mirror of
https://github.com/TheAlgorithms/Python.git
synced 2024-11-24 05:21:09 +00:00
61f3119467
* f-string update rsa_cipher.py * f-string update rsa_key_generator.py * f-string update burrows_wheeler.py * f-string update non_recursive_segment_tree.py * f-string update red_black_tree.py * f-string update deque_doubly.py * f-string update climbing_stairs.py * f-string update iterating_through_submasks.py * f-string update knn_sklearn.py * f-string update 3n_plus_1.py * f-string update quadratic_equations_complex_numbers.py * f-string update nth_fibonacci_using_matrix_exponentiation.py * f-string update sherman_morrison.py * f-string update levenshtein_distance.py * fix lines that were too long
73 lines
2.2 KiB
Python
73 lines
2.2 KiB
Python
"""
|
|
This is a Python implementation of the levenshtein distance.
|
|
Levenshtein distance is a string metric for measuring the
|
|
difference between two sequences.
|
|
|
|
For doctests run following command:
|
|
python -m doctest -v levenshtein-distance.py
|
|
or
|
|
python3 -m doctest -v levenshtein-distance.py
|
|
|
|
For manual testing run:
|
|
python levenshtein-distance.py
|
|
"""
|
|
|
|
|
|
def levenshtein_distance(first_word: str, second_word: str) -> int:
|
|
"""Implementation of the levenshtein distance in Python.
|
|
:param first_word: the first word to measure the difference.
|
|
:param second_word: the second word to measure the difference.
|
|
:return: the levenshtein distance between the two words.
|
|
Examples:
|
|
>>> levenshtein_distance("planet", "planetary")
|
|
3
|
|
>>> levenshtein_distance("", "test")
|
|
4
|
|
>>> levenshtein_distance("book", "back")
|
|
2
|
|
>>> levenshtein_distance("book", "book")
|
|
0
|
|
>>> levenshtein_distance("test", "")
|
|
4
|
|
>>> levenshtein_distance("", "")
|
|
0
|
|
>>> levenshtein_distance("orchestration", "container")
|
|
10
|
|
"""
|
|
# The longer word should come first
|
|
if len(first_word) < len(second_word):
|
|
return levenshtein_distance(second_word, first_word)
|
|
|
|
if len(second_word) == 0:
|
|
return len(first_word)
|
|
|
|
previous_row = range(len(second_word) + 1)
|
|
|
|
for i, c1 in enumerate(first_word):
|
|
|
|
current_row = [i + 1]
|
|
|
|
for j, c2 in enumerate(second_word):
|
|
|
|
# Calculate insertions, deletions and substitutions
|
|
insertions = previous_row[j + 1] + 1
|
|
deletions = current_row[j] + 1
|
|
substitutions = previous_row[j] + (c1 != c2)
|
|
|
|
# Get the minimum to append to the current row
|
|
current_row.append(min(insertions, deletions, substitutions))
|
|
|
|
# Store the previous row
|
|
previous_row = current_row
|
|
|
|
# Returns the last element (distance)
|
|
return previous_row[-1]
|
|
|
|
|
|
if __name__ == "__main__":
|
|
first_word = input("Enter the first word:\n").strip()
|
|
second_word = input("Enter the second word:\n").strip()
|
|
|
|
result = levenshtein_distance(first_word, second_word)
|
|
print(f"Levenshtein distance between {first_word} and {second_word} is {result}")
|