: LGTM!The
positional_to_nameddecorator is a good way to enforce named arguments and raise deprecation warnings for positional arguments. The implementation looks correct and should help with improving code clarity and usability.
147-177: LGTM!The
merge_into_channel_infodecorator is a good way to handle the deprecation ofchannel_names,default_coloring, andrangesarguments and merge them into thechannel_infoargument. The implementation looks correct and should help with backward compatibility.
211-225: LGTM!The updates to the
__init__method signature and the use of decorators improve code clarity, usability, and backward compatibility. Calling_adjust_channel_infoto centralize the processing ofchannel_infoand_channel_arraysis a good design choice.
371-373: LGTM!The
channel_infoproperty correctly returns a deep copy ofself._channel_info, which prevents unintended modifications to the original data.
375-381: LGTM!The
rangesanddefault_coloringproperties provide convenient access to thecontrast_limitsandcolor_mapattributes ofself._channel_info, respectively. This improves code readability and maintainability.
Line range hint
383-410: LGTM!The updates to the
mergeandsubstitutemethods to useself._channel_infoand acceptchannel_infodirectly are consistent with the newchannel_infoattribute and__init__method signature. These changes improve code consistency and maintainability.Also applies to: 497-501
969-983: LGTM!The
_hex_to_rgbfunction correctly converts a hex color code to an RGB tuple. It handles both short and long form hex codes and raises an appropriate error for invalid formats. The implementation is clear and concise.
986-995: LGTM!The
_name_to_rgbfunction correctly converts a color name to an RGB tuple. It uses the_NAMED_COLORSdictionary to map color names to hex codes and raises an appropriate error for unknown color names. The implementation is clear and concise.
998-1008: LGTM!The addition of the
_NAMED_COLORSdictionary is a good idea. It provides a convenient way for users to specify colors by name, which can improve code readability and usability. The chosen color names and hex codes are appropriate.package/PartSegCore/analysis/measurement_calculation.py (2)
211-211: LGTM!Removing the extraneous backtick at the end of the comment line is a good cleanup. The skip comment directive remains intact.
236-236: LGTM!Removing the extraneous backtick at the end of the comment line is a good cleanup. The skip comment directive remains intact.
To fast click to merge and do not spot that one change was not pushed. <!-- Generated by sourcery-ai[bot]: start summary --> ## Summary by Sourcery Refactor the _adjust_channel_info method for better readability and efficiency, and add a new test for the _name_to_rgb function to ensure it handles known and unknown color names correctly. Enhancements: - Refactor the _adjust_channel_info method to improve readability and efficiency by using list comprehensions. Tests: - Add a new test for the _name_to_rgb function to verify its correctness with known color names and handle unknown color names. <!-- Generated by sourcery-ai[bot]: end summary --> <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit - **New Features** - Introduced customizable default colors for channel information processing. - Added a new function to convert color names to RGB values, now handling case insensitivity. - **Bug Fixes** - Enhanced error handling for unknown color names in the new RGB conversion function. - **Tests** - Updated the test suite to include tests for the new RGB conversion functionality, ensuring accuracy and error handling. <!-- end of auto-generated comment: release notes by coderabbit.ai -->
Also make all except
dataarguments keyword onlySummary by Sourcery
Refactor the Image class to consolidate channel-specific attributes into a unified channel_info attribute, enforce keyword-only arguments, and update tests accordingly.
Enhancements:
Tests:
Summary by CodeRabbit
Release Notes
New Features
ChannelInfoandChannelInfoFullclasses for enhanced channel metadata management.spacinginstead ofimage_spacing, improving parameter clarity.Bug Fixes
Imageclass interface.Tests