def _load_data(self, data_locator):
# as of AnnData 0.6.19, backed mode performs initial load fast, but at the
# cost of significantly slower access to X data.
try:
# there is no guarantee data_locator indicates a local file. The AnnData
# API will only consume local file objects. If we get a non-local object,
# make a copy in tmp, and delete it after we load into memory.
with data_locator.local_handle() as lh:
# as of AnnData 0.6.19, backed mode performs initial load fast, but at the
# cost of significantly slower access to X data.
backed = 'r' if self.config['backed'] else None
self.data = anndata.read_h5ad(lh, backed=backed)
except ValueError:
raise ScanpyFileError(
"File must be in the .h5ad format. Please read "
"https://github.com/theislab/scanpy_usage/blob/master/170505_seurat/info_h5ad.md to "
"learn more about this format. You may be able to convert your file into this format "
"using `cellxgene prepare`, please run `cellxgene prepare --help` for more "
"information."
)
except MemoryError:
raise ScanpyFileError("Out of memory - file is too large for available memory.")
except Exception as e:
raise ScanpyFileError(
f"{e} - file not found or is inaccessible. File must be an .h5ad object. "
f"Please check your input and try again."
)
def annotation_put_fbs(self, axis, fbs, uid=None, collection=None):
if not self.config["annotations"]:
raise DisabledFeatureError("Writable annotations are not enabled")
fname = self.get_anno_fname(uid, collection)
if not fname:
raise ScanpyFileError("Writable annotations - unable to determine file name for annotations")
if axis != Axis.OBS:
raise ValueError("Only OBS dimension access is supported")
new_label_df = decode_matrix_fbs(fbs)
if not new_label_df.empty:
new_label_df.index = self.original_obs_index
self._validate_label_data(new_label_df) # paranoia
# if any of the new column labels overlap with our existing labels, raise error
duplicate_columns = list(set(new_label_df.columns) & set(self.data.obs.columns))
if not new_label_df.columns.is_unique or len(duplicate_columns) > 0:
raise KeyError(f"Labels file may not contain column names which overlap "
f"with h5ad obs columns {duplicate_columns}")
# update our internal state and save it. Multi-threading often enabled,
# so treat this as a critical section.
with self.label_lock:
lastmod = self.data_locator.lastmodtime()
lastmodstr = "'unknown'" if lastmod is None else lastmod.isoformat(timespec="seconds")
header = f"# Annotations generated on {datetime.now().isoformat(timespec='seconds')} " \
f"using cellxgene version {cellxgene_version}\n" \
f"# Input data file was {self.data_locator.uri_or_path}, " \
f"which was last modified on {lastmodstr}\n"
write_labels(fname, new_label_df, header, backup_dir=self.get_anno_backup_dir(uid, collection))
return jsonify_scanpy({"status": "OK"})
def _load_data(data):
# Based on benchmarking, cache=True has no impact on perf.
# Note: as of current scanpy/anndata release, setting backed='r' will
# result in an error. https://github.com/theislab/anndata/issues/79
try:
result = sc.read(data, cache=True)
except ValueError:
raise ScanpyFileError(
"File must be in the .h5ad format. Please read "
"https://github.com/theislab/scanpy_usage/blob/master/170505_seurat/info_h5ad.md to "
"learn more about this format. You may be able to convert your file into this format "
"using `cellxgene prepare`, please run `cellxgene prepare --help` for more "
"information.")
except Exception as e:
raise ScanpyFileError(
f"Error while loading file: {e}, File must be in the .h5ad format, please check "
f"that your input and try again.")
return result
def _load_data(self, data):
# as of AnnData 0.6.19, backed mode performs initial load fast, but at the
# cost of significantly slower access to X data.
try:
self.data = anndata.read_h5ad(data)
except ValueError:
raise ScanpyFileError(
"File must be in the .h5ad format. Please read "
"https://github.com/theislab/scanpy_usage/blob/master/170505_seurat/info_h5ad.md to "
"learn more about this format. You may be able to convert your file into this format "
"using `cellxgene prepare`, please run `cellxgene prepare --help` for more "
"information.")
except MemoryError:
raise ScanpyFileError(
"Error while loading file: out of memory, file is too large"
" for memory available")
except Exception as e:
raise ScanpyFileError(
f"Error while loading file: {e}, File must be in the .h5ad format, please check "
f"that your input and try again.")
def annotation_to_fbs_matrix(self, axis, fields=None, uid=None, collection=None):
if axis == Axis.OBS:
if self.config["annotations"]:
try:
labels = read_labels(self.get_anno_fname(uid, collection))
except Exception as e:
raise ScanpyFileError(
f"Error while loading label file: {e}, File must be in the .csv format, please check "
f"your input and try again."
)
else:
labels = None
if labels is not None and not labels.empty:
df = self.data.obs.join(labels, self.config['obs_names'])
else:
df = self.data.obs
else:
df = self.data.var
if fields is not None and len(fields) > 0:
df = df[fields]
return encode_matrix_fbs(df, col_idx=df.columns)