Neo4j 实战篇（一）基于Py2Neo构建电影知识图谱

    list_mid = df['popularity']['movieid_id']
    
    # 查找受欢迎的电影信息
    # Find the movies which is popularity 
    df_popularity_movie = df['movie'][df['movie']['movieid'].isin(list_mid)]
    df_popularity_movie
    
    
      
      
      
      
      
      
    
    代码解读

    # 将DataFrame格式转化为dict，到时候方便插入Neo4j
    # make DataFrame to Dict, in order to insert neo4j
    dict_movie = {}
    
    for i in range(len(df_popularity_movie)):
    row = df_popularity_movie.iloc[i]
    dict_movie.update({row['movieid'] : row.to_dict()})
    print('rows: ' , len(dict_movie))
    
    
      
      
      
      
      
      
      
      
    
    代码解读

    dict_actor_movie = {}
    for mid in df_popularity_movie['movieid']:
    flag = df['actor_movie']['movieid_id'].eq(mid)
    actors = df['actor_movie'][flag]['actorid_id'].to_list()
    dict_actor_movie.update({mid : actors})
    print('rows: ' , len(dict_actor_movie))
    
    
      
      
      
      
      
      
    
    代码解读

    dict_actor = {}
    actors = set()
    for ac in dict_actor_movie.values():
    for actor in ac:
        actors.add(actor)
    for aid in actors:
    flag = (df['actor']['actorid'] == aid)
    row = df['actor'][flag].iloc[0]
    dict_actor.update({aid: row.to_dict()})
    print('rows: ' , len(dict_actor_movie))
    
    
      
      
      
      
      
      
      
      
      
      
    
    代码解读

    from py2neo import Graph
    url = "http://localhost:7474"
    username = "neo4j"
    password = "123456"
    graph = Graph(url, auth=(username, password))
    print("neo4j info: {}".format(str(graph)))
    
    
      
      
      
      
      
      
    
    代码解读

    from py2neo import Graph, Node, Subgraph
    import time 
    s_time = time.time()
    
    node_list = []
    
    graph.delete_all()
    
    for mid, movie in dict_movie.items():
    node_list.append(Node("movie", **movie))
    for aid, actor in dict_actor.items():
    node_list.append(Node("actor", **actor))
    graph.create(subgraph=Subgraph(node_list))
    
    # 查看一个节点
    print(node_list[0])
    
    
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
    
    代码解读

    print('movie: ', graph.nodes.match("movie").count())
    print('actor: ', graph.nodes.match('actor').count())
    
    
      
      
    
    代码解读

    from py2neo import NodeMatcher, Relationship
    node_matcher = NodeMatcher(graph)
    list_rel = []
    for mid, actors in dict_actor_movie.items(): 
    node_movie = node_matcher.match("movie", movieid=mid).first()
    if node_movie != None:
        for actor in actors:
            node_actor = node_matcher.match("actor", actorid=actor).first()
            if node_actor != None:
                list_rel.append(Relationship(node_actor, "acted", node_movie, name='acted'))
    
    # 批量建立
    # batch build 
    once = 50
    maxi = len(list_rel)
    for i in range(0, maxi, once):
    subgraph = Subgraph(relationships=list_rel[i:i+once])
    graph.separate(subgraph)
    graph.create(subgraph)
    print(f'[INFO] >> created {len(subgraph)} relations')
    
    
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
    
    代码解读

    from py2neo import RelationshipMatcher
    rmatcher = RelationshipMatcher(graph)
    
    i = 0
    for node_movie in graph.nodes.match('movie').all():
    print(i, '-' * 10 , node_movie['name'] + '-' *10)
    for rel in graph.match([None, node_movie]).all():
        print('--', rel)
    i += 1
    print('\n\n')
    
    
      
      
      
      
      
      
      
      
      
      
    
    代码解读

    nodes_movie = graph.nodes.match('movie').all()
    
    #关于已出现的演员人数的前十名
    # Top10 about the number of appeared actor  
    
    # 如果演员人数一致就根据评分判断，选择评分高的电影
    # If the number of actors is the same,
    #   judge according to the score and choose the film with high rate.
    rm = RelationshipMatcher(graph)
    '''
    Top10
    '''
    dict_movie_top10 = {}
    for node_movie in nodes_movie:
    list_actors = rm.match([None, node_movie], r_type='acted').all()
    count = len(list_actors)
    dict_movie_top10.update({node_movie: {'count':int(count), 'actors':list_actors}})
    
    list_movie_top10 = sorted(dict_movie_top10.items(), 
        key = lambda k : (k[1]['count'], float(k[0]['rate'])), reverse=True)[:10]
    
    # list_movie_top10 is a list([turple(Node, dict)])
    print('------------------ Top10 ------------------')
    for node_movie, dict_count in list_movie_top10:
    print(dict_count['count'], node_movie['rate'], node_movie['name'])
    
    
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
    
    代码解读

    graph.delete(Subgraph(graph.nodes.match('actor_top10').all()))
    graph.delete(Subgraph(graph.nodes.match('movie_top10').all()))
    graph.delete(Subgraph(RelationshipMatcher(graph).match(name='acted_top10')))
    
    rel_top10 = []
    nodeMatcher = NodeMatcher(graph)
    for node_movie, dict_count in list_movie_top10:
    for actor_rel in dict_count['actors']:
    
        actor = Node('actor_top10', **dict(actor_rel.start_node))
        movie = Node('movie_top10', **dict(node_movie))
    
        actor_find = nodeMatcher.match('actor_top10', name=actor['name']).first()
        movie_find = nodeMatcher.match('movie_top10', name=movie['name']).first()
        if actor_find != None: ator = actor_find 
        if movie_find != None: movie = movie_find
        
        rel_top10.append(Relationship(actor, "acted", movie, name='acted_top10'))
        sub_rels=Subgraph(relationships=rel_top10)
        graph.separate(subgraph=sub_rels)
        graph.create(subgraph = sub_rels)
    
    print('The number of actor_top10 node: ',graph.nodes.match('actor_top10').count())
    print('The number of moive_top10 node: ', graph.nodes.match('movie_top10').count())
    print('The number of relationsip: ', graph.relationships.match(name='acted_top10').count())
    
    
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
    
    代码解读