Adding objects using the mean (average) consistently - python

Say we have a class AverageNumber which when adding, finds the mean of the numbers being added:
class AverageNumber():
def __init__(self, value):
self.value = value
def __add__(self, other):
average = ( self.value + other.value ) / 2 # This is the issue?
return AverageNumber(average)
def __str__(self):
return self.value
This code is incorrect, as it fails to respect the additive commutative and associative properties that I was looking for, namely that:
average(1 + 3 + 2) = average(1 + 2 + 3) etc.
However this does not occur, as the above class adds two at a time.
The INCORRECT results are below:
>>> b = AverageNumber(1) + AverageNumber(3) + AverageNumber(2)
>>> b.value
2.0
>>> b = AverageNumber(1) + AverageNumber(2) + AverageNumber(3)
>>> b.value
2.25
My question is: How can I modify the code above to fix this issue?

You just need to track the number of numbers involved:
class AverageNumber():
def __init__(self, value, count=1):
self.value = value
self.count = count
def __add__(self, other):
total = self.value + other.value
count = self.count + other.count
return AverageNumber(total, count)
def getValue(self):
return self.value / self.count
b = AverageNumber(1) + AverageNumber(3) + AverageNumber(2)
print(b.getValue())
b = AverageNumber(1) + AverageNumber(2) + AverageNumber(3)
print(b.getValue())
Output:
2.0
2.0

Related

How to implement Rope data structure split operation

I was reading about Rope(or cord) data structure https://en.wikipedia.org/wiki/Rope_(data_structure) and trying to implement it, but I am struggling to implement the split operation. I tried to look it up but all related answers I was able to find were incorrect.
Below is the split operation:
We want to find the character and return two nodes before and after the split. For example, if we want to split at index 5 of'MyNameIsSimon' then we should return the root of two ropes 'MyName' and 'IsSimon' respectively. Finding the index is easy as given by the pseudo-code in wiki. But I'm struggling the split part especially how to join and return the 2nd half as a new rope. Anyone can help with pseudo-code or any language is much appreciated.
Wikipedia’s diagram looks muddled to me. Here’s a working implementation in Python (without balancing).
class Leaf:
def __init__(self, s):
self._s = s
def __len__(self):
return len(self._s)
def __str__(self):
return self._s
def inspect(self, indent=0):
print(" " * indent + repr(self._s))
def split(self, i):
return Leaf(self._s[:i]), Leaf(self._s[i:])
class Branch:
def __init__(self, a, b):
self._a = a
self._b = b
self._l = len(a) + len(b)
def __len__(self):
return self._l
def __str__(self):
return str(self._a) + str(self._b)
def inspect(self, indent=0):
self._a.inspect(indent + 2)
print(" " * indent + str(len(self._a)))
self._b.inspect(indent + 2)
def split(self, i):
if i < len(self._a):
a0, a1 = self._a.split(i)
return a0, Branch(a1, self._b)
elif i == len(self._a):
return self._a, self._b
else:
assert i > len(self._a)
b0, b1 = self._b.split(i - len(self._a))
return Branch(self._a, b0), b1
def make_test_rope():
e = Leaf("Hello ")
f = Leaf("my ")
c = Branch(e, f)
j = Leaf("na")
k = Leaf("me i")
g = Branch(j, k)
m = Leaf("s")
n = Leaf(" Simon")
h = Branch(m, n)
d = Branch(g, h)
b = Branch(c, d)
a = Branch(b, Leaf(""))
return a
def test():
a = make_test_rope()
a.inspect()
b, c = a.split(11)
print("--")
b.inspect()
print("--")
c.inspect()
test()
Output:
'Hello '
6
'my '
9
'na'
2
'me i'
6
's'
1
' Simon'
22
''
--
'Hello '
6
'my '
9
'na'
--
'me i'
4
's'
1
' Simon'
11
''

Subtraction with metric prefixes as objects

Im trying to subtract with prefixes as objects.
Here is my code
class Prefix:
def __init__(self, m=0, cm=0):
self.m = m
self.cm = cm
def __sub__(self, other):
centim = self.cm - other.cm
meter = (self.m - other.m) - abs(centim/100)
if meter < 1:
centim = m*100
meter = 0
return Prefix(meter, cm)
Im trying to subtract in a way which creates a negative centimeter value and take 1m from the meter object such that this is fulfilled
Prefix(2, 20) - Prefix(1, 30) == Prefix(0, 90)
First, keep in mind that for a given length, everything to the right of the hundreds place goes into cm, and everything at it or to its left gets divided by 100, and then goes into m.
Given this, we can recast the problem as converting both Prefix objects into their full lengths, performing calculations there, and then creating a new Prefix from the result:
class Prefix:
def __init__(self, m=0, cm=0):
self.m = m
self.cm = cm
def __sub__(self, other):
self_length = self.m * 100 + self.cm
other_length = other.m * 100 + other.cm
result_length = self_length - other_length
result_m, result_cm = divmod(result_length, 100)
return Prefix(result_m, result_cm)
result = Prefix(2, 20) - Prefix(1, 30)
print(result.m, result.cm)
Output:
0 90
Since we've come this far, we might as well store a "length" and overload __repr__ to make the result prettier:
class Prefix:
def __init__(self, length):
self.length = length
def __sub__(self, other):
result_length = self.length - other.length
return Prefix(result_length)
def __repr__(self):
result_m, result_cm = self.split_up(self.length)
if result_m > 0:
return f'{result_m}m {result_cm}cm'
else:
return f'{result_cm}cm'
#staticmethod
def split_up(length):
return divmod(length, 100)
Prefix(220) - Prefix(130)
Output:
90cm

Which data structure to use when implementing graph representation using adjacency list

I have a graph that is very big about 1,000,000 nodes and many edges. This is what i wanted to know which is the best suited data structure when implementing an adjacency list. Here are the objects that i keep track of
Edge list
Node to node connection list
I am coding with python so I used a set(because according to this it has a o(1) average insertion time) for edge list and a dictionary to node to node connection list(by making it completely hashable according to How to make an object properly hashable?). Here is my code
class node:
def __init__(self, name = ""):
self.__name = name
def getName(self):
return self.__name
def __str__(self):
return self.__name
def __hash__(self):
return hash(self.__name)
def __lt__(self, other):
if(type(self) != type(other)):
return NotImplemented
return self.__name.__lt__(other.__name)
def __eq__(self, other):
if(type(self)) != type(other):
return NotImplemented
return self.__name == other.__name
class Edge:
def __init__(self, name = "", node1 = None, node2 = None, weight = 0):
self.__name = name
self.__firstNode = node1
self.__secondNode = node2
self.__weight = weight
def getName(self):
return self.__name
def getFirstNode(self):
return self.__firstNode
def getSecondNode(self):
return self.__secondNode
def getWeight(self):
return self.__weight
def __lt__(self, other):
if(type(self) != type(other)):
return NotImplemented
return self.__name.__lt__(other.__name) and self.__firstNode.__lt__(other.__firstNode) and self.__secondNode.__lt__(other.__secondNode) and self.__weight.__lt__(other.__weight)
def __eq__(self, other):
if(type(self) != type(other)):
return NotImplemented
return self.__name == other.__name and self.__firstNode == other.__firstNode and self.__secondNode == other.__secondNode and self.__weight == other.__weight
def __str__(self):
return self.__name + " " + str(self.__firstNode) + " " + str(self.__secondNode) + " " + str(self.__weight)
def __hash__(self):
return hash(hash(self.__name) + hash(self.__firstNode) + hash(self.__secondNode) + hash(self.__weight))
class graph:
def __init__(self):
self.__nodeToNode = {}
self.__edgeList = set()
def addEdge(self, edge):
if(type(edge) != type(Edge())):
return False
self.__edgeList.add(edge)
if(not edge.getFirstNode() in self.__nodeToNode):
self.__nodeToNode[edge.getFirstNode()] = set()
self.__nodeToNode[edge.getFirstNode()].add(edge.getSecondNode())
if(not edge.getSecondNode() in self.__nodeToNode):
self.__nodeToNode[edge.getSecondNode()] = set()
self.__nodeToNode[edge.getSecondNode()].add(edge.getSecondNode())
return True
def getNodes(self):
return dict(self.__nodeToNode)
def getEdges(self):
return set(self.__edgeList)
import string
import random
import time
grp = graph()
nodes = [None] * 20000
for i in range(20000):
st = ''.join(random.SystemRandom().choice(string.ascii_letters) for i in range(10))
node1 = node(st)
nodes[i] = node1
current = time.time()
for i in range(3000000):
rdm = random.randint(0, 199)
rdm2 = random.randint(0, 199)
st = ''.join(random.SystemRandom().choice(string.ascii_letters) for i in range(10))
eg = Edge(st, nodes[rdm], nodes[rdm2])
grp.addEdge(eg)
last = time.time()
print((last - current))
nodes = grp.getNodes()
edges = grp.getEdges()
but this code runs very slowly can i make it faster? If so by using what data structure?
Let me introduce you a way to create an adjacency list:
Suppose you have the input like this:
4 4
1 2
3 2
4 3
1 4
The first line contains 2 numbers V and E, the next E lines defines an edge between two vertices.
You can either create a .txt file and read the input or directly type in via sys.stdin.read():
input = sys.stdin.read()
data = list(map(int, input.split()))
n, m = data[0:2]
data = data[2:]
edges = list(zip(data[0:(2 * m):2], data[1:(2 * m):2]))
x, y = data[2 * m:]
adj = [[] for _ in range(n)]
x, y = x - 1, y - 1
for (a, b) in edges:
adj[a - 1].append(b - 1)
adj[b - 1].append(a - 1)
Let's output the adjacency list adj:
>>> print(adj)
[[1, 3], [0, 2], [1, 3], [2, 0]]
adj[0] have two adj nodes: 1 and 3. Meaning the node 1 have two adj nodes: 2 and 4.
And now, if you want a directed, weighted graph, you just need to modify the input like this:
4 4
1 2 3 # edge(1, 2) has the weight of 3
3 2 1
4 3 1
1 4 2
input = sys.stdin.read()
data = list(map(int, input.split()))
n, m = data[0:2]
data = data[2:]
edges = list(zip(zip(data[0:(3 * m):3], data[1:(3 * m):3]), data[2:(3 * m):3]))
data = data[3 * m:]
adj = [[] for _ in range(n)]
cost = [[] for _ in range(n)]
for ((a, b), w) in edges:
adj[a - 1].append(b - 1)
cost[a - 1].append(w)
You store the weight in cost, and for example, cost[0][1] = 3, cost[0][3] = 2.
Hope this helped!

Dependent variable in Python

I would like to define an Integer class in python, where an Integer (called y) can be related to another Integer (called x) and get updated automatically when this Integer x changes. More concretely I would like to have the following behavior
>>> x = Integer(7)
>>> y = x + 2
>>> print y
9
>>> x.set(9)
>>> print y
11
>>> z = x + y
>>> y.set(10)
>>> print z
19
I realize that one can do this in sympy but I am interested in implementing this myself. I would be grateful if someone can please point out how one would go about this in the simplest manner? Thank you.
I've not used Sympy before but here's my attempt:
class Integer(object):
def __init__(self, value_or_callback):
if isinstance(value_or_callback, int):
self._value_callback = lambda: value_or_callback
else:
self._value_callback = value_or_callback
#property
def value(self):
return self._value_callback()
def set(self, new_value):
self._value_callback = lambda: new_value
def __add__(self, other):
if isinstance(other, int):
return Integer(lambda: self.value + other)
elif isinstance(other, Integer):
return Integer(lambda: self.value + other.value)
else:
raise TypeError(other)
def __radd__(self, other):
return self.__add__(other)
def __repr__(self):
return str(self.value)
if __name__ == '__main__':
x = Integer(7)
y = x + 2
print(y)
x.set(9)
print(y)
z = x + y
y.set(10)
print(z)
Output
9
11
19

Python: using a custom number class or type

I am working with a custom number type which is best thought of as YearQuarter, (i.e. 20141, 20142, 20143, 20144, 20151, 20152, ...), or as I label it, quarter_code, q_code for short. Its incrementing function would be something like:
def code_sum(q_code, n):
q_code_year, q_code_quarter = q_code // 10, q_code % 10
n_year, n_quarter = (n // 4), (n % 4 - 1)
quarters = q_code_quarter + n_quarter
years = q_code_year + n_year + quarters // 4
return years * 10 + quarters % 4 + 1
# code_sum(20141, 1) = 20142, code_sum(20144, 1) = 20151
# code_sum(20144, -1) = 20143, code_sum(20151, -1) = 20144
# NOTE: code_sum(20147, 0) = 20153
I want to warn or raise exceptions for numbers which don't conform to the form year*10 + number_of_quarters. It easy to write and call a check function, but I'm wondering if constantly calling check is the best approach when using quarter_codes in many different functions. E.g.
def foo(qc1, qc2, qc3):
qc1, qc2, qc3 = check(qc1, qc2, qc3)
# do something
return bar
def foo2(qc, arg1, arg2) ...
qc = check(qc)
return 42
def fooN(qc1, qc2, arg1):
qc1, qc2 = check(qc1, qc2)
And so on. Here is a short check function as an example.
def check(*args):
checked = tuple()
for q_code in args:
if q_code % 10 > 4:
while q_code % 10 > 4:
q_code += 6
print('Number of quarters > 4. Using {}'.format(q_code))
checked += (q_code, )
else:
checked += (q_code, )
return checked[0] if len(checked) == 1 else checked
It seems a little laborious to create class YearQtr although maybe I am missing something here altogether. My question really boils to: how far should I go to creating a custom number class or type? And how would I do that?
I hope this can help you
class QuarterCode(object):
"""docstring for QuarterCode"""
#property
def value(self):
return self.__value;
#value.setter
def value(self, value):
assert 1 <= value%10 <=4, "Number of quarters differs from {1,2,3,4}"
self.__value = value
def __init__(self, value):
self.value = value
def code_sum(self, n):
q_code_year, q_code_quarter = self.value // 10, self.value % 10
n_year, n_quarter = (n // 4), (n % 4 - 1)
quarters = q_code_quarter + n_quarter
years = q_code_year + n_year + quarters // 4
self.value = years * 10 + quarters % 4 + 1
You can use this class as follows:
>>>q1 = QuarterCode(20142)
>>>q1.value
20142
>>>q1.code_sum(10)
20164
>>>q1.value = 20145
AssertionError: Number of quarters differs from {1,2,3,4}

Categories