bigdataAPI/crond_script/nd_qxz_data.py

from datetime import datetime
import pymongo
import pandas as pd
from urllib import parse
import requests
import os 
import sys
import django


BASE_DIR = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
sys.path.append(BASE_DIR)
os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'bigdataAPI.settings')
django.setup()
from apps.PestAnalysis.models import EnvTempHum, HeNanAddr


def bigata_mongo():
    user = parse.quote_plus("root")
    passwd = parse.quote_plus("yfkj@6020")
    myclient = pymongo.MongoClient("mongodb://{0}:{1}@8.136.98.49:57017/".format(user,passwd))
    return myclient

def device_aggrate():
    myclient = bigata_mongo() 
    mydb = myclient.smartfarming
    mycol = mydb.sa_device 
    query = [
        {
            "$match": {
                "province": "河南省",
                "device_type_id": 15
            }
        },
        {
            "$group": {
            "_id": {
                "province": "$province",
                "city": "$city",
                "district": "$district"
            },
            "device_ids": { "$addToSet": "$device_id" },
            "unique_count": { "$sum": 1 }
            }
        },
        {
            "$project": {
            "location": "$_id",
            "device_ids": 1,
            "unique_count": 1,
            "_id": 0
            }
        }
    ]
    result = mycol.aggregate(query)

    # for i in list(result):
    #     device_ids = i.get("device_ids")
    #     count = i.get("unique_count")
    #     location = i.get("location")
    #     print("地址：", location, "数量", count)
    myclient.close()
    return list(result)


def nd_qxz_data(device_ids, start, end):
    myclient = bigata_mongo()
    mydb = myclient.smartfarming
    mycol = mydb.sa_nd_qxz_data
    query = {
        "upl_time": {
            "$gte": start,
            "$lte": end
        },
        "device_id": {
            "$in": device_ids
        }
    }
    project = {
        "_id": 0,
        "temp": 1,
        "swc": 1
    }
    nd_data = mycol.find(query,project)
    myclient.close()
    nd_data = list(nd_data) 
    tmp_list = {}
    if nd_data:
        for k in nd_data: 
            temp = k.get("temp")
            swc = k.get("swc")
            if temp:
                temp = temp.split(",")
                for index, ti in enumerate(temp): 
                    try:
                        ti = float(ti)
                    except:
                        ti = 0
                    if "temp_" + str(index) in tmp_list:
                        tmp_list["temp_" + str(index)].append(ti)
                    else:
                        tmp_list["temp_" + str(index)] = [ti]
            if swc:
                swc = swc.split(",")
                for index, si in enumerate(swc):
                    try:
                        si = float(si)
                    except:
                        si = 0
                    if "swc_" + str(index) in tmp_list:
                        tmp_list["swc_" + str(index)].append(si)
                    else:
                        tmp_list["swc_" + str(index)] = [si]
    avg_data = {}
    for k, v in tmp_list.items():
        avg_data[k] = round(sum(v) / len(v), 2)
    return avg_data




def main(start_y, end_y):
    start_year = datetime(start_y, 1, 1, 0, 0, 0).timestamp()
    end_year = datetime(end_y, 1, 1, 0, 0, 0).timestamp()
    device_addr = device_aggrate()
    for i in device_addr:
        device_ids = i.get("device_ids")
        location = i.get("location")
        province = location.get("province")
        city = location.get("city")
        district = location.get("district")
        print(district)
        henan = HeNanAddr.objects.filter(province=province, city=city, district=district)
        if henan.exists():
            henan = henan.first() 
            addr_code = henan.code
            if addr_code:
                # 时间 
                for r in range(int(start_year), int(end_year), 86400):
                    data = nd_qxz_data(device_ids, r, r + 86400)
                    format_date = datetime.fromtimestamp(r).strftime("%Y-%m-%d")
                    for k, v in data.items():
                        if k.startswith("temp"): 
                            k_lst = k.split("_")
                            if len(k_lst) == 2:
                                title = f"{(int(k_lst[1]) + 1) * 10}cm土壤温度"
                                EnvTempHum.objects.create(
                                    title = title,
                                    value = v,
                                    unit = "℃",
                                    type = "1",
                                    date = r,
                                    format_date = format_date,
                                    province = province,
                                    city = city,
                                    district = district,
                                    addr_code = addr_code
                                )
                        elif k.startswith("swc"):
                            k_lst = k.split("_")
                            if len(k_lst) == 2:
                                title = f"{(int(k_lst[1]) + 1) * 10}cm土壤湿度"
                                EnvTempHum.objects.create(
                                    title = title,
                                    value = v,
                                    unit = "%",
                                    type = "2",
                                    date = r,
                                    format_date = format_date,
                                    province = province,
                                    city = city,
                                    district = district,
                                    addr_code = addr_code
                                )


if __name__ == '__main__':
    main(2024, 2025)