def fuzz(term, other):
d = distance(term.lower(), other.lower())
denominator = float(len(term + other))
if denominator == 0:
return False
return int(100 * float(d) / denominator) <= 25
def __eq__(self, other): from levenshtein_distance import levenshtein_distance as distance d = distance(self.lower(), other.lower()) return int(100 * float(d) / len(self+other)) <= 25
#!/usr/bin/env python3
# coding=utf-8
from levenshtein_distance import distance
if __name__ == '__main__':
# 3
print(distance("mitcmu", "mtacnu"))
# 3
print(distance("kitten", "sitting"))
# 192
dist = distance(
"Apache Spark achieves high performance for both batch and streaming data, using a state-of-the-art DAG scheduler, a query optimizer, and a physical execution engine. Write applications quickly in Java, Scala, Python, R, and SQL.",
"Apache Flink is a framework and distributed processing engine for stateful computations over unbounded and bounded data streams. Flink has been designed to run in all common cluster environments, perform computations at in-memory speed and at any scale."
)
print(dist)
def __eq__(self, other):
from levenshtein_distance import levenshtein_distance as distance
d = distance(self.lower(), other.lower())
return int(100 * float(d) / len(self + other)) <= 25