开发技术
协同过滤算法、机器学习、LSTM、vue.js、echarts、django、Python、MySQL

创新点
协同过滤推荐算法、爬虫、数据可视化、LSTM情感分析、短信、身份证识别

补充说明
适合大数据毕业设计、数据分析、爬虫类计算机毕业设计

介绍

• 音乐数据的爬取：爬取歌曲、歌手、歌词、评论
• 音乐数据的可视化：数据大屏+多种分析图【十几个图】
• 深度学习之LSTM 音乐评论情感分析
• 交互式协同过滤音乐推荐： 2种协同过滤算法、通过点击歌曲喜欢来修改用户对歌曲的评分
• 歌词、乐评的词云
• 登录、注册、修改个人信息等【集成身份证识别、短信验证码等】

核心算法代码分享如下：

# coding = utf-8# 基于项目的协同过滤推荐算法实现
import randomimport math
import pymysql                          #数据库
from operator import itemgetterfrom config import cnnclass ItemBasedCF():# 初始化参数def __init__(self):# 找到相似的8个，为目标用户推荐4个self.n_sim_movie = 8self.n_rec_movie = 4# 将数据集划分为训练集和测试集self.trainSet = {}self.testSet = {}# 用户相似度矩阵self.movie_sim_matrix = {}self.movie_popular = {}self.movie_count = 0print('Similar movie number = %d' % self.n_sim_movie)print('Recommneded movie number = %d' % self.n_rec_movie)# 从数据库得到“用户-物品”数据def get_dataset(self, pivot=0.75):trainSet_len = 0testSet_len = 0cnn.ping(reconnect=True)cursor = cnn.cursor()sql = ' select * from tb_rate'cursor.execute(sql)for item in cursor.fetchall():user, movie, rating = item[1:]self.trainSet.setdefault(user, {})self.trainSet[user][movie] = ratingtrainSet_len += 1self.testSet.setdefault(user, {})self.testSet[user][movie] = ratingtestSet_len += 1cursor.close()# cnn.close()print('Split trainingSet and testSet success!')print('TrainSet = %s' % trainSet_len)print('TestSet = %s' % testSet_len)# 读文件，返回文件的每一行def load_file(self, filename):with open(filename, 'r') as f:for i, line in enumerate(f):if i == 0:  # 去掉文件第一行的titlecontinueyield line.strip('\r\n')print('Load %s success!' % filename)# 计算物品之间的相似度def calc_movie_sim(self):for user, movies in self.trainSet.items():for movie in movies:if movie not in self.movie_popular:self.movie_popular[movie] = 0self.movie_popular[movie] += 1self.movie_count = len(self.movie_popular)print("Total movie number = %d" % self.movie_count)for user, movies in self.trainSet.items():for m1 in movies:for m2 in movies:if m1 == m2:continueself.movie_sim_matrix.setdefault(m1, {})self.movie_sim_matrix[m1].setdefault(m2, 0)self.movie_sim_matrix[m1][m2] += 1print("Build co-rated users matrix success!")# 计算物品之间的相似性 similarity matrixprint("Calculating movie similarity matrix ...")for m1, related_movies in self.movie_sim_matrix.items():for m2, count in related_movies.items():# 注意0向量的处理，即某物品的用户数为0if self.movie_popular[m1] == 0 or self.movie_popular[m2] == 0:self.movie_sim_matrix[m1][m2] = 0else:self.movie_sim_matrix[m1][m2] = count / math.sqrt(self.movie_popular[m1] * self.movie_popular[m2])print('Calculate movie similarity matrix success!')# 针对目标用户U，找到K部相似的物品，并推荐其N部物品def recommend(self, user):K = self.n_sim_movieN = self.n_rec_movierank = {}if user>len(self.trainSet):user = random.randint(1, len(self.trainSet))watched_movies = self.trainSet[user]for movie, rating in watched_movies.items():for related_movie, w in sorted(self.movie_sim_matrix[movie].items(), key=itemgetter(1), reverse=True)[:K]:if related_movie in watched_movies:continuerank.setdefault(related_movie, 0)rank[related_movie] += w * float(rating)return sorted(rank.items(), key=itemgetter(1), reverse=True)[:N]# 产生推荐并通过准确率、召回率和覆盖率进行评估def evaluate(self):print('Evaluating start ...')N = self.n_rec_movie# 准确率和召回率hit = 0rec_count = 0test_count = 0# 覆盖率all_rec_movies = set()for i, user in enumerate(self.trainSet):test_moives = self.testSet.get(user, {})rec_movies = self.recommend(user)for movie, w in rec_movies:if movie in test_moives:hit += 1all_rec_movies.add(movie)rec_count += Ntest_count += len(test_moives)precision = hit / (1.0 * rec_count)recall = hit / (1.0 * test_count)coverage = len(all_rec_movies) / (1.0 * self.movie_count)print('precisioin=%.4f\trecall=%.4f\tcoverage=%.4f' % (precision, recall, coverage))def rec_one(self,userId):print('推荐一个')rec_movies = self.recommend(userId)# print(rec_movies)return rec_movies# itemCF 推荐算法接口
def recommend(userId):itemCF = ItemBasedCF()itemCF.get_dataset()itemCF.calc_movie_sim()reclist = []recs = itemCF.rec_one(userId)return recs# for movie, rate in recs:#     # print(movie, rate)#     reclist.append(dict(item=movie, rate=rate))# # itemCF.evaluate()# return reclist# 测试
if __name__ == '__main__':print(recommend(1))