from BinarySearch import binarySearch # Binary search, base case: Empty sequence assert (binarySearch([], 4) == -1) # Binary search, base case: 1-element sequence assert (binarySearch([2], 1) == -1) assert (binarySearch([2], 2) == 0) # Binary search, recursive case: 3-element sequence assert (binarySearch([5, 7, 8], 4) == -1) assert (binarySearch([5, 7, 8], 5) == 0) assert (binarySearch([5, 7, 8], 7) == 1) assert (binarySearch([5, 7, 8], 8) == 2) assert (binarySearch([5, 7, 8], 9) == -1) # Binary search, recursive case: assert (binarySearch([0, 0, 0, 0, 0], 0) == 2)
from BinarySearch import binarySearch
def insertionSort(arr):
"""
Insertion sort is a simple sorting algorithm
that works the way we sort playing cards in our hands.
:param arr:
:return: arr
Complexity O(n^2
"""
for i in range(len(arr)):
current = arr[i]
j = i - 1
while j >= 0 and arr[j] > current:
arr[j + 1] = arr[j]
j = j - 1
arr[j + 1] = current
return arr
x_array = [54, 26, 93, 17, 77, 31, 44, 55, 20, 89, 0]
print("Insertion Sort Algorithm: " + str(insertionSort(x_array)))
y = binarySearch(55, x_array, 0, len(x_array) - 1)
print(y)
def test_case_2(self):
self.assertEqual(binarySearch([1, 5, 23, 111], 5), 1)
#load the long list of text or makei t
try:
if os.path.exists("url_text.txt"):
#url_text = pickle.load(open("url_text.txt","rb"))
url_text = pickle.load(open("url_text.txt","rb"))
print("read")
else:
for site in site_list:
url_text = openURL(url_text, site)
pickle.dump(url_text,open("url_text.txt","wb"))
except Exception, e:
print e
tokens = tokenize(url_text)
print "done tokenize"
found = binarySearch("alpha",sorted(set(tokens)))
print found
'''
#create the tokens
try:
url_tokens = tokenize(url_text)
url_bitokens = bigrams(url_tokens)
url_tritokens = trigrams(url_tokens)
fout = open("wikipedia_tokens.csv",'wb')
for item in sorted(set(url_tokens)):
if url_tokens.count(item) > 100:
fout.write(item + "," + str(url_tokens.count(item)) + "\n")
fout.close()
fout = open("wikipedia_bitokens.csv",'wb')
for item in sorted(set(url_bitokens)):
if url_bitokens.count(item) > 80:
def test_case_1(self):
self.assertEqual(binarySearch([1, 5, 23, 111], 111), 3)
def test_case_9(self):
self.assertEqual(
binarySearch([0, 1, 21, 33, 45, 45, 61, 71, 72, 73, 355], 354), -1)
def test_case_7(self):
self.assertEqual(
binarySearch([0, 1, 21, 33, 45, 45, 61, 71, 72, 73], 70), -1)
def test_case_4(self):
self.assertEqual(
binarySearch([0, 1, 21, 33, 45, 45, 61, 71, 72, 73], 33), 3)
def test_case_3(self):
self.assertEqual(binarySearch([1, 5, 23, 111], 35), -1)