大数据毕业设计：Python电影推荐系统 电影数据采集分析可视化系统✅

毕业设计：2023-2024年计算机专业毕业设计选题汇总（建议收藏）

毕业设计：2023-2024年最新最全计算机专业毕设选题推荐汇总

🍅感兴趣的可以先收藏起来，点赞、关注不迷路，大家在毕设选题，项目以及论文编写等相关问题都可以给我留言咨询，希望帮助同学们顺利毕业 。🍅

1、项目介绍

技术栈：
Python语言、Django框架、MySQL数据库、Echarts可视化、HTML、词云分析、协同过滤推荐算法

2、项目界面

（1）电影数据可视化分析

（2）电影首页

（4）我的收藏

（5）电影搜索查询

（6）电影推荐—协同过滤推荐算法

（7）注册登录界面

3、项目说明

协同过滤推荐算法是一种常见的推荐算法，可以用于搭建豆瓣电影推荐系统。在这个系统中，我们使用Django作为后端框架，以实现用户之间的协同过滤推荐。

首先，我们需要搜集用户的电影评分数据，包括用户对电影的打分和评论。可以通过用户注册和登录功能，让用户在豆瓣电影推荐系统中进行操作。用户可以通过搜索电影、查看电影详情、给电影打分和撰写评论等。

接下来，我们需要构建一个电影推荐的算法模型。协同过滤算法可以分为基于用户的协同过滤和基于物品的协同过滤。在基于用户的协同过滤中，我们可以使用用户的历史评分数据来计算相似用户，然后给用户推荐与他们相似度高的其他用户喜欢的电影。在基于物品的协同过滤中，我们可以根据电影的评分数据计算电影之间的相似度，并给用户推荐与他们喜欢的电影相似度高的其他电影。

在Django中，我们可以使用数据库来存储用户的电影评分数据和电影信息。可以使用ORM（对象关系映射）来操作数据库，方便地进行数据的增删改查操作。同时，我们可以使用Django的视图函数来处理用户的请求，并将推荐结果返回给用户。

为了提高推荐的准确性和多样性，我们可以使用一些优化方法。例如，可以引入时间衰减因子，对用户历史评分数据进行加权处理，使最近的评分具有更大的影响力。另外，可以引入随机推荐，给用户推荐一些与他们兴趣不完全相似的电影，以增加推荐的多样性。

最后，为了提高用户体验，可以使用前端技术来设计用户界面。可以使用HTML、CSS和JavaScript等技术来实现用户的交互功能，如搜索电影、查看电影详情和提交评分等。

总而言之，通过使用协同过滤推荐算法和Django框架，我们可以构建一个功能完善的豆瓣电影推荐系统，为用户提供个性化的电影推荐服务。

4、核心代码

# 验证登录
def check_login(func):
    def wrapper(request):
        # print("装饰器验证登录")
        cookie = request.COOKIES.get('uid')
        if not cookie:
            return redirect('/login/')
        else:
            return func(request)

    return wrapper


# Create your views here.
@check_login
def index(request):


    uid = int(request.COOKIES.get('uid', -1))
    if uid != -1:
        username = User.objects.filter(id=uid)[0].name

    relions = Movie.objects.all()
    all_type = {item.regions for item in relions}
    # all_type = ['历城', '天桥', '长清', '章丘', '高新', '市中', '济阳', '槐荫', '历下']

    if 'type' not in request.GET:  # 新闻类别
        type_ = '中国大陆'
        newlist = Movie.objects.filter(regions__contains=type_).values()
    else:
        type_ = request.GET.get('type')
        newlist = Movie.objects.filter(regions__contains=type_).values()
    tmp = []
    for item in newlist:
        if Like.objects.filter(uid_id=uid, hid_id=item['id']):
            is_like = 1
        else:
            is_like = 0
        item['is_like'] = is_like
        tmp.append(item)
    newlist = tmp
    return render(request, 'index.html', locals())


def star_ajax(request):
    res = {}
    yid = int(request.POST.get('id'))
    uid = int(request.COOKIES.get('uid', -1))

    if Like.objects.filter(uid_id=uid, hid_id=yid):
        Like.objects.filter(uid_id=uid, hid_id=yid).delete()
        res['color'] = 'black'
    else:
        Like.objects.create(uid_id=uid, hid_id=yid)
        res['color'] = 'red'
    return JsonResponse(res)




def my_shoucang(request):
    uid = int(request.COOKIES.get('uid', -1))
    if uid != -1:
        username = User.objects.filter(id=uid)[0].name

    newlist = []
    if Like.objects.filter(uid_id=uid):
        newlist = Like.objects.filter(uid_id=uid)
    id_list = [item.hid_id for item in newlist]
    newlist = Movie.objects.filter(id__in=id_list).values()
    tmp = []
    for item in newlist:
        if Like.objects.filter(uid_id=uid, hid_id=item['id']):
            is_like = 1
        else:
            is_like = 0
        item['is_like'] = is_like
        tmp.append(item)
    newlist = tmp
    return render(request, 'my_shoucang.html', locals())



@check_login
def detail(request):
    uid = int(request.COOKIES.get('uid', -1))
    if uid != -1:
        username = User.objects.filter(id=uid)[0].name
    id_ = request.GET.get('id')
    info = House.objects.get(id=int(id_))
    if See.objects.filter(uid_id=uid):
        See.objects.filter(uid_id=uid).update(num=F('num') + 1)
    else:
        See.objects.create(uid_id=uid,hid_id=int(id_),num=1)
    return render(request, 'detail_new.html', locals())



def scrawl_item(request):
    """
    爬取所有的电影元数据
    :param request:
    :return:
    """
    for i in tqdm( range(0,201,20)):
        # url = f'https://movie.douban.com/j/chart/top_list?type=10&interval_id=10:90&action=None&start={i}&limit=20'
        url = "https://movie.douban.com/j/chart/top_list"
        payload = {
            "type": 10,
            "interval_id": "100:90",
            "action": None,
            "start": i,
            "limit": 20
        }
        headers = {
            "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/95.0.4638.54 Safari/537.36"
        }
        res = requests.get(url=url, params=payload, headers=headers, )
        time.sleep(10)
        data_jsons = res.json()
        for data_json in data_jsons:
            id_ = data_json['id']#  int
            id_ = int(id_)
            # rating = data_json['rating'][0]#  float
            rank = data_json['rank']#  int
            rank = int(rank)
            img = data_json['cover_url']
            isPlayable = data_json['is_playable']
            kind = data_json['types'] # list
            kind = ','.join(kind)
            regions = data_json['regions'][0]
            title = data_json['title']
            url = data_json['url']
            releaseDate = data_json['release_date']
            actorCount = data_json['actor_count']#  int
            actorCount = int(actorCount)
            voteNum = data_json['vote_count']#  int
            voteNum = int(voteNum)
            score = data_json['score'] #  float
            score = float(score)
            actors = data_json['actors']  # list
            actors = ','.join(actors)
            # print(id_,rank,img,isPlayable,kind,regions,title,url,releaseDate,actorCount,voteNum,score,actors)
            if not Movie.objects.filter(id=id_):
                try:
                    Movie.objects.create(id=id_,rank=rank,img=img,isPlayable=isPlayable,kind=kind,
                                     regions=regions,title=title,url=url,releaseDate=releaseDate,actorCount=actorCount,voteNum=voteNum,score=score,actors=actors)
                except:
                    continue
    return  HttpResponse('全部电影元数据已经爬取OK')

def scrawl_comment(request):
    """
    爬取所有的电影元数据
    :param request:
    :return:
    """
    return  HttpResponse('全部电影评论已经爬取OK')






@check_login
def tuijian(request):

    uid = int(request.COOKIES.get('uid', -1))
    if uid != -1:
        username = User.objects.filter(id=uid)[0].name

    train = dict()
    history = Like.objects.all()  # 0.1
    for item in history:
        if item.uid_id not in train.keys():
            train[item.uid_id] = {item.hid_id: uid}
        else:
            train[item.uid_id][item.hid_id] = train[item.uid_id].get(item.hid_id, 0) + 10
    history = See.objects.all()  # 0.1
    for item in history:
        if item.uid_id not in train.keys():
            train[item.uid_id] = {item.hid_id: 0.1 * item.num}
        else:
            train[item.uid_id][item.hid_id] = train[item.uid_id].get(item.hid_id, 0) + 1 * item.num
    # 声明一个的对象
    newlist = []
    try:
        item = KNN(train)
        item.ItemSimilarity()
        recommedDict = item.Recommend(int(uid))  # 字典
        newlist = Movie.objects.filter(id__in=list(recommedDict.keys()))

    except:
        print("协同过滤异常啦")
        pass
    if len(newlist) == 0:
        msg = "你还没有在该网站有过评论、浏览行为，请去浏览吧！"
        newlist = Movie.objects.order_by('-id')[:10].values()
    else:
        msg = ""
    #
    tmp = []
    print(newlist)
    for item in newlist:

        try:
            id = item["id"]
        except:
            id = item.id

        if Like.objects.filter(uid_id=uid, hid_id=id):
            is_like = 1
        else:
            is_like = 0
        try:

            item['is_like'] = is_like
        except:
            item.is_like = is_like
        tmp.append(item)
    newlist = tmp
    return render(request, 'tuijian.html', locals())


def test(request):
    return HttpResponse('测试完成')


@check_login
def search(request):
    uid = int(request.COOKIES.get('uid', -1))
    if uid != -1:
        username = User.objects.filter(id=uid)[0].name
    newlist = []
    if request.method == 'POST':
        keywords = request.POST.get('keywords')
        newlist = Movie.objects.filter(title__contains=keywords).values()
        tmp = []
        for item in newlist:
            if Like.objects.filter(uid_id=uid, hid_id=item['id']):
                is_like = 1
            else:
                is_like = 0
            item['is_like'] = is_like
            tmp.append(item)
        newlist = tmp
    else:
        keywords = ''
    return render(request, 'search.html', locals())


def login(request):
    if request.method == "POST":
        tel, pwd = request.POST.get('tel'), request.POST.get('pwd')
        if User.objects.filter(tel=tel, password=pwd):

            obj = redirect('/')
            obj.set_cookie('uid', User.objects.filter(tel=tel, password=pwd)[0].id, max_age=60 * 60 * 24)
            return obj
        else:
            msg = "用户信息错误，请重新输入！！"
            return render(request, 'login.html', locals())
    else:
        return render(request, 'login.html', locals())


def register(request):
    if request.method == "POST":
        name, tel, pwd = request.POST.get('name'), request.POST.get('tel'), request.POST.get('pwd')
        print(name, tel, pwd)
        if User.objects.filter(tel=tel):
            msg = "你已经有账号了，请登录"
        else:
            User.objects.create(name=name, tel=tel, password=pwd)
            msg = "注册成功，请登录！"
        return render(request, 'login.html', locals())
    else:
        msg = ""
        return render(request, 'register.html', locals())


def logout(request):
    obj = redirect('/')
    obj.delete_cookie('uid')
    return obj

def plot(request):
    raw_data = Movie.objects.all()
    # 1  每个国家 电影排行榜
    main1 = raw_data.values('regions').annotate(count=Count('regions')).order_by('-count')[:10]
    main1_x = [item['regions'] for item in main1]
    main1_y = [item['count'] for item in main1]

    # 2  每年电影排行
    year_list = list(range(1999,2020))
    main2_x = year_list
    main2_y = []
    for year in year_list:
        main2_y.append(raw_data.filter(releaseDate__year=year).count())
    # print(main1)

    # 3  类别被购买前十
    tmp = [item.actors for item in raw_data]
    result_list = []
    for item in tmp:
        result_list = result_list + item.split(',')

    result_dict = {k: result_list.count(k) for k in result_list}
    result_dict = sorted(result_dict.items(), key=lambda x: x[1], reverse=True)  # 最大到最小
    print(result_dict)
    main3 = [{'value': item[1], 'name': item[0]}
             for item in result_dict
             ]
  

    tmp = [item.kind for item in raw_data]
    result_list = []
    for item in tmp:
        result_list = result_list + item.split(',')

    result_dict = {k: result_list.count(k)  for k in result_list}
    result_dict = sorted(result_dict.items(),key=lambda x:x[1],reverse=True)[:5] # 最大到最小
    print(result_dict)
    main4 = [{'value': item[1],'name': item[0]}
        for item in result_dict
    ]
    main4_x = [item['name'] for item in main4]

    return render(request,'plot.html',locals())

源码获取：

🍅由于篇幅限制，获取完整文章或源码、代做项目的，查看我的【用户名】、【专栏名称】、【顶部选题链接】就可以找到我啦🍅

感兴趣的可以先收藏起来，点赞、关注不迷路，下方查看👇🏻获取联系方式👇🏻