mirror of
https://github.com/chanzuckerberg/cellxgene.git
synced 2026-09-15 20:57:56 +08:00
f3015cb9df
* Fix Makefile whitespace and .PHONY use
* Fix Makefile filename
* Modularize Makefile into client and server Makefiles
Part of the reason that the Makefile in the root directory is a bit
complicated is that it tries to handle tasks that can be handled
separately in the client and server modules.
This commit pushes some of the make logic specific to each module into
their own makefiles and calls out to those makefiles from that in the
project root.
* Add auto-formatting to client and server modules
One thing that can make linting faster is auto-formatting. This commit
adds the yapf auto-formatting tool to the server module and uses
eslint's "fix" functionality to speed up the linting/formatting process.
* Add yapf for automatic code formatting
* Add a root test target that calls sub-tests
* Apply yapf to python files
* Do not duplicate npm commands, simply pass through
* Update documentation
* Do not shadow reserved word len
* Add general test target
* Fix make call in dev-env
* Use black instead of yapf
* Run flake8 from the root directory
* Revert "Apply yapf to python files"
This reverts commit cdca128a01.
* Apply black to python code
* Resolve lint errors resulting from black format
* Add explanation of server unit tests in dev guidelines
62 lines
1.9 KiB
Python
62 lines
1.9 KiB
Python
"""
|
|
Helpers for user annotations
|
|
"""
|
|
import os
|
|
import os.path
|
|
from datetime import datetime
|
|
import pandas as pd
|
|
|
|
|
|
def read_labels(fname):
|
|
if fname is not None and os.path.exists(fname) and os.path.getsize(fname) > 0:
|
|
return pd.read_csv(fname, dtype="category", index_col=0, header=0, comment="#")
|
|
else:
|
|
return pd.DataFrame()
|
|
|
|
|
|
def write_labels(fname, df, header=None, backup_dir=None):
|
|
if backup_dir is not None:
|
|
backup(fname, backup_dir)
|
|
# rotate_fname(fname, backup_dir)
|
|
if not df.empty:
|
|
with open(fname, "w", newline="") as f:
|
|
if header is not None:
|
|
f.write(header)
|
|
df.to_csv(f)
|
|
else:
|
|
open(fname, "w").close()
|
|
|
|
|
|
def backup(fname, backup_dir, max_backups=9):
|
|
"""
|
|
save N backups of file to backup_dir.
|
|
1. fname -> backup_dir/fname-TIME
|
|
2. delete excess files in backup_dir
|
|
"""
|
|
|
|
# Make sure there is work to do
|
|
if not os.path.exists(fname):
|
|
return
|
|
|
|
# Ensure backup_dir exists
|
|
if not os.path.exists(backup_dir):
|
|
os.mkdir(backup_dir)
|
|
|
|
# Save current file to backup_dir
|
|
fname_base = os.path.basename(fname)
|
|
fname_base_root, fname_base_ext = os.path.splitext(fname_base)
|
|
# don't use ISO standard time format, as it contains characters illegal on some filesytems.
|
|
nowish = datetime.now().strftime("%Y-%m-%dT%H-%M-%S")
|
|
backup_fname = os.path.join(backup_dir, f"{fname_base_root}-{nowish}{fname_base_ext}")
|
|
if os.path.exists(backup_fname):
|
|
os.remove(backup_fname)
|
|
os.rename(fname, backup_fname)
|
|
|
|
# prune the backup_dir to max number of backup files, keeping the most recent backups
|
|
backups = list(filter(lambda s: s.startswith(fname_base_root), os.listdir(backup_dir)))
|
|
excess_count = len(backups) - max_backups
|
|
if excess_count > 0:
|
|
backups.sort()
|
|
for bu in backups[0:excess_count]:
|
|
os.remove(os.path.join(backup_dir, bu))
|