NLP知识图谱day3

MedicalGraph 中代码理解

#!/usr/bin/env python3
# coding: utf-8
from py2neo import Graph, Node, Relationship
import pandas as pd
import re
import os


class MedicalGraph:
    def __init__(self):
        cur_dir = '/'.join(os.path.abspath(__file__).split('/')[:-1]) #获取数据路径
        self.data_path = os.path.join(cur_dir, 'DATA/disease.csv')
        self.graph = Graph("http://localhost:7474", username="neo4j", password="你的密码")

    def read_file(self):
        """
        读取文件，获得实体，实体关系
        :return:
        """
        # cols = ["name", "alias", "part", "age", "infection", "insurance", "department", "checklist", "symptom",
        #         "complication", "treatment", "drug", "period", "rate", "money"]
        # 实体
        diseases = []  # 疾病
        aliases = []  # 别名
        symptoms = []  # 症状
        parts = []  # 部位
        departments = []  # 科室
        complications = []  # 并发症
        drugs = []  # 药品

        # 疾病的属性：age, infection, insurance, checklist, treatment, period, rate, money
        diseases_infos = []
        # 关系
        disease_to_symptom = []  # 疾病与症状关系
        disease_to_alias = []  # 疾病与别名关系
        diseases_to_part = []  # 疾病与部位关系
        disease_to_department = []  # 疾病与科室关系
        disease_to_complication = []  # 疾病与并发症关系
        disease_to_drug = []  # 疾病与药品关系

        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
            # 别名
            line = re.sub("[，、；,.;]", " ", str(data[1])) if str(data