机器学习如何从Python 2迁移到Python 3

from pathlib import Path

dataset = 'wiki_images'
datasets_root = Path('/path/to/datasets/') 
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

p.exists()
p.is_dir()
p.parts()
p.with_name('sibling.png') # only change the name, but keep the folder
p.with_suffix('.jpg') # only change the extension, but keep the folder and the name
p.chmod(mode)
p.rmdir()

def repeat_each_entry(data):
    """ Each entry in the data is doubled
    <blah blah nobody reads the documentation till the end>
    """
    index = numpy.repeat(numpy.arange(len(data)), 2)
        return data[index]

repeat_each_entry(pandas.Series(data=[0, 1, 2], index=[3, 4, 5])) # returns Series with Nones inside

def repeat_each_entry(data: Union[numpy.ndarray, bcolz.carray]):

@enforce.runtime_validation
def foo(text: str) -> None:
    print(text)

foo('Hi') # ok
foo(5)    # fails

@enforce.runtime_validation
def any2(x: List[bool]) -> bool:
        return any(x)

any ([False, False, True, False]) # True
any2([False, False, True, False]) # True

any (['False']) # True
any2(['False']) # fails

any ([False, None, "", 0]) # False
any2([False, None, "", 0]) # fails

# Python 3
from astropy import units as u
@u.quantity_input()
def frequency(speed: u.meter / u.s, wavelength: u.m) -> u.terahertz:
    return speed / wavelength
    
frequency(speed=300_000 * u.km / u.s, wavelength=555 * u.nm)
# output: 540.5405405405404 THz, frequency of green visible light

# l2-regularized linear regression: || AX - b ||^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(b))
# Python 3
X = np.linalg.inv(A.T @ A + alpha * np.eye(A.shape[1])) @ (A.T @ b)

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 3found_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='\t')
print(batch, epoch, loss, accuracy, time, sep='\t')

# 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)

# 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)
))

120  12 / 300  accuracy: 0.8180±0.4649 time: 56.60

# Python 3.6+

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}')

query = f"INSERT INTO STATION VALUES (13, '{city}', '{state}', {latitude}, {longitude})"

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

n_gifts = money // gift_price  # correct for int and float arguments

# All these comparisons are illegal in Python 3
3 < '3'
2 < None(3, 4) < (3, None)
(4, 5) < [4, 5]

# False in both Python 2 and Python 3
(4, 5) == [4, 5]

sorted([2, '1', 3])  # invalid for Python 3, in Python 2 returns [2, 3, '1']

if a is not None:
  pass
if a: # WRONG check for None
  pass

s = '您好'
print(len(s))
print(s[: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)

# Python 2
import cPickle as pickle
import numpy
print len(pickle.dumps(numpy.random.normal(size=[1000, 1000])))
# result: 23691675

# Python 3
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 3

# 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)

model = sklearn.svm.SVC(2, 'poly', 2, 4, 0.5)

class SVC(BaseSVC):
    def __init__(self, *, C=1.0, kernel='rbf', degree=3, gamma='auto', coef0=0.0, ... )

# Python 3

math.inf # 'largest' number
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

map(lambda x, (y, z): x, z, dict.items())

{x:z for x, (y, z) in d.items()}