from pathlib import Path
dataset = 'wiki_images'
datasets_root = Path('/path/to/datasets/')
#Navigating inside a directory tree,use:/
train_path = datasets_root / dataset / 'train'
test_path = datasets_root / dataset / 'test'
for image_path in train_path.iterdir():
 with image_path.open() as f: # note, open is a method of Path object
  # do something with an image

from pathlib import Path
a = Path("/data")
b = "test"
c = a / b
print(c)
print(c.exists()) # 路径是否存在
print(c.is_dir()) # 判断是否为文件夹
print(c.parts) # 分离路径
print(c.with_name('sibling.png')) # 只修改拓展名, 不会修改源文件
print(c.with_suffix('.jpg')) # 只修改拓展名, 不会修改源文件
c.chmod(777) # 修改目录权限
c.rmdir() # 删除目录

import enforce
@enforce.runtime_validation
def foo(text: str) -> None:
 print(text)
foo('Hi') # ok
foo(5) # fails

Hi
Traceback (most recent call last):
 File "/Users/chennan/pythonproject/dataanalysis/e.py", line 10, in <module>
 foo(5) # fails
 File "/Users/chennan/Desktop/2019/env/lib/python3.6/site-packages/enforce/decorators.py", line 104, in universal
 _args, _kwargs, _ = enforcer.validate_inputs(parameters)
 File "/Users/chennan/Desktop/2019/env/lib/python3.6/site-packages/enforce/enforcers.py", line 86, in validate_inputs
 raise RuntimeTypeError(exception_text)
enforce.exceptions.RuntimeTypeError: 
 The following runtime type errors were encountered:
  Argument 'text' was not of type <class 'str'>. Actual type was int.

# l2-regularized linear regression: || AX - y ||^2 + alpha * ||x||^2 -> min
# Python 2
X = np.linalg.inv(np.dot(A.T, A) + alpha * np.eye(A.shape[1])).dot(A.T.dot(y))
# Python 3
X = np.linalg.inv(A.T @ A + alpha * np.eye(A.shape[1])) @ (A.T @ y)

import glob
# Python 2
found_images = (
 glob.glob('/path/*.jpg')
 + glob.glob('/path/*/*.jpg')
 + glob.glob('/path/*/*/*.jpg')
 + glob.glob('/path/*/*/*/*.jpg')
 + glob.glob('/path/*/*/*/*/*.jpg'))
# Python 3
found_images = glob.glob('/path/**/*.jpg', recursive=True)

# Python 3
import pathlib
import glob
found_images = pathlib.Path('/path/').glob('**/*.jpg')

print sys.stderr, "critical error"  # Python 2
print("critical error", file=sys.stderr) # Python 3

# Python 3
print(*array, sep=' ')
print(batch, epoch, loss, accuracy, time, sep=' ')

# Python 3
_print = print # store the original print function
def print(*args, **kargs):
 pass # do something useful, e.g. store output to some file

@contextlib.contextmanager
def replace_print():
 import builtins
 _print = print # saving old print function
 # or use some other function here
 builtins.print = lambda *args, **kwargs: _print('new printing', *args, **kwargs)
 yield
 builtins.print = _print
with replace_print():
 <code here will invoke other print function>

# Python 3
result = process(x) if is_valid(x) else print('invalid item: ', x)

# grouping decimal numbers by thousands
one_million = 1_000_000
# grouping hexadecimal addresses by words
addr = 0xCAFE_F00D
# grouping bits into nibbles in a binary literal
flags = 0b_0011_1111_0100_1110
# same, for string conversions
flags = int('0b_1111_0000', 2)

# Python 2
print '{batch:3} {epoch:3} / {total_epochs:3} accuracy: {acc_mean:0.4f}±{acc_std:0.4f} time: {avg_time:3.2f}'.format(
 batch=batch, epoch=epoch, total_epochs=total_epochs,
 acc_mean=numpy.mean(accuracies), acc_std=numpy.std(accuracies),
 avg_time=time / len(data_batch)
)
# Python 2 (too error-prone during fast modifications, please avoid):
print '{:3} {:3} / {:3} accuracy: {:0.4f}±{:0.4f} time: {:3.2f}'.format(
 batch, epoch, total_epochs, numpy.mean(accuracies), numpy.std(accuracies),
 time / len(data_batch)
)

print(f'{batch:3} {epoch:3} / {total_epochs:3} accuracy: {numpy.mean(accuracies):0.4f}±{numpy.std(accuracies):0.4f} time: {time / len(data_batch):3.2f}')

data = pandas.read_csv('timing.csv')
velocity = data['distance'] / data['time']

n_gifts = money // gift_price # correct for int and float arguments
nutshell
> from operator import truediv, floordiv
> truediv.__doc__, floordiv.__doc__
('truediv(a, b) -- Same as a / b.', 'floordiv(a, b) -- Same as a // b.')
> (3 / 2), (3 // 2), (3.0 // 2.0)
(1.5, 1, 1.0)

3 < '3'
2 < None
(3, 4) < (3, None)
(4, 5) < [4, 5]

if a is not None:
 pass
if a: # WRONG check for None
 pass
NLP Unicode问题
s = '您好'
print(len(s))
print(s[:2])

Python 2: 6
Python 3: 2

x = u'со'
x += 'co' # ok
x += 'со' # fail

'a' < type < u'a' # Python 2: True
'a' < u'a'     # Python 2: False

from collections import Counter
Counter('Möbelstück')

import json
x = {str(i):i for i in range(5)}
json.loads(json.dumps(x))
# Python 2
{u'1': 1, u'0': 0, u'3': 3, u'2': 2, u'4': 4}
# Python 3
{'0': 0, '1': 1, '2': 2, '3': 3, '4': 4}

from torch import nn
# Python 2
model = nn.Sequential(OrderedDict([
     ('conv1', nn.Conv2d(1,20,5)),
     ('relu1', nn.ReLU()),
     ('conv2', nn.Conv2d(20,64,5)),
     ('relu2', nn.ReLU())
    ]))

# Python 3.6+, how it *can* be done, not supported right now in pytorch
model = nn.Sequential(
  conv1=nn.Conv2d(1,20,5),
  relu1=nn.ReLU(),
  conv2=nn.Conv2d(20,64,5),
  relu2=nn.ReLU())
)

# handy when amount of additional stored info may vary between experiments, but the same code can be used in all cases
model_paramteres, optimizer_parameters, *other_params = load(checkpoint_name)
# picking two last values from a sequence
*prev, next_to_last, last = values_history
# This also works with any iterables, so if you have a function that yields e.g. qualities,
# below is a simple way to take only last two values from a list
*prev, next_to_last, last = iter_train(args)

import cPickle as pickle
import numpy
print len(pickle.dumps(numpy.random.normal(size=[1000, 1000])))
# result: 23691675
Python3
import pickle
import numpy
len(pickle.dumps(numpy.random.normal(size=[1000, 1000])))
# result: 8000162

labels = <initial_value>
predictions = [model.predict(data) for data, labels in dataset]
# labels are overwritten in Python 2
# labels are not affected by comprehension in Python 

# Python 2
class MySubClass(MySuperClass):
  def __init__(self, name, **options):
    super(MySubClass, self).__init__(name='subclass', **options)
# Python 3
class MySubClass(MySuperClass):
  def __init__(self, name, **options):
    super().__init__(name='subclass', **options)

x = dict(a=1, b=2)
y = dict(b=3, d=4)
# Python 3.5+
z = {**x, **y}
# z = {'a': 1, 'b': 3, 'd': 4}, note that value for `b` is taken from the latter dict.

[*a, *b, *c] # list, concatenating
(*a, *b, *c) # tuple, concatenating
{*a, *b, *c} # set, union

# Python 3.5+
do_something(**{**default_settings, **custom_settings})
# Also possible, this code also checks there is no intersection between keys of dictionaries
do_something(**first_args, **second_args)
Data classes

@dataclass
class Person:
  name: str
  age: int
@dataclass
class Coder(Person):
  preferred_language: str = 'Python 3'

# nprandom.py
import numpy
__random_state = numpy.random.RandomState()
def __getattr__(name):
  return getattr(__random_state, name)
def __dir__():
  return dir(__random_state)
def seed(seed):
  __random_state = numpy.random.RandomState(seed=seed)

# Python 3.7+, not all IDEs support this at the moment
foo()
breakpoint()
bar()

# Python 3
math.inf # Infinite float
math.nan # not a number
max_quality = -math.inf # no more magic initial values!
for model in trained_models:
  max_quality = max(max_quality, compute_quality(model, data))

isinstance(x, numbers.Integral) # Python 2, the canonical way
isinstance(x, (long, int))   # Python 2
isinstance(x, int)       # Python 3, easier to remember