import difflib

Str = '上海中心大廈'
s1 ?= '大廈'
s2 ?= '上海中心'
s3 ?= '上海中心大樓'

print(difflib.SequenceMatcher(None, Str, s1).quick_ratio()) ?
print(difflib.SequenceMatcher(None, Str, s2).quick_ratio()) ?
print(difflib.SequenceMatcher(None, Str, s3).quick_ratio())

0.5
0.8
0.8333333333333334

import numpy as np
# 余弦相似度（法1）：
def cosin_distance2(vector1, vector2):
?
? ? user_item_matric = np.vstack((vector1, vector2))
? ? sim = user_item_matric.dot(user_item_matric.T)
? ? norms = np.array([np.sqrt(np.diagonal(sim))])
? ? user_similarity = (sim / norms / norms.T)[0][1]
? ? return user_similarity
?
data = np.load("data/all_features.npy")
#sim = cosin_distance(data[22], data[828])
sim = cosin_distance2(data[22], data[828])
print(sim)
?
# 余弦相似度（法2）
from sklearn.metrics.pairwise import cosine_similarity
a = np.array([1, 2, 8, 4, 6])
a1 = np.argsort(a)
user_tag_matric = np.vstack((a, a1))
user_similarity = cosine_similarity(user_tag_matric)
print(user_similarity[0][1])
?
# 余弦相似度（法3）
from sklearn.metrics.pairwise import pairwise_distances
a = np.array([1, 2, 8, 4, 6])
a1 = np.argsort(a)
user_tag_matric = np.vstack((a, a1))
user_similarity = pairwise_distances(user_tag_matric, metric='cosine')
print(1-user_similarity[0][1])

# 1) given two data points, calculate the euclidean distance between them
def get_distance(data1, data2):
? ? points = zip(data1, data2)
? ? diffs_squared_distance = [pow(a - b, 2) for (a, b) in points]
? ? return math.sqrt(sum(diffs_squared_distance))

def Manhattan(vec1, vec2):
? ? npvec1, npvec2 = np.array(vec1), np.array(vec2)
? ? return np.abs(npvec1-npvec2).sum()
# Manhattan_Distance,

def Chebyshev(vec1, vec2):
? ? npvec1, npvec2 = np.array(vec1), np.array(vec2)
? ? return max(np.abs(npvec1-npvec2))
# Chebyshev_Distance

#!/usr/bin/env python
?
from math import*
from decimal import Decimal
?
def nth_root(value,n_root):
? ? root_value=1/float(n_root)
? ? return round(Decimal(value)**Decimal(root_value),3)
?
def minkowski_distance(x,y,p_value):
? ? return nth_root(sum(pow(abs(a-b),p_value) for a,b in zip(x,y)),p_value)
?
print(minkowski_distance([0,3,4,5],[7,6,3,-1],3))

def Standardized_Euclidean(vec1,vec2,v):
? ? from scipy import spatial
? ? npvec = np.array([np.array(vec1), np.array(vec2)])
? ? return spatial.distance.pdist(npvec, 'seuclidean', V=None)
# Standardized Euclidean distance
# http://blog.csdn.net/jinzhichaoshuiping/article/details/51019473

def Mahalanobis(vec1, vec2):
? ? npvec1, npvec2 = np.array(vec1), np.array(vec2)
? ? npvec = np.array([npvec1, npvec2])
? ? sub = npvec.T[0]-npvec.T[1]
? ? inv_sub = np.linalg.inv(np.cov(npvec1, npvec2))
? ? return math.sqrt(np.dot(inv_sub, sub).dot(sub.T))
# MahalanobisDistance

def Edit_distance_str(str1, str2):
? ? import Levenshtein
? ? edit_distance_distance = Levenshtein.distance(str1, str2)
? ? similarity = 1-(edit_distance_distance/max(len(str1), len(str2)))
? ? return {'Distance': edit_distance_distance, 'Similarity': similarity}
# Levenshtein distance