Поскольку вы действительно не смогли продемонстрировать кристалл, вот мой лучший снимок:
list_A = ['email','user','this','email','address','customer']
list_B = ['email','mail','address','netmail']
В приведенных выше двух списках мы найдем косинусное сходство между каждым элементом списка и остальными. т.е. email
из list_B
с каждым элементом в list_A
:
def word2vec(word):
from collections import Counter
from math import sqrt
# count the characters in word
cw = Counter(word)
# precomputes a set of the different characters
sw = set(cw)
# precomputes the "length" of the word vector
lw = sqrt(sum(c*c for c in cw.values()))
# return a tuple
return cw, sw, lw
def cosdis(v1, v2):
# which characters are common to the two words?
common = v1[1].intersection(v2[1])
# by definition of cosine distance we have
return sum(v1[0][ch]*v2[0][ch] for ch in common)/v1[2]/v2[2]
list_A = ['email','user','this','email','address','customer']
list_B = ['email','mail','address','netmail']
threshold = 0.80 # if needed
for key in list_A:
for word in list_B:
try:
# print(key)
# print(word)
res = cosdis(word2vec(word), word2vec(key))
# print(res)
print("The cosine similarity between : {} and : {} is: {}".format(word, key, res*100))
# if res > threshold:
# print("Found a word with cosine distance > 80 : {} with original word: {}".format(word, key))
except IndexError:
pass
OUTPUT :
The cosine similarity between : email and : email is: 100.0
The cosine similarity between : mail and : email is: 89.44271909999159
The cosine similarity between : address and : email is: 26.967994498529684
The cosine similarity between : netmail and : email is: 84.51542547285166
The cosine similarity between : email and : user is: 22.360679774997898
The cosine similarity between : mail and : user is: 0.0
The cosine similarity between : address and : user is: 60.30226891555272
The cosine similarity between : netmail and : user is: 18.89822365046136
The cosine similarity between : email and : this is: 22.360679774997898
The cosine similarity between : mail and : this is: 25.0
The cosine similarity between : address and : this is: 30.15113445777636
The cosine similarity between : netmail and : this is: 37.79644730092272
The cosine similarity between : email and : email is: 100.0
The cosine similarity between : mail and : email is: 89.44271909999159
The cosine similarity between : address and : email is: 26.967994498529684
The cosine similarity between : netmail and : email is: 84.51542547285166
The cosine similarity between : email and : address is: 26.967994498529684
The cosine similarity between : mail and : address is: 15.07556722888818
The cosine similarity between : address and : address is: 100.0
The cosine similarity between : netmail and : address is: 22.79211529192759
The cosine similarity between : email and : customer is: 31.62277660168379
The cosine similarity between : mail and : customer is: 17.677669529663685
The cosine similarity between : address and : customer is: 42.640143271122085
The cosine similarity between : netmail and : customer is: 40.08918628686365
Примечание: я также прокомментировал часть threshold
в коде, на случай, если
слова нужны только в том случае, если их сходство превышает
порог, то есть 80%
EDIT
OP : но то, что я хочу точно сделать, не сравнение слово за словом, а список за списком
Использование Counter
и math
:
from collections import Counter
import math
counterA = Counter(list_A)
counterB = Counter(list_B)
def counter_cosine_similarity(c1, c2):
terms = set(c1).union(c2)
dotprod = sum(c1.get(k, 0) * c2.get(k, 0) for k in terms)
magA = math.sqrt(sum(c1.get(k, 0)**2 for k in terms))
magB = math.sqrt(sum(c2.get(k, 0)**2 for k in terms))
return dotprod / (magA * magB)
print(counter_cosine_similarity(counterA, counterB) * 100)
OUTPUT
53.03300858899106