You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

103 lines
3.3 KiB

import contextlib
import glob
import os
import urllib
from datetime import datetime
from pathlib import Path
from zipfile import ZipFile
import yaml
class WorkingDirectory(contextlib.ContextDecorator):
# Usage: @WorkingDirectory(dir) decorator or 'with WorkingDirectory(dir):' context manager
def __init__(self, new_dir):
self.dir = new_dir # new dir
self.cwd = Path.cwd().resolve() # current dir
def __enter__(self):
os.chdir(self.dir)
def __exit__(self, exc_type, exc_val, exc_tb):
os.chdir(self.cwd)
def increment_path(path, exist_ok=False, sep='', mkdir=False):
"""
Increment file or directory path, i.e. runs/exp --> runs/exp{sep}2, runs/exp{sep}3, ... etc.
# TODO: docs
"""
path = Path(path) # os-agnostic
if path.exists() and not exist_ok:
path, suffix = (path.with_suffix(''), path.suffix) if path.is_file() else (path, '')
# Method 1
for n in range(2, 9999):
p = f'{path}{sep}{n}{suffix}' # increment path
if not os.path.exists(p): #
break
path = Path(p)
if mkdir:
path.mkdir(parents=True, exist_ok=True) # make directory
return path
def yaml_save(file='data.yaml', data=None):
# Single-line safe yaml saving
with open(file, 'w') as f:
yaml.safe_dump({k: str(v) if isinstance(v, Path) else v for k, v in data.items()}, f, sort_keys=False)
def yaml_load(file='data.yaml'):
# Single-line safe yaml loading
with open(file, errors='ignore') as f:
return {**yaml.safe_load(f), 'yaml_file': file} # add YAML filename to dict and return
def unzip_file(file, path=None, exclude=('.DS_Store', '__MACOSX')):
# Unzip a *.zip file to path/, excluding files containing strings in exclude list
if path is None:
path = Path(file).parent # default path
with ZipFile(file) as zipObj:
for f in zipObj.namelist(): # list all archived filenames in the zip
if all(x not in f for x in exclude):
zipObj.extract(f, path=path)
def file_age(path=__file__):
# Return days since last file update
dt = (datetime.now() - datetime.fromtimestamp(Path(path).stat().st_mtime)) # delta
return dt.days # + dt.seconds / 86400 # fractional days
def file_date(path=__file__):
# Return human-readable file modification date, i.e. '2021-3-26'
t = datetime.fromtimestamp(Path(path).stat().st_mtime)
return f'{t.year}-{t.month}-{t.day}'
def file_size(path):
# Return file/dir size (MB)
mb = 1 << 20 # bytes to MiB (1024 ** 2)
path = Path(path)
if path.is_file():
return path.stat().st_size / mb
elif path.is_dir():
return sum(f.stat().st_size for f in path.glob('**/*') if f.is_file()) / mb
else:
return 0.0
def url2file(url):
# Convert URL to filename, i.e. https://url.com/file.txt?auth -> file.txt
url = str(Path(url)).replace(':/', '://') # Pathlib turns :// -> :/
return Path(urllib.parse.unquote(url)).name.split('?')[0] # '%2F' to '/', split https://url.com/file.txt?auth
def get_latest_run(search_dir='.'):
# Return path to most recent 'last.pt' in /runs (i.e. to --resume from)
last_list = glob.glob(f'{search_dir}/**/last*.pt', recursive=True)
return max(last_list, key=os.path.getctime) if last_list else ''