def getLCSFromFiles(fileOne,
fileTwo,
ignoreLineDir=True,
ignoreComments=True,
ignoreFileSpecifics=False):
"""
Process an LCS object given two files
see getStringsFromFiles for arg info
"""
seqOne, seqTwo = getStringsFromFiles(fileOne, fileTwo, ignoreLineDir,
ignoreComments, ignoreFileSpecifics)
retLCS = LCS.LCS(seqOne, seqTwo)
return retLCS
def __calcEdgeWeights(self, content):
edgeWeights = [
] #holds the edge weight values where entry at index i is
#the edge weight from the new article to the article with
#id number i
c2 = content.lower()
Arr2len = len(c2)
c2 = nltk.word_tokenize(c2)
tagged2 = nltk.pos_tag(c2)
c1 = [
w for w, t in tagged2
if t != "DT" and t != "IN" and t != "WP" and t != "WRB" and
t != "WP$" and t != "WDT" and t != "EX" and t != "TO" and t != "RP"
]
c2 = c2[0:500]
for i in range(len(self.contents)):
c1 = self.contents[i].lower()
Arr1len = len(c1)
c1 = nltk.word_tokenize(c1)
tagged1 = nltk.pos_tag(c1)
c1 = [
w for w, t in tagged1 if t != "DT" and t != "IN" and t != "WP"
and t != "WRB" and t != "WP$" and t != "WDT" and t != "EX"
and t != "TO" and t != "RP"
]
c1 = c1[0:500]
weight = LCS.LCS(c1, c2)
weight = weight / ((Arr1len + Arr2len) / 2)
#weight = weight * weight
edgeWeights.append(weight)
edgeWeights.append(0)
return edgeWeights
#!/usr/bin/python # Filename: Longest-Common-Subsequence.py import random import LCSLength import LCS arrayX = [0, 'a', 'b', 'c', 'b', 'd', 'a', 'b'] arrayY = [0, 'b', 'd', 'c', 'a', 'b', 'a'] m = len(arrayX) - 1 n = len(arrayY) - 1 c = [] b = [] for i in range(0, m + 1): c.append([]) for j in range(0, n + 1): c[i].append(0) for i in range(0, m + 1): b.append([]) for j in range(0, n + 1): b[i].append(0) LCSLength.LCSLength(m, n, arrayX, arrayY, c, b) LCS.LCS(m, n, arrayX, b)
import os
import time
import sys
import LCS
if __name__ == '__main__':
size = readSize.readSize('input/size.txt')
#每轮都会随机产生字符串，所以这里写入时为了保存，而不是读取
inputA = open('input/inputA.txt', 'w')
inputB = open('input/inputB.txt', 'w')
timeTXT = open('output/time.txt', 'w')
for key, value in size.items():
for m, n in value:
str1 = createString.createString(m) #产生指定长度的字符串
str2 = createString.createString(n)
if (key == str('A')): #将产生的字符串保存起来
inputA.writelines(str1 + '\n')
inputA.writelines(str2 + '\n')
else:
inputB.writelines(str1 + '\n')
inputB.writelines(str2 + '\n')
t1 = time.time()
b, c = LCS.LCS(str1, str2)
print('{}组规模为({}, {})的字符串组的LCS长度为：{}，其中一个解为：'.format(
key, m, n, c[-1][-1]),
end='')
LCS.print_LCS(b, str1, m, n)
print()
t2 = time.time()
timeTXT.writelines(str(t2 - t1) + ' ms\n')
new_list1 = []
new_list2 = []
for i in range(size1):
new_list1.append(choice(ascii_uppercase))
for j in range(size2):
new_list2.append(choice(ascii_uppercase))
return new_list1, new_list2
if __name__ == "__main__":
# input length of sequences
m = int(input("Set the length of the first sequence: "))
n = int(input("Set the length of the second sequence: "))
# generate two random character sequences
new_lists = generate_List(10, m, n)
print(new_lists[0])
print(new_lists[1])
# create an instance of a naiveMethod algorithm and run it to solve the lcs problem
nm = nm.naiveMethod()
nm_lcs = lcs.LCS(new_lists[0], new_lists[1], nm)
nm_result, nm_time = nm_lcs.run()
print("The result: " + str(nm_result) + "\nThe time: " + str(nm_time))
# create an instance of a dynamicProgramming algorithm and run it to solve the lcs problem
dp = dp.dynamicProgramming(m, n)
dp_lcs = lcs.LCS(new_lists[0], new_lists[1], dp)
dp_result, dp_time = dp_lcs.run()
print("The result: " + str(dp_result) + "\nThe time: " + str(dp_time - 1))
def test_ExpectedOutput(self):
'''
Checks if returned output is as expected.
'''
output = LCS.LCS(["abcabb", "bacb"])
self.assertEqual(output, 3)