HassanSamo/Mistral7b-instruc-v2-python
Text Generation
•
Updated
•
2
text
stringlengths 185
26.5k
|
|---|
<s>[INST] What does the "yield" keyword do? What is the use of the yield keyword in Python? What does it do?
For example, I'm trying to understand this code1:
def _get_child_candidates(self, distance, min_dist, max_dist):
if self._leftchild and distance - max_dist < self._median:
yield self._leftchild
if self._rightchild and distance + max_dist >= self._median:
yield self._rightchild
And this is the caller:
result, candidates = list(), [self]
while candidates:
node = candidates.pop()
distance = node._get_dist(obj)
if distance <= max_dist and distance >= min_dist:
result.extend(node._values)
candidates.extend(node._get_child_candidates(distance, min_dist, max_dist))
return result
What happens when the method _get_child_candidates is called?
A list is returned? A single element is returned? Is it called again? When will subsequent calls stop?
1. The code comes from Jochen Schulz (jrschulz), who made a great Python library for metric spaces. This is the link to the complete source: Module mspace.
[/INST] To understand what yield does, you must understand what generators are. And before generators come iterables.
Iterables
When you create a list, you can read its items one by one. Reading its items one by one is called iteration:
>>> mylist = [1, 2, 3]
>>> for i in mylist:
... print(i)
1
2
3
mylist is an iterable. When you use a list comprehension, you create a list, and so an iterable:
>>> mylist = [x*x for x in range(3)]
>>> for i in mylist:
... print(i)
0
1
4
Everything you can use "for... in..." on is an iterable; lists, strings, files...
These iterables are handy because you can read them as much as you wish, but you store all the values in memory and this is not always what you want when you have a lot of values.
Generators
Generators are iterators, but you can only iterate over them once. It's because they do not store all the values in memory, they generate the values on the fly:
>>> mygenerator = (x*x for x in range(3))
>>> for i in mygenerator:
... print(i)
0
1
4
It is just the same except you used () instead of []. BUT, you cannot perform for i in mygenerator a second time since generators can only be used once: they calculate 0, then forget about it and calculate 1, and end calculating 4, one by one.
Yield
Yield is a keyword that is used like return, except the function will return a generator.
>>> def createGenerator():
... mylist = range(3)
... for i in mylist:
... yield i*i
...
>>> mygenerator = createGenerator() # create a generator
>>> print(mygenerator) # mygenerator is an object!
<generator object createGenerator at 0xb7555c34>
>>> for i in mygenerator:
... print(i)
0
1
4
Here it's a useless example, but it's handy when you know your function will return a huge set of values that you will only need to read once.
To master yield, you must understand that when you call the function, the code you have written in the function body does not run. The function only returns the generator object, this is a bit tricky :-)
Then, your code will be run each time the for uses the generator.
Now the hard part:
The first time the for calls the generator object created from your function, it will run the code in your function from the beginning until it hits yield, then it'll return the first value of the loop. Then, each other call will run the loop you have written in the function one more time, and return the next value, until there is no value to return.
The generator is considered empty once the function runs but does not hit yield anymore. It can be because the loop had come to an end, or because you do not satisfy an "if/else" anymore.
Your code explained
Generator:
# Here you create the method of the node object that will return the generator
def node._get_child_candidates(self, distance, min_dist, max_dist):
# Here is the code that will be called each time you use the generator object:
# If there is still a child of the node object on its left
# AND if distance is ok, return the next child
if self._leftchild and distance - max_dist < self._median:
yield self._leftchild
# If there is still a child of the node object on its right
# AND if distance is ok, return the next child
if self._rightchild and distance + max_dist >= self._median:
yield self._rightchild
# If the function arrives here, the generator will be considered empty
# there is no more than two values: the left and the right children
Caller:
# Create an empty list and a list with the current object reference
result, candidates = list(), [self]
# Loop on candidates (they contain only one element at the beginning)
while candidates:
# Get the last candidate and remove it from the list
node = candidates.pop()
# Get the distance between obj and the candidate
distance = node._get_dist(obj)
# If distance is ok, then you can fill the result
if distance <= max_dist and distance >= min_dist:
result.extend(node._values)
# Add the children of the candidate in the candidates list
# so the loop will keep running until it will have looked
# at all the children of the children of the children, etc. of the candidate
candidates.extend(node._get_child_candidates(distance, min_dist, max_dist))
return result
This code contains several smart parts:
The loop iterates on a list but the list expands while the loop is being iterated :-) It's a concise way to go through all these nested data even if it's a bit dangerous since you can end up with an infinite loop. In this case, candidates.extend(node._get_child_candidates(distance, min_dist, max_dist)) exhausts all the values of the generator, but while keeps creating new generator objects which will produce different values from the previous ones since it's not applied on the same node.
The extend() method is a list object method that expects an iterable and adds its values to the list.
Usually we pass a list to it:
>>> a = [1, 2]
>>> b = [3, 4]
>>> a.extend(b)
>>> print(a)
[1, 2, 3, 4]
But in your code it gets a generator, which is good because:
You don't need to read the values twice.
You may have a lot of children and you don't want them all stored in memory.
And it works because Python does not care if the argument of a method is a list or not. Python expects iterables so it will work with strings, lists, tuples and generators! This is called duck typing and is one of the reason why Python is so cool. But this is another story, for another question...
You can stop here, or read a little bit to see an advanced use of a generator:
Controlling a generator exhaustion
>>> class Bank(): # let's create a bank, building ATMs
... crisis = False
... def create_atm(self):
... while not self.crisis:
... yield "$100"
>>> hsbc = Bank() # when everything's ok the ATM gives you as much as you want
>>> corner_street_atm = hsbc.create_atm()
>>> print(corner_street_atm.next())
$100
>>> print(corner_street_atm.next())
$100
>>> print([corner_street_atm.next() for cash in range(5)])
['$100', '$100', '$100', '$100', '$100']
>>> hsbc.crisis = True # crisis is coming, no more money!
>>> print(corner_street_atm.next())
<type 'exceptions.StopIteration'>
>>> wall_street_atm = hsbc.create_atm() # it's even true for new ATMs
>>> print(wall_street_atm.next())
<type 'exceptions.StopIteration'>
>>> hsbc.crisis = False # trouble is, even post-crisis the ATM remains empty
>>> print(corner_street_atm.next())
<type 'exceptions.StopIteration'>
>>> brand_new_atm = hsbc.create_atm() # build a new one to get back in business
>>> for cash in brand_new_atm:
... print cash
$100
$100
$100
$100
$100
$100
$100
$100
$100
...
It can be useful for various things like controlling access to a resource.
Itertools, your best friend
The itertools module contains special functions to manipulate iterables. Ever wish to duplicate a generator?
Chain two generators? Group values in a nested list with a one liner? Map / Zip without creating another list?
Then just import itertools.
An example? Let's see the possible orders of arrival for a 4 horse race:
>>> horses = [1, 2, 3, 4]
>>> races = itertools.permutations(horses)
>>> print(races)
<itertools.permutations object at 0xb754f1dc>
>>> print(list(itertools.permutations(horses)))
[(1, 2, 3, 4),
(1, 2, 4, 3),
(1, 3, 2, 4),
(1, 3, 4, 2),
(1, 4, 2, 3),
(1, 4, 3, 2),
(2, 1, 3, 4),
(2, 1, 4, 3),
(2, 3, 1, 4),
(2, 3, 4, 1),
(2, 4, 1, 3),
(2, 4, 3, 1),
(3, 1, 2, 4),
(3, 1, 4, 2),
(3, 2, 1, 4),
(3, 2, 4, 1),
(3, 4, 1, 2),
(3, 4, 2, 1),
(4, 1, 2, 3),
(4, 1, 3, 2),
(4, 2, 1, 3),
(4, 2, 3, 1),
(4, 3, 1, 2),
(4, 3, 2, 1)]
Understanding the inner mechanisms of iteration
Iteration is a process implying iterables (implementing the __iter__() method) and iterators (implementing the __next__() method).
Iterables are any objects you can get an iterator from. Iterators are objects that let you iterate on iterables.
More about it in this article about how does the for loop work.
</s> |
<s>[INST] What is a metaclass in Python? What are metaclasses? What do you use them for?
[/INST] Classes as objects
Before understanding metaclasses, you need to master classes in Python. And Python has a very peculiar idea of what classes are, borrowed from the Smalltalk language.
In most languages, classes are just pieces of code that describe how to produce an object. That's kinda true in Python too:
>>> class ObjectCreator(object):
... pass
...
>>> my_object = ObjectCreator()
>>> print(my_object)
<__main__.ObjectCreator object at 0x8974f2c>
But classes are more than that in Python. Classes are objects too.
Yes, objects.
As soon as you use the keyword class, Python executes it and creates
an OBJECT. The instruction
>>> class ObjectCreator(object):
... pass
...
creates in memory an object with the name "ObjectCreator".
This object (the class) is itself capable of creating objects (the instances),
and this is why it's a class.
But still, it's an object, and therefore:
you can assign it to a variable
you can copy it
you can add attributes to it
you can pass it as a function parameter
e.g.:
>>> print(ObjectCreator) # you can print a class because it's an object
<class '__main__.ObjectCreator'>
>>> def echo(o):
... print(o)
...
>>> echo(ObjectCreator) # you can pass a class as a parameter
<class '__main__.ObjectCreator'>
>>> print(hasattr(ObjectCreator, 'new_attribute'))
False
>>> ObjectCreator.new_attribute = 'foo' # you can add attributes to a class
>>> print(hasattr(ObjectCreator, 'new_attribute'))
True
>>> print(ObjectCreator.new_attribute)
foo
>>> ObjectCreatorMirror = ObjectCreator # you can assign a class to a variable
>>> print(ObjectCreatorMirror.new_attribute)
foo
>>> print(ObjectCreatorMirror())
<__main__.ObjectCreator object at 0x8997b4c>
Creating classes dynamically
Since classes are objects, you can create them on the fly, like any object.
First, you can create a class in a function using class:
>>> def choose_class(name):
... if name == 'foo':
... class Foo(object):
... pass
... return Foo # return the class, not an instance
... else:
... class Bar(object):
... pass
... return Bar
...
>>> MyClass = choose_class('foo')
>>> print(MyClass) # the function returns a class, not an instance
<class '__main__.Foo'>
>>> print(MyClass()) # you can create an object from this class
<__main__.Foo object at 0x89c6d4c>
But it's not so dynamic, since you still have to write the whole class yourself.
Since classes are objects, they must be generated by something.
When you use the class keyword, Python creates this object automatically. But as
with most things in Python, it gives you a way to do it manually.
Remember the function type? The good old function that lets you know what
type an object is:
>>> print(type(1))
<type 'int'>
>>> print(type("1"))
<type 'str'>
>>> print(type(ObjectCreator))
<type 'type'>
>>> print(type(ObjectCreator()))
<class '__main__.ObjectCreator'>
Well, type has a completely different ability, it can also create classes on the fly. type can take the description of a class as parameters,
and return a class.
(I know, it's silly that the same function can have two completely different uses according to the parameters you pass to it. It's an issue due to backwards
compatibility in Python)
type works this way:
type(name of the class,
tuple of the parent class (for inheritance, can be empty),
dictionary containing attributes names and values)
e.g.:
>>> class MyShinyClass(object):
... pass
can be created manually this way:
>>> MyShinyClass = type('MyShinyClass', (), {}) # returns a class object
>>> print(MyShinyClass)
<class '__main__.MyShinyClass'>
>>> print(MyShinyClass()) # create an instance with the class
<__main__.MyShinyClass object at 0x8997cec>
You'll notice that we use "MyShinyClass" as the name of the class
and as the variable to hold the class reference. They can be different,
but there is no reason to complicate things.
type accepts a dictionary to define the attributes of the class. So:
>>> class Foo(object):
... bar = True
Can be translated to:
>>> Foo = type('Foo', (), {'bar':True})
And used as a normal class:
>>> print(Foo)
<class '__main__.Foo'>
>>> print(Foo.bar)
True
>>> f = Foo()
>>> print(f)
<__main__.Foo object at 0x8a9b84c>
>>> print(f.bar)
True
And of course, you can inherit from it, so:
>>> class FooChild(Foo):
... pass
would be:
>>> FooChild = type('FooChild', (Foo,), {})
>>> print(FooChild)
<class '__main__.FooChild'>
>>> print(FooChild.bar) # bar is inherited from Foo
True
Eventually you'll want to add methods to your class. Just define a function
with the proper signature and assign it as an attribute.
>>> def echo_bar(self):
... print(self.bar)
...
>>> FooChild = type('FooChild', (Foo,), {'echo_bar': echo_bar})
>>> hasattr(Foo, 'echo_bar')
False
>>> hasattr(FooChild, 'echo_bar')
True
>>> my_foo = FooChild()
>>> my_foo.echo_bar()
True
And you can add even more methods after you dynamically create the class, just like adding methods to a normally created class object.
>>> def echo_bar_more(self):
... print('yet another method')
...
>>> FooChild.echo_bar_more = echo_bar_more
>>> hasattr(FooChild, 'echo_bar_more')
True
You see where we are going: in Python, classes are objects, and you can create a class on the fly, dynamically.
This is what Python does when you use the keyword class, and it does so by using a metaclass.
What are metaclasses (finally)
Metaclasses are the 'stuff' that creates classes.
You define classes in order to create objects, right?
But we learned that Python classes are objects.
Well, metaclasses are what create these objects. They are the classes' classes,
you can picture them this way:
MyClass = MetaClass()
MyObject = MyClass()
You've seen that type lets you do something like this:
MyClass = type('MyClass', (), {})
It's because the function type is in fact a metaclass. type is the
metaclass Python uses to create all classes behind the scenes.
Now you wonder why the heck is it written in lowercase, and not Type?
Well, I guess it's a matter of consistency with str, the class that creates
strings objects, and int the class that creates integer objects. type is
just the class that creates class objects.
You see that by checking the __class__ attribute.
Everything, and I mean everything, is an object in Python. That includes ints,
strings, functions and classes. All of them are objects. And all of them have
been created from a class:
>>> age = 35
>>> age.__class__
<type 'int'>
>>> name = 'bob'
>>> name.__class__
<type 'str'>
>>> def foo(): pass
>>> foo.__class__
<type 'function'>
>>> class Bar(object): pass
>>> b = Bar()
>>> b.__class__
<class '__main__.Bar'>
Now, what is the __class__ of any __class__ ?
>>> age.__class__.__class__
<type 'type'>
>>> name.__class__.__class__
<type 'type'>
>>> foo.__class__.__class__
<type 'type'>
>>> b.__class__.__class__
<type 'type'>
So, a metaclass is just the stuff that creates class objects.
You can call it a 'class factory' if you wish.
type is the built-in metaclass Python uses, but of course, you can create your
own metaclass.
The __metaclass__ attribute
You can add a __metaclass__ attribute when you write a class:
class Foo(object):
__metaclass__ = something...
[...]
If you do so, Python will use the metaclass to create the class Foo.
Careful, it's tricky.
You write class Foo(object) first, but the class object Foo is not created
in memory yet.
Python will look for __metaclass__ in the class definition. If it finds it,
it will use it to create the object class Foo. If it doesn't, it will use
type to create the class.
Read that several times.
When you do:
class Foo(Bar):
pass
Python does the following:
Is there a __metaclass__ attribute in Foo?
If yes, create in memory a class object (I said a class object, stay with me here), with the name Foo by using what is in __metaclass__.
If Python can't find __metaclass__, it will look for a __metaclass__ at the MODULE level, and try to do the same (but only for classes that don't inherit anything, basically old-style classes).
Then if it can't find any __metaclass__ at all, it will use the Bar's (the first parent) own metaclass (which might be the default type) to create the class object.
Be careful here that the __metaclass__ attribute will not be inherited, the metaclass of the parent (Bar.__class__) will be. If Bar used a __metaclass__ attribute that created Bar with type() (and not type.__new__()), the subclasses will not inherit that behavior.
Now the big question is, what can you put in __metaclass__ ?
The answer is: something that can create a class.
And what can create a class? type, or anything that subclasses or uses it.
Custom metaclasses
The main purpose of a metaclass is to change the class automatically,
when it's created.
You usually do this for APIs, where you want to create classes matching the
current context.
Imagine a stupid example, where you decide that all classes in your module
should have their attributes written in uppercase. There are several ways to
do this, but one way is to set __metaclass__ at the module level.
This way, all classes of this module will be created using this metaclass,
and we just have to tell the metaclass to turn all attributes to uppercase.
Luckily, __metaclass__ can actually be any callable, it doesn't need to be a
formal class (I know, something with 'class' in its name doesn't need to be
a class, go figure... but it's helpful).
So we will start with a simple example, by using a function.
# the metaclass will automatically get passed the same argument
# that you usually pass to `type`
def upper_attr(future_class_name, future_class_parents, future_class_attr):
"""
Return a class object, with the list of its attribute turned
into uppercase.
"""
# pick up any attribute that doesn't start with '__' and uppercase it
uppercase_attr = {}
for name, val in future_class_attr.items():
if not name.startswith('__'):
uppercase_attr[name.upper()] = val
else:
uppercase_attr[name] = val
# let `type` do the class creation
return type(future_class_name, future_class_parents, uppercase_attr)
__metaclass__ = upper_attr # this will affect all classes in the module
class Foo(): # global __metaclass__ won't work with "object" though
# but we can define __metaclass__ here instead to affect only this class
# and this will work with "object" children
bar = 'bip'
print(hasattr(Foo, 'bar'))
# Out: False
print(hasattr(Foo, 'BAR'))
# Out: True
f = Foo()
print(f.BAR)
# Out: 'bip'
Now, let's do exactly the same, but using a real class for a metaclass:
# remember that `type` is actually a class like `str` and `int`
# so you can inherit from it
class UpperAttrMetaclass(type):
# __new__ is the method called before __init__
# it's the method that creates the object and returns it
# while __init__ just initializes the object passed as parameter
# you rarely use __new__, except when you want to control how the object
# is created.
# here the created object is the class, and we want to customize it
# so we override __new__
# you can do some stuff in __init__ too if you wish
# some advanced use involves overriding __call__ as well, but we won't
# see this
def __new__(upperattr_metaclass, future_class_name,
future_class_parents, future_class_attr):
uppercase_attr = {}
for name, val in future_class_attr.items():
if not name.startswith('__'):
uppercase_attr[name.upper()] = val
else:
uppercase_attr[name] = val
return type(future_class_name, future_class_parents, uppercase_attr)
But this is not really OOP. We call type directly and we don't override
or call the parent __new__. Let's do it:
class UpperAttrMetaclass(type):
def __new__(upperattr_metaclass, future_class_name,
future_class_parents, future_class_attr):
uppercase_attr = {}
for name, val in future_class_attr.items():
if not name.startswith('__'):
uppercase_attr[name.upper()] = val
else:
uppercase_attr[name] = val
# reuse the type.__new__ method
# this is basic OOP, nothing magic in there
return type.__new__(upperattr_metaclass, future_class_name,
future_class_parents, uppercase_attr)
You may have noticed the extra argument upperattr_metaclass. There is
nothing special about it: __new__ always receives the class it's defined in, as first parameter. Just like you have self for ordinary methods which receive the instance as first parameter, or the defining class for class methods.
Of course, the names I used here are long for the sake of clarity, but like
for self, all the arguments have conventional names. So a real production
metaclass would look like this:
class UpperAttrMetaclass(type):
def __new__(cls, clsname, bases, dct):
uppercase_attr = {}
for name, val in dct.items():
if not name.startswith('__'):
uppercase_attr[name.upper()] = val
else:
uppercase_attr[name] = val
return type.__new__(cls, clsname, bases, uppercase_attr)
We can make it even cleaner by using super, which will ease inheritance (because yes, you can have metaclasses, inheriting from metaclasses, inheriting from type):
class UpperAttrMetaclass(type):
def __new__(cls, clsname, bases, dct):
uppercase_attr = {}
for name, val in dct.items():
if not name.startswith('__'):
uppercase_attr[name.upper()] = val
else:
uppercase_attr[name] = val
return super(UpperAttrMetaclass, cls).__new__(cls, clsname, bases, uppercase_attr)
That's it. There is really nothing more about metaclasses.
The reason behind the complexity of the code using metaclasses is not because
of metaclasses, it's because you usually use metaclasses to do twisted stuff
relying on introspection, manipulating inheritance, vars such as __dict__, etc.
Indeed, metaclasses are especially useful to do black magic, and therefore
complicated stuff. But by themselves, they are simple:
intercept a class creation
modify the class
return the modified class
Why would you use metaclasses classes instead of functions?
Since __metaclass__ can accept any callable, why would you use a class
since it's obviously more complicated?
There are several reasons to do so:
The intention is clear. When you read UpperAttrMetaclass(type), you know
what's going to follow
You can use OOP. Metaclass can inherit from metaclass, override parent methods. Metaclasses can even use metaclasses.
You can structure your code better. You never use metaclasses for something as
trivial as the above example. It's usually for something complicated. Having the
ability to make several methods and group them in one class is very useful
to make the code easier to read.
You can hook on __new__, __init__ and __call__. Which will allow
you to do different stuff. Even if usually you can do it all in __new__,
some people are just more comfortable using __init__.
These are called metaclasses, damn it! It must mean something!
Why would you use metaclasses?
Now the big question. Why would you use some obscure error prone feature?
Well, usually you don't:
Metaclasses are deeper magic that
99% of users should never worry about.
If you wonder whether you need them,
you don't (the people who actually
need them know with certainty that
they need them, and don't need an
explanation about why).
Python Guru Tim Peters
The main use case for a metaclass is creating an API. A typical example of this is the Django ORM.
It allows you to define something like this:
class Person(models.Model):
name = models.CharField(max_length=30)
age = models.IntegerField()
But if you do this:
guy = Person(name='bob', age='35')
print(guy.age)
It won't return an IntegerField object. It will return an int, and can even take it directly from the database.
This is possible because models.Model defines __metaclass__ and
it uses some magic that will turn the Person you just defined with simple statements
into a complex hook to a database field.
Django makes something complex look simple by exposing a simple API
and using metaclasses, recreating code from this API to do the real job
behind the scenes.
The last word
First, you know that classes are objects that can create instances.
Well in fact, classes are themselves instances. Of metaclasses.
>>> class Foo(object): pass
>>> id(Foo)
142630324
Everything is an object in Python, and they are all either instances of classes
or instances of metaclasses.
Except for type.
type is actually its own metaclass. This is not something you could
reproduce in pure Python, and is done by cheating a little bit at the implementation
level.
Secondly, metaclasses are complicated. You may not want to use them for
very simple class alterations. You can change classes by using two different techniques:
monkey patching
class decorators
99% of the time you need class alteration, you are better off using these.
But 99% of the time, you don't need class alteration at all.
</s> |
<s>[INST] How do I check whether a file exists using Python? How do I check whether a file exists, without using the try statement?
[/INST] You can also use os.path.isfile
Return True if path is an existing regular file. This follows symbolic links, so both islink() and isfile() can be true for the same path.
import os.path
os.path.isfile(fname)
if you need to be sure it's a file.
Starting with Python 3.4, the pathlib module offers an object-oriented approach:
from pathlib import Path
my_file = Path("/path/to/file")
if my_file.is_file():
# file exists
</s> |
<s>[INST] Does Python have a ternary conditional operator? If Python does not have a ternary conditional operator, is it possible to simulate one using other language constructs?
[/INST] Yes, it was added in version 2.5.
The syntax is:
a if condition else b
First condition is evaluated, then either a or b is returned based on the Boolean value of condition
If condition evaluates to True a is returned, else b is returned.
For example:
>>> 'true' if True else 'false'
'true'
>>> 'true' if False else 'false'
'false'
Keep in mind that it's frowned upon by some Pythonistas for several reasons:
The order of the arguments is different from many other languages (such as C, Ruby, Java, etc.), which may lead to bugs when people unfamiliar with Python's "surprising" behaviour use it (they may reverse the order).
Some find it "unwieldy", since it goes contrary to the normal flow of thought (thinking of the condition first and then the effects).
Stylistic reasons.
If you're having trouble remembering the order, then remember that if you read it out loud, you (almost) say what you mean. For example, x = 4 if b > 8 else 9 is read aloud as x will be 4 if b is greater than 8 otherwise 9.
Official documentation:
Conditional expressions
Is there an equivalent of Câs â?:â ternary operator?
</s> |
<s>[INST] Calling an external command in Python How can I call an external command (as if I'd typed it at the Unix shell or Windows command prompt) from within a Python script?
[/INST] Look at the subprocess module in the stdlib:
from subprocess import call
call(["ls", "-l"])
The advantage of subprocess vs system is that it is more flexible (you can get the stdout, stderr, the "real" status code, better error handling, etc...). I think os.system is deprecated, too, or will be:
https://docs.python.org/2/library/subprocess.html#replacing-older-functions-with-the-subprocess-module
For quick/dirty/one time scripts, os.system is enough, though.
</s> |
<s>[INST] What does `if __name__ == "__main__":` do? What does the if __name__ == "__main__": do?
# Threading example
import time, thread
def myfunction(string, sleeptime, lock, *args):
while 1:
lock.acquire()
time.sleep(sleeptime)
lock.release()
time.sleep(sleeptime)
if __name__ == "__main__":
lock = thread.allocate_lock()
thread.start_new_thread(myfunction, ("Thread #: 1", 2, lock))
thread.start_new_thread(myfunction, ("Thread #: 2", 2, lock))
[/INST] When the Python interpreter reads a source file, it executes all of the code found in it.
Before executing the code, it will define a few special variables. For example, if the python interpreter is running that module (the source file) as the main program, it sets the special __name__ variable to have a value "__main__". If this file is being imported from another module, __name__ will be set to the module's name.
In the case of your script, let's assume that it's executing as the main function, e.g. you said something like
python threading_example.py
on the command line. After setting up the special variables, it will execute the import statement and load those modules. It will then evaluate the def block, creating a function object and creating a variable called myfunction that points to the function object. It will then read the if statement and see that __name__ does equal "__main__", so it will execute the block shown there.
One of the reasons for doing this is that sometimes you write a module (a .py file) where it can be executed directly. Alternatively, it can also be imported and used in another module. By doing the main check, you can have that code only execute when you want to run the module as a program and not have it execute when someone just wants to import your module and call your functions themselves.
See this page for some extra details.
</s> |
<s>[INST] How to make a chain of function decorators in Python? How can I make two decorators in Python that would do the following?
@makebold
@makeitalic
def say():
return "Hello"
...which should return:
"<b><i>Hello</i></b>"
I'm not trying to make HTML this way in a real application - just trying to understand how decorators and decorator chaining works.
[/INST] If you are not into long explanations, see Paolo Bergantinoâs answer.
Decorator Basics
Pythonâs functions are objects
To understand decorators, you must first understand that functions are objects in Python. This has important consequences. Letâs see why with a simple example :
def shout(word="yes"):
return word.capitalize()+"!"
print(shout())
# outputs : 'Yes!'
# As an object, you can assign the function to a variable like any other object
scream = shout
# Notice we don't use parentheses: we are not calling the function, we are putting the function "shout" into the variable "scream". It means you can then call "shout" from "scream":
print(scream())
# outputs : 'Yes!'
# More than that, it means you can remove the old name 'shout', and the function will still be accessible from 'scream'
del shout
try:
print(shout())
except NameError, e:
print(e)
#outputs: "name 'shout' is not defined"
print(scream())
# outputs: 'Yes!'
Keep this in mind. Weâll circle back to it shortly.
Another interesting property of Python functions is they can be defined inside another function!
def talk():
# You can define a function on the fly in "talk" ...
def whisper(word="yes"):
return word.lower()+"..."
# ... and use it right away!
print(whisper())
# You call "talk", that defines "whisper" EVERY TIME you call it, then
# "whisper" is called in "talk".
talk()
# outputs:
# "yes..."
# But "whisper" DOES NOT EXIST outside "talk":
try:
print(whisper())
except NameError, e:
print(e)
#outputs : "name 'whisper' is not defined"*
#Python's functions are objects
Functions references
Okay, still here? Now the fun part...
Youâve seen that functions are objects. Therefore, functions:
can be assigned to a variable
can be defined in another function
That means that a function can return another function.
def getTalk(kind="shout"):
# We define functions on the fly
def shout(word="yes"):
return word.capitalize()+"!"
def whisper(word="yes") :
return word.lower()+"...";
# Then we return one of them
if kind == "shout":
# We don't use "()", we are not calling the function, we are returning the function object
return shout
else:
return whisper
# How do you use this strange beast?
# Get the function and assign it to a variable
talk = getTalk()
# You can see that "talk" is here a function object:
print(talk)
#outputs : <function shout at 0xb7ea817c>
# The object is the one returned by the function:
print(talk())
#outputs : Yes!
# And you can even use it directly if you feel wild:
print(getTalk("whisper")())
#outputs : yes...
Thereâs more!
If you can return a function, you can pass one as a parameter:
def doSomethingBefore(func):
print("I do something before then I call the function you gave me")
print(func())
doSomethingBefore(scream)
#outputs:
#I do something before then I call the function you gave me
#Yes!
Well, you just have everything needed to understand decorators. You see, decorators are âwrappersâ, which means that they let you execute code before and after the function they decorate without modifying the function itself.
Handcrafted decorators
How youâd do it manually:
# A decorator is a function that expects ANOTHER function as parameter
def my_shiny_new_decorator(a_function_to_decorate):
# Inside, the decorator defines a function on the fly: the wrapper.
# This function is going to be wrapped around the original function
# so it can execute code before and after it.
def the_wrapper_around_the_original_function():
# Put here the code you want to be executed BEFORE the original function is called
print("Before the function runs")
# Call the function here (using parentheses)
a_function_to_decorate()
# Put here the code you want to be executed AFTER the original function is called
print("After the function runs")
# At this point, "a_function_to_decorate" HAS NEVER BEEN EXECUTED.
# We return the wrapper function we have just created.
# The wrapper contains the function and the code to execute before and after. Itâs ready to use!
return the_wrapper_around_the_original_function
# Now imagine you create a function you don't want to ever touch again.
def a_stand_alone_function():
print("I am a stand alone function, don't you dare modify me")
a_stand_alone_function()
#outputs: I am a stand alone function, don't you dare modify me
# Well, you can decorate it to extend its behavior.
# Just pass it to the decorator, it will wrap it dynamically in
# any code you want and return you a new function ready to be used:
a_stand_alone_function_decorated = my_shiny_new_decorator(a_stand_alone_function)
a_stand_alone_function_decorated()
#outputs:
#Before the function runs
#I am a stand alone function, don't you dare modify me
#After the function runs
Now, you probably want that every time you call a_stand_alone_function, a_stand_alone_function_decorated is called instead. Thatâs easy, just overwrite a_stand_alone_function with the function returned by my_shiny_new_decorator:
a_stand_alone_function = my_shiny_new_decorator(a_stand_alone_function)
a_stand_alone_function()
#outputs:
#Before the function runs
#I am a stand alone function, don't you dare modify me
#After the function runs
# Thatâs EXACTLY what decorators do!
Decorators demystified
The previous example, using the decorator syntax:
@my_shiny_new_decorator
def another_stand_alone_function():
print("Leave me alone")
another_stand_alone_function()
#outputs:
#Before the function runs
#Leave me alone
#After the function runs
Yes, thatâs all, itâs that simple. @decorator is just a shortcut to:
another_stand_alone_function = my_shiny_new_decorator(another_stand_alone_function)
Decorators are just a pythonic variant of the decorator design pattern. There are several classic design patterns embedded in Python to ease development (like iterators).
Of course, you can accumulate decorators:
def bread(func):
def wrapper():
print("</''''''\>")
func()
print("<\______/>")
return wrapper
def ingredients(func):
def wrapper():
print("#tomatoes#")
func()
print("~salad~")
return wrapper
def sandwich(food="--ham--"):
print(food)
sandwich()
#outputs: --ham--
sandwich = bread(ingredients(sandwich))
sandwich()
#outputs:
#</''''''\>
# #tomatoes#
# --ham--
# ~salad~
#<\______/>
Using the Python decorator syntax:
@bread
@ingredients
def sandwich(food="--ham--"):
print(food)
sandwich()
#outputs:
#</''''''\>
# #tomatoes#
# --ham--
# ~salad~
#<\______/>
The order you set the decorators MATTERS:
@ingredients
@bread
def strange_sandwich(food="--ham--"):
print(food)
strange_sandwich()
#outputs:
##tomatoes#
#</''''''\>
# --ham--
#<\______/>
# ~salad~
Now: to answer the question...
As a conclusion, you can easily see how to answer the question:
# The decorator to make it bold
def makebold(fn):
# The new function the decorator returns
def wrapper():
# Insertion of some code before and after
return "<b>" + fn() + "</b>"
return wrapper
# The decorator to make it italic
def makeitalic(fn):
# The new function the decorator returns
def wrapper():
# Insertion of some code before and after
return "<i>" + fn() + "</i>"
return wrapper
@makebold
@makeitalic
def say():
return "hello"
print(say())
#outputs: <b><i>hello</i></b>
# This is the exact equivalent to
def say():
return "hello"
say = makebold(makeitalic(say))
print(say())
#outputs: <b><i>hello</i></b>
You can now just leave happy, or burn your brain a little bit more and see advanced uses of decorators.
Taking decorators to the next level
Passing arguments to the decorated function
# Itâs not black magic, you just have to let the wrapper
# pass the argument:
def a_decorator_passing_arguments(function_to_decorate):
def a_wrapper_accepting_arguments(arg1, arg2):
print("I got args! Look: {0}, {1}".format(arg1, arg2))
function_to_decorate(arg1, arg2)
return a_wrapper_accepting_arguments
# Since when you are calling the function returned by the decorator, you are
# calling the wrapper, passing arguments to the wrapper will let it pass them to
# the decorated function
@a_decorator_passing_arguments
def print_full_name(first_name, last_name):
print("My name is {0} {1}".format(first_name, last_name))
print_full_name("Peter", "Venkman")
# outputs:
#I got args! Look: Peter Venkman
#My name is Peter Venkman
Decorating methods
One nifty thing about Python is that methods and functions are really the same. The only difference is that methods expect that their first argument is a reference to the current object (self).
That means you can build a decorator for methods the same way! Just remember to take self into consideration:
def method_friendly_decorator(method_to_decorate):
def wrapper(self, lie):
lie = lie - 3 # very friendly, decrease age even more :-)
return method_to_decorate(self, lie)
return wrapper
class Lucy(object):
def __init__(self):
self.age = 32
@method_friendly_decorator
def sayYourAge(self, lie):
print("I am {0}, what did you think?".format(self.age + lie))
l = Lucy()
l.sayYourAge(-3)
#outputs: I am 26, what did you think?
If youâre making general-purpose decorator--one youâll apply to any function or method, no matter its arguments--then just use *args, **kwargs:
def a_decorator_passing_arbitrary_arguments(function_to_decorate):
# The wrapper accepts any arguments
def a_wrapper_accepting_arbitrary_arguments(*args, **kwargs):
print("Do I have args?:")
print(args)
print(kwargs)
# Then you unpack the arguments, here *args, **kwargs
# If you are not familiar with unpacking, check:
# http://www.saltycrane.com/blog/2008/01/how-to-use-args-and-kwargs-in-python/
function_to_decorate(*args, **kwargs)
return a_wrapper_accepting_arbitrary_arguments
@a_decorator_passing_arbitrary_arguments
def function_with_no_argument():
print("Python is cool, no argument here.")
function_with_no_argument()
#outputs
#Do I have args?:
#()
#{}
#Python is cool, no argument here.
@a_decorator_passing_arbitrary_arguments
def function_with_arguments(a, b, c):
print(a, b, c)
function_with_arguments(1,2,3)
#outputs
#Do I have args?:
#(1, 2, 3)
#{}
#1 2 3
@a_decorator_passing_arbitrary_arguments
def function_with_named_arguments(a, b, c, platypus="Why not ?"):
print("Do {0}, {1} and {2} like platypus? {3}".format(a, b, c, platypus))
function_with_named_arguments("Bill", "Linus", "Steve", platypus="Indeed!")
#outputs
#Do I have args ? :
#('Bill', 'Linus', 'Steve')
#{'platypus': 'Indeed!'}
#Do Bill, Linus and Steve like platypus? Indeed!
class Mary(object):
def __init__(self):
self.age = 31
@a_decorator_passing_arbitrary_arguments
def sayYourAge(self, lie=-3): # You can now add a default value
print("I am {0}, what did you think?".format(self.age + lie))
m = Mary()
m.sayYourAge()
#outputs
# Do I have args?:
#(<__main__.Mary object at 0xb7d303ac>,)
#{}
#I am 28, what did you think?
Passing arguments to the decorator
Great, now what would you say about passing arguments to the decorator itself?
This can get somewhat twisted, since a decorator must accept a function as an argument. Therefore, you cannot pass the decorated functionâs arguments directly to the decorator.
Before rushing to the solution, letâs write a little reminder:
# Decorators are ORDINARY functions
def my_decorator(func):
print("I am an ordinary function")
def wrapper():
print("I am function returned by the decorator")
func()
return wrapper
# Therefore, you can call it without any "@"
def lazy_function():
print("zzzzzzzz")
decorated_function = my_decorator(lazy_function)
#outputs: I am an ordinary function
# It outputs "I am an ordinary function", because thatâs just what you do:
# calling a function. Nothing magic.
@my_decorator
def lazy_function():
print("zzzzzzzz")
#outputs: I am an ordinary function
Itâs exactly the same. "my_decorator" is called. So when you @my_decorator, you are telling Python to call the function 'labelled by the variable "my_decorator"'.
This is important! The label you give can point directly to the decoratorâor not.
Letâs get evil. âº
def decorator_maker():
print("I make decorators! I am executed only once: "
"when you make me create a decorator.")
def my_decorator(func):
print("I am a decorator! I am executed only when you decorate a function.")
def wrapped():
print("I am the wrapper around the decorated function. "
"I am called when you call the decorated function. "
"As the wrapper, I return the RESULT of the decorated function.")
return func()
print("As the decorator, I return the wrapped function.")
return wrapped
print("As a decorator maker, I return a decorator")
return my_decorator
# Letâs create a decorator. Itâs just a new function after all.
new_decorator = decorator_maker()
#outputs:
#I make decorators! I am executed only once: when you make me create a decorator.
#As a decorator maker, I return a decorator
# Then we decorate the function
def decorated_function():
print("I am the decorated function.")
decorated_function = new_decorator(decorated_function)
#outputs:
#I am a decorator! I am executed only when you decorate a function.
#As the decorator, I return the wrapped function
# Letâs call the function:
decorated_function()
#outputs:
#I am the wrapper around the decorated function. I am called when you call the decorated function.
#As the wrapper, I return the RESULT of the decorated function.
#I am the decorated function.
No surprise here.
Letâs do EXACTLY the same thing, but skip all the pesky intermediate variables:
def decorated_function():
print("I am the decorated function.")
decorated_function = decorator_maker()(decorated_function)
#outputs:
#I make decorators! I am executed only once: when you make me create a decorator.
#As a decorator maker, I return a decorator
#I am a decorator! I am executed only when you decorate a function.
#As the decorator, I return the wrapped function.
# Finally:
decorated_function()
#outputs:
#I am the wrapper around the decorated function. I am called when you call the decorated function.
#As the wrapper, I return the RESULT of the decorated function.
#I am the decorated function.
Letâs make it even shorter:
@decorator_maker()
def decorated_function():
print("I am the decorated function.")
#outputs:
#I make decorators! I am executed only once: when you make me create a decorator.
#As a decorator maker, I return a decorator
#I am a decorator! I am executed only when you decorate a function.
#As the decorator, I return the wrapped function.
#Eventually:
decorated_function()
#outputs:
#I am the wrapper around the decorated function. I am called when you call the decorated function.
#As the wrapper, I return the RESULT of the decorated function.
#I am the decorated function.
Hey, did you see that? We used a function call with the "@" syntax! :-)
So, back to decorators with arguments. If we can use functions to generate the decorator on the fly, we can pass arguments to that function, right?
def decorator_maker_with_arguments(decorator_arg1, decorator_arg2):
print("I make decorators! And I accept arguments: {0}, {1}".format(decorator_arg1, decorator_arg2))
def my_decorator(func):
# The ability to pass arguments here is a gift from closures.
# If you are not comfortable with closures, you can assume itâs ok,
# or read: http://stackoverflow.com/questions/13857/can-you-explain-closures-as-they-relate-to-python
print("I am the decorator. Somehow you passed me arguments: {0}, {1}".format(decorator_arg1, decorator_arg2))
# Don't confuse decorator arguments and function arguments!
def wrapped(function_arg1, function_arg2) :
print("I am the wrapper around the decorated function.\n"
"I can access all the variables\n"
"\t- from the decorator: {0} {1}\n"
"\t- from the function call: {2} {3}\n"
"Then I can pass them to the decorated function"
.format(decorator_arg1, decorator_arg2,
function_arg1, function_arg2))
return func(function_arg1, function_arg2)
return wrapped
return my_decorator
@decorator_maker_with_arguments("Leonard", "Sheldon")
def decorated_function_with_arguments(function_arg1, function_arg2):
print("I am the decorated function and only knows about my arguments: {0}"
" {1}".format(function_arg1, function_arg2))
decorated_function_with_arguments("Rajesh", "Howard")
#outputs:
#I make decorators! And I accept arguments: Leonard Sheldon
#I am the decorator. Somehow you passed me arguments: Leonard Sheldon
#I am the wrapper around the decorated function.
#I can access all the variables
# - from the decorator: Leonard Sheldon
# - from the function call: Rajesh Howard
#Then I can pass them to the decorated function
#I am the decorated function and only knows about my arguments: Rajesh Howard
Here it is: a decorator with arguments. Arguments can be set as variable:
c1 = "Penny"
c2 = "Leslie"
@decorator_maker_with_arguments("Leonard", c1)
def decorated_function_with_arguments(function_arg1, function_arg2):
print("I am the decorated function and only knows about my arguments:"
" {0} {1}".format(function_arg1, function_arg2))
decorated_function_with_arguments(c2, "Howard")
#outputs:
#I make decorators! And I accept arguments: Leonard Penny
#I am the decorator. Somehow you passed me arguments: Leonard Penny
#I am the wrapper around the decorated function.
#I can access all the variables
# - from the decorator: Leonard Penny
# - from the function call: Leslie Howard
#Then I can pass them to the decorated function
#I am the decorated function and only knows about my arguments: Leslie Howard
As you can see, you can pass arguments to the decorator like any function using this trick. You can even use *args, **kwargs if you wish. But remember decorators are called only once. Just when Python imports the script. You can't dynamically set the arguments afterwards. When you do "import x", the function is already decorated, so you can't
change anything.
Letâs practice: decorating a decorator
Okay, as a bonus, I'll give you a snippet to make any decorator accept generically any argument. After all, in order to accept arguments, we created our decorator using another function.
We wrapped the decorator.
Anything else we saw recently that wrapped function?
Oh yes, decorators!
Letâs have some fun and write a decorator for the decorators:
def decorator_with_args(decorator_to_enhance):
"""
This function is supposed to be used as a decorator.
It must decorate an other function, that is intended to be used as a decorator.
Take a cup of coffee.
It will allow any decorator to accept an arbitrary number of arguments,
saving you the headache to remember how to do that every time.
"""
# We use the same trick we did to pass arguments
def decorator_maker(*args, **kwargs):
# We create on the fly a decorator that accepts only a function
# but keeps the passed arguments from the maker.
def decorator_wrapper(func):
# We return the result of the original decorator, which, after all,
# IS JUST AN ORDINARY FUNCTION (which returns a function).
# Only pitfall: the decorator must have this specific signature or it won't work:
return decorator_to_enhance(func, *args, **kwargs)
return decorator_wrapper
return decorator_maker
It can be used as follows:
# You create the function you will use as a decorator. And stick a decorator on it :-)
# Don't forget, the signature is "decorator(func, *args, **kwargs)"
@decorator_with_args
def decorated_decorator(func, *args, **kwargs):
def wrapper(function_arg1, function_arg2):
print("Decorated with {0} {1}".format(args, kwargs))
return func(function_arg1, function_arg2)
return wrapper
# Then you decorate the functions you wish with your brand new decorated decorator.
@decorated_decorator(42, 404, 1024)
def decorated_function(function_arg1, function_arg2):
print("Hello {0} {1}".format(function_arg1, function_arg2))
decorated_function("Universe and", "everything")
#outputs:
#Decorated with (42, 404, 1024) {}
#Hello Universe and everything
# Whoooot!
I know, the last time you had this feeling, it was after listening a guy saying: "before understanding recursion, you must first understand recursion". But now, don't you feel good about mastering this?
Best practices: decorators
Decorators were introduced in Python 2.4, so be sure your code will be run on >= 2.4.
Decorators slow down the function call. Keep that in mind.
You cannot un-decorate a function. (There are hacks to create decorators that can be removed, but nobody uses them.) So once a function is decorated, itâs decorated for all the code.
Decorators wrap functions, which can make them hard to debug. (This gets better from Python >= 2.5; see below.)
The functools module was introduced in Python 2.5. It includes the function functools.wraps(), which copies the name, module, and docstring of the decorated function to its wrapper.
(Fun fact: functools.wraps() is a decorator! âº)
# For debugging, the stacktrace prints you the function __name__
def foo():
print("foo")
print(foo.__name__)
#outputs: foo
# With a decorator, it gets messy
def bar(func):
def wrapper():
print("bar")
return func()
return wrapper
@bar
def foo():
print("foo")
print(foo.__name__)
#outputs: wrapper
# "functools" can help for that
import functools
def bar(func):
# We say that "wrapper", is wrapping "func"
# and the magic begins
@functools.wraps(func)
def wrapper():
print("bar")
return func()
return wrapper
@bar
def foo():
print("foo")
print(foo.__name__)
#outputs: foo
How can the decorators be useful?
Now the big question: What can I use decorators for?
Seem cool and powerful, but a practical example would be great. Well, there are 1000 possibilities. Classic uses are extending a function behavior from an external lib (you can't modify it), or for debugging (you don't want to modify it because itâs temporary).
You can use them to extend several functions in a DRYâs way, like so:
def benchmark(func):
"""
A decorator that prints the time a function takes
to execute.
"""
import time
def wrapper(*args, **kwargs):
t = time.clock()
res = func(*args, **kwargs)
print("{0} {1}".format(func.__name__, time.clock()-t))
return res
return wrapper
def logging(func):
"""
A decorator that logs the activity of the script.
(it actually just prints it, but it could be logging!)
"""
def wrapper(*args, **kwargs):
res = func(*args, **kwargs)
print("{0} {1} {2}".format(func.__name__, args, kwargs))
return res
return wrapper
def counter(func):
"""
A decorator that counts and prints the number of times a function has been executed
"""
def wrapper(*args, **kwargs):
wrapper.count = wrapper.count + 1
res = func(*args, **kwargs)
print("{0} has been used: {1}x".format(func.__name__, wrapper.count))
return res
wrapper.count = 0
return wrapper
@counter
@benchmark
@logging
def reverse_string(string):
return str(reversed(string))
print(reverse_string("Able was I ere I saw Elba"))
print(reverse_string("A man, a plan, a canoe, pasta, heros, rajahs, a coloratura, maps, snipe, percale, macaroni, a gag, a banana bag, a tan, a tag, a banana bag again (or a camel), a crepe, pins, Spam, a rut, a Rolo, cash, a jar, sore hats, a peon, a canal: Panama!"))
#outputs:
#reverse_string ('Able was I ere I saw Elba',) {}
#wrapper 0.0
#wrapper has been used: 1x
#ablE was I ere I saw elbA
#reverse_string ('A man, a plan, a canoe, pasta, heros, rajahs, a coloratura, maps, snipe, percale, macaroni, a gag, a banana bag, a tan, a tag, a banana bag again (or a camel), a crepe, pins, Spam, a rut, a Rolo, cash, a jar, sore hats, a peon, a canal: Panama!',) {}
#wrapper 0.0
#wrapper has been used: 2x
#!amanaP :lanac a ,noep a ,stah eros ,raj a ,hsac ,oloR a ,tur a ,mapS ,snip ,eperc a ,)lemac a ro( niaga gab ananab a ,gat a ,nat a ,gab ananab a ,gag a ,inoracam ,elacrep ,epins ,spam ,arutaroloc a ,shajar ,soreh ,atsap ,eonac a ,nalp a ,nam A
Of course the good thing with decorators is that you can use them right away on almost anything without rewriting. DRY, I said:
@counter
@benchmark
@logging
def get_random_futurama_quote():
from urllib import urlopen
result = urlopen("http://subfusion.net/cgi-bin/quote.pl?quote=futurama").read()
try:
value = result.split("<br><b><hr><br>")[1].split("<br><br><hr>")[0]
return value.strip()
except:
return "No, I'm ... doesn't!"
print(get_random_futurama_quote())
print(get_random_futurama_quote())
#outputs:
#get_random_futurama_quote () {}
#wrapper 0.02
#wrapper has been used: 1x
#The laws of science be a harsh mistress.
#get_random_futurama_quote () {}
#wrapper 0.01
#wrapper has been used: 2x
#Curse you, merciful Poseidon!
Python itself provides several decorators: property, staticmethod, etc.
Django uses decorators to manage caching and view permissions.
Twisted to fake inlining asynchronous functions calls.
This really is a large playground.
</s> |
<s>[INST] How to merge two Python dictionaries in a single expression? I have two Python dictionaries, and I want to write a single expression that returns these two dictionaries, merged. The update() method would be what I need, if it returned its result instead of modifying a dict in-place.
>>> x = {'a':1, 'b': 2}
>>> y = {'b':10, 'c': 11}
>>> z = x.update(y)
>>> print z
None
>>> x
{'a': 1, 'b': 10, 'c': 11}
How can I get that final merged dict in z, not x?
(To be extra-clear, the last-one-wins conflict-handling of dict.update() is what I'm looking for as well.)
[/INST] In your case, what you can do is:
z = dict(x.items() + y.items())
This will, as you want it, put the final dict in z, and make the value for key b be properly overridden by the second (y) dict's value:
>>> x = {'a':1, 'b': 2}
>>> y = {'b':10, 'c': 11}
>>> z = dict(x.items() + y.items())
>>> z
{'a': 1, 'c': 11, 'b': 10}
If you use Python 3, it is only a little more complicated. To create z:
>>> z = dict(list(x.items()) + list(y.items()))
>>> z
{'a': 1, 'c': 11, 'b': 10}
</s> |
<s>[INST] Sort a Python dictionary by value I have a dictionary of values read from two fields in a database: a string field and a numeric field. The string field is unique, so that is the key of the dictionary.
I can sort on the keys, but how can I sort based on the values?
Note: I have read Stack Overflow question How do I sort a list of dictionaries by values of the dictionary in Python? and probably could change my code to have a list of dictionaries, but since I do not really need a list of dictionaries I wanted to know if there is a simpler solution.
[/INST] It is not possible to sort a dict, only to get a representation of a dict that is sorted. Dicts are inherently orderless, but other types, such as lists and tuples, are not. So you need a sorted representation, which will be a listâprobably a list of tuples.
For instance,
import operator
x = {1: 2, 3: 4, 4: 3, 2: 1, 0: 0}
sorted_x = sorted(x.items(), key=operator.itemgetter(1))
sorted_x will be a list of tuples sorted by the second element in each tuple. dict(sorted_x) == x.
And for those wishing to sort on keys instead of values:
import operator
x = {1: 2, 3: 4, 4: 3, 2: 1, 0: 0}
sorted_x = sorted(x.items(), key=operator.itemgetter(0))
</s> |
<s>[INST] How to check if a directory exists and create it if necessary? What is the most elegant way to check if the directory a file is going to be written to exists, and if not, create the directory using Python? Here is what I tried:
filename = "/my/directory/filename.txt"
dir = os.path.dirname(filename)
try:
os.stat(dir)
except:
os.mkdir(dir)
f = file(filename)
Somehow, I missed os.path.exists (thanks kanja, Blair, and Douglas). This is what I have now:
def ensure_dir(f):
d = os.path.dirname(f)
if not os.path.exists(d):
os.makedirs(d)
Is there a flag for "open", that makes this happen automatically?
[/INST] I see two answers with good qualities, each with a small flaw, so I will give my take on it:
Try os.path.exists, and consider os.makedirs for the creation.
if not os.path.exists(directory):
os.makedirs(directory)
As noted in comments and elsewhere, there's a race condition - if the directory is created between the os.path.exists and the os.makedirs calls, the os.makedirs will fail with an OSError. Unfortunately, blanket-catching OSError and continuing is not foolproof, as it will ignore a failure to create the directory due to other factors, such as insufficient permissions, full disk, etc.
One option would be to trap the OSError and examine the embedded error code, if one knew what's what (on my OS, 13 seems to indicate that permission is denied, and 17 that the file exists - it's not clear that that's even remotely portable, but is explored in Is there a cross-platform way of getting information from Pythonâs OSError). Alternatively, there could be a second os.path.exists, but suppose another created the directory after the first check, then removed it before the second one - we could still be fooled.
Depending on the application, the danger of concurrent operations may be more or less than the danger posed by other factors such as file permissions. The developer would have to know more about the particular application being developed and its expected environment before choosing an implementation.
</s> |
<s>[INST] Using global variables in a function other than the one that created them If I create a global variable in one function, how can I use that variable in another function?
Do I need to store the global variable in a local variable of the function which needs its access?
[/INST] You can use a global variable in other functions by declaring it as global in each function that assigns to it:
globvar = 0
def set_globvar_to_one():
global globvar # Needed to modify global copy of globvar
globvar = 1
def print_globvar():
print globvar # No need for global declaration to read value of globvar
set_globvar_to_one()
print_globvar() # Prints 1
I imagine the reason for it is that, since global variables are so dangerous, Python wants to make sure that you really know that's what you're playing with by explicitly requiring the global keyword.
See other answers if you want to share a global variable across modules.
</s> |
<s>[INST] How do I install pip on Windows? pip is a replacement for easy_install. But should I install pip using easy_install on Windows? Is there a better way?
[/INST] Python 2.7.9+ and 3.4+
Good news! Python 3.4 (released March 2014) and Python 2.7.9 (released December 2014) ship with Pip. This is the best feature of any Python release. It makes the community's wealth of libraries accessible to everyone. Newbies are no longer excluded from using community libraries by the prohibitive difficulty of setup. In shipping with a package manager, Python joins Ruby, Node.js, Haskell, Perl, Go--almost every other contemporary language with a majority open-source community. Thank you Python.
Of course, that doesn't mean Python packaging is problem solved. The experience remains frustrating. I discuss this in Stack Overflow question Does Python have a package/module management system?.
And, alas for everyone using Python 2.7.8 or earlier (a sizable portion of the community). There's no plan to ship Pip to you. Manual instructions follow.
Python 2 ⤠2.7.8 and Python 3 ⤠3.3
Flying in the face of its 'batteries included' motto, Python ships without a package manager. To make matters worse, Pip was--until recently--ironically difficult to install.
Official instructions
Per http://www.pip-installer.org/en/latest/installing.html:
Download get-pip.py, being careful to save it as a .py file rather than .txt. Then, run it from the command prompt:
python get-pip.py
You possibly need an administrator command prompt to do this. Follow Start a Command Prompt as an Administrator (Microsoft TechNet).
Alternative instructions
The official documentation tells users to install Pip and each of its dependencies from source. That's tedious for the experienced, and prohibitively difficult for newbies.
For our sake, Christoph Gohlke prepares Windows installers (.msi) for popular Python packages. He builds installers for all Python versions, both 32 and 64 bit. You need to
Install setuptools
Install pip
For me, this installed Pip at C:\Python27\Scripts\pip.exe. Find pip.exe on your computer, then add its folder (for example, C:\Python27\Scripts) to your path (Start / Edit environment variables). Now you should be able to run pip from the command line. Try installing a package:
pip install httpie
There you go (hopefully)! Solutions for common problems are given below:
Proxy problems
If you work in an office, you might be behind a HTTP proxy. If so, set the environment variables http_proxy and https_proxy. Most Python applications (and other free software) respect these. Example syntax:
http://proxy_url:port
http://username:password@proxy_url:port
If you're really unlucky, your proxy might be a Microsoft NTLM proxy. Free software can't cope. The only solution is to install a free software friendly proxy that forwards to the nasty proxy. http://cntlm.sourceforge.net/
Unable to find vcvarsall.bat
Python modules can be part written in C or C++. Pip tries to compile from source. If you don't have a C/C++ compiler installed and configured, you'll see this cryptic error message.
Error: Unable to find vcvarsall.bat
You can fix that by installing a C++ compiler such as MinGW or Visual C++. Microsoft actually ship one specifically for use with Python. Or try Microsoft Visual C++ Compiler for Python 2.7.
Often though it's easier to check Christoph's site for your package.
</s> |
<s>[INST] Best way to check if a list is empty For example, if passed the following:
a = []
How do I check to see if a is empty?
[/INST] if not a:
print("List is empty")
Using the implicit booleanness of the empty list a is quite pythonic.
</s> |
<s>[INST] What is the difference between @staticmethod and @classmethod in Python? What is the difference between a function decorated with @staticmethod and one decorated with @classmethod?
[/INST] Maybe a bit of example code will help: Notice the difference in the call signatures of foo, class_foo and static_foo:
class A(object):
def foo(self,x):
print "executing foo(%s,%s)"%(self,x)
@classmethod
def class_foo(cls,x):
print "executing class_foo(%s,%s)"%(cls,x)
@staticmethod
def static_foo(x):
print "executing static_foo(%s)"%x
a=A()
Below is the usual way an object instance calls a method. The object instance, a, is implicitly passed as the first argument.
a.foo(1)
# executing foo(<__main__.A object at 0xb7dbef0c>,1)
With classmethods, the class of the object instance is implicitly passed as the first argument instead of self.
a.class_foo(1)
# executing class_foo(<class '__main__.A'>,1)
You can also call class_foo using the class. In fact, if you define something to be
a classmethod, it is probably because you intend to call it from the class rather than from a class instance. A.foo(1) would have raised a TypeError, but A.class_foo(1) works just fine:
A.class_foo(1)
# executing class_foo(<class '__main__.A'>,1)
One use people have found for class methods is to create inheritable alternative constructors.
With staticmethods, neither self (the object instance) nor cls (the class) is implicitly passed as the first argument. They behave like plain functions except that you can call them from an instance or the class:
a.static_foo(1)
# executing static_foo(1)
A.static_foo('hi')
# executing static_foo(hi)
Staticmethods are used to group functions which have some logical connection with a class to the class.
foo is just a function, but when you call a.foo you don't just get the function,
you get a "partially applied" version of the function with the object instance a bound as the first argument to the function. foo expects 2 arguments, while a.foo only expects 1 argument.
a is bound to foo. That is what is meant by the term "bound" below:
print(a.foo)
# <bound method A.foo of <__main__.A object at 0xb7d52f0c>>
With a.class_foo, a is not bound to class_foo, rather the class A is bound to class_foo.
print(a.class_foo)
# <bound method type.class_foo of <class '__main__.A'>>
Here, with a staticmethod, even though it is a method, a.static_foo just returns
a good 'ole function with no arguments bound. static_foo expects 1 argument, and
a.static_foo expects 1 argument too.
print(a.static_foo)
# <function static_foo at 0xb7d479cc>
And of course the same thing happens when you call static_foo with the class A instead.
print(A.static_foo)
# <function static_foo at 0xb7d479cc>
</s> |
<s>[INST] append vs. extend What's the difference between the list methods append() and extend()?
[/INST] append: Appends object at end.
x = [1, 2, 3]
x.append([4, 5])
print (x)
gives you: [1, 2, 3, [4, 5]]
extend: Extends list by appending elements from the iterable.
x = [1, 2, 3]
x.extend([4, 5])
print (x)
gives you: [1, 2, 3, 4, 5]
</s> |
<s>[INST] Does Python have a string contains substring method? I'm looking for a string.contains or string.indexof method in Python.
I want to do:
if not somestring.contains("blah"):
continue
[/INST] You can use the in operator:
if "blah" not in somestring:
continue
</s> |
<s>[INST] Accessing the index in Python 'for' loops How do I access the index itself for a list like the following?
ints = [8, 23, 45, 12, 78]
When I loop through it using a for loop, how do I access the loop index, from 1 to 5 in this case?
[/INST] Using an additional state variable, such as an index variable (which you would normally use in languages such as C or PHP), is considered non-pythonic.
The better option is to use the built-in function enumerate(), available in both Python 2 and 3:
for idx, val in enumerate(ints):
print(idx, val)
Check out PEP 279 for more.
</s> |
<s>[INST] How to list all files of a directory in Python How can I list all files of a directory in python and add them to a list?
[/INST] os.listdir() will get you everything that's in a directory - files and directories.
If you want just files, you could either filter this down using os.path:
from os import listdir
from os.path import isfile, join
onlyfiles = [f for f in listdir(mypath) if isfile(join(mypath, f))]
or you could use os.walk() which will yield two lists for each directory it visits - splitting into files and dirs for you. If you only want the top directory you can just break the first time it yields
from os import walk
f = []
for (dirpath, dirnames, filenames) in walk(mypath):
f.extend(filenames)
break
And lastly, as that example shows, adding one list to another you can either use .extend() or
>>> q = [1, 2, 3]
>>> w = [4, 5, 6]
>>> q = q + w
>>> q
[1, 2, 3, 4, 5, 6]
Personally, I prefer .extend()
</s> |
<s>[INST] "Least Astonishment" and the Mutable Default Argument Anyone tinkering with Python long enough has been bitten (or torn to pieces) by the following issue:
def foo(a=[]):
a.append(5)
return a
Python novices would expect this function to always return a list with only one element: [5]. The result is instead very different, and very astonishing (for a novice):
>>> foo()
[5]
>>> foo()
[5, 5]
>>> foo()
[5, 5, 5]
>>> foo()
[5, 5, 5, 5]
>>> foo()
A manager of mine once had his first encounter with this feature, and called it "a dramatic design flaw" of the language. I replied that the behavior had an underlying explanation, and it is indeed very puzzling and unexpected if you don't understand the internals. However, I was not able to answer (to myself) the following question: what is the reason for binding the default argument at function definition, and not at function execution? I doubt the experienced behavior has a practical use (who really used static variables in C, without breeding bugs?)
Edit:
Baczek made an interesting example. Together with most of your comments and Utaal's in particular, I elaborated further:
>>> def a():
... print "a executed"
... return []
...
>>>
>>> def b(x=a()):
... x.append(5)
... print x
...
a executed
>>> b()
[5]
>>> b()
[5, 5]
To me, it seems that the design decision was relative to where to put the scope of parameters: inside the function or "together" with it?
Doing the binding inside the function would mean that x is effectively bound to the specified default when the function is called, not defined, something that would present a deep flaw: the def line would be "hybrid" in the sense that part of the binding (of the function object) would happen at definition, and part (assignment of default parameters) at function invocation time.
The actual behavior is more consistent: everything of that line gets evaluated when that line is executed, meaning at function definition.
[/INST] Actually, this is not a design flaw, and it is not because of internals, or performance.
It comes simply from the fact that functions in Python are first-class objects, and not only a piece of code.
As soon as you get to think into this way, then it completely makes sense: a function is an object being evaluated on its definition; default parameters are kind of "member data" and therefore their state may change from one call to the other - exactly as in any other object.
In any case, Effbot has a very nice explanation of the reasons for this behavior in Default Parameter Values in Python.
I found it very clear, and I really suggest reading it for a better knowledge of how function objects work.
</s> |
<s>[INST] How do I pass a variable by reference? The Python documentation seems unclear about whether parameters are passed by reference or value, and the following code produces the unchanged value 'Original'
class PassByReference:
def __init__(self):
self.variable = 'Original'
self.Change(self.variable)
print self.variable
def Change(self, var):
var = 'Changed'
Is there something I can do to pass the variable by actual reference?
[/INST] Arguments are passed by assignment. The rationale behind this is twofold:
the parameter passed in is actually a reference to an object (but the reference is passed by value)
some data types are mutable, but others aren't
So:
If you pass a mutable object into a method, the method gets a reference to that same object and you can mutate it to your heart's delight, but if you rebind the reference in the method, the outer scope will know nothing about it, and after you're done, the outer reference will still point at the original object.
If you pass an immutable object to a method, you still can't rebind the outer reference, and you can't even mutate the object.
To make it even more clear, let's have some examples.
List - a mutable type
Let's try to modify the list that was passed to a method:
def try_to_change_list_contents(the_list):
print 'got', the_list
the_list.append('four')
print 'changed to', the_list
outer_list = ['one', 'two', 'three']
print 'before, outer_list =', outer_list
try_to_change_list_contents(outer_list)
print 'after, outer_list =', outer_list
Output:
before, outer_list = ['one', 'two', 'three']
got ['one', 'two', 'three']
changed to ['one', 'two', 'three', 'four']
after, outer_list = ['one', 'two', 'three', 'four']
Since the parameter passed in is a reference to outer_list, not a copy of it, we can use the mutating list methods to change it and have the changes reflected in the outer scope.
Now let's see what happens when we try to change the reference that was passed in as a parameter:
def try_to_change_list_reference(the_list):
print 'got', the_list
the_list = ['and', 'we', 'can', 'not', 'lie']
print 'set to', the_list
outer_list = ['we', 'like', 'proper', 'English']
print 'before, outer_list =', outer_list
try_to_change_list_reference(outer_list)
print 'after, outer_list =', outer_list
Output:
before, outer_list = ['we', 'like', 'proper', 'English']
got ['we', 'like', 'proper', 'English']
set to ['and', 'we', 'can', 'not', 'lie']
after, outer_list = ['we', 'like', 'proper', 'English']
Since the the_list parameter was passed by value, assigning a new list to it had no effect that the code outside the method could see. The the_list was a copy of the outer_list reference, and we had the_list point to a new list, but there was no way to change where outer_list pointed.
String - an immutable type
It's immutable, so there's nothing we can do to change the contents of the string
Now, let's try to change the reference
def try_to_change_string_reference(the_string):
print 'got', the_string
the_string = 'In a kingdom by the sea'
print 'set to', the_string
outer_string = 'It was many and many a year ago'
print 'before, outer_string =', outer_string
try_to_change_string_reference(outer_string)
print 'after, outer_string =', outer_string
Output:
before, outer_string = It was many and many a year ago
got It was many and many a year ago
set to In a kingdom by the sea
after, outer_string = It was many and many a year ago
Again, since the the_string parameter was passed by value, assigning a new string to it had no effect that the code outside the method could see. The the_string was a copy of the outer_string reference, and we had the_string point to a new string, but there was no way to change where outer_string pointed.
I hope this clears things up a little.
EDIT: It's been noted that this doesn't answer the question that @David originally asked, "Is there something I can do to pass the variable by actual reference?". Let's work on that.
How do we get around this?
As @Andrea's answer shows, you could return the new value. This doesn't change the way things are passed in, but does let you get the information you want back out:
def return_a_whole_new_string(the_string):
new_string = something_to_do_with_the_old_string(the_string)
return new_string
# then you could call it like
my_string = return_a_whole_new_string(my_string)
If you really wanted to avoid using a return value, you could create a class to hold your value and pass it into the function or use an existing class, like a list:
def use_a_wrapper_to_simulate_pass_by_reference(stuff_to_change):
new_string = something_to_do_with_the_old_string(stuff_to_change[0])
stuff_to_change[0] = new_string
# then you could call it like
wrapper = [my_string]
use_a_wrapper_to_simulate_pass_by_reference(wrapper)
do_something_with(wrapper[0])
Although this seems a little cumbersome.
</s> |
<s>[INST] Difference between __str__ and __repr__ in Python What is the difference between __str__ and __repr__ in Python?
[/INST] Alex summarized well but, surprisingly, was too succinct.
First, let me reiterate the main points in Alexâs post:
The default implementation is useless (itâs hard to think of one which wouldnât be, but yeah)
__repr__ goal is to be unambiguous
__str__ goal is to be readable
Containerâs __str__ uses contained objectsâ __repr__
Default implementation is useless
This is mostly a surprise because Pythonâs defaults tend to be fairly useful. However, in this case, having a default for __repr__ which would act like:
return "%s(%r)" % (self.__class__, self.__dict__)
would have been too dangerous (for example, too easy to get into infinite recursion if objects reference each other). So Python cops out. Note that there is one default which is true: if __repr__ is defined, and __str__ is not, the object will behave as though __str__=__repr__.
This means, in simple terms: almost every object you implement should have a functional __repr__ thatâs usable for understanding the object. Implementing __str__ is optional: do that if you need a âpretty printâ functionality (for example, used by a report generator).
The goal of __repr__ is to be unambiguous
Let me come right out and say it â I do not believe in debuggers. I donât really know how to use any debugger, and have never used one seriously. Furthermore, I believe that the big fault in debuggers is their basic nature â most failures I debug happened a long long time ago, in a galaxy far far away. This means that I do believe, with religious fervor, in logging. Logging is the lifeblood of any decent fire-and-forget server system. Python makes it easy to log: with maybe some project specific wrappers, all you need is a
log(INFO, "I am in the weird function and a is", a, "and b is", b, "but I got a null C â using default", default_c)
But you have to do the last step â make sure every object you implement has a useful repr, so code like that can just work. This is why the âevalâ thing comes up: if you have enough information so eval(repr(c))==c, that means you know everything there is to know about c. If thatâs easy enough, at least in a fuzzy way, do it. If not, make sure you have enough information about c anyway. I usually use an eval-like format: "MyClass(this=%r,that=%r)" % (self.this,self.that). It does not mean that you can actually construct MyClass, or that those are the right constructor arguments â but it is a useful form to express âthis is everything you need to know about this instanceâ.
Note: I used %r above, not %s. You always want to use repr() [or %r formatting character, equivalently] inside __repr__ implementation, or youâre defeating the goal of repr. You want to be able to differentiate MyClass(3) and MyClass("3").
The goal of __str__ is to be readable
Specifically, it is not intended to be unambiguous â notice that str(3)==str("3"). Likewise, if you implement an IP abstraction, having the str of it look like 192.168.1.1 is just fine. When implementing a date/time abstraction, the str can be "2010/4/12 15:35:22", etc. The goal is to represent it in a way that a user, not a programmer, would want to read it. Chop off useless digits, pretend to be some other class â as long is it supports readability, it is an improvement.
Containerâs __str__ uses contained objectsâ __repr__
This seems surprising, doesnât it? It is a little, but how readable would
[moshe is, 3, hello
world, this is a list, oh I don't know, containing just 4 elements]
be? Not very. Specifically, the strings in a container would find it way too easy to disturb its string representation. In the face of ambiguity, remember, Python resists the temptation to guess. If you want the above behavior when youâre printing a list, just
print "["+", ".join(l)+"]"
(you can probably also figure out what to do about dictionaries.
Summary
Implement __repr__ for any class you implement. This should be second nature. Implement __str__ if you think it would be useful to have a string version which errs on the side of more readability in favor of more ambiguity.
</s> |
<s>[INST] Is there a way to run Python on Android? We are working on an S60 version and this platform has a nice Python API.
However, there is nothing official about Python on Android, but since Jython exists, is there a way to let the snake and the robot work together?
[/INST] One way is to use Kivy:
Open source Python library for rapid development of applications
that make use of innovative user interfaces, such as multi-touch apps.
Kivy runs on Linux, Windows, OS X, Android and iOS. You can run the same [python] code on all supported platforms.
Kivy Showcase app
</s> |
<s>[INST] Explain Python's slice notation I need a good explanation (references are a plus) on Python's slice notation.
To me, this notation needs a bit of picking up.
It looks extremely powerful, but I haven't quite got my head around it.
[/INST] It's pretty simple really:
a[start:end] # items start through end-1
a[start:] # items start through the rest of the array
a[:end] # items from the beginning through end-1
a[:] # a copy of the whole array
There is also the step value, which can be used with any of the above:
a[start:end:step] # start through not past end, by step
The key point to remember is that the :end value represents the first value that is not in the selected slice. So, the difference beween end and start is the number of elements selected (if step is 1, the default).
The other feature is that start or end may be a negative number, which means it counts from the end of the array instead of the beginning. So:
a[-1] # last item in the array
a[-2:] # last two items in the array
a[:-2] # everything except the last two items
Python is kind to the programmer if there are fewer items than you ask for. For example, if you ask for a[:-2] and a only contains one element, you get an empty list instead of an error. Sometimes you would prefer the error, so you have to be aware that this may happen.
</s> |
<s>[INST] Finding the index of an item given a list containing it in Python For a list ["foo", "bar", "baz"] and an item in the list "bar", what's the cleanest way to get its index (1) in Python?
[/INST] >>> ["foo", "bar", "baz"].index("bar")
1
Reference: Data Structures > More on Lists
</s> |
<s>[INST] Catch multiple exceptions in one line (except block) I know that I can do:
try:
# do something that may fail
except:
# do this if ANYTHING goes wrong
I can also do this:
try:
# do something that may fail
except IDontLikeYourFaceException:
# put on makeup or smile
except YouAreTooShortException:
# stand on a ladder
But if I want to do the same thing inside two different exceptions, the best I can think of right now is to do this:
try:
# do something that may fail
except IDontLikeYouException:
# say please
except YouAreBeingMeanException:
# say please
Is there any way that I can do something like this (since the action to take in both exceptions is to say please):
try:
# do something that may fail
except IDontLikeYouException, YouAreBeingMeanException:
# say please
Now this really won't work, as it matches the syntax for:
try:
# do something that may fail
except Exception, e:
# say please
So, my effort to catch the two distinct exceptions doesn't exactly come through.
Is there a way to do this?
[/INST] From https://docs.python.org/2/tutorial/errors.html#handling-exceptions: "An except clause may name multiple exceptions as a parenthesized tuple, for example":
except (IDontLikeYouException, YouAreBeingMeanException) as e:
pass
Separating the exception from the variable with a comma will still work in Python 2.6 and 2.7, but is now deprecated and does not work in Python 3; now you should be using as.
</s> |
<s>[INST] Check if a given key already exists in a dictionary I wanted to test if a key exists in a dictionary before updating the value for the key.
I wrote the following code:
if 'key1' in dict.keys():
print "blah"
else:
print "boo"
I think this is not the best way to accomplish this task. Is there a better way to test for a key in the dictionary?
[/INST] in is the intended way to test for the existence of a key in a dict.
d = dict()
for i in xrange(100):
key = i % 10
if key in d:
d[key] += 1
else:
d[key] = 1
If you wanted a default, you can always use dict.get():
d = dict()
for i in xrange(100):
key = i % 10
d[key] = d.get(key, 0) + 1
... and if you wanted to always ensure a default value for any key you can use defaultdict from the collections module, like so:
from collections import defaultdict
d = defaultdict(lambda: 0)
for i in xrange(100):
d[i % 10] += 1
... but in general, the in keyword is the best way to do it.
</s> |
<s>[INST] Add key to a dictionary in Python? Is it possible to add a key to a Python dictionary after it has been created? It doesn't seem to have an .add() method.
[/INST] >>> d = {'key':'value'}
>>> print d
{'key': 'value'}
>>> d['mynewkey'] = 'mynewvalue'
>>> print d
{'mynewkey': 'mynewvalue', 'key': 'value'}
</s> |
<s>[INST] How to get current time in Python What is the module/method used to get current time?
[/INST] >>> import datetime
>>> datetime.datetime.now()
datetime(2009, 1, 6, 15, 8, 24, 78915)
And just the time:
>>> datetime.datetime.time(datetime.datetime.now())
datetime.time(15, 8, 24, 78915)
The same but slightly more compact:
>>> datetime.datetime.now().time()
See the documentation for more info.
To save typing, you can import the datetime object from the datetime module:
>>> from datetime import datetime
Then remove the leading datetime. from all the above.
</s> |
<s>[INST] How can I represent an 'Enum' in Python? I'm mainly a C# developer, but I'm currently working on a project in Python.
How can I represent the equivalent of an Enum in Python?
[/INST] Enums have been added to Python 3.4 as described in PEP 435. It has also been backported to 3.3, 3.2, 3.1, 2.7, 2.6, 2.5, and 2.4 on pypi.
For more advanced Enum techniques try the aenum library (2.7, 3.3+, same author as enum34. Code is not perfectly compatible between py2 and py3, e.g. you'll need __order__ in python 2).
To use enum34, do $ pip install enum34
To use aenum, do $ pip install aenum
Installing enum (no numbers) will install a completely different and incompatible version.
from enum import Enum # for enum34, or the stdlib version
# from aenum import Enum # for the aenum version
Animal = Enum('Animal', 'ant bee cat dog')
Animal.ant # returns <Animal.ant: 1>
Animal['ant'] # returns <Animal.ant: 1> (string lookup)
Animal.ant.name # returns 'ant' (inverse lookup)
or equivalently:
class Animal(Enum):
ant = 1
bee = 2
cat = 3
dog = 4
In earlier versions, one way of accomplishing enums is:
def enum(**enums):
return type('Enum', (), enums)
which is used like so:
>>> Numbers = enum(ONE=1, TWO=2, THREE='three')
>>> Numbers.ONE
1
>>> Numbers.TWO
2
>>> Numbers.THREE
'three'
You can also easily support automatic enumeration with something like this:
def enum(*sequential, **named):
enums = dict(zip(sequential, range(len(sequential))), **named)
return type('Enum', (), enums)
and used like so:
>>> Numbers = enum('ZERO', 'ONE', 'TWO')
>>> Numbers.ZERO
0
>>> Numbers.ONE
1
Support for converting the values back to names can be added this way:
def enum(*sequential, **named):
enums = dict(zip(sequential, range(len(sequential))), **named)
reverse = dict((value, key) for key, value in enums.iteritems())
enums['reverse_mapping'] = reverse
return type('Enum', (), enums)
This overwrites anything with that name, but it is useful for rendering your enums in output. It will throw KeyError if the reverse mapping doesn't exist. With the first example:
>>> Numbers.reverse_mapping['three']
'THREE'
</s> |
<s>[INST] Parse String to Float or Int In Python, how can I parse a numeric string like "545.2222" to its corresponding float value, 542.2222? Or parse the string "31" to an integer, 31?
I just want to know how to parse a float string to a float, and (separately) an int string to an int.
[/INST] >>> a = "545.2222"
>>> float(a)
545.22220000000004
>>> int(float(a))
545
</s> |
<s>[INST] How can I make a time delay in Python? I would like to know how to put a time delay in a Python script.
[/INST] import time
time.sleep(5) # delays for 5 seconds
Here is another example where something is run once a minute:
import time
while True:
print "This prints once a minute."
time.sleep(60) # Delay for 1 minute (60 seconds)
</s> |
<s>[INST] Iterating over dictionaries using for loops in Python I am a bit puzzled by the following code:
d = {'x': 1, 'y': 2, 'z': 3}
for key in d:
print key, 'corresponds to', d[key]
What I don't understand is the key portion. How does Python recognize that it needs only to read the key from the dictionary? Is key a special word in Python? Or is it simply a variable?
[/INST] key is just a variable name.
for key in d:
will simply loop over the keys in the dictionary, rather than the keys and values. To loop over both key and value you can use the following:
For Python 2.x:
for key, value in d.iteritems():
For Python 3.x:
for key, value in d.items():
To test for yourself, change the word key to poop.
For Python 3.x, iteritems() has been replaced with simply items(), which returns a set-like view backed by the dict, like iteritems() but even better.
This is also available in 2.7 as viewitems().
The operation items() will work for both 2 and 3, but in 2 it will return a list of the dictionary's (key, value) pairs, which will not reflect changes to the dict that happen after the items() call. If you want the 2.x behavior in 3.x, you can call list(d.items()).
</s> |
<s>[INST] Making a flat list out of list of lists in Python I wonder whether there is a shortcut to make a simple list out of list of lists in Python.
I can do that in a for loop, but maybe there is some cool "one-liner"? I tried it with reduce, but I get an error.
Code
l = [[1, 2, 3], [4, 5, 6], [7], [8, 9]]
reduce(lambda x, y: x.extend(y), l)
Error message
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "<stdin>", line 1, in <lambda>
AttributeError: 'NoneType' object has no attribute 'extend'
[/INST] [item for sublist in l for item in sublist]
is faster than the shortcuts posted so far. (l is the list to flatten.)
For evidence, as always, you can use the timeit module in the standard library:
$ python -mtimeit -s'l=[[1,2,3],[4,5,6], [7], [8,9]]*99' '[item for sublist in l for item in sublist]'
10000 loops, best of 3: 143 usec per loop
$ python -mtimeit -s'l=[[1,2,3],[4,5,6], [7], [8,9]]*99' 'sum(l, [])'
1000 loops, best of 3: 969 usec per loop
$ python -mtimeit -s'l=[[1,2,3],[4,5,6], [7], [8,9]]*99' 'reduce(lambda x,y: x+y,l)'
1000 loops, best of 3: 1.1 msec per loop
Explanation: the shortcuts based on + (including the implied use in sum) are, of necessity, O(L**2) when there are L sublists -- as the intermediate result list keeps getting longer, at each step a new intermediate result list object gets allocated, and all the items in the previous intermediate result must be copied over (as well as a few new ones added at the end). So (for simplicity and without actual loss of generality) say you have L sublists of I items each: the first I items are copied back and forth L-1 times, the second I items L-2 times, and so on; total number of copies is I times the sum of x for x from 1 to L excluded, i.e., I * (L**2)/2.
The list comprehension just generates one list, once, and copies each item over (from its original place of residence to the result list) also exactly once.
</s> |
<s>[INST] Print in terminal with colors using Python? How can I output colored text to the terminal, in Python?
What is the best Unicode symbol to represent a solid block?
[/INST] This somewhat depends on what platform you are on. The most common way to do this is by printing ANSI escape sequences. For a simple example, here's some python code from the blender build scripts:
class bcolors:
HEADER = '\033[95m'
OKBLUE = '\033[94m'
OKGREEN = '\033[92m'
WARNING = '\033[93m'
FAIL = '\033[91m'
ENDC = '\033[0m'
BOLD = '\033[1m'
UNDERLINE = '\033[4m'
To use code like this, you can do something like
print bcolors.WARNING + "Warning: No active frommets remain. Continue?"
+ bcolors.ENDC
This will work on unixes including OS X, linux and windows (provided you use ANSICON, or in Windows 10 provided you enable VT100 emulation). There are ansi codes for setting the color, moving the cursor, and more.
If you are going to get complicated with this (and it sounds like you are if you are writing a game), you should look into the "curses" module, which handles a lot of the complicated parts of this for you. The Python Curses HowTO is a good introduction.
If you are not using extended ASCII (i.e. not on a PC), you are stuck with the ascii characters below 127, and '#' or '@' is probably your best bet for a block. If you can ensure your terminal is using a IBM extended ascii character set, you have many more options. Characters 176, 177, 178 and 219 are the "block characters".
Some modern text-based programs, such as "Dwarf Fortress", emulate text mode in a graphical mode, and use images of the classic PC font. You can find some of these bitmaps that you can use on the Dwarf Fortress Wiki see (user-made tilesets).
The Text Mode Demo Contest has more resources for doing graphics in text mode.
Hmm.. I think got a little carried away on this answer. I am in the midst of planning an epic text-based adventure game, though. Good luck with your colored text!
</s> |
<s>[INST] Static class variables in Python Is it possible to have static class variables or methods in python? What syntax is required to do this?
[/INST] Variables declared inside the class definition, but not inside a method are class or static variables:
>>> class MyClass:
... i = 3
...
>>> MyClass.i
3
As @millerdev points out, this creates a class-level "i" variable, but this is distinct from any instance-level "i" variable, so you could have
>>> m = MyClass()
>>> m.i = 4
>>> MyClass.i, m.i
>>> (3, 4)
This is different from C++ and Java, but not so different from C#, where a static member can't be accessed using a reference to an instance.
See what the Python tutorial has to say on the subject of classes and class objects.
@Steve Johnson has already answered regarding static methods, also documented under "Built-in Functions" in the Python Library Reference.
class C:
@staticmethod
def f(arg1, arg2, ...): ...
@beidy recommends classmethods over staticmethod, as the method then receives the class type as the first argument, but I'm still a little fuzzy on the advantages of this approach over staticmethod. If you are too, then it probably doesn't matter.
</s> |
<s>[INST] How to get the size of a list items = []
items.append("apple")
items.append("orange")
items.append("banana")
# FAKE METHOD::
items.amount() # Should return 3
How do I do it right?
[/INST] The len() function can be used with a lot of types in Python - both built-in types and library types.
>>> len([1,2,3])
3
</s> |
<s>[INST] Is there a way to substring a string in Python? Is there a way to substring a string in Python, to get a new string from the 3rd character to the end of the string?
Maybe like myString[2:end]?
If leaving the second part means 'till the end', if you leave the first part, does it start from the start?
[/INST] >>> x = "Hello World!"
>>> x[2:]
'llo World!'
>>> x[:2]
'He'
>>> x[:-2]
'Hello Worl'
>>> x[-2:]
'd!'
>>> x[2:-2]
'llo Worl'
Python calls this concept "slicing" and it works on more than just strings. Take a look here for a comprehensive introduction.
</s> |
<s>[INST] How do you split a list into evenly sized chunks? I have a list of arbitrary length, and I need to split it up into equal size chunks and operate on it. There are some obvious ways to do this, like keeping a counter and two lists, and when the second list fills up, add it to the first list and empty the second list for the next round of data, but this is potentially extremely expensive.
I was wondering if anyone had a good solution to this for lists of any length, e.g. using generators.
This should work:
l = range(1, 1000)
print chunks(l, 10) -> [ [ 1..10 ], [ 11..20 ], .., [ 991..999 ] ]
I was looking for something useful in itertools but I couldn't find anything obviously useful. Might've missed it, though.
Related question: What is the most âpythonicâ way to iterate over a list in chunks?
[/INST] Here's a generator that yields the chunks you want:
def chunks(l, n):
"""Yield successive n-sized chunks from l."""
for i in range(0, len(l), n):
yield l[i:i + n]
import pprint
pprint.pprint(list(chunks(range(10, 75), 10)))
[[10, 11, 12, 13, 14, 15, 16, 17, 18, 19],
[20, 21, 22, 23, 24, 25, 26, 27, 28, 29],
[30, 31, 32, 33, 34, 35, 36, 37, 38, 39],
[40, 41, 42, 43, 44, 45, 46, 47, 48, 49],
[50, 51, 52, 53, 54, 55, 56, 57, 58, 59],
[60, 61, 62, 63, 64, 65, 66, 67, 68, 69],
[70, 71, 72, 73, 74]]
If you're using Python 2, you should use xrange() instead of range():
def chunks(l, n):
"""Yield successive n-sized chunks from l."""
for i in xrange(0, len(l), n):
yield l[i:i + n]
Also you can simply use list comprehension instead of write a function. Python 3:
[l[i:i + n] for i in range(0, len(l), n)]
Python 2 version:
[l[i:i + n] for i in xrange(0, len(l), n)]
</s> |
<s>[INST] How can I remove (chomp) a newline in Python? What is the Python equivalent of Perl's chomp function, which removes the last character of a value?
[/INST] Try the rstrip method.
>>> 'test string\n'.rstrip()
'test string'
Note that Python's rstrip method strips all kinds of trailing whitespace by default, not just one newline as Perl does with chomp. To strip only newlines:
>>> 'test string \n\n'.rstrip('\n')
'test string '
There is also the lstrip and strip methods.
>>> s = " \n abc def "
>>> s.strip()
'abc def'
>>> s.rstrip()
' \n abc def'
>>> s.lstrip()
'abc def '
>>>
</s> |
<s>[INST] Static methods in Python? Is it possible to have static methods in Python so I can call them without initializing a class, like:
ClassName.StaticMethod ( )
[/INST] Yep, using the staticmethod decorator
class MyClass(object):
@staticmethod
def the_static_method(x):
print x
MyClass.the_static_method(2) # outputs 2
Note that some code might use the old method of defining a static method, using staticmethod as a function rather than a decorator. This should only be used if you have to support ancient versions of Python (2.2 and 2.3)
class MyClass(object):
def the_static_method(x):
print x
the_static_method = staticmethod(the_static_method)
MyClass.the_static_method(2) # outputs 2
This is entirely identical to the first example (using @staticmethod), just not using the nice decorator syntax
Finally, use staticmethod() sparingly! There are very few situations where static-methods are necessary in Python, and I've seen them used many times where a separate "top-level" function would have been clearer.
The following is verbatim from the documentation::
A static method does not receive an implicit first argument. To declare a static method, use this idiom:
class C:
@staticmethod
def f(arg1, arg2, ...): ...
The @staticmethod form is a function decorator â see the description of function definitions in Function definitions for details.
It can be called either on the class (such as C.f()) or on an instance (such as C().f()). The instance is ignored except for its class.
Static methods in Python are similar to those found in Java or C++. For a more advanced concept, see classmethod().
For more information on static methods, consult the documentation on the standard type hierarchy in The standard type hierarchy.
New in version 2.2.
Changed in version 2.4: Function decorator syntax added.
</s> |
<s>[INST] How to clone or copy a list? What are the options to clone or copy a list in Python?
Using new_list = my_list then modifies new_list every time my_list changes.
Why is this?
[/INST] You have various possibilities:
You can slice it:
new_list = old_list[:]
Alex Martelli's opinion (at least back in 2007) about this is, that it is a weird syntax and it does not make sense to use it ever. ;) (In his opinion, the next one is more readable).
You can use the built in list() function:
new_list = list(old_list)
You can use generic copy.copy():
import copy
new_list = copy.copy(old_list)
This is a little slower than list() because it has to find out the datatype of old_list first.
If the list contains objects and you want to copy them as well, use generic copy.deepcopy():
import copy
new_list = copy.deepcopy(old_list)
Obviously the slowest and most memory-needing method, but sometimes unavoidable.
Example:
import copy
class Foo(object):
def __init__(self, val):
self.val = val
def __repr__(self):
return str(self.val)
foo = Foo(1)
a = ['foo', foo]
b = a[:]
c = list(a)
d = copy.copy(a)
e = copy.deepcopy(a)
# edit orignal list and instance
a.append('baz')
foo.val = 5
print('original: %r\n slice: %r\n list(): %r\n copy: %r\n deepcopy: %r'
% (a, b, c, d, e))
Result:
original: ['foo', 5, 'baz']
slice: ['foo', 5]
list(): ['foo', 5]
copy: ['foo', 5]
deepcopy: ['foo', 1]
</s> |
<s>[INST] How to append list to second list (concatenate lists) How do I concatenate two lists in Python?
Example:
listone = [1, 2, 3]
listtwo = [4, 5, 6]
Expected outcome:
joinedlist == [1, 2, 3, 4, 5, 6]
[/INST] Python makes this ridiculously easy.
mergedlist = listone + listtwo
</s> |
<s>[INST] Python join, why is it string.join(list) instead of list.join(string)? This has always confused me. It seems like this would be nicer:
my_list = ["Hello", "world"]
print my_list.join("-")
# Produce: "Hello-world"
Than this:
my_list = ["Hello", "world"]
print "-".join(my_list)
# Produce: "Hello-world"
Is there a specific reason it does it like this?
[/INST] It's because any iterable can be joined, not just lists, but the result and the "joiner" are always strings.
E.G:
import urllib2
print '\n############\n'.join(
urllib2.urlopen('http://data.stackexchange.com/users/7095'))
</s> |
<s>[INST] Why is reading lines from stdin much slower in C++ than Python? I wanted to compare reading lines of string input from stdin using Python and C++ and was shocked to see my C++ code run an order of magnitude slower than the equivalent Python code. Since my C++ is rusty and I'm not yet an expert Pythonista, please tell me if I'm doing something wrong or if I'm misunderstanding something.
(tl;dr answer: include the statement: cin.sync_with_stdio(false) or just use fgets instead.
tl;dr results: scroll all the way down to the bottom of my question and look at the table.)
C++ code:
#include <iostream>
#include <time.h>
using namespace std;
int main() {
string input_line;
long line_count = 0;
time_t start = time(NULL);
int sec;
int lps;
while (cin) {
getline(cin, input_line);
if (!cin.eof())
line_count++;
};
sec = (int) time(NULL) - start;
cerr << "Read " << line_count << " lines in " << sec << " seconds." ;
if (sec > 0) {
lps = line_count / sec;
cerr << " LPS: " << lps << endl;
} else
cerr << endl;
return 0;
}
//Compiled with:
//g++ -O3 -o readline_test_cpp foo.cpp
Python Equivalent:
#!/usr/bin/env python
import time
import sys
count = 0
start = time.time()
for line in sys.stdin:
count += 1
delta_sec = int(time.time() - start_time)
if delta_sec >= 0:
lines_per_sec = int(round(count/delta_sec))
print("Read {0} lines in {1} seconds. LPS: {2}".format(count, delta_sec,
lines_per_sec))
Here are my results:
$ cat test_lines | ./readline_test_cpp
Read 5570000 lines in 9 seconds. LPS: 618889
$cat test_lines | ./readline_test.py
Read 5570000 lines in 1 seconds. LPS: 5570000
Edit: I should note that I tried this both under OS-X (10.6.8) and Linux 2.6.32 (RHEL 6.2). The former is a macbook pro, the latter is a very beefy server, not that this is too pertinent.
Edit 2: (Removed this edit, as no longer applicable)
$ for i in {1..5}; do echo "Test run $i at `date`"; echo -n "CPP:"; cat test_lines | ./readline_test_cpp ; echo -n "Python:"; cat test_lines | ./readline_test.py ; done
Test run 1 at Mon Feb 20 21:29:28 EST 2012
CPP: Read 5570001 lines in 9 seconds. LPS: 618889
Python:Read 5570000 lines in 1 seconds. LPS: 5570000
Test run 2 at Mon Feb 20 21:29:39 EST 2012
CPP: Read 5570001 lines in 9 seconds. LPS: 618889
Python:Read 5570000 lines in 1 seconds. LPS: 5570000
Test run 3 at Mon Feb 20 21:29:50 EST 2012
CPP: Read 5570001 lines in 9 seconds. LPS: 618889
Python:Read 5570000 lines in 1 seconds. LPS: 5570000
Test run 4 at Mon Feb 20 21:30:01 EST 2012
CPP: Read 5570001 lines in 9 seconds. LPS: 618889
Python:Read 5570000 lines in 1 seconds. LPS: 5570000
Test run 5 at Mon Feb 20 21:30:11 EST 2012
CPP: Read 5570001 lines in 10 seconds. LPS: 557000
Python:Read 5570000 lines in 1 seconds. LPS: 5570000
Edit 3:
Okay, I tried J.N.'s suggestion of trying having python store the line read: but it made no difference to python's speed.
I also tried J.N.'s suggestion of using scanf into a char array instead of getline into a std::string. Bingo! This resulted in equivalent performance for both python and c++. (3,333,333 LPS with my input data, which by the way are just short lines of three fields each, usually about 20 chars wide, though sometimes more).
Code:
char input_a[512];
char input_b[32];
char input_c[512];
while(scanf("%s %s %s\n", input_a, input_b, input_c) != EOF) {
line_count++;
};
Speed:
$ cat test_lines | ./readline_test_cpp2
Read 10000000 lines in 3 seconds. LPS: 3333333
$ cat test_lines | ./readline_test2.py
Read 10000000 lines in 3 seconds. LPS: 3333333
(Yes, I ran it several times.) So, I guess I will now use scanf instead of getline. But, I'm still curious if people think this performance hit from std::string/getline is typical and reasonable.
Edit 4 (was: Final Edit / Solution):
Adding:
cin.sync_with_stdio(false);
Immediately above my original while loop above results in code that runs faster than Python.
New performance comparison (this is on my 2011 Macbook Pro), using the original code, the original with the sync disabled, and the original python, respectively, on a file with 20M lines of text. Yes, I ran it several times to eliminate disk caching confound.
$ /usr/bin/time cat test_lines_double | ./readline_test_cpp
33.30 real 0.04 user 0.74 sys
Read 20000001 lines in 33 seconds. LPS: 606060
$ /usr/bin/time cat test_lines_double | ./readline_test_cpp1b
3.79 real 0.01 user 0.50 sys
Read 20000000 lines in 4 seconds. LPS: 5000000
$ /usr/bin/time cat test_lines_double | ./readline_test.py
6.88 real 0.01 user 0.38 sys
Read 20000000 lines in 6 seconds. LPS: 3333333
Thanks to @Vaughn Cato for his answer! Any elaboration people can make or good references people can point to as to why this sync happens, what it means, when it's useful, and when it's okay to disable would be greatly appreciated by posterity. :-)
Edit 5 / Better Solution:
As suggested by Gandalf The Gray below, gets is even faster than scanf or the unsynchronized cin approach. I also learned that scanf and gets are both UNSAFE and should NOT BE USED due to potential of buffer overflow. So, I wrote this iteration using fgets, the safer alternative to gets. Here are the pertinent lines for my fellow noobs:
char input_line[MAX_LINE];
char *result;
//<snip>
while((result = fgets(input_line, MAX_LINE, stdin )) != NULL)
line_count++;
if (ferror(stdin))
perror("Error reading stdin.");
Now, here are the results using an even larger file (100M lines; ~3.4GB) on a fast server with very fast disk, comparing the python, the unsynced cin, and the fgets approaches, as well as comparing with the wc utility. [The scanf version segfaulted and I don't feel like troubleshooting it.]:
$ /usr/bin/time cat temp_big_file | readline_test.py
0.03user 2.04system 0:28.06elapsed 7%CPU (0avgtext+0avgdata 2464maxresident)k
0inputs+0outputs (0major+182minor)pagefaults 0swaps
Read 100000000 lines in 28 seconds. LPS: 3571428
$ /usr/bin/time cat temp_big_file | readline_test_unsync_cin
0.03user 1.64system 0:08.10elapsed 20%CPU (0avgtext+0avgdata 2464maxresident)k
0inputs+0outputs (0major+182minor)pagefaults 0swaps
Read 100000000 lines in 8 seconds. LPS: 12500000
$ /usr/bin/time cat temp_big_file | readline_test_fgets
0.00user 0.93system 0:07.01elapsed 13%CPU (0avgtext+0avgdata 2448maxresident)k
0inputs+0outputs (0major+181minor)pagefaults 0swaps
Read 100000000 lines in 7 seconds. LPS: 14285714
$ /usr/bin/time cat temp_big_file | wc -l
0.01user 1.34system 0:01.83elapsed 74%CPU (0avgtext+0avgdata 2464maxresident)k
0inputs+0outputs (0major+182minor)pagefaults 0swaps
100000000
Recap (lines per second):
python: 3,571,428
cin (no sync): 12,500,000
fgets: 14,285,714
wc: 54,644,808
As you can see, fgets is better but still pretty far from wc performance; I'm pretty sure this is due to the fact that wc examines each character without any memory copying. I suspect that, at this point, other parts of the code will become the bottleneck, so I don't think optimizing to that level would even be worthwhile, even if possible (since, after all, I actually need to store the read lines in memory).
Also note that a small tradeoff with using a char * buffer and fgets vs unsynced cin to string is that the latter can read lines of any length, while the former requires limiting input to some finite number. In practice, this is probably a non-issue for reading most line-based input files, as the buffer can be set to a very large value that would not be exceeded by valid input.
This has been educational. Thanks to all for your comments and suggestions.
Edit 6:
As suggested by J.F. Sebastian in the comments below, the GNU wc utility uses plain C read() (within the safe-read.c wrapper) to read chunks (of 16k bytes) at a time and count new lines. Here's a python equivalent based on J.F.'s code (just showing the relevant snippet that replaces the python for loop:
BUFFER_SIZE = 16384
count = sum(chunk.count('\n') for chunk in iter(partial(sys.stdin.read, BUFFER_SIZE), ''))
The performance of this version is quite fast (though still a bit slower than the raw c wc utility, of course:
$ /usr/bin/time cat temp_big_file | readline_test3.py
0.01user 1.16system 0:04.74elapsed 24%CPU (0avgtext+0avgdata 2448maxresident)k
0inputs+0outputs (0major+181minor)pagefaults 0swaps
Read 100000000 lines in 4.7275 seconds. LPS: 21152829
Again, it's a bit silly for me to compare C++ fgets/cin and the first python code on the one hand to wc -l and this last python snippet on the other, as the latter two don't actually store the read lines but merely count newlines. Still, it's interesting to explore all the different implementations and think about the performance implications. Thanks again!
Edit 7: Tiny benchmark addendum and recap
For completeness, I thought I'd update the read speed for the same file on the same box with the original (synced) C++ code. Again, this is for a 100M line file on a fast disk. Here's the complete table now:
Implementation Lines per second
python (default) 3,571,428
cin (default/naive) 819,672
cin (no sync) 12,500,000
fgets 14,285,714
wc (not fair comparison) 54,644,808
[/INST] By default, cin is synchronized with stdio, which causes it to avoid any input buffering. If you add this to the top of your main, you should see much better performance:
std::ios_base::sync_with_stdio(false);
Normally, when an input stream is buffered, instead of reading one character at a time, the stream will be read in larger chunks. This reduces the number of system calls, which are typically relatively expensive. However, since the FILE* based stdio and iostreams often have separate implementations and therefore separate buffers, this could lead to a problem if both were used together. For example:
int myvalue1;
cin >> myvalue1;
int myvalue2;
scanf("%d",&myvalue2);
If more input was read by cin than it actually needed, then the second integer value wouldn't be available for the scanf function, which has its own independent buffer. This would lead to unexpected results.
To avoid this, by default, streams are synchronized with stdio. One common way to achieve this is to have cin read each character one at a time as needed using stdio functions. Unfortunately, this introduces a lot of overhead. For small amounts of input, this isn't a big problem, but when you are reading millions of lines, the performance penalty is significant.
Fortunately, the library designers decided that you should also be able to disable this feature to get improved performance if you knew what you were doing, so they provided the sync_with_stdio method.
</s> |
<s>[INST] How to read a file line by line into a list with Python How do I read every line of a file in Python and store each line as an element in list?
I want to read the file line by line and each line is appended to the end of the list.
[/INST] with open(fname) as f:
content = f.readlines()
I'm guessing that you meant list and not array.
</s> |
<s>[INST] Installing pip on Mac OS X I spent most of the day yesterday searching for a clear answer for installing pip. I can't find a good solution.
Can somebody help me install it?
[/INST] All you need to do is
sudo easy_install pip
</s> |
<s>[INST] How do I check if a string is a number (float) in Python? What is the best possible way to check if a string can be represented as a number in Python?
The function I currently have right now is:
def is_number(s):
try:
float(s)
return True
except ValueError:
return False
Which, not only is ugly and slow, seems clunky. However I haven't found a better method because calling float in the main function is even worse.
[/INST] In case you are looking for parsing (positive, unsigned) integers instead of floats, you can use the isdigit() function for string objects.
>>> a = "03523"
>>> a.isdigit()
True
>>> b = "963spam"
>>> b.isdigit()
False
String Methods - isdigit()
There's also something on Unicode strings, which I'm not too familiar with
Unicode - Is decimal/decimal
</s> |
<s>[INST] Upgrading all packages with pip Is it possible to upgrade all Python packages at one time with pip?
Note that there is a feature request for this on the official issue tracker.
[/INST] There isn't a built-in flag yet, but you can use
pip freeze --local | grep -v '^\-e' | cut -d = -f 1 | xargs -n1 pip install -U
Note: there are infinite potential variations for this. I'm trying to keep this answer short and simple, but please do suggest variations in the comments!
Relevant edits:
Added a grep to skip "-e" package definitions, as suggested by @jawache (Yes, you could replace grep+cut with sed or awk or Perl or...).
Newer versions of pip allow you to list outdated packages, though not in "requirements" format: pip list --outdated
Added -n1 to xargs, prevents stopping everything if updating one package fails (thanks @andsens)
</s> |
<s>[INST] How do you read from stdin in Python? I'm trying to do some of the code golf challenges, but they all require the input to be taken from stdin. How do I get that in Python?
[/INST] You could use the fileinput module:
import fileinput
for line in fileinput.input():
pass
fileinput will loop through all the lines in the input specified as file names given in command-line arguments, or the standard input if no arguments are provided.
</s> |
<s>[INST] Python string formatting: % vs. .format Python 2.6 introduced the str.format() method with a slightly different syntax from the existing % operator. Which is better and for what situations?
The following uses each method and has the same outcome, so what is the difference?
#!/usr/bin/python
sub1 = "python string!"
sub2 = "an arg"
a = "i am a %s" % sub1
b = "i am a {0}".format(sub1)
c = "with %(kwarg)s!" % {'kwarg':sub2}
d = "with {kwarg}!".format(kwarg=sub2)
print a # "i am a python string!"
print b # "i am a python string!"
print c # "with an arg!"
print d # "with an arg!"
Furthermore when does string formatting occur in Python? For example, if my logging level is set to HIGH will I still take a hit for performing the following % operation? And if so, is there a way to avoid this?
log.debug("some debug info: %s" % some_info)
[/INST] To answer your first question... .format just seems more sophisticated in many ways. An annoying thing about % is also how it can either take a variable or a tuple. You'd think the following would always work:
"hi there %s" % name
yet, if name happens to be (1, 2, 3), it will throw a TypeError. To guarantee that it always prints, you'd need to do
"hi there %s" % (name,) # supply the single argument as a single-item tuple
which is just ugly. .format doesn't have those issues. Also in the second example you gave, the .format example is much cleaner looking.
Why would you not use it?
not knowing about it (me before reading this)
having to be compatible with Python 2.5
To answer your second question, string formatting happens at the same time as any other operation - when the string formatting expression is evaluated. And Python, not being a lazy language, evaluates expressions before calling functions, so in your log.debug example, the expression "some debug info: %s"%some_infowill first evaluate to, e.g. "some debug info: roflcopters are active", then that string will be passed to log.debug().
</s> |
<s>[INST] Determine the type of a Python object Is there a simple way to determine if a variable is a list, dictionary, or something else? I am getting an object back that may be either type and I need to be able to tell the difference.
[/INST] To get the type of an object, you can use the built-in type() function. Passing an object as the only parameter will return the type object of that object:
>>> type([]) is list
True
>>> type({}) is dict
True
>>> type('') is str
True
>>> type(0) is int
True
>>> type({})
<type 'dict'>
>>> type([])
<type 'list'>
This of course also works for custom types:
>>> class Test1 (object):
pass
>>> class Test2 (Test1):
pass
>>> a = Test1()
>>> b = Test2()
>>> type(a) is Test1
True
>>> type(b) is Test2
True
Note that type() will only return the immediate type of the object, but wonât be able to tell you about type inheritance.
>>> type(b) is Test1
False
To cover that, you should use the isinstance function. This of course also works for built-in types:
>>> isinstance(b, Test1)
True
>>> isinstance(b, Test2)
True
>>> isinstance(a, Test1)
True
>>> isinstance(a, Test2)
False
>>> isinstance([], list)
True
>>> isinstance({}, dict)
True
isinstance() is usually the preferred way to ensure the type of an object because it will also accept derived types. So unless you actually need the type object (for whatever reason), using isinstance() is preferred over type().
The second parameter of isinstance() also accepts a tuple of types, so itâs possible to check for multiple types at once. isinstance will then return true, if the object is of any of those types:
>>> isinstance([], (tuple, list, set))
True
</s> |
<s>[INST] What does ** (double star) and * (star) do for Python parameters? In the following method definitions, what does the * and ** do for param2?
def foo(param1, *param2):
def bar(param1, **param2):
[/INST] The *args and **kwargs is a common idiom to allow arbitrary number of arguments to functions as described in the section more on defining functions in the Python documentation.
The *args will give you all function parameters as a tuple:
In [1]: def foo(*args):
...: for a in args:
...: print a
...:
...:
In [2]: foo(1)
1
In [4]: foo(1,2,3)
1
2
3
The **kwargs will give you all
keyword arguments except for those corresponding to a formal parameter as a dictionary.
In [5]: def bar(**kwargs):
...: for a in kwargs:
...: print a, kwargs[a]
...:
...:
In [6]: bar(name='one', age=27)
age 27
name one
Both idioms can be mixed with normal arguments to allow a set of fixed and some variable arguments:
def foo(kind, *args, **kwargs):
pass
Another usage of the *l idiom is to unpack argument lists when calling a function.
In [9]: def foo(bar, lee):
...: print bar, lee
...:
...:
In [10]: l = [1,2]
In [11]: foo(*l)
1 2
In Python 3 it is possible to use *l on the left side of an assignment (Extended Iterable Unpacking):
first, *rest = [1,2,3,4]
first, *l, last = [1,2,3,4]
Also Python 3 adds new semantic (refer PEP 3102):
def func(arg1, arg2, arg3='default', *, kwarg1='abc', kwarg2='xyz'):
pass
Such function accepts only 2 positional arguments, and everything after * can only be passed as keyword argument, not positional one.
In Python 2 similar was true for all parameters after *args.
</s> |
<s>[INST] How to convert string to lowercase in Python? Is there any way to convert an entire user inputted string from uppercase, or even part uppercase to lowercase?
E.g. Kilometers --> kilometers.
[/INST] s = "Kilometer"
print(s.lower())
Official documentation here
</s> |
<s>[INST] Converting string into datetime Short and simple. I've got a huge list of date-times like this as strings:
Jun 1 2005 1:33PM
Aug 28 1999 12:00AM
I'm going to be shoving these back into proper datetime fields in a database so I need to magic them into real datetime objects.
Any help (even if it's just a kick in the right direction) would be appreciated.
Edit: This is going through Django's ORM so I can't use SQL to do the conversion on insert.
[/INST] from datetime import datetime
date_object = datetime.strptime('Jun 1 2005 1:33PM', '%b %d %Y %I:%M%p')
Link to the Python documentation for strptime
and a link for the strftime format mask
This is also a really nice reference for stftime
</s> |
<s>[INST] Getting the last element of a list in Python In Python, how do you get the last element of a list?
[/INST] some_list[-1] is the shortest and most Pythonic.
In fact, you can do much more with this syntax. The some_list[-n] syntax gets the nth-to-last element. So some_list[-1] gets the last element, some_list[-2] gets the second to last, etc, all the way down to some_list[-len(some_list)], which gives you the first element.
You can also set list elements in this way. For instance:
>>> some_list = [1, 2, 3]
>>> some_list[-1] = 5 # Set the last element
>>> some_list[-2] = 3 # Set the second to last element
>>> some_list
[1, 3, 5]
</s> |
<s>[INST] How do I randomly select an item from a list using Python? Assume I have the following list:
foo = ['a', 'b', 'c', 'd', 'e']
What is the simplest way to retrieve an item at random from this list?
[/INST] Use random.choice:
import random
foo = ['a', 'b', 'c', 'd', 'e']
print(random.choice(foo))
</s> |
<s>[INST] How do I sort a list of dictionaries by values of the dictionary in Python? I got a list of dictionaries and want that to be sorted by a value of that dictionary.
This
[{'name':'Homer', 'age':39}, {'name':'Bart', 'age':10}]
sorted by name, should become
[{'name':'Bart', 'age':10}, {'name':'Homer', 'age':39}]
[/INST] It may look cleaner using a key instead a cmp:
newlist = sorted(list_to_be_sorted, key=lambda k: k['name'])
or as J.F.Sebastian and others suggested,
from operator import itemgetter
newlist = sorted(list_to_be_sorted, key=itemgetter('name'))
For completeness (as pointed out in comments by fitzgeraldsteele), add reverse=True to sort descending
newlist = sorted(l, key=itemgetter('name'), reverse=True)
</s> |
<s>[INST] How do I copy a file in python? How do I copy a file in Python? I couldn't find anything under os.
[/INST] shutil has many methods you can use. One of which is:
from shutil import copyfile
copyfile(src, dst)
Copy the contents of the file named src to a file named dst. The destination location must be writable; otherwise, an IOError exception will be raised. If dst already exists, it will be replaced. Special files such as character or block devices and pipes cannot be copied with this function. src and dst are path names given as strings.
</s> |
<s>[INST] Manually raising (throwing) an exception in Python How can I raise an exception in Python so that it can later be caught via an except block?
[/INST]
How do I manually throw/raise an exception in Python?
Use the most specific Exception constructor that semantically fits your issue.
Be specific in your message, e.g.:
raise ValueError('A very specific bad thing happened')
Don't do this:
Avoid raising a generic Exception, to catch it, you'll have to catch all other more specific exceptions that subclass it.
Hiding bugs
raise Exception('I know Python!') # don't, if you catch, likely to hide bugs.
For example:
def demo_bad_catch():
try:
raise ValueError('represents a hidden bug, do not catch this')
raise Exception('This is the exception you expect to handle')
except Exception as error:
print('caught this error: ' + repr(error))
>>> demo_bad_catch()
caught this error: ValueError('represents a hidden bug, do not catch this',)
Won't catch
and more specific catches won't catch the general exception:
def demo_no_catch():
try:
raise Exception('general exceptions not caught by specific handling')
except ValueError as e:
print('we will not catch e')
>>> demo_no_catch()
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "<stdin>", line 3, in demo_no_catch
Exception: general exceptions not caught by specific handling
Best Practice:
Instead, use the most specific Exception constructor that semantically fits your issue.
raise ValueError('A very specific bad thing happened')
which also handily allows an arbitrary number of arguments to be passed to the constructor. This works in Python 2 and 3.
raise ValueError('A very specific bad thing happened', 'foo', 'bar', 'baz')
These arguments are accessed by the args attribute on the Exception object. For example:
try:
some_code_that_may_raise_our_value_error()
except ValueError as err:
print(err.args)
prints
('message', 'foo', 'bar', 'baz')
In Python 2.5, an actual message attribute was added to BaseException in favor of encouraging users to subclass Exceptions and stop using args, but the introduction of message and the original deprecation of args has been retracted.
When in except clause
When inside an except clause, you might want to, e.g. log that a specific type of error happened, and then reraise. The best way to do this while preserving the stack trace is to use a bare raise statement, e.g.:
try:
do_something_in_app_that_breaks_easily()
except AppError as error:
logger.error(error)
raise # just this!
# raise AppError # Don't do this, you'll lose the stack trace!
You can preserve the stacktrace (and error value) with sys.exc_info(), but this is way more error prone, prefer to use a bare raise to reraise. This is the syntax in Python 2:
raise AppError, error, sys.exc_info()[2] # avoid this.
# Equivalently, as error *is* the second object:
raise sys.exc_info()[0], sys.exc_info()[1], sys.exc_info()[2]
In Python 3:
raise error.with_traceback(sys.exc_info()[2])
Again: avoid manually manipulating tracebacks. It's less efficient and more error prone. And if you're using threading and sys.exc_info you may even get the wrong traceback (especially if you're using exception handling for control flow - which I'd personally tend to avoid.)
Python 3, Exception chaining
In Python 3, you can chain Exceptions, which preserve tracebacks:
raise RuntimeError('specific message') from error
But beware, this does change the error type raised.
Deprecated Methods:
These can easily hide and even get into production code. You want to raise an exception/error, and doing them will raise an error, but not the one intended!
Valid in Python 2, but not in Python 3 is the following:
raise ValueError, 'message' # Don't do this, it's deprecated!
Only valid in much older versions of Python (2.4 and lower), you may still see people raising strings:
raise 'message' # really really wrong. don't do this.
In all modern versions, this will actually raise a TypeError, because you're not raising a BaseException type. If you're not checking for the right exception and don't have a reviewer that's aware of the issue, it could get into production.
Example Usage:
I raise Exceptions to warn consumers of my API if they're using it incorrectly:
def api_func(foo):
'''foo should be either 'baz' or 'bar'. returns something very useful.'''
if foo not in _ALLOWED_ARGS:
raise ValueError('{foo} wrong, use "baz" or "bar"'.format(foo=repr(foo)))
Create your own error types when apropos:
"I want to make an error on purpose, so that it would go into the except"
You can create your own error types, if you want to indicate something specific is wrong with your application, just subclass the appropriate point in the exception hierarchy:
class MyAppLookupError(LookupError):
'''raise this when there's a lookup error for my app'''
and usage:
if important_key not in resource_dict and not ok_to_be_missing:
raise MyAppLookupError('resource is missing, and that is not ok.')
</s> |
<s>[INST] Replacements for switch statement in Python? I want to write a function in Python that returns different fixed values based on the value of an input index.
In other languages I would use a switch or case statement, but Python does not appear to have a switch statement. What are the recommended Python solutions in this scenario?
[/INST] If you'd like defaults you could use the dictionary get(key[, default]) method:
def f(x):
return {
'a': 1,
'b': 2,
}.get(x, 9) # 9 is default if x not found
</s> |
<s>[INST] How to print in Python without newline or space? The question is in the title.
I'd like to do in python what I do in this example in c:
#include <stdio.h>
int main() {
int i;
for (i=0; i<10; i++) printf(".");
return 0;
}
Output:
..........
In Python:
>>> for i in xrange(0,10): print '.'
.
.
.
.
.
.
.
.
.
.
>>> for i in xrange(0,10): print '.',
. . . . . . . . . .
In Python print will add a \n or a space, how can I avoid that? Now, it's just an example. Don't tell me I can first make a string then print it. I'd like to know how to "append" strings to the stdout (I don't know if it's worded correctly).
[/INST] General way
import sys
sys.stdout.write('.')
You may also need to call
sys.stdout.flush()
to ensure stdout is flushed immediately.
Python 2.6+
From Python 2.6 you can import the print function from Python 3:
from __future__ import print_function
This allows you to use the Python 3 solution below.
Python 3
In Python 3, the print statement has been changed into a function. In Python 3, you can instead do:
print('.', end="")
This also works in Python 2, provided that you've used from __future__ import print_function.
If you are having trouble with buffering, you can flush the output by adding flush=True keyword argument:
print('.', end="", flush=True)
</s> |
<s>[INST] Why is "1000000000000000 in range(1000000000000001)" so fast in Python 3? It is my understanding that the range() function, which is actually an object type in Python 3, generates its contents on the fly, similar to a generator.
This being the case, I would have expected the following line to take an inordinate amount of time, because in order to determine whether 1 quadrillion is in the range, a quadrillion values would have to be generated:
1000000000000000 in range(1000000000000001)
Furthermore: it seems that no matter how many zeroes I add on, the calculation more or less takes the same amount of time (basically instantaneous).
I have also tried things like this, but the calculation is still almost instant:
1000000000000000000000 in range(0,1000000000000000000001,10) # count by tens
If I try to implement my own range function, the result is not so nice!!
def my_crappy_range(N):
i = 0
while i < N:
yield i
i += 1
return
What is the range() object doing under the hood that makes it so fast?
EDIT: This has turned out to be a much more nuanced topic than I anticipated - there seems to be a bit of history behind the optimization of range().
Martijn Pieters' answer was chosen for its completeness, but also see abarnert's first answer for a good discussion of what it means for range to be a full-fledged sequence in Python 3, and some information/warning regarding potential inconsistency for __contains__ function optimization across Python implementations. abarnert's other answer goes into some more detail and provides links for those interested in the history behind the optimization in Python 3 (and lack of optimization of xrange in Python 2). Answers by poke and by wim provide the relevant C source code and explanations for those who are interested.
[/INST] The Python 3 range() object doesn't produce numbers immediately; it is a smart sequence object that produces numbers on demand. All it contains is your start, stop and step values, then as you iterate over the object the next integer is calculated each iteration.
The object also implements the object.__contains__ hook, and calculates if your number is part of its range. Calculating is a O(1) constant time operation. There is never a need to scan through all possible integers in the range.
From the range() object documentation:
The advantage of the range type over a regular list or tuple is that a range object will always take the same (small) amount of memory, no matter the size of the range it represents (as it only stores the start, stop and step values, calculating individual items and subranges as needed).
So at a minimum, your range() object would do:
class my_range(object):
def __init__(self, start, stop=None, step=1):
if stop is None:
start, stop = 0, start
self.start, self.stop, self.step = start, stop, step
if step < 0:
lo, hi = stop, start
else:
lo, hi = start, stop
self.length = ((hi - lo - 1) // abs(step)) + 1
def __iter__(self):
current = self.start
if self.step < 0:
while current > self.stop:
yield current
current += self.step
else:
while current < self.stop:
yield current
current += self.step
def __len__(self):
return self.length
def __getitem__(self, i):
if 0 <= i < self.length:
return self.start + i * self.step
raise IndexError('Index out of range: {}'.format(i))
def __contains__(self, num):
if self.step < 0:
if not (self.stop < num <= self.start):
return False
else:
if not (self.start <= num < self.stop):
return False
return (num - self.start) % self.step == 0
This is still missing several things that a real range() supports (such as the .index() or .count() methods, hashing, equality testing, or slicing), but should give you an idea.
I also simplified the __contains__ implementation to only focus on integer tests; if you give a real range() object a non-integer value (including subclasses of int), a slow scan is initiated to see if there is a match, just as if you use a containment test against a list of all the contained values. This was done to continue to support other numeric types that just happen to support equality testing with integers but are not expected to support integer arithmetic as well. See the original Python issue that implemented the containment test.
</s> |
<s>[INST] Calling a function of a module from a string with the function's name in Python What is the best way to go about calling a function given a string with the function's name in a Python program. For example, let's say that I have a module foo, and I have a string whose contents are "bar". What is the best way to go about calling foo.bar()?
I need to get the return value of the function, which is why I don't just use eval. I figured out how to do it by using eval to define a temp function that returns the result of that function call, but I'm hoping that there is a more elegant way to do this.
[/INST] Assuming module foo with method bar:
import foo
methodToCall = getattr(foo, 'bar')
result = methodToCall()
As far as that goes, lines 2 and 3 can be compressed to:
result = getattr(foo, 'bar')()
if that makes more sense for your use case. You can use getattr in this fashion on class instance bound methods, module-level methods, class methods... the list goes on.
</s> |
<s>[INST] Find current directory and file's directory In Python, what commands can I use to find:
the current directory (where I was in the terminal when I ran the Python script), and
where the file I am executing is?
[/INST] To get the full path to the directory a Python file is contained in, write this in that file:
import os
dir_path = os.path.dirname(os.path.realpath(__file__))
(Note that the incantation above won't work if you've already used os.chdir() to change your current working directory, since the value of the __file__ constant is relative to the current working directory and is not changed by an os.chdir() call.)
To get the current working directory use
import os
cwd = os.getcwd()
Documentation references for the modules, constants and functions used above:
The os and os.path modules.
The __file__ constant
os.path.realpath(path) (returns "the canonical path of the specified filename, eliminating any symbolic links encountered in the path")
os.path.dirname(path) (returns "the directory name of pathname path")
os.getcwd() (returns "a string representing the current working directory")
os.chdir(path) ("change the current working directory to path")
</s> |
<s>[INST] Reverse a string in Python There is no built in reverse function in Python's str object. What is the best way of implementing this?
If supplying a very concise answer, please elaborate on it's efficiency. Is the str converted to a different object, etc.
[/INST] How about:
>>> 'hello world'[::-1]
'dlrow olleh'
This is extended slice syntax. It works by doing [begin:end:step] - by leaving begin and end off and specifying a step of -1, it reverses a string.
</s> |
<s>[INST] What is __init__.py for? What is __init__.py for in a Python source directory?
[/INST] It's a part of a package. Here's the documentation.
The __init__.py files are required to make Python treat the directories as containing packages; this is done to prevent directories with a common name, such as string, from unintentionally hiding valid modules that occur later (deeper) on the module search path. In the simplest case, __init__.py can just be an empty file, but it can also execute initialization code for the package or set the __all__ variable, described later.
</s> |
<s>[INST] How to know if an object has an attribute in Python Is there a way in Python to determine if an object has some attribute? For example:
>>> a = SomeClass()
>>> a.someProperty = value
>>> a.property
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
AttributeError: SomeClass instance has no attribute 'property'
How can you tell if a has the attribute property before using it?
[/INST] Try hasattr():
if hasattr(a, 'property'):
a.property
EDIT: See zweiterlinde's answer below, who offers good advice about asking forgiveness! A very pythonic approach!
The general practice in python is that, if the property is likely to be there most of the time, simply call it and either let the exception propagate, or trap it with a try/except block. This will likely be faster than hasattr. If the property is likely to not be there most of the time, or you're not sure, using hasattr will probably be faster than repeatedly falling into an exception block.
</s> |
<s>[INST] How do you append to a file in Python? How do you append to the file instead of overwriting it? Is there a special function that appends to the file?
[/INST] with open("test.txt", "a") as myfile:
myfile.write("appended text")
</s> |
<s>[INST] Python @classmethod and @staticmethod for beginner? Could someone explain to me the meaning of @classmethod and @staticmethod in python? I need to know the difference and the meaning.
As far as I understand, @classmethod tells a class that it's a method which should be inherited into subclasses, or... something. However, what's the point of that? Why not just define the class method without adding @classmethod or @staticmethod or any @ definitions?
tl;dr: when should I use them, why should I use them, and how should I use them?
I'm pretty advanced with C++, so using more advanced programming concepts shouldn't be a problem. Feel free giving me a corresponding C++ example if possible.
[/INST] Though classmethod and staticmethod are quite similar, there's a slight difference in usage for both entities: classmethod must have a reference to a class object as the first parameter, whereas staticmethod can have no parameters at all.
Let's look at all that was said in real examples.
Boilerplate
Let's assume an example of a class, dealing with date information (this is what will be our boilerplate to cook on):
class Date(object):
day = 0
month = 0
year = 0
def __init__(self, day=0, month=0, year=0):
self.day = day
self.month = month
self.year = year
This class obviously could be used to store information about certain dates (without timezone information; let's assume all dates are presented in UTC).
Here we have __init__, a typical initializer of Python class instances, which receives arguments as a typical instancemethod, having the first non-optional argument (self) that holds reference to a newly created instance.
Class Method
We have some tasks that can be nicely done using classmethods.
Let's assume that we want to create a lot of Date class instances having date information coming from outer source encoded as a string of next format ('dd-mm-yyyy'). We have to do that in different places of our source code in project.
So what we must do here is:
Parse a string to receive day, month and year as three integer variables or a 3-item tuple consisting of that variable.
Instantiate Date by passing those values to initialization call.
This will look like:
day, month, year = map(int, string_date.split('-'))
date1 = Date(day, month, year)
For this purpose, C++ has such feature as overloading, but Python lacks that feature- so here's when classmethod applies. Lets create another "constructor".
@classmethod
def from_string(cls, date_as_string):
day, month, year = map(int, date_as_string.split('-'))
date1 = cls(day, month, year)
return date1
date2 = Date.from_string('11-09-2012')
Let's look more carefully at the above implementation, and review what advantages we have here:
We've implemented date string parsing in one place and it's reusable now.
Encapsulation works fine here (if you think that you could implement string parsing as a single function elsewhere, this solution fits OOP paradigm far better).
cls is an object that holds class itself, not an instance of the class. It's pretty cool because if we inherit our Date class, all children will have from_string defined also.
Static method
What about staticmethod? It's pretty similar to classmethod but doesn't take any obligatory parameters (like a class method or instance method does).
Let's look at the next use case.
We have a date string that we want to validate somehow. This task is also logically bound to Date class we've used so far, but still doesn't require instantiation of it.
Here is where staticmethod can be useful. Let's look at the next piece of code:
@staticmethod
def is_date_valid(date_as_string):
day, month, year = map(int, date_as_string.split('-'))
return day <= 31 and month <= 12 and year <= 3999
# usage:
is_date = Date.is_date_valid('11-09-2012')
So, as we can see from usage of staticmethod, we don't have any access to what the class is- it's basically just a function, called syntactically like a method, but without access to the object and it's internals (fields and another methods), while classmethod does.
</s> |
<s>[INST] How can you profile a Python script? Project Euler and other coding contests often have a maximum time to run or people boast of how fast their particular solution runs. With python, sometimes the approaches are somewhat kludgey - i.e., adding timing code to __main__.
What is a good way to profile how long a python program takes to run?
[/INST] Python includes a profiler called cProfile. It not only gives the total running time, but also times each function separately, and tells you how many times each function was called, making it easy to determine where you should make optimizations.
You can call it from within your code, or from the interpreter, like this:
import cProfile
cProfile.run('foo()')
Even more usefully, you can invoke the cProfile when running a script:
python -m cProfile myscript.py
To make it even easier, I made a little batch file called 'profile.bat':
python -m cProfile %1
So all I have to do is run:
profile euler048.py
And I get this:
1007 function calls in 0.061 CPU seconds
Ordered by: standard name
ncalls tottime percall cumtime percall filename:lineno(function)
1 0.000 0.000 0.061 0.061 <string>:1(<module>)
1000 0.051 0.000 0.051 0.000 euler048.py:2(<lambda>)
1 0.005 0.005 0.061 0.061 euler048.py:2(<module>)
1 0.000 0.000 0.061 0.061 {execfile}
1 0.002 0.002 0.053 0.053 {map}
1 0.000 0.000 0.000 0.000 {method 'disable' of '_lsprof.Profiler objects}
1 0.000 0.000 0.000 0.000 {range}
1 0.003 0.003 0.003 0.003 {sum}
EDIT: Updated link to a good video resource from PyCon 2013: http://lanyrd.com/2013/pycon/scdywg/
</s> |
<s>[INST] Find all files in directory with extension .txt in Python How can I find all files in directory with the extension .txt in python?
[/INST] You can use glob:
import glob, os
os.chdir("/mydir")
for file in glob.glob("*.txt"):
print(file)
or simply os.listdir:
import os
for file in os.listdir("/mydir"):
if file.endswith(".txt"):
print(file)
or if you want to traverse directory, use os.walk:
import os
for root, dirs, files in os.walk("/mydir"):
for file in files:
if file.endswith(".txt"):
print(os.path.join(root, file))
</s> |
<s>[INST] Create a dictionary with list comprehension in Python I like the Python list comprehension syntax.
Can it be used to create dictionaries too? For example, by iterating over pairs of keys and values:
mydict = {(k,v) for (k,v) in blah blah blah} # doesn't work :(
[/INST] In Python 2.6 and earlier, the dict constructor can receive an iterable of key/value pairs:
d = dict((key, value) for (key, value) in iterable)
From Python 2.7 and 3 onwards, you can just use the dict comprehension syntax directly:
d = {key: value for (key, value) in iterable}
Of course, you can use the iterable in any way you want (tuples and lists literals, generator comprehensions, list comprehensions, generator functions, functional composition... feel creative) as long as each element is an iterable itself of two elements:
d = {value: foo(value) for value in sequence if bar(value)}
def key_value_gen(k):
yield chr(k+65)
yield chr((k+13)%26+65)
d = dict(map(key_value_gen, range(26)))
</s> |
<s>[INST] error: Unable to find vcvarsall.bat I tried to install the Python package dulwich:
pip install dulwich
But I get a cryptic error message:
error: Unable to find vcvarsall.bat
The same happens if I try installing the package manually:
> python setup.py install
running build_ext
building 'dulwich._objects' extension
error: Unable to find vcvarsall.bat
[/INST] Update: Comments point out that the instructions here may be dangerous. Consider using the Visual C++ 2008 Express edition or the purpose-built Microsoft Visual C++ Compiler for Python (details) and NOT using the original answer below. Original error message means the required version of Visual C++ is not installed.
For Windows installations:
While running setup.py for package installations, Python 2.7 searches for an installed Visual Studio 2008. You can trick Python to use a newer Visual Studio by setting the correct path in VS90COMNTOOLS environment variable before calling setup.py.
Execute the following command based on the version of Visual Studio installed:
Visual Studio 2010 (VS10): SET VS90COMNTOOLS=%VS100COMNTOOLS%
Visual Studio 2012 (VS11): SET VS90COMNTOOLS=%VS110COMNTOOLS%
Visual Studio 2013 (VS12): SET VS90COMNTOOLS=%VS120COMNTOOLS%
Visual Studio 2015 (VS14): SET VS90COMNTOOLS=%VS140COMNTOOLS%
WARNING: As noted below, this answer is unlikely to work if you are trying to compile python modules.
See Building lxml for Python 2.7 on Windows for details.
</s> |
<s>[INST] How do I delete a file or folder in Python? How do I delete a file or folder in Python?
I am using the Python scripting language running on the Windows XP operating system.
[/INST] os.remove() will remove a file.
os.rmdir() will remove an empty directory.
shutil.rmtree() will delete a directory and all its contents.
</s> |
<s>[INST] Getting the class name of an instance in Python How do I find out a name of class that created an instance of an object in Python if the function I am doing this from is the base class of which the class of the instance has been derived?
Was thinking maybe the inspect module might have helped me out here, but it doesn't seem to give me what I want. And short of parsing the __class__ member, I'm not sure how to get at this information.
[/INST] Have you tried the __name__ attribute of the class? ie type(x).__name__ will give you the name of the class, which I think is what you want.
>>> import itertools
>>> x = itertools.count(0)
>>> type(x).__name__
'count'
This method works with new-style classes only. Your code might use some old-style classes. The following works for both:
x.__class__.__name__
</s> |
<s>[INST] Random string generation with upper case letters and digits in Python I want to generate a string of size N.
It should be made up of numbers and uppercase English letters such as:
6U1S75
4Z4UKK
U911K4
How can I achieve this in a pythonic way?
[/INST] Answer in one line:
''.join(random.choice(string.ascii_uppercase + string.digits) for _ in range(N))
A more secure version; see http://stackoverflow.com/a/23728630/2213647:
''.join(random.SystemRandom().choice(string.ascii_uppercase + string.digits) for _ in range(N))
In details, with a clean function for further reuse:
>>> import string
>>> import random
>>> def id_generator(size=6, chars=string.ascii_uppercase + string.digits):
... return ''.join(random.choice(chars) for _ in range(size))
...
>>> id_generator()
'G5G74W'
>>> id_generator(3, "6793YUIO")
'Y3U'
How does it work ?
We import string, a module that contains sequences of common ASCII characters, and random, a module that deals with random generation.
string.ascii_uppercase + string.digits just concatenates the list of characters representing uppercase ASCII chars and digits:
>>> string.ascii_uppercase
'ABCDEFGHIJKLMNOPQRSTUVWXYZ'
>>> string.digits
'0123456789'
>>> string.ascii_uppercase + string.digits
'ABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789'
Then we use a list comprehension to create a list of 'n' elements:
>>> range(4) # range create a list of 'n' numbers
[0, 1, 2, 3]
>>> ['elem' for _ in range(4)] # we use range to create 4 times 'elem'
['elem', 'elem', 'elem', 'elem']
In the example above, we use [ to create the list, but we don't in the id_generator function so Python doesn't create the list in memory, but generates the elements on the fly, one by one (more about this here).
Instead of asking to create 'n' times the string elem, we will ask Python to create 'n' times a random character, picked from a sequence of characters:
>>> random.choice("abcde")
'a'
>>> random.choice("abcde")
'd'
>>> random.choice("abcde")
'b'
Therefore random.choice(chars) for _ in range(size) really is creating a sequence of size characters. Characters that are randomly picked from chars:
>>> [random.choice('abcde') for _ in range(3)]
['a', 'b', 'b']
>>> [random.choice('abcde') for _ in range(3)]
['e', 'b', 'e']
>>> [random.choice('abcde') for _ in range(3)]
['d', 'a', 'c']
Then we just join them with an empty string so the sequence becomes a string:
>>> ''.join(['a', 'b', 'b'])
'abb'
>>> [random.choice('abcde') for _ in range(3)]
['d', 'c', 'b']
>>> ''.join(random.choice('abcde') for _ in range(3))
'dac'
</s> |
<s>[INST] How do I connect to a MySQL Database in Python? How do I connect to a MySQL database using a python program?
[/INST]
Connecting to MYSQL with Python in 3 steps
1 - Setting
You must install a MySQL driver before doing anything. Unlike PHP, only the SQLite driver is installed by default with Python. The most used package to do so is MySQLdb but it's hard to install it using easy_install.
For Windows user, you can get an exe of MySQLdb.
For Linux, this is a casual package (python-mysqldb). (You can use sudo apt-get install python-mysqldb (for debian based distros), yum install mysql-python (for rpm-based), or dnf install python-mysql (for modern fedora distro) in command line to download.)
For Mac, you can install MySQLdb using Macport.
2 - Usage
After installing, reboot. This is not mandatory, but will prevent me from answering 3 or 4 other questions in this post if something goes wrong. So please reboot.
Then it is just like using another package :
#!/usr/bin/python
import MySQLdb
db = MySQLdb.connect(host="localhost", # your host, usually localhost
user="john", # your username
passwd="megajonhy", # your password
db="jonhydb") # name of the data base
# you must create a Cursor object. It will let
# you execute all the queries you need
cur = db.cursor()
# Use all the SQL you like
cur.execute("SELECT * FROM YOUR_TABLE_NAME")
# print all the first cell of all the rows
for row in cur.fetchall():
print row[0]
db.close()
Of course, there are thousand of possibilities and options; this is a very basic example. You will have to look at the documentation. A good starting point.
3 - More advanced usage
Once you know how it works, you may want to use an ORM to avoid writting SQL manually and manipulate your tables as they were Python objects. The most famous ORM in the Python community is SQLAlchemy.
I strongly advise you to use it: your life is going to be much easier.
I recently discovered another jewel in the Python world: peewee. It's a very lite ORM, really easy and fast to setup then use. It makes my day for small projects or stand alone apps, where using big tools like SQLAlchemy or Django is overkill :
import peewee
from peewee import *
db = MySQLDatabase('jonhydb', user='john',passwd='megajonhy')
class Book(peewee.Model):
author = peewee.CharField()
title = peewee.TextField()
class Meta:
database = db
Book.create_table()
book = Book(author="me", title='Peewee is cool')
book.save()
for book in Book.filter(author="me"):
print book.title
Peewee is cool
This example works out of the box. Nothing other than having peewee (pip install peewee :-)) is required. No complicated setup. It's really cool.
</s> |
<s>[INST] How to print to stderr in Python? I've come across at least three ways to print to stderr:
import sys
print >> sys.stderr, 'spam'
sys.stderr.write('spam\n')
from __future__ import print_function
print('spam', file=sys.stderr)
It seems to contradict zen of Python #13 â , so what's the preferred way to do it? Are there any advantages or disadvantages to one way or the other?
â There should be one â and preferably only one â obvious way to do it.
[/INST] I found this to be the only one short + flexible + portable + readable:
from __future__ import print_function
import sys
def eprint(*args, **kwargs):
print(*args, file=sys.stderr, **kwargs)
The function eprint can be used in the same was as the standard print function:
>>> print("Test")
Test
>>> eprint("Test")
Test
>>> eprint("foo", "bar", "baz", sep="---")
foo---bar---baz
</s> |
<s>[INST] The meaning of a single- and a double-underscore before an object name in Python I want to clear this up once and for all. Can someone please explain the exact meaning of having leading underscores before an object's name in Python? Also explain the difference between a single and a double leading underscore. Also, does that meaning stay the same whether the object in question is a variable, a function, a method, etcetera?
[/INST] Single Underscore
Names, in a class, with a leading underscore are simply to indicate to other programmers that the attribute or method is intended to be private. However, nothing special is done with the name itself.
To quote PEP-8:
_single_leading_underscore: weak "internal use" indicator. E.g. from M import * does not import objects whose name starts with an underscore.
Double Underscore (Name Mangling)
From the Python docs:
Any identifier of the form __spam (at least two leading underscores, at most one trailing underscore) is textually replaced with _classname__spam, where classname is the current class name with leading underscore(s) stripped. This mangling is done without regard to the syntactic position of the identifier, so it can be used to define class-private instance and class variables, methods, variables stored in globals, and even variables stored in instances. private to this class on instances of other classes.
And a warning from the same page:
Name mangling is intended to give classes an easy way to define âprivateâ instance variables and methods, without having to worry about instance variables defined by derived classes, or mucking with instance variables by code outside the class. Note that the mangling rules are designed mostly to avoid accidents; it still is possible for a determined soul to access or modify a variable that is considered private.
Example
>>> class MyClass():
... def __init__(self):
... self.__superprivate = "Hello"
... self._semiprivate = ", world!"
...
>>> mc = MyClass()
>>> print mc.__superprivate
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
AttributeError: myClass instance has no attribute '__superprivate'
>>> print mc._semiprivate
, world!
>>> print mc.__dict__
{'_MyClass__superprivate': 'Hello', '_semiprivate': ', world!'}
</s> |
<s>[INST] How to leave/exit/deactivate a python virtualenv? I'm using virtualenv and the virtualenvwrapper. I can switch between virtualenv's just fine using the workon command.
me@mymachine:~$ workon env1
(env1)me@mymachine:~$ workon env2
(env2)me@mymachine:~$ workon env1
(env1)me@mymachine:~$
However, how do I exit all virtual machines and workon my real machine again? Right now, the only way I have of getting back to
me@mymachine:~$
is to exit the shell and start a new one. That's kind of annoying. Is there a command to workon "nothing", and if so, what is it? If such a command does not exist, how would I go about creating it?
[/INST] Usually, activating a virtualenv gives you a shell function named:
$ deactivate
which puts things back to normal.
Edit: I have just looked specifically again at the code for virtualenvwrapper, and, yes, it too supports "deactivate" as the way to escape from all virtualenvs.
Edit: If you are trying to leave an Anaconda environment, the procedure is a bit different: run the two-word command source deactivate since they implement deactivation using a stand-alone script.
bash-4.3$ deactivate
pyenv-virtualenv: deactivate must be sourced. Run 'source deactivate' instead of 'deactivate'
bash-4.3$ source deactivate
pyenv-virtualenv: no virtualenv has been activated.
</s> |
<s>[INST] Python progression path - From apprentice to guru I've been learning, working, and playing with Python for a year and a half now. As a biologist slowly making the turn to bio-informatics, this language has been at the very core of all the major contributions I have made in the lab. I more or less fell in love with the way Python permits me to express beautiful solutions and also with the semantics of the language that allows such a natural flow from thoughts to workable code.
What I would like to know is your answer to a kind of question I have seldom seen in this or other forums. This question seems central to me for anyone on the path to Python improvement but who wonders what his next steps should be.
Let me sum up what I do NOT want to ask first ;)
I don't want to know how to QUICKLY learn Python
Nor do I want to find out the best way to get acquainted with the language
Finally, I don't want to know a 'one trick that does it all' approach.
What I do want to know your opinion about, is:
What are the steps YOU would recommend to a Python journeyman, from apprenticeship to guru status (feel free to stop wherever your expertise dictates it), in order that one IMPROVES CONSTANTLY, becoming a better and better Python coder, one step at a time. Some of the people on SO almost seem worthy of worship for their Python prowess, please enlighten us :)
The kind of answers I would enjoy (but feel free to surprise the readership :P ), is formatted more or less like this:
Read this (eg: python tutorial), pay attention to that kind of details
Code for so manytime/problems/lines of code
Then, read this (eg: this or that book), but this time, pay attention to this
Tackle a few real-life problems
Then, proceed to reading Y.
Be sure to grasp these concepts
Code for X time
Come back to such and such basics or move further to...
(you get the point :)
I really care about knowing your opinion on what exactly one should pay attention to, at various stages, in order to progress CONSTANTLY (with due efforts, of course). If you come from a specific field of expertise, discuss the path you see as appropriate in this field.
EDIT: Thanks to your great input, I'm back on the Python improvement track! I really appreciate!
[/INST] I thought the process of Python mastery went something like:
Discover list comprehensions
Discover generators
Incorporate map, reduce, filter, iter, range, xrange often into your code
Discover Decorators
Write recursive functions, a lot
Discover itertools and functools
Read Real World Haskell (read free online)
Rewrite all your old Python code with tons of higher order functions, recursion, and whatnot.
Annoy your cubicle mates every time they present you with a Python class. Claim it could be "better" implemented as a dictionary plus some functions. Embrace functional programming.
Rediscover the Strategy pattern and then all those things from imperative code you tried so hard to forget after Haskell.
Find a balance.
</s> |
<s>[INST] Converting integer to string in Python? I want to convert an integer to a string in Python. I am typecasting it in vain:
t=raw_input()
c=[]
for j in range(0,int(t)):
n=raw_input()
a=[]
a,b= (int(i) for i in n.split(' '))
d=pow(a,b)
d.str()
c.append(d[0])
for j in c:
print j
When I try to convert it to string, it's showing an error like int doesn't have any attribute called str.
[/INST] >>> str(10)
'10'
>>> int('10')
10
[Edit]
Links to the documentation:
int()
str()
[Edit]
The problem seems to come from this line: d.str()
Conversion to string is done with the builtin str() function, which basically calls the __str__() method of its parameter.
Also, it shouldn't be necessary to call pow(). Try using the ** operator.
</s> |
<s>[INST] Nicest way to pad zeroes to string What is the nicest/shortest way to pad a string with zeroes to the left, so the string length has a specific length?
[/INST] Strings:
>>> n = '4'
>>> print n.zfill(3)
004
And for numbers:
>>> n = 4
>>> print '%03d' % n
004
>>> print format(4, '03') # python >= 2.6
004
>>> print '{0:03d}'.format(4) # python >= 2.6
004
>>> print '{foo:03d}'.format(foo=4) # python >= 2.6
004
>>> print('{:03d}'.format(4)) # python >= 2.7 + python3
004
>>> print('{0:03d}'.format(4)) # python 3
004
String formatting documentation.
</s> |
<s>[INST] Peak detection in a 2D array I'm helping a veterinary clinic measuring pressure under a dogs paw. I use Python for my data analysis and now I'm stuck trying to divide the paws into (anatomical) subregions.
I made a 2D array of each paw, that consists of the maximal values for each sensor that has been loaded by the paw over time. Here's an example of one paw, where I used Excel to draw the areas I want to 'detect'. These are 2 by 2 boxes around the sensor with local maxima's, that together have the largest sum.
So I tried some experimenting and decide to simply look for the maximums of each column and row (can't look in one direction due to the shape of the paw). This seems to 'detect' the location of the separate toes fairly well, but it also marks neighboring sensors.
So what would be the best way to tell Python which of these maximums are the ones I want?
Note: The 2x2 squares can't overlap, since they have to be separate toes!
Also I took 2x2 as a convenience, any more advanced solution is welcome, but I'm simply a human movement scientist, so I'm neither a real programmer or a mathematician, so please keep it 'simple'.
Here's a version that can be loaded with np.loadtxt
Results
So I tried @jextee's solution (see the results below). As you can see, it works very on the front paws, but it works less well for the hind legs.
More specifically, it can't recognize the small peak that's the fourth toe. This is obviously inherent to the fact that the loop looks top down towards the lowest value, without taking into account where this is.
Would anyone know how to tweak @jextee's algorithm, so that it might be able to find the 4th toe too?
Since I haven't processed any other trials yet, I can't supply any other samples. But the data I gave before were the averages of each paw. This file is an array with the maximal data of 9 paws in the order they made contact with the plate.
This image shows how they were spatially spread out over the plate.
Update:
I have set up a blog for anyone interested and I have setup a SkyDrive with all the raw measurements. So to anyone requesting more data: more power to you!
New update:
So after the help I got with my questions regarding paw detection and paw sorting, I was finally able to check the toe detection for every paw! Turns out, it doesn't work so well in anything but paws sized like the one in my own example. Off course in hindsight, it's my own fault for choosing the 2x2 so arbitrarily.
Here's a nice example of where it goes wrong: a nail is being recognized as a toe and the 'heel' is so wide, it gets recognized twice!
The paw is too large, so taking a 2x2 size with no overlap, causes some toes to be detected twice. The other way around, in small dogs it often fails to find a 5th toe, which I suspect is being caused by the 2x2 area being too large.
After trying the current solution on all my measurements I came to the staggering conclusion that for nearly all my small dogs it didn't find a 5th toe and that in over 50% of the impacts for the large dogs it would find more!
So clearly I need to change it. My own guess was changing the size of the neighborhood to something smaller for small dogs and larger for large dogs. But generate_binary_structure wouldn't let me change the size of the array.
Therefore, I'm hoping that anyone else has a better suggestion for locating the toes, perhaps having the toe area scale with the paw size?
[/INST] I detected the peaks using a local maximum filter. Here is the result on your first dataset of 4 paws:
I also ran it on the second dataset of 9 paws and it worked as well.
Here is how you do it:
import numpy as np
from scipy.ndimage.filters import maximum_filter
from scipy.ndimage.morphology import generate_binary_structure, binary_erosion
import matplotlib.pyplot as pp
#for some reason I had to reshape. Numpy ignored the shape header.
paws_data = np.loadtxt("paws.txt").reshape(4,11,14)
#getting a list of images
paws = [p.squeeze() for p in np.vsplit(paws_data,4)]
def detect_peaks(image):
"""
Takes an image and detect the peaks usingthe local maximum filter.
Returns a boolean mask of the peaks (i.e. 1 when
the pixel's value is the neighborhood maximum, 0 otherwise)
"""
# define an 8-connected neighborhood
neighborhood = generate_binary_structure(2,2)
#apply the local maximum filter; all pixel of maximal value
#in their neighborhood are set to 1
local_max = maximum_filter(image, footprint=neighborhood)==image
#local_max is a mask that contains the peaks we are
#looking for, but also the background.
#In order to isolate the peaks we must remove the background from the mask.
#we create the mask of the background
background = (image==0)
#a little technicality: we must erode the background in order to
#successfully subtract it form local_max, otherwise a line will
#appear along the background border (artifact of the local maximum filter)
eroded_background = binary_erosion(background, structure=neighborhood, border_value=1)
#we obtain the final mask, containing only peaks,
#by removing the background from the local_max mask
detected_peaks = local_max - eroded_background
return detected_peaks
#applying the detection and plotting results
for i, paw in enumerate(paws):
detected_peaks = detect_peaks(paw)
pp.subplot(4,2,(2*i+1))
pp.imshow(paw)
pp.subplot(4,2,(2*i+2) )
pp.imshow(detected_peaks)
pp.show()
All you need to do after is use scipy.ndimage.measurements.label on the mask to label all distinct objects. Then you'll be able to play with them individually.
Note that the method works well because the background is not noisy. If it were, you would detect a bunch of other unwanted peaks in the background. Another important factor is the size of the neighborhood. You will need to adjust it if the peak size changes (the should remain roughly proportional).
</s> |
<s>[INST] Access environment variables from Python I set an environment variable that I want to access in my Python application. How do I get this value?
[/INST] Environment variables are accessed through os.environ
import os
print os.environ['HOME']
Or you can see a list of all the environment variables using:
os.environ
As sometimes you might need to see a complete list!
# using get will return `None` if a key is not present rather than raise a `KeyError`
print os.environ.get('KEY_THAT_MIGHT_EXIST')
# os.getenv is equivalent, and can also give a default value instead of `None`
print os.getenv('KEY_THAT_MIGHT_EXIST', default_value)
Python default installation on Windows is C:\Python. If you want to find out while running python you can do:
import sys
print sys.prefix
</s> |
<s>[INST] How to trim whitespace (including tabs)? Is there a function that will trim not only spaces for whitespace, but also tabs?
[/INST] Whitespace on the both sides:
s = " \t a string example\t "
s = s.strip()
Whitespace on the right side:
s = s.rstrip()
Whitespace on the left side:
s = s.lstrip()
As thedz points out, you can provide an argument to strip arbitrary characters to any of these functions like this:
s = s.strip(' \t\n\r')
This will strip any space, \t, \n, or \r characters from the left-hand side, right-hand side, or both sides of the string.
The examples above only remove strings from the left-hand and right-hand sides of strings. If you want to also remove characters from the middle of a string, try re.sub:
import re
print re.sub('[\s+]', '', s)
That should print out:
astringexample
</s> |
<s>[INST] How to remove an element from a list by index in Python? How to remove an element from a list by index in Python?
I found the list.remove method, but say I want to remove the last element, how do I do this? It seems like the default remove searches the list, but I don't want any search to be performed.
[/INST] Use del and specify the element you want to delete with the index:
In [9]: a = range(10)
In [10]: a
Out[10]: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]
In [11]: del a[-1]
In [12]: a
Out[12]: [0, 1, 2, 3, 4, 5, 6, 7, 8]
Here is the section from the tutorial.
</s> |
<s>[INST] Why does Python code run faster in a function? def main():
for i in xrange(10**8):
pass
main()
This piece of code in Python runs in
real 0m1.841s
user 0m1.828s
sys 0m0.012s
However, if the for loop isn't placed within a function,
for i in xrange(10**8):
pass
then it runs for a much longer time:
real 0m4.543s
user 0m4.524s
sys 0m0.012s
Why is this?
Note: The timing is done with the time function in BASH in Linux.
[/INST] Inside a function, the bytecode is
2 0 SETUP_LOOP 20 (to 23)
3 LOAD_GLOBAL 0 (xrange)
6 LOAD_CONST 3 (100000000)
9 CALL_FUNCTION 1
12 GET_ITER
>> 13 FOR_ITER 6 (to 22)
16 STORE_FAST 0 (i)
3 19 JUMP_ABSOLUTE 13
>> 22 POP_BLOCK
>> 23 LOAD_CONST 0 (None)
26 RETURN_VALUE
At top level, the bytecode is
1 0 SETUP_LOOP 20 (to 23)
3 LOAD_NAME 0 (xrange)
6 LOAD_CONST 3 (100000000)
9 CALL_FUNCTION 1
12 GET_ITER
>> 13 FOR_ITER 6 (to 22)
16 STORE_NAME 1 (i)
2 19 JUMP_ABSOLUTE 13
>> 22 POP_BLOCK
>> 23 LOAD_CONST 2 (None)
26 RETURN_VALUE
The difference is that STORE_FAST is faster (!) than STORE_NAME. This is because in a function, i is a local but at toplevel it is a global.
To examine bytecode, use the dis module. I was able to disassemble the function directly, but to disassemble the toplevel code I had to use the compile builtin.
</s> |
<s>[INST] Trimming a string in Python How do I remove leading and trailing whitespace from a string in Python?
For example:
" Hello " --> "Hello"
" Hello" --> "Hello"
"Hello " --> "Hello"
"Bob has a cat" --> "Bob has a cat"
[/INST] Just one space, or all such spaces? If the second, then strings already have a .strip() method:
>>> ' Hello '.strip()
'Hello'
>>> ' Hello'.strip()
'Hello'
>>> 'Bob has a cat'.strip()
'Bob has a cat'
>>> ' Hello '.strip() # ALL spaces at ends removed
'Hello'
If you need only to remove one space however, you could do it with:
def strip_one_space(s):
if s.endswith(" "): s = s[:-1]
if s.startswith(" "): s = s[1:]
return s
>>> strip_one_space(" Hello ")
' Hello'
Also, note that str.strip() removes other whitespace characters as well (e.g. tabs and newlines). To remove only spaces, you can specify the character to remove as an argument to strip, i.e.:
>>> " Hello\n".strip(" ")
'Hello\n'
</s> |
<s>[INST] Limiting floats to two decimal points I want a to be rounded to 13.95.
>>> a
13.949999999999999
>>> round(a, 2)
13.949999999999999
The round function does not work the way I expected.
[/INST] You are running into the old problem with floating point numbers that all numbers cannot be represented. The command line is just showing you the full floating point form from memory. In floating point your rounded version is the same number. Since computers are binary they store floating point numbers as an integer and then divide it by a power of two so 13.95 will be represented in a similar fashion to 125650429603636838/(2**53). Double precision numbers have 53 bits (16 digits) of precision and regular floats have 24 bits (8 digits) of precision. The floating point in python uses double precision to store the values.
for example
>>> 125650429603636838/(2**53)
13.949999999999999
>>> 234042163/(2**24)
13.949999988079071
>>> a=13.946
>>> print(a)
13.946
>>> print("%.2f" % a)
13.95
>>> round(a,2)
13.949999999999999
>>> print("%.2f" % round(a,2))
13.95
>>> print("{0:.2f}".format(a))
13.95
>>> print("{0:.2f}".format(round(a,2)))
13.95
>>> print("{0:.15f}".format(round(a,2)))
13.949999999999999
If you are after only two decimal places as in currency then you have a couple of better choices use integers and store values in cents not dollars and then divide by 100 to convert to dollars. Or use a fixed point number like decimal
</s> |
<s>[INST] How to determine the variable type in Python? How do I see the type of a variable whether it is unsigned 32 bit, signed 16 bit, etc.?
How do I view it?
[/INST] Python doesn't have the same types as C/C++, which appears to be your question.
Try this:
>>> i = 123
>>> type(i)
<type 'int'>
>>> type(i) is int
True
>>> i = 123456789L
>>> type(i)
<type 'long'>
>>> type(i) is long
True
>>> i = 123.456
>>> type(i)
<type 'float'>
>>> type(i) is float
True
The distinction between int and long goes away in Python 3.0, though.
</s> |
<s>[INST] How to flush output of Python print? How do I force Python's print function to output to the screen?
[/INST] import sys
sys.stdout.flush()
Print by default prints to sys.stdout.
References:
http://docs.python.org/reference/simple_stmts.html#the-print-statement
http://docs.python.org/library/sys.html
http://docs.python.org/library/stdtypes.html#file-objects
</s> |
<s>[INST] What is the difference between old style and new style classes in Python? What is the difference between old style and new style classes in Python? Is there ever a reason to use old-style classes these days?
[/INST] From http://docs.python.org/2/reference/datamodel.html#new-style-and-classic-classes :
Up to Python 2.1, old-style classes were the only flavour available to the user. The concept of (old-style) class is unrelated to the concept of type: if x is an instance of an old-style class, then x.__class__ designates the class of x, but type(x) is always <type 'instance'>. This reflects the fact that all old-style instances, independently of their class, are implemented with a single built-in type, called instance.
New-style classes were introduced in Python 2.2 to unify the concepts of class and type. A new-style class is simply a user-defined type, no more, no less. If x is an instance of a new-style class, then type(x) is typically the same as x.__class__ (although this is not guaranteed â a new-style class instance is permitted to override the value returned for x.__class__).
The major motivation for introducing new-style classes is to provide a unified object model with a full meta-model. It also has a number of immediate benefits, like the ability to subclass most built-in types, or the introduction of "descriptors", which enable computed properties.
For compatibility reasons, classes are still old-style by default. New-style classes are created by specifying another new-style class (i.e. a type) as a parent class, or the "top-level type" object if no other parent is needed. The behaviour of new-style classes differs from that of old-style classes in a number of important details in addition to what type returns. Some of these changes are fundamental to the new object model, like the way special methods are invoked. Others are "fixes" that could not be implemented before for compatibility concerns, like the method resolution order in case of multiple inheritance.
Python 3 only has new-style classes. No matter if you subclass from object or not, classes are new-style in Python 3. It is however recommended that you still subclass from object.
</s> |
<s>[INST] Extracting extension from filename in Python Is there a function to extract the extension from a filename?
[/INST] Yes. Use os.path.splitext:
>>> import os
>>> filename, file_extension = os.path.splitext('/path/to/somefile.ext')
>>> filename
'/path/to/somefile'
>>> file_extension
'.ext'
</s> |
<s>[INST] Proper way to declare custom exceptions in modern Python? What's the proper way to declare custom exception classes in modern Python? My primary goal is to follow whatever standard other exception classes have, so that (for instance) any extra string I include in the exception is printed out by whatever tool caught the exception.
By "modern Python" I mean something that will run in Python 2.5 but be 'correct' for the Python 2.6 and Python 3.* way of doing things. And by "custom" I mean an Exception object that can include extra data about the cause of the error: a string, maybe also some other arbitrary object relevant to the exception.
I was tripped up by the following deprecation warning in Python 2.6.2:
>>> class MyError(Exception):
... def __init__(self, message):
... self.message = message
...
>>> MyError("foo")
_sandbox.py:3: DeprecationWarning: BaseException.message has been deprecated as of Python 2.6
It seems crazy that BaseException has a special meaning for attributes named message. I gather from PEP-352 that attribute did have a special meaning in 2.5 they're trying to deprecate away, so I guess that name (and that one alone) is now forbidden? Ugh.
I'm also fuzzily aware that Exception has some magic parameter args, but I've never known how to use it. Nor am I sure it's the right way to do things going forward; a lot of the discussion I found online suggested they were trying to do away with args in Python 3.
Update: two answers have suggested overriding __init__, and __str__/__unicode__/__repr__. That seems like a lot of typing, is it necessary?
[/INST] Maybe I missed the question, but why not:
class MyException(Exception):
pass
Edit: to override something (or pass extra args), do this:
class ValidationError(Exception):
def __init__(self, message, errors):
# Call the base class constructor with the parameters it needs
super(ValidationError, self).__init__(message)
# Now for your custom code...
self.errors = errors
That way you could pass dict of error messages to the second param, and get to it later with e.errors
</s> |
<s>[INST] Why does comparing strings in Python using either '==' or 'is' sometimes produce a different result? I've got a Python program where two variables are set to the value 'public'. In a conditional expression I have the comparison var1 is var2 which fails, but if I change it to var1 == var2 it returns True.
Now if I open my Python interpreter and do the same "is" comparison, it succeeds.
>>> s1 = 'public'
>>> s2 = 'public'
>>> s2 is s1
True
What am I missing here?
[/INST] is is identity testing, == is equality testing. what happens in your code would be emulated in the interpreter like this:
>>> a = 'pub'
>>> b = ''.join(['p', 'u', 'b'])
>>> a == b
True
>>> a is b
False
so, no wonder they're not the same, right?
In other words: is is the id(a) == id(b)
</s> |
<s>[INST] How can I count the occurrences of a list item in Python? Given an item, how can I count its occurrences in a list in Python?
[/INST] If you are using Python 2.7 or 3 and you want number of occurrences for each element:
>>> from collections import Counter
>>> z = ['blue', 'red', 'blue', 'yellow', 'blue', 'red']
>>> Counter(z)
Counter({'blue': 3, 'red': 2, 'yellow': 1})
</s> |
<s>[INST] What's the canonical way to check for type in python? What is the best way to check whether a given object is of a given type? How about checking whether the object inherits from a given type?
Let's say I have an object o. How do I check whether it's a str?
[/INST] To check if the type of o is exactly str:
type(o) is str
To check if o is an instance of str or any subclass of str (this would be the "canonical" way):
isinstance(o, str)
The following also works, and can be useful in some cases:
issubclass(type(o), str)
type(o) in ([str] + str.__subclasses__())
See Built-in Functions in the Python Library Reference for relevant information.
One more note: in this case, you may actually want to use:
isinstance(o, basestring)
because this will also catch Unicode strings (unicode is not a subclass of str; both str and unicode are subclasses of basestring).
Alternatively, isinstance accepts a tuple of classes. This will return True if x is an instance of any subclass of any of (str, unicode):
isinstance(o, (str, unicode))
</s> |
End of preview. Expand
in Dataset Viewer.
YAML Metadata
Warning:
The task_categories "conversational" is not in the official list: text-classification, token-classification, table-question-answering, question-answering, zero-shot-classification, translation, summarization, feature-extraction, text-generation, text2text-generation, fill-mask, sentence-similarity, text-to-speech, text-to-audio, automatic-speech-recognition, audio-to-audio, audio-classification, voice-activity-detection, depth-estimation, image-classification, object-detection, image-segmentation, text-to-image, image-to-text, image-to-image, image-to-video, unconditional-image-generation, video-classification, reinforcement-learning, robotics, tabular-classification, tabular-regression, tabular-to-text, table-to-text, multiple-choice, text-retrieval, time-series-forecasting, text-to-video, image-text-to-text, visual-question-answering, document-question-answering, zero-shot-image-classification, graph-ml, mask-generation, zero-shot-object-detection, text-to-3d, image-to-3d, image-feature-extraction, other
Dataset Card for Python Q/A pair
This dataset card provides information about the Python Q/A pair dataset.
Dataset Details
Dataset Description
The Python Q/A pair dataset is a preprocessed version of a Python Q/A dataset from StackOverflow, which was originally hosted on Kaggle. The dataset contains high-ranked questions and their corresponding high-ranked answers, sorted from high to low rank.
- Curated by: [More Information Needed]
- Funded by [optional]: [More Information Needed]
- Shared by [optional]: [More Information Needed]
- Language(s) (NLP): [More Information Needed]
- License: [More Information Needed]
Dataset Sources [optional]
- Repository: [More Information Needed]
- Paper [optional]: [More Information Needed]
- Demo [optional]: [More Information Needed]
Uses
Direct Use
This dataset can be used for tasks such as question answering, text generation, and conversational AI research and development.
[More Information Needed]
Out-of-Scope Use
This dataset should not be used for tasks outside of natural language processing, such as image recognition or voice recognition.
[More Information Needed]
Dataset Structure
The dataset contains 100k rows of high-ranked questions and their corresponding high-ranked answers from StackOverflow.
[More Information Needed]
Dataset Creation
Curation Rationale
The dataset was curated to provide a resource for developing and testing natural language processing models, particularly in the domain of question answering and text generation.
[More Information Needed]
Source Data
The data in this dataset comes from StackOverflow Q/A pairs that were ranked 1 or above. The raw form of this dataset is hosted on Kaggle.
Data Collection and Processing
The data was collected from StackOverflow and preprocessed to include only high-ranked questions and their corresponding high-ranked answers.
[More Information Needed]
Who are the source data producers?
The source data was produced by users of StackOverflow.
[More Information Needed]
Annotations [optional]
This dataset does not contain any additional annotations.
Annotation process
[More Information Needed]
Who are the annotators?
[More Information Needed]
Personal and Sensitive Information
The dataset does not contain any personal or sensitive information as it was derived from publicly available data on StackOverflow.
[More Information Needed]
Bias, Risks, and Limitations
[More Information Needed]
Recommendations
Users should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations.
Citation [optional]
BibTeX:
[More Information Needed]
APA:
[More Information Needed]
Glossary [optional]
[More Information Needed]
More Information [optional]
[More Information Needed]
Dataset Card Authors [optional]
[More Information Needed]
Dataset Card Contact
[More Information Needed]
- Downloads last month
- 42
Size of downloaded dataset files:
887 kB
Size of the auto-converted Parquet files:
887 kB
Number of rows:
1,000
Models trained or fine-tuned on HassanSamo/Python-Q_A