Python/dynamic_programming/edit_distance.py

106 lines
2.9 KiB
Python
Raw Normal View History

2016-10-12 14:48:37 +00:00
"""
Author : Turfa Auliarachman
Date : October 12, 2016
This is a pure Python implementation of Dynamic Programming solution to the edit
distance problem.
2016-10-12 14:48:37 +00:00
The problem is :
Given two strings A and B. Find the minimum number of operations to string B such that
A = B. The permitted operations are removal, insertion, and substitution.
2016-10-12 14:48:37 +00:00
"""
2016-10-12 14:48:37 +00:00
class EditDistance:
"""
Use :
solver = EditDistance()
editDistanceResult = solver.solve(firstString, secondString)
"""
def __init__(self):
self.__prepare__()
def __prepare__(self, n=0, m=0):
self.dp = [[-1 for y in range(0, m)] for x in range(0, n)]
2016-10-12 14:48:37 +00:00
def __solve_dp(self, x, y):
2019-10-05 05:14:13 +00:00
if x == -1:
return y + 1
elif y == -1:
return x + 1
elif self.dp[x][y] > -1:
2016-10-12 14:48:37 +00:00
return self.dp[x][y]
else:
if self.a[x] == self.b[y]:
self.dp[x][y] = self.__solve_dp(x - 1, y - 1)
2016-10-12 14:48:37 +00:00
else:
2019-10-05 05:14:13 +00:00
self.dp[x][y] = 1 + min(
self.__solve_dp(x, y - 1),
self.__solve_dp(x - 1, y),
self.__solve_dp(x - 1, y - 1),
2019-10-05 05:14:13 +00:00
)
2016-10-12 14:48:37 +00:00
return self.dp[x][y]
def solve(self, a, b):
if isinstance(a, bytes):
a = a.decode("ascii")
2016-10-12 14:48:37 +00:00
if isinstance(b, bytes):
b = b.decode("ascii")
2016-10-12 14:48:37 +00:00
self.a = str(a)
self.b = str(b)
2016-10-12 14:48:37 +00:00
self.__prepare__(len(a), len(b))
2016-10-12 14:48:37 +00:00
return self.__solve_dp(len(a) - 1, len(b) - 1)
2016-10-12 14:48:37 +00:00
def min_distance_bottom_up(word1: str, word2: str) -> int:
"""
>>> min_distance_bottom_up("intention", "execution")
5
>>> min_distance_bottom_up("intention", "")
9
>>> min_distance_bottom_up("", "")
0
"""
m = len(word1)
n = len(word2)
2019-10-05 05:14:13 +00:00
dp = [[0 for _ in range(n + 1)] for _ in range(m + 1)]
for i in range(m + 1):
for j in range(n + 1):
2019-10-05 05:14:13 +00:00
if i == 0: # first string is empty
dp[i][j] = j
2019-10-05 05:14:13 +00:00
elif j == 0: # second string is empty
dp[i][j] = i
2019-10-05 05:14:13 +00:00
elif (
word1[i - 1] == word2[j - 1]
): # last character of both substing is equal
dp[i][j] = dp[i - 1][j - 1]
else:
2019-10-05 05:14:13 +00:00
insert = dp[i][j - 1]
delete = dp[i - 1][j]
replace = dp[i - 1][j - 1]
dp[i][j] = 1 + min(insert, delete, replace)
return dp[m][n]
2019-10-05 05:14:13 +00:00
if __name__ == "__main__":
solver = EditDistance()
2019-10-05 05:14:13 +00:00
print("****************** Testing Edit Distance DP Algorithm ******************")
print()
2019-10-05 05:14:13 +00:00
S1 = input("Enter the first string: ").strip()
S2 = input("Enter the second string: ").strip()
2019-10-05 05:14:13 +00:00
print()
print("The minimum Edit Distance is: %d" % (solver.solve(S1, S2)))
print("The minimum Edit Distance is: %d" % (min_distance_bottom_up(S1, S2)))
print()
print("*************** End of Testing Edit Distance DP Algorithm ***************")