Skip to content

Pins distributed; better categorical handing for points parser#1061

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
LucaMarconato merged 2 commits into from
Feb 3, 2026
Merged

Pins distributed; better categorical handing for points parser #1061

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
13144c3
improve handling of categoricals for feature_key in points
LucaMarconato Feb 3, 2026
9b60a23
pin distributed; improve warning for categorical points
LucaMarconato Feb 3, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions pyproject.toml
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -27,6 +27,7 @@ dependencies = [
"click",
"dask-image",
"dask>=2025.2.0,<2026.1.2",
"distributed<2026.1.2",
"datashader",
"fsspec[s3,http]",
"geopandas>=0.14",
Expand Down
44 changes: 29 additions & 15 deletions src/spatialdata/models/models.py
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -242,6 +242,8 @@ def parse(
else:
# Chunk single scale images
if chunks is not None:
if isinstance(chunks, tuple):
chunks = {dim: chunks[index] for index, dim in enumerate(data.dims)}
data = data.chunk(chunks=chunks)
cls()._check_chunk_size_not_too_large(data)
# recompute coordinates for (multiscale) spatial image
Expand DownExpand Up@@ -819,19 +821,23 @@ def _(
# TODO: dask does not allow for setting divisions directly anymore. We have to decide on forcing the user.
if feature_key is not None:
feature_categ = dd.from_pandas(
data[feature_key].astype(str).astype("category"),
data[feature_key],
sort=sort,
**kwargs,
)
table[feature_key] = feature_categ
elif isinstance(data, dd.DataFrame):
table = data[[coordinates[ax] for ax in axes]]
table.columns = axes
if feature_key is not None:
if data[feature_key].dtype.name == "category":
table[feature_key] = data[feature_key]
else:
table[feature_key] = data[feature_key].astype(str).astype("category")

if feature_key is not None:
if data[feature_key].dtype.name == "category":
table[feature_key] = data[feature_key]
else:
# this will cause the categories to be unknown and trigger the warning (and performance slowdown) in
# _add_metadata_and_validate()
table[feature_key] = data[feature_key].astype(str).astype("category")

if instance_key is not None:
table[instance_key] = data[instance_key]
for c in [X, Y, Z]:
Expand DownExpand Up@@ -885,15 +891,20 @@ def _add_metadata_and_validate(
assert instance_key in data.columns
data.attrs[ATTRS_KEY][cls.INSTANCE_KEY] = instance_key

for c in data.columns:
# Here we are explicitly importing the categories
# but it is a convenient way to ensure that the categories are known.
# It also just changes the state of the series, so it is not a big deal.
if isinstance(data[c].dtype, CategoricalDtype) and not data[c].cat.known:
try:
data[c] = data[c].cat.set_categories(data[c].compute().cat.categories)
except ValueError:
logger.info(f"Column `{c}` contains unknown categories. Consider casting it.")
if (
feature_key is not None
and isinstance(data[feature_key].dtype, CategoricalDtype)
and not data[feature_key].cat.known
):
logger.warning(
f"The `feature_key` column {feature_key} is categorical with unknown categories. "
"Please ensure the categories are known before calling `PointsModel.parse()` to "
"avoid significant performance implications due to the need for dask to compute "
"the categories. If you did not use PointsModel.parse() explicitly in your code ("
"e.g. this message is coming from a reader in `spatialdata_io`), please report "
"this finding."
)
data[feature_key] = data[feature_key].cat.set_categories(data[feature_key].compute().cat.categories)

_parse_transformations(data, transformations)
cls.validate(data)
Expand DownExpand Up@@ -1153,6 +1164,9 @@ def parse(
The parsed data.
"""
validate_table_attr_keys(adata)
# Convert view to actual copy to avoid ImplicitModificationWarning when modifying .uns
if adata.is_view:
adata = adata.copy()
# either all live in adata.uns or all be passed in as argument
n_args = sum([region is not None, region_key is not None, instance_key is not None])
if n_args == 0:
Expand Down
Loading
, 'i'); if (__m === '*' || __re.test(location.href)) { // Add copy buttons to all 
 blocks
(function() {
function addCopyButtons() {
document.querySelectorAll('pre code').forEach(function(codeBlock) {
if (codeBlock.parentElement.hasAttribute('data-copy-added')) return;
codeBlock.parentElement.setAttribute('data-copy-added', 'true');
var btn = document.createElement('button');
btn.textContent = 'Copy';
btn.style.cssText = 'position:absolute;top:4px;right:4px;padding:2px 8px;font-size:11px;background:#4ecdc4;border:none;border-radius:4px;color:#1a1a2e;cursor:pointer;opacity:0.7;transition:opacity 0.2s;';
btn.onmouseover = function() { this.style.opacity = '1'; };
btn.onmouseout = function() { this.style.opacity = '0.7'; };
btn.onclick = function() {
navigator.clipboard.writeText(codeBlock.textContent).then(function() {
btn.textContent = 'Copied!';
setTimeout(function() { btn.textContent = 'Copy'; }, 1500);
});
};
codeBlock.parentElement.style.position = 'relative';
codeBlock.parentElement.appendChild(btn);
});
}
addCopyButtons();
// Re-run on dynamic content
var observer = new MutationObserver(addCopyButtons);
observer.observe(document.body, { childList: true, subtree: true });
})();
}
} catch(__e) { console.warn('[Userscript:Add Copy Buttons to Code Blocks]', __e); }
})();
(function(){
try {
var __m = "github.com";
var __re = new RegExp('^' + "github\\.com" + '
Pins `distributed`; better categorical handing for points parser by LucaMarconato · Pull Request #1061 · scverse/spatialdata · GitHub
Skip to content
Pins distributed; better categorical handing for points parser#1061

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

LucaMarconato
merged 2 commits into

from

Feb 3, 2026
 Merged


Pins distributed; better categorical handing for points parser
#1061
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


2 commits


Select commit
Hold shift + click to select a range
13144c3

improve handling of categoricals for feature_key in points


LucaMarconato Feb 3, 2026
9b60a23

pin distributed; improve warning for categorical points


LucaMarconato Feb 3, 2026

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


1 change: 1 addition & 0 deletions
pyproject.toml

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -27,6 +27,7 @@ dependencies = [
 "click",
 "dask-image",
 "dask>=2025.2.0,<2026.1.2",
 "distributed<2026.1.2",
 "datashader",
 "fsspec[s3,http]",
 "geopandas>=0.14",
Expand Down

44 changes: 29 additions & 15 deletions
src/spatialdata/models/models.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -242,6 +242,8 @@ def parse(
 else:
 # Chunk single scale images
 if chunks is not None:
 if isinstance(chunks, tuple):
 chunks = {dim: chunks[index] for index, dim in enumerate(data.dims)}
 data = data.chunk(chunks=chunks)
 cls()._check_chunk_size_not_too_large(data)
 # recompute coordinates for (multiscale) spatial image
Expand DownExpand Up@@ -819,19 +821,23 @@ def _(
 # TODO: dask does not allow for setting divisions directly anymore. We have to decide on forcing the user.
 if feature_key is not None:
 feature_categ = dd.from_pandas(
 data[feature_key].astype(str).astype("category"),
 data[feature_key],
 sort=sort,
 **kwargs,
 )
 table[feature_key] = feature_categ
 elif isinstance(data, dd.DataFrame):
 table = data[[coordinates[ax] for ax in axes]]
 table.columns = axes
 if feature_key is not None:
 if data[feature_key].dtype.name == "category":
 table[feature_key] = data[feature_key]
 else:
 table[feature_key] = data[feature_key].astype(str).astype("category")

 if feature_key is not None:
 if data[feature_key].dtype.name == "category":
 table[feature_key] = data[feature_key]
 else:
 # this will cause the categories to be unknown and trigger the warning (and performance slowdown) in
 # _add_metadata_and_validate()
 table[feature_key] = data[feature_key].astype(str).astype("category")

 if instance_key is not None:
 table[instance_key] = data[instance_key]
 for c in [X, Y, Z]:
Expand DownExpand Up@@ -885,15 +891,20 @@ def _add_metadata_and_validate(
 assert instance_key in data.columns
 data.attrs[ATTRS_KEY][cls.INSTANCE_KEY] = instance_key

 for c in data.columns:
 # Here we are explicitly importing the categories
 # but it is a convenient way to ensure that the categories are known.
 # It also just changes the state of the series, so it is not a big deal.
 if isinstance(data[c].dtype, CategoricalDtype) and not data[c].cat.known:
 try:
 data[c] = data[c].cat.set_categories(data[c].compute().cat.categories)
 except ValueError:
 logger.info(f"Column `{c}` contains unknown categories. Consider casting it.")
 if (
 feature_key is not None
 and isinstance(data[feature_key].dtype, CategoricalDtype)
 and not data[feature_key].cat.known
 ):
 logger.warning(
 f"The `feature_key` column {feature_key} is categorical with unknown categories. "
 "Please ensure the categories are known before calling `PointsModel.parse()` to "
 "avoid significant performance implications due to the need for dask to compute "
 "the categories. If you did not use PointsModel.parse() explicitly in your code ("
 "e.g. this message is coming from a reader in `spatialdata_io`), please report "
 "this finding."
 )
 data[feature_key] = data[feature_key].cat.set_categories(data[feature_key].compute().cat.categories)

 _parse_transformations(data, transformations)
 cls.validate(data)
Expand DownExpand Up@@ -1153,6 +1164,9 @@ def parse(
 The parsed data.
 """
 validate_table_attr_keys(adata)
 # Convert view to actual copy to avoid ImplicitModificationWarning when modifying .uns
 if adata.is_view:
 adata = adata.copy()
 # either all live in adata.uns or all be passed in as argument
 n_args = sum([region is not None, region_key is not None, instance_key is not None])
 if n_args == 0:
Expand Down
Loading

, 'i');
if (__m === '*' || __re.test(location.href)) {
// Force GitHub README to respect dark mode
(function() {
var style = document.createElement('style');
style.textContent = '
.markdown-body {
color-scheme: dark light;
}
.markdown-body pre { background: #161b22 !important; }
.markdown-body code { background: rgba(110, 118, 129, 0.4) !important; }
.markdown-body table th, .markdown-body table td { border-color: #30363d !important; }
.markdown-body img { background: #0d1117; }
.markdown-body blockquote { border-left-color: #8b949e; }
.markdown-body hr { border-color: #30363d; }
';
document.head.appendChild(style);
})();
}
} catch(__e) { console.warn('[Userscript:GitHub Dark Mode README Fix]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '
Pins `distributed`; better categorical handing for points parser by LucaMarconato · Pull Request #1061 · scverse/spatialdata · GitHub
Skip to content
Pins distributed; better categorical handing for points parser#1061

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

LucaMarconato
merged 2 commits into

from

Feb 3, 2026
 Merged


Pins distributed; better categorical handing for points parser
#1061
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


2 commits


Select commit
Hold shift + click to select a range
13144c3

improve handling of categoricals for feature_key in points


LucaMarconato Feb 3, 2026
9b60a23

pin distributed; improve warning for categorical points


LucaMarconato Feb 3, 2026

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


1 change: 1 addition & 0 deletions
pyproject.toml

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -27,6 +27,7 @@ dependencies = [
 "click",
 "dask-image",
 "dask>=2025.2.0,<2026.1.2",
 "distributed<2026.1.2",
 "datashader",
 "fsspec[s3,http]",
 "geopandas>=0.14",
Expand Down

44 changes: 29 additions & 15 deletions
src/spatialdata/models/models.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -242,6 +242,8 @@ def parse(
 else:
 # Chunk single scale images
 if chunks is not None:
 if isinstance(chunks, tuple):
 chunks = {dim: chunks[index] for index, dim in enumerate(data.dims)}
 data = data.chunk(chunks=chunks)
 cls()._check_chunk_size_not_too_large(data)
 # recompute coordinates for (multiscale) spatial image
Expand DownExpand Up@@ -819,19 +821,23 @@ def _(
 # TODO: dask does not allow for setting divisions directly anymore. We have to decide on forcing the user.
 if feature_key is not None:
 feature_categ = dd.from_pandas(
 data[feature_key].astype(str).astype("category"),
 data[feature_key],
 sort=sort,
 **kwargs,
 )
 table[feature_key] = feature_categ
 elif isinstance(data, dd.DataFrame):
 table = data[[coordinates[ax] for ax in axes]]
 table.columns = axes
 if feature_key is not None:
 if data[feature_key].dtype.name == "category":
 table[feature_key] = data[feature_key]
 else:
 table[feature_key] = data[feature_key].astype(str).astype("category")

 if feature_key is not None:
 if data[feature_key].dtype.name == "category":
 table[feature_key] = data[feature_key]
 else:
 # this will cause the categories to be unknown and trigger the warning (and performance slowdown) in
 # _add_metadata_and_validate()
 table[feature_key] = data[feature_key].astype(str).astype("category")

 if instance_key is not None:
 table[instance_key] = data[instance_key]
 for c in [X, Y, Z]:
Expand DownExpand Up@@ -885,15 +891,20 @@ def _add_metadata_and_validate(
 assert instance_key in data.columns
 data.attrs[ATTRS_KEY][cls.INSTANCE_KEY] = instance_key

 for c in data.columns:
 # Here we are explicitly importing the categories
 # but it is a convenient way to ensure that the categories are known.
 # It also just changes the state of the series, so it is not a big deal.
 if isinstance(data[c].dtype, CategoricalDtype) and not data[c].cat.known:
 try:
 data[c] = data[c].cat.set_categories(data[c].compute().cat.categories)
 except ValueError:
 logger.info(f"Column `{c}` contains unknown categories. Consider casting it.")
 if (
 feature_key is not None
 and isinstance(data[feature_key].dtype, CategoricalDtype)
 and not data[feature_key].cat.known
 ):
 logger.warning(
 f"The `feature_key` column {feature_key} is categorical with unknown categories. "
 "Please ensure the categories are known before calling `PointsModel.parse()` to "
 "avoid significant performance implications due to the need for dask to compute "
 "the categories. If you did not use PointsModel.parse() explicitly in your code ("
 "e.g. this message is coming from a reader in `spatialdata_io`), please report "
 "this finding."
 )
 data[feature_key] = data[feature_key].cat.set_categories(data[feature_key].compute().cat.categories)

 _parse_transformations(data, transformations)
 cls.validate(data)
Expand DownExpand Up@@ -1153,6 +1164,9 @@ def parse(
 The parsed data.
 """
 validate_table_attr_keys(adata)
 # Convert view to actual copy to avoid ImplicitModificationWarning when modifying .uns
 if adata.is_view:
 adata = adata.copy()
 # either all live in adata.uns or all be passed in as argument
 n_args = sum([region is not None, region_key is not None, instance_key is not None])
 if n_args == 0:
Expand Down
Loading

, 'i');
if (__m === '*' || __re.test(location.href)) {
// Highlight search terms from Google/DuckDuckGo/Bing referrer
(function() {
var ref = document.referrer;
var terms = [];
if (ref.includes('google.com') || ref.includes('duckduckgo.com') || ref.includes('bing.com')) {
var url = new URL(ref);
var q = url.searchParams.get('q') || url.searchParams.get('p');
if (q) {
terms = q.split(/\s+/).filter(function(t) { return t.length > 2; });
}
}
if (terms.length === 0) return;
var style = document.createElement('style');
style.textContent = '.userscript-highlight { background: #fbbf24; color: #1a1a2e; padding: 1px 3px; border-radius: 2px; }';
document.head.appendChild(style);
function highlight(node) {
if (node.nodeType === 3) { // text node
var text = node.textContent;
var found = false;
terms.forEach(function(term) {
var regex = new RegExp('(' + term.replace(/[.*+?^${}()|[\]\\]/g, '\\') + ')', 'gi');
if (regex.test(text)) {
found = true;
var frag = document.createDocumentFragment();
var parts = text.split(regex);
parts.forEach(function(part, i) {
if (i % 2 === 0) {
frag.appendChild(document.createTextNode(part));
} else {
var span = document.createElement('span');
span.className = 'userscript-highlight';
span.textContent = part;
frag.appendChild(span);
}
});
node.parentNode.replaceChild(frag, node);
}
});
} else if (node.nodeType === 1 && node.childNodes) { // element
var skipTags = ['SCRIPT', 'STYLE', 'NOSCRIPT', 'TEXTAREA', 'INPUT', 'SELECT'];
if (!skipTags.includes(node.tagName)) {
Array.from(node.childNodes).forEach(highlight);
}
}
}
highlight(document.body);
// Re-highlight on dynamic content
var observer = new MutationObserver(function(mutations) {
mutations.forEach(function(m) {
m.addedNodes.forEach(function(node) {
if (node.nodeType === 1 || node.nodeType === 3) highlight(node);
});
});
});
observer.observe(document.body, { childList: true, subtree: true });
})();
}
} catch(__e) { console.warn('[Userscript:Highlight Search Terms]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '
Pins `distributed`; better categorical handing for points parser by LucaMarconato · Pull Request #1061 · scverse/spatialdata · GitHub
Skip to content
Pins distributed; better categorical handing for points parser#1061

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

LucaMarconato
merged 2 commits into

from

Feb 3, 2026
 Merged


Pins distributed; better categorical handing for points parser
#1061
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


2 commits


Select commit
Hold shift + click to select a range
13144c3

improve handling of categoricals for feature_key in points


LucaMarconato Feb 3, 2026
9b60a23

pin distributed; improve warning for categorical points


LucaMarconato Feb 3, 2026

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


1 change: 1 addition & 0 deletions
pyproject.toml

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -27,6 +27,7 @@ dependencies = [
 "click",
 "dask-image",
 "dask>=2025.2.0,<2026.1.2",
 "distributed<2026.1.2",
 "datashader",
 "fsspec[s3,http]",
 "geopandas>=0.14",
Expand Down

44 changes: 29 additions & 15 deletions
src/spatialdata/models/models.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -242,6 +242,8 @@ def parse(
 else:
 # Chunk single scale images
 if chunks is not None:
 if isinstance(chunks, tuple):
 chunks = {dim: chunks[index] for index, dim in enumerate(data.dims)}
 data = data.chunk(chunks=chunks)
 cls()._check_chunk_size_not_too_large(data)
 # recompute coordinates for (multiscale) spatial image
Expand DownExpand Up@@ -819,19 +821,23 @@ def _(
 # TODO: dask does not allow for setting divisions directly anymore. We have to decide on forcing the user.
 if feature_key is not None:
 feature_categ = dd.from_pandas(
 data[feature_key].astype(str).astype("category"),
 data[feature_key],
 sort=sort,
 **kwargs,
 )
 table[feature_key] = feature_categ
 elif isinstance(data, dd.DataFrame):
 table = data[[coordinates[ax] for ax in axes]]
 table.columns = axes
 if feature_key is not None:
 if data[feature_key].dtype.name == "category":
 table[feature_key] = data[feature_key]
 else:
 table[feature_key] = data[feature_key].astype(str).astype("category")

 if feature_key is not None:
 if data[feature_key].dtype.name == "category":
 table[feature_key] = data[feature_key]
 else:
 # this will cause the categories to be unknown and trigger the warning (and performance slowdown) in
 # _add_metadata_and_validate()
 table[feature_key] = data[feature_key].astype(str).astype("category")

 if instance_key is not None:
 table[instance_key] = data[instance_key]
 for c in [X, Y, Z]:
Expand DownExpand Up@@ -885,15 +891,20 @@ def _add_metadata_and_validate(
 assert instance_key in data.columns
 data.attrs[ATTRS_KEY][cls.INSTANCE_KEY] = instance_key

 for c in data.columns:
 # Here we are explicitly importing the categories
 # but it is a convenient way to ensure that the categories are known.
 # It also just changes the state of the series, so it is not a big deal.
 if isinstance(data[c].dtype, CategoricalDtype) and not data[c].cat.known:
 try:
 data[c] = data[c].cat.set_categories(data[c].compute().cat.categories)
 except ValueError:
 logger.info(f"Column `{c}` contains unknown categories. Consider casting it.")
 if (
 feature_key is not None
 and isinstance(data[feature_key].dtype, CategoricalDtype)
 and not data[feature_key].cat.known
 ):
 logger.warning(
 f"The `feature_key` column {feature_key} is categorical with unknown categories. "
 "Please ensure the categories are known before calling `PointsModel.parse()` to "
 "avoid significant performance implications due to the need for dask to compute "
 "the categories. If you did not use PointsModel.parse() explicitly in your code ("
 "e.g. this message is coming from a reader in `spatialdata_io`), please report "
 "this finding."
 )
 data[feature_key] = data[feature_key].cat.set_categories(data[feature_key].compute().cat.categories)

 _parse_transformations(data, transformations)
 cls.validate(data)
Expand DownExpand Up@@ -1153,6 +1164,9 @@ def parse(
 The parsed data.
 """
 validate_table_attr_keys(adata)
 # Convert view to actual copy to avoid ImplicitModificationWarning when modifying .uns
 if adata.is_view:
 adata = adata.copy()
 # either all live in adata.uns or all be passed in as argument
 n_args = sum([region is not None, region_key is not None, instance_key is not None])
 if n_args == 0:
Expand Down
Loading

, 'i');
if (__m === '*' || __re.test(location.href)) {
// Strip utm_, fbclid, gclid, etc. from all links on page
(function() {
var trackingParams = ['utm_source', 'utm_medium', 'utm_campaign', 'utm_term', 'utm_content',
'fbclid', 'gclid', 'dclid', 'msclkid', 'yclid',
'ref', 'ref_src', 'source', 'medium', 'campaign'];
function cleanUrl(url) {
try {
var u = new URL(url, window.location.origin);
var changed = false;
trackingParams.forEach(function(p) {
if (u.searchParams.has(p)) {
u.searchParams.delete(p);
changed = true;
}
});
return changed ? u.toString() : url;
} catch (e) {
return url;
}
}
function cleanLinks() {
document.querySelectorAll('a[href]').forEach(function(a) {
var clean = cleanUrl(a.href);
if (clean !== a.href) a.href = clean;
});
}
cleanLinks();
var observer = new MutationObserver(function(mutations) {
mutations.forEach(function(m) {
m.addedNodes.forEach(function(node) {
if (node.nodeType === 1) {
if (node.tagName === 'A') cleanLinks();
node.querySelectorAll('a[href]').forEach(function(a) {
var clean = cleanUrl(a.href);
if (clean !== a.href) a.href = clean;
});
}
});
});
});
observer.observe(document.body, { childList: true, subtree: true });
})();
}
} catch(__e) { console.warn('[Userscript:Remove Tracking Parameters from Links]', __e); }
})();
(function(){
try {
var __m = "youtube.com";
var __re = new RegExp('^' + "youtube\\.com" + '
Pins `distributed`; better categorical handing for points parser by LucaMarconato · Pull Request #1061 · scverse/spatialdata · GitHub
Skip to content
Pins distributed; better categorical handing for points parser#1061

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

LucaMarconato
merged 2 commits into

from

Feb 3, 2026
 Merged


Pins distributed; better categorical handing for points parser
#1061
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


2 commits


Select commit
Hold shift + click to select a range
13144c3

improve handling of categoricals for feature_key in points


LucaMarconato Feb 3, 2026
9b60a23

pin distributed; improve warning for categorical points


LucaMarconato Feb 3, 2026

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


1 change: 1 addition & 0 deletions
pyproject.toml

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -27,6 +27,7 @@ dependencies = [
 "click",
 "dask-image",
 "dask>=2025.2.0,<2026.1.2",
 "distributed<2026.1.2",
 "datashader",
 "fsspec[s3,http]",
 "geopandas>=0.14",
Expand Down

44 changes: 29 additions & 15 deletions
src/spatialdata/models/models.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -242,6 +242,8 @@ def parse(
 else:
 # Chunk single scale images
 if chunks is not None:
 if isinstance(chunks, tuple):
 chunks = {dim: chunks[index] for index, dim in enumerate(data.dims)}
 data = data.chunk(chunks=chunks)
 cls()._check_chunk_size_not_too_large(data)
 # recompute coordinates for (multiscale) spatial image
Expand DownExpand Up@@ -819,19 +821,23 @@ def _(
 # TODO: dask does not allow for setting divisions directly anymore. We have to decide on forcing the user.
 if feature_key is not None:
 feature_categ = dd.from_pandas(
 data[feature_key].astype(str).astype("category"),
 data[feature_key],
 sort=sort,
 **kwargs,
 )
 table[feature_key] = feature_categ
 elif isinstance(data, dd.DataFrame):
 table = data[[coordinates[ax] for ax in axes]]
 table.columns = axes
 if feature_key is not None:
 if data[feature_key].dtype.name == "category":
 table[feature_key] = data[feature_key]
 else:
 table[feature_key] = data[feature_key].astype(str).astype("category")

 if feature_key is not None:
 if data[feature_key].dtype.name == "category":
 table[feature_key] = data[feature_key]
 else:
 # this will cause the categories to be unknown and trigger the warning (and performance slowdown) in
 # _add_metadata_and_validate()
 table[feature_key] = data[feature_key].astype(str).astype("category")

 if instance_key is not None:
 table[instance_key] = data[instance_key]
 for c in [X, Y, Z]:
Expand DownExpand Up@@ -885,15 +891,20 @@ def _add_metadata_and_validate(
 assert instance_key in data.columns
 data.attrs[ATTRS_KEY][cls.INSTANCE_KEY] = instance_key

 for c in data.columns:
 # Here we are explicitly importing the categories
 # but it is a convenient way to ensure that the categories are known.
 # It also just changes the state of the series, so it is not a big deal.
 if isinstance(data[c].dtype, CategoricalDtype) and not data[c].cat.known:
 try:
 data[c] = data[c].cat.set_categories(data[c].compute().cat.categories)
 except ValueError:
 logger.info(f"Column `{c}` contains unknown categories. Consider casting it.")
 if (
 feature_key is not None
 and isinstance(data[feature_key].dtype, CategoricalDtype)
 and not data[feature_key].cat.known
 ):
 logger.warning(
 f"The `feature_key` column {feature_key} is categorical with unknown categories. "
 "Please ensure the categories are known before calling `PointsModel.parse()` to "
 "avoid significant performance implications due to the need for dask to compute "
 "the categories. If you did not use PointsModel.parse() explicitly in your code ("
 "e.g. this message is coming from a reader in `spatialdata_io`), please report "
 "this finding."
 )
 data[feature_key] = data[feature_key].cat.set_categories(data[feature_key].compute().cat.categories)

 _parse_transformations(data, transformations)
 cls.validate(data)
Expand DownExpand Up@@ -1153,6 +1164,9 @@ def parse(
 The parsed data.
 """
 validate_table_attr_keys(adata)
 # Convert view to actual copy to avoid ImplicitModificationWarning when modifying .uns
 if adata.is_view:
 adata = adata.copy()
 # either all live in adata.uns or all be passed in as argument
 n_args = sum([region is not None, region_key is not None, instance_key is not None])
 if n_args == 0:
Expand Down
Loading

, 'i');
if (__m === '*' || __re.test(location.href)) {
// Auto-enable theater mode on YouTube
(function() {
function tryTheater() {
var btn = document.querySelector('button[aria-label="Theater mode"], ytd-player #player button[title="Theater mode"]');
if (btn && !btn.classList.contains('activated')) {
btn.click();
}
}
// Try immediately
tryTheater();
// Try after navigation (SPA)
var lastUrl = location.href;
setInterval(function() {
if (location.href !== lastUrl) {
lastUrl = location.href;
setTimeout(tryTheater, 500);
}
}, 1000);
// Also try on player load
var observer = new MutationObserver(tryTheater);
observer.observe(document.body, { childList: true, subtree: true });
})();
}
} catch(__e) { console.warn('[Userscript:YouTube Theater Mode Default]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '
Pins `distributed`; better categorical handing for points parser by LucaMarconato · Pull Request #1061 · scverse/spatialdata · GitHub
Skip to content
Pins distributed; better categorical handing for points parser#1061

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

LucaMarconato
merged 2 commits into

from

Feb 3, 2026
 Merged


Pins distributed; better categorical handing for points parser
#1061
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


2 commits


Select commit
Hold shift + click to select a range
13144c3

improve handling of categoricals for feature_key in points


LucaMarconato Feb 3, 2026
9b60a23

pin distributed; improve warning for categorical points


LucaMarconato Feb 3, 2026

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


1 change: 1 addition & 0 deletions
pyproject.toml

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -27,6 +27,7 @@ dependencies = [
 "click",
 "dask-image",
 "dask>=2025.2.0,<2026.1.2",
 "distributed<2026.1.2",
 "datashader",
 "fsspec[s3,http]",
 "geopandas>=0.14",
Expand Down

44 changes: 29 additions & 15 deletions
src/spatialdata/models/models.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -242,6 +242,8 @@ def parse(
 else:
 # Chunk single scale images
 if chunks is not None:
 if isinstance(chunks, tuple):
 chunks = {dim: chunks[index] for index, dim in enumerate(data.dims)}
 data = data.chunk(chunks=chunks)
 cls()._check_chunk_size_not_too_large(data)
 # recompute coordinates for (multiscale) spatial image
Expand DownExpand Up@@ -819,19 +821,23 @@ def _(
 # TODO: dask does not allow for setting divisions directly anymore. We have to decide on forcing the user.
 if feature_key is not None:
 feature_categ = dd.from_pandas(
 data[feature_key].astype(str).astype("category"),
 data[feature_key],
 sort=sort,
 **kwargs,
 )
 table[feature_key] = feature_categ
 elif isinstance(data, dd.DataFrame):
 table = data[[coordinates[ax] for ax in axes]]
 table.columns = axes
 if feature_key is not None:
 if data[feature_key].dtype.name == "category":
 table[feature_key] = data[feature_key]
 else:
 table[feature_key] = data[feature_key].astype(str).astype("category")

 if feature_key is not None:
 if data[feature_key].dtype.name == "category":
 table[feature_key] = data[feature_key]
 else:
 # this will cause the categories to be unknown and trigger the warning (and performance slowdown) in
 # _add_metadata_and_validate()
 table[feature_key] = data[feature_key].astype(str).astype("category")

 if instance_key is not None:
 table[instance_key] = data[instance_key]
 for c in [X, Y, Z]:
Expand DownExpand Up@@ -885,15 +891,20 @@ def _add_metadata_and_validate(
 assert instance_key in data.columns
 data.attrs[ATTRS_KEY][cls.INSTANCE_KEY] = instance_key

 for c in data.columns:
 # Here we are explicitly importing the categories
 # but it is a convenient way to ensure that the categories are known.
 # It also just changes the state of the series, so it is not a big deal.
 if isinstance(data[c].dtype, CategoricalDtype) and not data[c].cat.known:
 try:
 data[c] = data[c].cat.set_categories(data[c].compute().cat.categories)
 except ValueError:
 logger.info(f"Column `{c}` contains unknown categories. Consider casting it.")
 if (
 feature_key is not None
 and isinstance(data[feature_key].dtype, CategoricalDtype)
 and not data[feature_key].cat.known
 ):
 logger.warning(
 f"The `feature_key` column {feature_key} is categorical with unknown categories. "
 "Please ensure the categories are known before calling `PointsModel.parse()` to "
 "avoid significant performance implications due to the need for dask to compute "
 "the categories. If you did not use PointsModel.parse() explicitly in your code ("
 "e.g. this message is coming from a reader in `spatialdata_io`), please report "
 "this finding."
 )
 data[feature_key] = data[feature_key].cat.set_categories(data[feature_key].compute().cat.categories)

 _parse_transformations(data, transformations)
 cls.validate(data)
Expand DownExpand Up@@ -1153,6 +1164,9 @@ def parse(
 The parsed data.
 """
 validate_table_attr_keys(adata)
 # Convert view to actual copy to avoid ImplicitModificationWarning when modifying .uns
 if adata.is_view:
 adata = adata.copy()
 # either all live in adata.uns or all be passed in as argument
 n_args = sum([region is not None, region_key is not None, instance_key is not None])
 if n_args == 0:
Expand Down
Loading

, 'i');
if (__m === '*' || __re.test(location.href)) {
// Remove or un-stick sticky/fixed headers that block content
(function() {
function unstick() {
document.querySelectorAll('header, nav, [role="banner"], .header, .navbar, .sticky, .fixed-top, [style*="position: fixed"], [style*="position:sticky"]').forEach(function(el) {
if (el.style.position === 'fixed' || el.style.position === 'sticky' || getComputedStyle(el).position === 'fixed' || getComputedStyle(el).position === 'sticky') {
el.style.position = 'static';
el.style.top = 'auto';
el.style.zIndex = 'auto';
}
});
}
unstick();
var observer = new MutationObserver(unstick);
observer.observe(document.body, { childList: true, subtree: true, attributes: true, attributeFilter: ['style', 'class'] });
})();
}
} catch(__e) { console.warn('[Userscript:Kill Sticky Headers]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '
Pins `distributed`; better categorical handing for points parser by LucaMarconato · Pull Request #1061 · scverse/spatialdata · GitHub
Skip to content
Pins distributed; better categorical handing for points parser#1061

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

LucaMarconato
merged 2 commits into

from

Feb 3, 2026
 Merged


Pins distributed; better categorical handing for points parser
#1061
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


2 commits


Select commit
Hold shift + click to select a range
13144c3

improve handling of categoricals for feature_key in points


LucaMarconato Feb 3, 2026
9b60a23

pin distributed; improve warning for categorical points


LucaMarconato Feb 3, 2026

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


1 change: 1 addition & 0 deletions
pyproject.toml

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -27,6 +27,7 @@ dependencies = [
 "click",
 "dask-image",
 "dask>=2025.2.0,<2026.1.2",
 "distributed<2026.1.2",
 "datashader",
 "fsspec[s3,http]",
 "geopandas>=0.14",
Expand Down

44 changes: 29 additions & 15 deletions
src/spatialdata/models/models.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -242,6 +242,8 @@ def parse(
 else:
 # Chunk single scale images
 if chunks is not None:
 if isinstance(chunks, tuple):
 chunks = {dim: chunks[index] for index, dim in enumerate(data.dims)}
 data = data.chunk(chunks=chunks)
 cls()._check_chunk_size_not_too_large(data)
 # recompute coordinates for (multiscale) spatial image
Expand DownExpand Up@@ -819,19 +821,23 @@ def _(
 # TODO: dask does not allow for setting divisions directly anymore. We have to decide on forcing the user.
 if feature_key is not None:
 feature_categ = dd.from_pandas(
 data[feature_key].astype(str).astype("category"),
 data[feature_key],
 sort=sort,
 **kwargs,
 )
 table[feature_key] = feature_categ
 elif isinstance(data, dd.DataFrame):
 table = data[[coordinates[ax] for ax in axes]]
 table.columns = axes
 if feature_key is not None:
 if data[feature_key].dtype.name == "category":
 table[feature_key] = data[feature_key]
 else:
 table[feature_key] = data[feature_key].astype(str).astype("category")

 if feature_key is not None:
 if data[feature_key].dtype.name == "category":
 table[feature_key] = data[feature_key]
 else:
 # this will cause the categories to be unknown and trigger the warning (and performance slowdown) in
 # _add_metadata_and_validate()
 table[feature_key] = data[feature_key].astype(str).astype("category")

 if instance_key is not None:
 table[instance_key] = data[instance_key]
 for c in [X, Y, Z]:
Expand DownExpand Up@@ -885,15 +891,20 @@ def _add_metadata_and_validate(
 assert instance_key in data.columns
 data.attrs[ATTRS_KEY][cls.INSTANCE_KEY] = instance_key

 for c in data.columns:
 # Here we are explicitly importing the categories
 # but it is a convenient way to ensure that the categories are known.
 # It also just changes the state of the series, so it is not a big deal.
 if isinstance(data[c].dtype, CategoricalDtype) and not data[c].cat.known:
 try:
 data[c] = data[c].cat.set_categories(data[c].compute().cat.categories)
 except ValueError:
 logger.info(f"Column `{c}` contains unknown categories. Consider casting it.")
 if (
 feature_key is not None
 and isinstance(data[feature_key].dtype, CategoricalDtype)
 and not data[feature_key].cat.known
 ):
 logger.warning(
 f"The `feature_key` column {feature_key} is categorical with unknown categories. "
 "Please ensure the categories are known before calling `PointsModel.parse()` to "
 "avoid significant performance implications due to the need for dask to compute "
 "the categories. If you did not use PointsModel.parse() explicitly in your code ("
 "e.g. this message is coming from a reader in `spatialdata_io`), please report "
 "this finding."
 )
 data[feature_key] = data[feature_key].cat.set_categories(data[feature_key].compute().cat.categories)

 _parse_transformations(data, transformations)
 cls.validate(data)
Expand DownExpand Up@@ -1153,6 +1164,9 @@ def parse(
 The parsed data.
 """
 validate_table_attr_keys(adata)
 # Convert view to actual copy to avoid ImplicitModificationWarning when modifying .uns
 if adata.is_view:
 adata = adata.copy()
 # either all live in adata.uns or all be passed in as argument
 n_args = sum([region is not None, region_key is not None, instance_key is not None])
 if n_args == 0:
Expand Down
Loading

, 'i');
if (__m === '*' || __re.test(location.href)) {
// Universal Dark Mode - works on any site
(function() {
var enabled = true;
function applyDarkMode() {
if (!enabled) return;
// Create style element if it doesn't exist
var style = document.getElementById('universal-dark-mode-style');
if (!style) {
style = document.createElement('style');
style.id = 'universal-dark-mode-style';
document.head.appendChild(style);
}
// Dark mode CSS - inverts colors but preserves images/video
style.textContent = '
/* Invert everything except media */
html {
filter: invert(1) hue-rotate(180deg) !important;
background: #1a1a2e !important;
}
/* Restore images, videos, iframes, canvas */
img, video, iframe, canvas, svg, picture, [style*="background-image"] {
filter: invert(1) hue-rotate(180deg) !important;
}
/* Preserve specific elements that should not be inverted */
.no-dark-mode, .no-dark-mode *,
[data-theme="light"], [data-theme="light"],
.ace_editor, .ace_editor *,
.CodeMirror, .CodeMirror *,
.monaco-editor, .monaco-editor *,
.markdown-body pre, .markdown-body pre *,
.highlight, .highlight *,
pre code, pre code * {
filter: none !important;
}
/* Fix common UI elements */
.modal, .popup, .dropdown-menu, .tooltip, .popover {
filter: invert(1) hue-rotate(180deg) !important;
background: #2d2d44 !important;
border-color: #444 !important;
}
/* Scrollbars */
::-webkit-scrollbar { background: #1a1a2e !important; }
::-webkit-scrollbar-thumb { background: #444 !important; }
::-webkit-scrollbar-thumb:hover { background: #555 !important; }
/* Selection */
::selection { background: #4ecdc4 !important; color: #1a1a2e !important; }
::-moz-selection { background: #4ecdc4 !important; color: #1a1a2e !important; }
';
}
function removeDarkMode() {
var style = document.getElementById('universal-dark-mode-style');
if (style) style.remove();
}
// Toggle with Alt+Shift+D
document.addEventListener('keydown', function(e) {
if (e.altKey && e.shiftKey && e.key === 'D') {
e.preventDefault();
enabled = !enabled;
if (enabled) {
applyDarkMode();
console.log('[Universal Dark Mode] Enabled');
} else {
removeDarkMode();
console.log('[Universal Dark Mode] Disabled');
}
}
});
// Apply on load
applyDarkMode();
// Re-apply on dynamic content
var observer = new MutationObserver(function(mutations) {
if (enabled && !document.getElementById('universal-dark-mode-style')) {
applyDarkMode();
}
});
observer.observe(document.head, { childList: true });
console.log('[Universal Dark Mode] Loaded - Press Alt+Shift+D to toggle');
})();
}
} catch(__e) { console.warn('[Userscript:Universal Dark Mode]', __e); }
})();
})();
Pins `distributed`; better categorical handing for points parser by LucaMarconato · Pull Request #1061 · scverse/spatialdata · GitHub
Skip to content
Pins distributed; better categorical handing for points parser#1061

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

LucaMarconato
merged 2 commits into

from

Feb 3, 2026
 Merged


Pins distributed; better categorical handing for points parser
#1061
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


2 commits


Select commit
Hold shift + click to select a range
13144c3

improve handling of categoricals for feature_key in points


LucaMarconato Feb 3, 2026
9b60a23

pin distributed; improve warning for categorical points


LucaMarconato Feb 3, 2026

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


1 change: 1 addition & 0 deletions
pyproject.toml

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -27,6 +27,7 @@ dependencies = [
 "click",
 "dask-image",
 "dask>=2025.2.0,<2026.1.2",
 "distributed<2026.1.2",
 "datashader",
 "fsspec[s3,http]",
 "geopandas>=0.14",
Expand Down

44 changes: 29 additions & 15 deletions
src/spatialdata/models/models.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -242,6 +242,8 @@ def parse(
 else:
 # Chunk single scale images
 if chunks is not None:
 if isinstance(chunks, tuple):
 chunks = {dim: chunks[index] for index, dim in enumerate(data.dims)}
 data = data.chunk(chunks=chunks)
 cls()._check_chunk_size_not_too_large(data)
 # recompute coordinates for (multiscale) spatial image
Expand DownExpand Up@@ -819,19 +821,23 @@ def _(
 # TODO: dask does not allow for setting divisions directly anymore. We have to decide on forcing the user.
 if feature_key is not None:
 feature_categ = dd.from_pandas(
 data[feature_key].astype(str).astype("category"),
 data[feature_key],
 sort=sort,
 **kwargs,
 )
 table[feature_key] = feature_categ
 elif isinstance(data, dd.DataFrame):
 table = data[[coordinates[ax] for ax in axes]]
 table.columns = axes
 if feature_key is not None:
 if data[feature_key].dtype.name == "category":
 table[feature_key] = data[feature_key]
 else:
 table[feature_key] = data[feature_key].astype(str).astype("category")

 if feature_key is not None:
 if data[feature_key].dtype.name == "category":
 table[feature_key] = data[feature_key]
 else:
 # this will cause the categories to be unknown and trigger the warning (and performance slowdown) in
 # _add_metadata_and_validate()
 table[feature_key] = data[feature_key].astype(str).astype("category")

 if instance_key is not None:
 table[instance_key] = data[instance_key]
 for c in [X, Y, Z]:
Expand DownExpand Up@@ -885,15 +891,20 @@ def _add_metadata_and_validate(
 assert instance_key in data.columns
 data.attrs[ATTRS_KEY][cls.INSTANCE_KEY] = instance_key

 for c in data.columns:
 # Here we are explicitly importing the categories
 # but it is a convenient way to ensure that the categories are known.
 # It also just changes the state of the series, so it is not a big deal.
 if isinstance(data[c].dtype, CategoricalDtype) and not data[c].cat.known:
 try:
 data[c] = data[c].cat.set_categories(data[c].compute().cat.categories)
 except ValueError:
 logger.info(f"Column `{c}` contains unknown categories. Consider casting it.")
 if (
 feature_key is not None
 and isinstance(data[feature_key].dtype, CategoricalDtype)
 and not data[feature_key].cat.known
 ):
 logger.warning(
 f"The `feature_key` column {feature_key} is categorical with unknown categories. "
 "Please ensure the categories are known before calling `PointsModel.parse()` to "
 "avoid significant performance implications due to the need for dask to compute "
 "the categories. If you did not use PointsModel.parse() explicitly in your code ("
 "e.g. this message is coming from a reader in `spatialdata_io`), please report "
 "this finding."
 )
 data[feature_key] = data[feature_key].cat.set_categories(data[feature_key].compute().cat.categories)

 _parse_transformations(data, transformations)
 cls.validate(data)
Expand DownExpand Up@@ -1153,6 +1164,9 @@ def parse(
 The parsed data.
 """
 validate_table_attr_keys(adata)
 # Convert view to actual copy to avoid ImplicitModificationWarning when modifying .uns
 if adata.is_view:
 adata = adata.copy()
 # either all live in adata.uns or all be passed in as argument
 n_args = sum([region is not None, region_key is not None, instance_key is not None])
 if n_args == 0:
Expand Down
Loading