Generating 3 billion-th element of a sequence in python - python

I am trying to generate the following sequence:
011212201220200112 ... constructed as follows: first is 0,
then repeated the following action:
already written part is attributed to the right with replacement
0 to 1, 1 to 2, 2 to 0.
E.g.
0 -> 01 -> 0112 -> 01121220 -> ...
I am trying to find the 3 billion-th element of this sequence.
I realized that the sequence grows exponentially and hence derived that:
log(base2) (3 billion) ~ 32
So I just need to generate this sequence 32 times.
Here is what I tried in python:
import os
import sys
s=['0']
num_dict = {'0':'1' , '1':'2' , '2':'0'}
def mapper(b):
return num_dict[b]
def gen(s):
while True:
yield s
s.extend( map(mapper,s) )
a = gen(s)
for i in xrange(32):
a.next()
print a.next()[3000000000 - 1]
The problem is my RAM gets filled up before hitting the 3 billion mark.
Is there a better way to do this problem ?
EDIT: This program could crash your machine.Please try for xrange(25) for testing purposes

There are enough hints in the comments that you should be able to find the one-line solution. I think that it's more interesting to try to derive it with a more general tool, namely, implicit data structures. Here's a class for singleton lists.
class Singleton:
def __init__(self, x):
self.x = x
def __getitem__(self, i):
if not isinstance(i, int): raise TypeError(i)
elif not (0 <= i < len(self)): raise IndexError(i)
else: return self.x
def __len__(self): return 1
We can use this class like so.
>>> lst = Singleton(42)
>>> lst[0]
42
>>> len(lst)
1
Now we define a concatenation class and a mapper class, where the latter takes a function and implicitly applies it to each list element.
class Concatenation:
def __init__(self, lst1, lst2):
self.lst1 = lst1
self.lst2 = lst2
self.cachedlen = len(lst1) + len(lst2)
def __getitem__(self, i):
if not isinstance(i, int): raise TypeError(i)
elif not (0 <= i < len(self)): raise IndexError(i)
elif i < len(self.lst1): return self.lst1[i]
else: return self.lst2[i - len(self.lst1)]
def __len__(self): return self.cachedlen
class Mapper:
def __init__(self, f, lst):
self.f = f
self.lst = lst
def __getitem__(self, i): return self.f(self.lst[i])
def __len__(self): return len(self.lst)
Now let's rewrite your code to use these classes.
a = Singleton(0)
for i in range(32):
a = Concatenation(a, Mapper({0: 1, 1: 2, 2: 0}.get, a))
print(a[3000000000 - 1])
As an exercise: why do we need cachedlen?

Related

How to return a copy of an instance of a class?

I am currently practising python on code wars, here is a prompt:
Create a Vector object that supports addition, subtraction, dot products, and norms. So, for example:
a = Vector([1, 2, 3])
b = Vector([3, 4, 5])
c = Vector([5, 6, 7, 8])
a.add(b) # should return a new Vector([4, 6, 8])
a.subtract(b) # should return a new Vector([-2, -2, -2])
a.dot(b) # should return 1*3 + 2*4 + 3*5 = 26
a.norm() # should return sqrt(1^2 + 2^2 + 3^2) = sqrt(14)
a.add(c) # raises an exception
I have written functions add and subtract that pass some of the tests. However, I am running into issues with overwriting my previous list values of 'a' after running the add function. When I go into subtract, the 'a' values in the vector are the summations computed from the previous instance of the add function.
I suspect its due to me running this line of code:
return self.__class__(self.list) causing the instance of the class to overwrite itself.
Kindly please help, I believe I need to return a copy of the instance of the class but don't know how to do it.
class Vector:
def __init__(self, list):
self.list = list #[1,2]
self.copylist = list
def add(self,Vector):
try:
self.list = self.copylist
#take list from other vector
other = Vector.list
#take each value from other Vector and add it to self.list
for index,item in enumerate(Vector.list,0):
self.list[index] = item + self.list[index]
except:
print("Different size vectors")
#return the instance of a class
return self.__class__(self.list)
def subtract(self,Vector):
self.list = self.copylist
other = Vector.list
print(self.list)
print(other)
for index,item in enumerate(Vector.list,0):
self.list[index] = self.list[index] - item
return self.__class__(self.list)
def dot(self,Vector):
self.list = self.copylist
other = Vector.list
#print(self.list)
#print(other)
running_sum =0
for index,item in enumerate(Vector.list,0):
running_sum = running_sum + item * self.list[index]
#print(running_sum, " ", self.list[index], " ", item)
return running_sum
def norm(self):
running_sum = 0
for item in self.list:
running_sum += item**2
return running_sum ** 0.5
def toString(self):
return str(self.list)
`def equals(self,Vector):
return self.list == Vector.list
Here are some of the tests:
a = Vector([1, 2])
b = Vector([3, 4])
test.expect(a.add(b).equals(Vector([4, 6])))
a = Vector([1, 2, 3])
b = Vector([3, 4, 5])
test.expect(a.add(b).equals(Vector([4, 6, 8])))
test.expect(a.subtract(b).equals(Vector([-2, -2, -2]))) #code fails here
test.assert_equals(a.dot(b), 26)
test.assert_equals(a.norm(), 14 ** 0.5)
I think you're making this more complicated than it needs to be. You shouldn't be working with class objects at all. You should just be working with instances of the Vector class. Here's what I think your code should look like:
class Vector:
def __init__(self, initial_elements):
self.elements = list(initial_elements) # make a copy of the incoming list of elements
def add(self, other):
# insure that the two vectors match in length
if len(self.elements) != len(other.elements):
raise Exception("Vector sizes are different")
# copy our elements
r = list(self.elements)
# add the elements from the second vector
for index, item in enumerate(other.elements, 0):
r[index] += item
# return a new vector object defined by the computed elements
return Vector(r)
def subtract(self, other):
# insure that the two vectors match in length
if len(self.elements) != len(other.elements):
raise Exception("Vector sizes are different")
# copy our elements
r = list(self.elements)
# subtract the elements from the second vector
for index, item in enumerate(other.elements, 0):
r[index] -= item
# return a new vector object defined by the computed elements
return Vector(r)
def dot(self, other):
running_sum = 0
for index, item in enumerate(other.elements, 0):
running_sum += item * self.elements[index]
return running_sum
def norm(self):
running_sum = 0
for item in self.elements:
running_sum += item ** 2
return running_sum ** 0.5
def toString(self):
return str(self.elements)
def equals(self, other):
return self.elements == other.elements
def test():
a = Vector([1, 2])
b = Vector([3, 4])
print(a.add(b).equals(Vector([4, 6])))
a = Vector([1, 2, 3])
b = Vector([3, 4, 5])
print(a.add(b).equals(Vector([4, 6, 8])))
print(a.subtract(b).equals(Vector([-2, -2, -2])))
print(a.dot(b) == 26)
print(a.norm() == 14 ** 0.5)
test()
Result:
True
True
True
True
True
The general structure of your code is spot on.
One thing to note is that you shouldn't be using list as a variable name, as it is a type name in Python. Also, you don't want to be passing around Vector as a value. You want to be passing instances of Vector and list, with names that do not conflict with these type names.
My solution assumes you want Vector instances to be immutable, so each of your operations will return a new Vector object. You could also have them not be immutable and have, for example, the add method just add the incoming vector into the target vector without creating a new object. I like keeping them immutable. I've been doing more and more of this "functional style" programming lately, where calls to object methods don't modify the target object (don't have side effects), but rather just return a new object.
I like your use of the test class to do your testing. I chose to not deal with this, and just print the results of each test comparison to see that they all come out to True. I'll leave it to you to restore your tests to using a test object with expect and assert_equals methods.
UPDATE: Here is a more compact way to write your add and subtract methods:
def add(self, other):
# insure that the two vectors match in length
if len(self.elements) != len(other.elements):
raise Exception("Vector sizes are different")
return Vector([self.elements[i] + other.elements[i] for i in range(len(self.elements))])
def subtract(self, other):
# insure that the two vectors match in length
if len(self.elements) != len(other.elements):
raise Exception("Vector sizes are different")
return Vector([self.elements[i] - other.elements[i] for i in range(len(self.elements))])
change:
return self.__class__(self.list)
to:
return self
although this would the same as,
return Vector(self.list)
if the class is more complicated it is better to return self
I think that's the issue, hope it helps :)
also, it is good practice to use different names. you used Vector for the class name as well as many of the inputs of the functions, you will run into problems when you do that.
Please change function toString to str . its' already done.
class Vector :
def __init__(self , lst_vec):
self.lst_vec = lst_vec
def show_vector(self):
return self.lst_vec
def add(self , v ):
size_self = len(self.lst_vec)
size_v = len(v.lst_vec)
new_vector = []
if ( size_self != size_v ):
return Exception("error add")
else:
for i in range(size_self):
new_vector.append(self.lst_vec[i] + v.lst_vec[i])
return Vector(new_vector)
def subtract(self , v ):
size_self = len(self.lst_vec)
size_v = len(v.lst_vec)
new_vector = []
if ( size_self != size_v ):
return Exception("error subtract")
else:
for i in range(size_self):
new_vector.append(self.lst_vec[i] - v.lst_vec[i])
return Vector(new_vector)
def dot(self , v ):
size_self = len(self.lst_vec)
size_v = len(v.lst_vec)
new_vector = []
sum_vec = 0
if ( size_self != size_v ):
return Exception("Vector sizes are different")
else:
for i in range(size_self):
new_vector.append(self.lst_vec[i] * v.lst_vec[i])
for i in range(len(new_vector)):
sum_vec+=new_vector[i]
return sum_vec
def norm (self):
new_vec_sum = 0
for i in range(len(self.lst_vec)):
new_vec_sum +=( self.lst_vec[i] ) **2
return new_vec_sum ** 0.5
def toString(self):
str_self = '('
for i in range(len(self.lst_vec)):
str_self += str(self.lst_vec[i])
if i < (len(self.lst_vec)-1):
str_self+=','
else : pass
str_self+=')'
return str_self
def equals(self , v ):
return self.lst_vec == v.lst_vec
a = Vector([1,2,3])
b = Vector([3,4,5])
c = Vector([5,6,7,8])
print(a.add(b).show_vector())
print( a.add(b).equals(Vector([4,6,8])) )
print(a.subtract(b).show_vector())
print(a.dot(b))
print(a.norm())
print((a.toString() == '(1,2,3)'))
print(c.toString())

Create an insert and pop method on list class

I need to implement an insert method (insert(self, index, val)), that inserts val before index, and a pop method (pop(self)), that removes the last element from mylist, onto the MyList class. The behavior should be identical to the methods already available in python.
Note: For the insert method, similarly with the append method already done, the capacity of the array should be doubled if there is no room for an additional element. The pop method should return the element removed from the list, and put None
in its place in the array. If pop was called on an empty list, an IndexError
exception should be raised.
My code thus far:
import ctypes # provides low-level arrays
def make_array(n):
return (n * ctypes.py_object)()
class MyList:
def __init__(self):
self.data = make_array(1)
self.capacity = 1
self.n = 0
def __len__(self):
return self.n
def append(self, val):
if(self.n == self.capacity):
self.resize(2 * self.capacity)
self.data[self.n] = val
self.n += 1
def resize(self, new_size):
new_array = make_array(new_size)
for ind in range(self.n):
new_array[ind] = self.data[ind]
self.data = new_array
self.capacity = new_size
def extend(self, other):
for elem in other:
self.append(elem)
def __getitem__(self, ind):
if not(0 <= ind <= self.n - 1):
raise IndexError('MyList index is out of range')
return self.data[ind]
def __setitem__(self, ind, val):
if not(0 <= ind <= self.n - 1):
raise IndexError('MyList index is out of range')
self.data[ind] = val
mylst1 = MyList()
for i in range(5):
mylst1.append(i)

Return generator VS iterate with while until None

From two options below what is more appealing(readable code, more pythonic, efficiency , etc..) for running through iterable and if I want add more logic in the future(for example add 1 to every returned value)?
One of options returns generator, the other returns next item and None when done all iterations.
Is there a preferable method? If yes, why? Is there limitations some method has that another don't.
class Option1():
def __init__(self):
self.current = 0
def get_next_batch(self, my_list):
if self.current == len(my_list):
self.current = 0
return None
self.current += 1
return [my_list[self.current-1]]
class Option2():
def __init__(self):
self.current = 0
def get_next_batch(self, my_list):
while self.current < len(my_list):
yield [my_list[self.current]]
self.current += 1
self.current = 0
raise StopIteration()
Usage:
o1 = Option1()
o2 = Option2()
arr = [1,2,3,4,5]
a = o1.get_next_batch(arr)
while a is not None:
print a
a = o1.get_next_batch(arr)
for item in o2.get_next_batch(arr):
print item
Output in both cases:
[1]
[2]
[3]
[4]
[5]
You almost certainly want to go with the second. Less lines, less opportunity for things to go wrong.
However, seeing as you're not using current outside the iterator I would just optimise the whole thing down to:
def get_next_batch(my_list):
for item in my_list:
yield [item]
arr = [1,2,3,4,5]
for item in get_next_batch(arr):
print item
Side points. Always make your classes inherit from object in python 2.7, and don't raise StopIteration to halt a generator in python -- it's deprecated behaviour that can lead to bugs. Use return instead. eg.
def get_next_batch(my_list):
for item in my_list:
if item > 3:
return
yield [item]
batched = list(get_next_batch([1,2,3,4,5]))
expected = [[1], [2], [3]]
print batched == expected
You can tidy up Option1 to make it easy to use in for loops. To do this you can make it with the iterator protocol. That is an __iter__ method that returns self and a next method to get the next item. eg.
class UsingNext(object):
def __init__(self, mylist):
self.current = 0
self.mylist = mylist
def __iter__(self):
return self
def next(self): # __next__ in python 3
if self.current >= len(self.mylist):
raise StopIteration
if self.current == 2:
self.current += 1
return "special"
item = self.mylist[self.current]
self.current += 1
return [item]
class UsingYield(object):
def __init__(self, mylist):
self.mylist = mylist
def __iter__(self):
for current, item in enumerate(self.mylist):
if current == 2:
yield "special"
continue
yield [item]
arr = range(1, 6)
# both print
# [1]
# [2]
# special
# [4]
# [5]
for item in UsingNext(arr):
print item
for item in UsingYield(arr):
print item
In my mind the generator version is cleaner, and easier to understand.

Creating Vectors with Python

I'm creating a vector class that has one parameter being the length of a vector. The length is automatically 0 if none is entered by user. If a vector is given a length, however, each number will be set to 0. For example: v(5) would be [0,0,0,0,0] and v() would be [].
This is the code i have thus far, but it's not quite working. Any advice?
class V:
def __init__(self, length = 0):
self.vector = [0]*length
def __str__(self):
print(self.vector)
def __len__(self):
return len(self.vector)
Then i plug in a = V() b = V(5) and when i print(a) and print(b) i get an TypeError. Any advice?
I'd probably cheat and go for sub-classing list:
class V(list):
def __init__(self, length=0):
super(V, self).__init__([0] * length)
This way you get the length, repr and other goodies for free.
class V:
def __init__(self, length = 0):
self.data = [0]*length
def __str__(self):
return '[{}]'.format(', '.join(str(d) for d in self.data))
def __len__(self):
return len(self.data)

Fixing array indices in Python

I'd like to have arrays that start from say an index of 4 and go to 9. I'm not interested in creating memory space for < 4, so how is best to proceed? My 2D code is as follows:
arr = [[ 0 for row in range(2)] for col in range(1, 129)]
>>> arr[0][0] = 1
>>> arr[128][0] = 1
Traceback (most recent call last):
File "<stdin>", line 1, in ?
IndexError: list index out of range
>>> arr[127][0] = 1
How can selectively just use the specific range i.e. where the last index runs from 1 to 128 inclusive not 0 to 127. This maybe obvious, but is there a way to do this?
Thanks for the suggestion for dicts, I have been avoiding these - I know - much of the code I'm converting is from C, but I think dictionaries might the saviour. Is there a way to do what I am asking with arrays?
For sparse arrays, use a dict:
sparseArray = {}
sparseArray[(0,0)] = 1
sparseArray[(128,128)] = 1
print sparseArray # Show the content of the sparse array
print sparseArray.keys() # Get all used indices.
You can simply emulate a list:
class OffsetList(object):
def __init__(self, offset=4):
self._offset = offset
self._lst = []
def __len__(self):
return len(self._lst)
def __getitem__(self, key):
return self._lst[key - self._offset]
def __setitem__(self, key, val):
self._lst[key - self._offset] = val
def __delitem__(self, key):
del self._lst[key - self._offset]
def __iter__(self):
return iter(self._lst)
def __contains__(self, item):
return item in self._lst
# All other methods go to the backing list.
def __getattr__(self, a):
return getattr(self._lst, a)
# Test it like this:
ol = OffsetList(4)
ol.append(2)
assert ol[4] == 2
assert len(ol) == 1
You have two options here. You can use sparse lists, or you can create a container type that basically has a normal list and a start index, such that when you request
specialist.get(4)
you actually get
specialist.innerlist[4 - startidx]
If you really wanted list semantics and all, I suppose you could do
class OffsetyList(list):
def __init__(self, *args, **kwargs):
list.__init__(self, *args)
self._offset = int(kwargs.get("offset", 0))
def __getitem__(self, idx):
return list.__getitem__(self, idx + self._offset)
def __setitem__(self, idx, value):
list.__setitem__(self, idx + self._offset, value)
# Implementing the rest of the class
# is left as an exercise for the reader.
ol = OffsetyList(offset = -5)
ol.extend(("foo", "bar", "baz"))
print ol[5], ol[7], ol[6]
but this seems very fragile to say the least.

Categories

Resources