Neo4j圖數據庫導入數據

一.Neo4j簡介

1.數據構成

Neo4j使用圖相關的概念來描述數據模型，把數據保存為圖中的節點以及節點之間的關系。數據主要由三部分構成：

• 節點。節點表示對象實例，每個節點有唯一的ID區別其它節點，節點帶有屬性；
• 關系。就是圖里面的邊，連接兩個節點，另外這里的關系是有向的並帶有屬性；
• 屬性。key-value對，存在於節點和關系中，如圖1所示。

2.索引

Neo4j使用遍歷操作進行查詢。為了加速查詢，Neo4j會建立索引，並根據索引找到遍歷用的起始節點

3.特點

查詢的高性能

利用圖結構進行查詢，因此效率較高

設計的靈活性

開發的敏捷性

 

二.導入數據

#賬號密碼設置
    class MedicalGraph:
        def __init__(self):
            ...
            self.graph = Graph("http://localhost:7474", username="neo4j", password="自己的")
#獲取數據路徑
    cur_dir = '/'.join(os.path.abspath(__file__).split('/')[:-1])
    self.data_path = os.path.join(cur_dir, 'DATA/disease.csv')

#讀取文件
def read_file(self):
        """
        讀取文件，獲得實體，實體關系
        :return:
        """
        # cols = ["name", "alias", "part", "age", "infection", "insurance", "department", "checklist", "symptom",
        #         "complication", "treatment", "drug", "period", "rate", "money"]
        # 實體
        diseases = []  # 疾病
        aliases = []  # 別名
        symptoms = []  # 症狀
        parts = []  # 部位
        departments = []  # 科室
        complications = []  # 並發症
        drugs = []  # 葯品

        # 疾病的屬性：age, infection, insurance, checklist, treatment, period, rate, money
        diseases_infos = []
        # 關系
        disease_to_symptom = []  # 疾病與症狀關系
        disease_to_alias = []  # 疾病與別名關系
        diseases_to_part = []  # 疾病與部位關系
        disease_to_department = []  # 疾病與科室關系
        disease_to_complication = []  # 疾病與並發症關系
        disease_to_drug = []  # 疾病與葯品關系

        all_data = pd.read_csv(self.data_path, encoding='gb18030').loc[:, :].values
        for data in all_data:
            disease_dict = {}  # 疾病信息
            # 疾病
            disease = str(data[0]).replace("...", " ").strip()
            disease_dict["name"] = disease
            # 別名
            line = re.sub("[，、；,.;]", " ", str(data[1])) if str(data[1]) else "未知"
            for alias in line.strip().split():
                aliases.append(alias)
                disease_to_alias.append([disease, alias])
            # 部位
            part_list = str(data[2]).strip().split() if str(data[2]) else "未知"
            for part in part_list:
                parts.append(part)
                diseases_to_part.append([disease, part])
            # 年齡
            age = str(data[3]).strip()
            disease_dict["age"] = age
            # 傳染性
            infect = str(data[4]).strip()
            disease_dict["infection"] = infect
            # 醫保
            insurance = str(data[5]).strip()
            disease_dict["insurance"] = insurance
            # 科室
            department_list = str(data[6]).strip().split()
            for department in department_list:
                departments.append(department)
                disease_to_department.append([disease, department])
            # 檢查項
            check = str(data[7]).strip()
            disease_dict["checklist"] = check
            # 症狀
            symptom_list = str(data[8]).replace("...", " ").strip().split()[:-1]
            for symptom in symptom_list:
                symptoms.append(symptom)
                disease_to_symptom.append([disease, symptom])
            # 並發症
            complication_list = str(data[9]).strip().split()[:-1] if str(data[9]) else "未知"
            for complication in complication_list:
                complications.append(complication)
                disease_to_complication.append([disease, complication])
            # 治療方法
            treat = str(data[10]).strip()[:-4]
            disease_dict["treatment"] = treat
            # 葯品
            drug_string = str(data[11]).replace("...", " ").strip()
            for drug in drug_string.split()[:-1]:
                drugs.append(drug)
                disease_to_drug.append([disease, drug])
            # 治愈周期
            period = str(data[12]).strip()
            disease_dict["period"] = period
            # 治愈率
            rate = str(data[13]).strip()
            disease_dict["rate"] = rate
            # 費用
            money = str(data[14]).strip() if str(data[14]) else "未知"
            disease_dict["money"] = money

            diseases_infos.append(disease_dict)

        return set(diseases), set(symptoms), set(aliases), set(parts), set(departments), set(complications), \
                set(drugs), disease_to_alias, disease_to_symptom, diseases_to_part, disease_to_department, \
                disease_to_complication, disease_to_drug, diseases_infos