def median_maintenance(data):
yield data[0]
if data[0] < data[1]:
h_high, h_low = MinHeap([data[1]]), MaxHeap([data[0]])
else:
h_high, h_low = MinHeap([data[0]]), MaxHeap([data[1]])
median = h_low.extract_max()
h_low.insert(median)
yield median
for k in data[2:]:
lower, upper = h_low.extract_max(), h_high.extract_min()
if k <= lower:
h_low.insert(k)
else:
h_high.insert(k)
h_low.insert(lower)
h_high.insert(upper)
if abs(h_high.size() - h_low.size()) > 1:
if h_high.size() > h_low.size():
h_low.insert(h_high.extract_min())
else:
h_high.insert(h_low.extract_max())
if (h_high.size() + h_low.size()) % 2 == 0 or h_low.size() > h_high.size():
median = h_low.extract_max()
h_low.insert(median)
yield median
else:
median = h_high.extract_min()
h_high.insert(median)
yield median
def test_insert_and_get_many_random_items(self):
heap = MinHeap()
items = random.sample(range(1000), 50)
for index, item in enumerate(items):
heap.insert(item)
assert heap.size() == index + 1
min_item = min(items[: index + 1])
assert heap.get_min() == min_item
assert heap.size() == len(items)
def test_insert_and_get_many_items(self):
heap = MinHeap()
items = [9, 25, 86, 3, 29, 5, 55]
for index, item in enumerate(items):
heap.insert(item)
assert heap.size() == index + 1
min_item = min(items[: index + 1])
assert heap.get_min() == min_item
assert heap.size() == len(items)
assert heap.items == [3, 9, 5, 25, 29, 86, 55]
def test_insert_and_remove_many_random_items(self):
heap = MinHeap()
items = random.sample(range(1000), 50)
for item in items:
heap.insert(item)
assert heap.size() == len(items)
sorted_items = sorted(items)
for index, item in enumerate(sorted_items):
min_item = heap.remove_min()
assert sorted_items[index] == min_item
assert heap.size() == 0
def test_insert_and_remove_many_items(self):
heap = MinHeap()
items = [9, 25, 86, 3, 29, 5, 55]
for item in items:
heap.insert(item)
assert heap.size() == len(items)
sorted_items = sorted(items)
for index, item in enumerate(sorted_items):
min_item = heap.remove_min()
assert sorted_items[index] == min_item
assert heap.size() == 0
def test_append(self):
mh = MinHeap()
self.assertEqual(0, mh.size())
mh.append(1)
self.assertEqual(1, mh.size())
mh.append(1)
self.assertEqual(2, mh.size())
mh.append(2)
self.assertEqual(3, mh.size())
def get_trie(s):
# get frequencies:
frequencies = {}
for c in s:
if c not in frequencies:
frequencies[c] = 1
else:
frequencies[c] += 1
# build trie:
heap = MinHeap()
for c in frequencies:
heap.insert(Node(frequencies[c], c))
while heap.size() > 1:
left = heap.extractmin()
right = heap.extractmin()
assert (left is not None)
assert (right is not None)
assert (left.frequency >= 0)
assert (right.frequency >= 0)
frequency = left.frequency + right.frequency
node = Node(frequency)
node.left = left
node.right = right
heap.insert(node)
return heap.extractmin()
class HeapMedian:
''' solution using min-, max- heaps '''
def __init__(self):
self.upper = MinHeap()
self.lower = MaxHeap()
def add(self, i):
assert self.lower.size() >= self.upper.size()
if self.lower.size()==0 or\
i <= self.lower.peek():
self.lower.push(i)
else:
self.upper.push(i)
if self.lower.size() < self.upper.size():
self.lower.push(self.upper.pop())
elif self.lower.size() > self.upper.size()+1:
self.upper.push(self.lower.pop())
def get(self):
return self.lower.peek()
from heap import MinHeap, MaxHeap
from math import floor
import sys
#invariant: maintain min heap size = floor(n/2), median is the the max in max heap
with open('Median.txt') as f:
#with open('median10_test.txt') as f:
a = [int(l) for l in f]
minHeap = MinHeap([])
maxHeap = MaxHeap([])
medians = []
for i in range(len(a)):
if minHeap.size() == 0 and maxHeap.size() == 0:
maxHeap.insert(a[i])
else:
if a[i] < maxHeap.top():
maxHeap.insert(a[i])
else:
minHeap.insert(a[i])
if minHeap.size() > floor((i+1)/2):
maxHeap.insert(minHeap.extract())
elif minHeap.size() < floor((i+1)/2):
minHeap.insert(maxHeap.extract())
medians.append(maxHeap.top())
print(sum(medians)%10000)
def find_shortest(self):
return len(self.encoding)
def find_longest(self):
return len(self.encoding)
with open("huffman.txt", "r") as infile:
infile = [int(i) for i in infile.readlines()[1:]]
infile = list(enumerate(infile))
##infile = [(0,1), (1,5), (2,7), (3,2), (4,3)]
min_heap = MinHeap()
for i in infile:
min_heap.insert(i[1], HCLeafNode(i[0], i[1]))
#do until only one node left, the root
while min_heap.size() > 1:
#get two smallest nodes
small = min_heap.pop().get_data()[0]
small.add_prefix("0")
two_small = min_heap.pop().get_data()[0]
two_small.add_prefix("1")
#merge them together
merged = HCMiddleNode(small, two_small)
min_heap.insert(merged.get_frequency(), merged)
tree = min_heap.pop().get_data()[0]
def test_size_of_empty_heap(self):
heap = MinHeap()
assert heap.size() == 0
def test_insert_and_get_one_item(self):
heap = MinHeap()
heap.insert(5)
assert heap.size() == 1
assert heap.get_min() == 5
assert heap.items == [5]
def test_insert_and_remove_one_item(self):
heap = MinHeap()
heap.insert(5)
assert heap.size() == 1
assert heap.remove_min() == 5
assert heap.size() == 0
