Introduction
I recently got asked to me what did __init__ dunder method did in Python. And I was like, "it is used to initialize variables inside a class". And just after that, the follow-up question was, "then what is __new__ used for. And I was completely blank and was not able to answer that.
I was not able to answer that question because there are not many tutorials out there that talk about __new__. I didn't want to happen this with you. And that is why I came up with this blog post for you.
Similarities
Let's start with similarities.
- Both of them are called/invoked during the creation of the instance.
Differences
Let's start with differences.
| new | init | |
|---|---|---|
| 1 | Called before init | Called after new |
| 2 | Accepts a type as the first argument | Accepts an instance as the first argument |
| 3 | Is supposed to return an instance of the type received | Is not supposed to return anything |
| 4 | Used to control instance creation | Used to initialize instance variables |
Talking about the first point. __new__ is called when the instance is first created. This happens before the initialization of the class.
By the way, did you note that the first argument to __init__ is always self? This self is the instance of the class. self is what __new__ returns.
Coming to the third point, __new__ is supposed to return an instance of the class. Note that if __new__ does not returns anything, __init__ is not called.
Which one of them is a constructor?
If you are coming from another language, you might be surprised that there are two similar things doing the same kind of work. Most languages you might have worked with would have something called a constructor.
In Python, that concept is broken down into constructor and initializer. And you might have guessed, __new__ is the constructor and __init__ is the initializer.
Please note that __new__ is implicit. Meaning that if you don't actually need to modify the creation of an instance of the class, you don't need to have a new method.
One more thing I'd like to add is... instance variables are local to an instance. So anything you are doing in init is local to that instance only. But anything you are doing in new will be affecting anything created for that type.
Execution flow with an example
I am going to add some code to make this more engaging. Consider this example:
class Demo:
def __new__(cls, *args):
print("__new__ called")
return object.__new__(cls)
def __init__(self):
print("__init__ called")
d = Demo()
This is the simplest example of both __new__ and __init__ in action. If you save the above code in a file and run it, you'd see something like this:
$ python3 in_it.py
__new__ called
__init__ called
As you can see, the new method is called first and then execution is passed to the init method.
Use Cases
Use case for __new__
One of the best use cases I can take an example of is when creating a Singleton. As we know, Singleton ensures a class only has one instance and provides a global point of access to it.
Some of the places I have seen singleton in action are in game programming where there is only one instance of the player. Another place, if you have used frontend libraries like Vuex (or Redux), there is only one global instance of the store. Doesn't matter how many instances you create, you'll end up having only one.
Let's see how to achieve similar behavior in Python:
class Singleton:
__instance = None
def __new__(cls):
if cls.__instance is None:
print("creating...")
cls.__instance = object.__new__(cls)
return cls.__instance
s1 = Singleton()
s2 = Singleton()
print(s1)
print(s2)
Output:
$ python3 singleton.py
creating...
<__main__.Singleton object at 0x7f943301d350>
<__main__.Singleton object at 0x7f943301d350>
As you can see, creating... is printed only once. they both point to the same memory location. In my case, it's 0x7f943301d350.
You might be guessing that can't we do the same thing with __init__? No! That's because __init__ does not return anything. We'll see in the next section what __init__ is well suited for.
But first, I wanted to show you another use case of new.
class Animal:
def __new__(cls, legs):
if legs == 2:
return Biped()
else:
return Quadruped()
class Biped:
def __init__(self):
print("Initializing 2-legged animal")
class Quadruped:
def __init__(self):
print("Initializing 4-legged animal")
anim1 = Animal(legs=4)
anim1 = Animal(legs=2)
Output:
$ python3 newexample.py
Initializing 4-legged animal
Initializing 2-legged animal
I am by no means a zoologist. But you get my point here. You can use __new__ to conditionally create an instance from a class.
Use case for __init__
As we have already seen previously. init is there to initialize an instance variable. These instance variables can later be used in different methods of the instance.
I have extensively used __init__ when I used to work with Qt framework. Qt is a framework for desktop-based UI development. When initializing UI objects, you can set how wide or long the window could be. You can also read preferences from a file and apply that during the initialization phase of an application. Setting the window title could be another example.
Here I'll demonstrate one such example:
class Window(QWidget):
def __init__(self, parent = None):
super(Window, self).__init__(parent)
self.resize(200, 100)
self.setWindowTitle("My App")
The above example is by no means a complete example, but when set up correctly, it will show a window similar to this.
Key Takeaways
- In most cases, you don't need
-
__new__is called before__init__. -
__new__returns a instance of class. -
__init__receives the instances of the class returned by__new__. - Use
__init__to initilize value.
The same concept can be used to answer the question of abstraction vs encapsulation.
Conclusion
That is all I know about __init__ vs __new__. If you have something in your mind that I missed. Please let me know.
I'll also list some references I look to write this blog post so that you can really the real source of information.
Top comments (0)