暑期实训：Unsplash网站图片推荐算法

前言

根据Unsplash网站图片的tags，计算所需图片的tags和所需图片所在类的其它图片的余弦相似度，取相似度最大的某些图片。

提示：爬取tags是json格式，数据库连接使用mongodb。

一、根据tags，在同一类别和作者中推荐

代码如下：

#保证在同一类别下计算余弦相似度，排序，获得前6个，排除自己一个，获得前5个
import pymongo
import math
import re
import time
#starttime=time.time()

def compute_cosine(text_a, text_b):
    # 找单词及词频
    words1 = text_a.split(' ')
    words2 = text_b.split(' ')
    # print(words1)
    words1_dict = {
   }
    words2_dict = {
   }
    for word in words1:
        # word = word.strip(",.?!;")
        word = re.sub('[^a-zA-Z]', '', word)
        word = word.lower()
        # print(word)
        if word != '' and word in words1_dict: 
            num = words1_dict[word]
            words1_dict[word] = num + 1
        elif word != '':
            words1_dict[word] = 1
        else:
            continue
    for word in words2:
        # word = word.strip(",.?!;")
        word = re.sub('[^a-zA-Z]', '', word)
        word = word.lower()
        if word != '' and word in words2_dict:
            num = words2_dict[word]
            words2_dict[word] = num + 1
        elif word != '':
            words2_dict[word] = 1
        else:
            continue
    #print(words1_dict)
    #print(words2_dict)

    # 排序
    dic1 = sorted(words1_dict.items(), key=lambda asd: asd[1], reverse=True)
    dic2 = sorted(words2_dict.items(), key=lambda asd: asd[1], reverse=True)
    #print(dic1)
    #print(dic2)

    # 得到词向量
    words_key = []
    for i in range(len(dic1)):
        words_key.append(dic1[i][0])  # 向数组中添加元素
    for i in range(len(dic2)):
        if dic2[i][0] in words_key:
            # print 'has_key', dic2[i][0]
            pass
        else:  # 合并
            words_key.append(dic2[i][0])
    # print(words_key)
    vect1 = []
    vect2 = []
    for word in words_key:
        if word in words1_dict:
            vect1.append(words1_dict[word])
        else:
            vect1.append(0)