学习进度2020.02.10

Posted liurx

tags:

篇首语:本文由小常识网(cha138.com)小编为大家整理,主要介绍了学习进度2020.02.10相关的知识,希望对你有一定的参考价值。

学习进度2020.02.10

 

今天跟着做新增的数据筛选,学习地址:https://blog.csdn.net/qq_42768234/article/details/104162180

 

import re
import time
import json
import datetime
import requests
import pymysql
import pandas as pd


class VirusSupervise(object):
    def __init__(self):
        self.url = https://3g.dxy.cn/newh5/view/pneumonia?scene=2&clicktime=1579582238&enterid=1579582238&from=timeline&isappinstalled=0
        self.all_data = list()
        self.host_ip = "localhost"  # 数据库地图
        self.host_user = "root"  # 用户
        self.password = "root"  # 数据库密码

    def request_page(self):
        """
        请求页面数据
        """
        res = requests.get(self.url)
        res.encoding = utf-8
        pat0 = re.compile(window.getAreaStat = ([sS]*?)</script>)
        data_list = pat0.findall(res.text)
        data = data_list[0].replace(}catch(e){}, ‘‘)
        data = eval(data)
        return data

    def deep_spider(self, data, province_name):
        """
        深度提取出标签里详细的数据
        :param data:
        :param province_name:
        :return:
        """
        for temp_data in data:
            self.all_data.append([temp_data["cityName"], temp_data["confirmedCount"], temp_data["curedCount"],
                                  temp_data["deadCount"], province_name, datetime.date.today(),
                                  datetime.datetime.now().strftime(%H:%M:%S)])

    def filtration_data(self):
        """
        过滤数据
        """
        temp_data = self.request_page()
        province_short_names, confirmed_counts, cured_counts, dead_counts = list(), list(), list(), list()
        for i in temp_data:
            province_short_names.append(i[provinceShortName])  # 省份
            confirmed_counts.append(i[confirmedCount])  # 确诊
            cured_counts.append(i[curedCount])  # 治愈
            dead_counts.append(i[deadCount])  # 死亡
            self.deep_spider(i[cities], i["provinceShortName"])  # 深度解析数据添加到实例属性中

        data_all = pd.DataFrame(self.all_data, columns=["城市", "确诊", "治愈", "死亡", "省份", "日期", "时间"])
        # print(data_all[data_all["省份"] == "陕西"])
        df = pd.DataFrame()
        df[省份] = province_short_names
        df[确诊] = confirmed_counts
        df[治愈] = cured_counts
        df[死亡] = dead_counts
        print(df)
        data_all.to_csv("疫情数据_1.csv", encoding="utf_8_sig")
        return data_all



    def data_analysis(self):
        """
        数据分析返回结果
        :return:
        """
        importance_province = "陕西"  # 你所在的省市(注意数据库里是否有此数据)
        importance_city = "西安"  # 你所在的城市(同上) result中的需要自己修改
        result = "您好!
我是你的智能疫情监控机器人ABL
现在是北京时间: %s %s
%s
在十二小时内
全国内陆"                  "30个地区:
总病例:%s
全国新增病例:%s
西安新增病例:%s 积累病例:%s
陕西积累病例:%s
下面是新增疫情详细数据:%s疫情期间,注意保护好自己和家"                  "人的健康
如什么问题可以问我哦"  # 时间 天气 昨天时间 今日时间 疫情数据
        coon = pymysql.connect(host=self.host_ip, user=self.host_user, password=self.password, database="epidemic_data",
                               charset="utf8")
        number = pd.read_sql("select cycle from all_data order by id DESC limit 1", coon)["cycle"].to_list()[0]
        data1 = pd.read_sql("select * from all_data where cycle = %s" % number, coon)
        data2 = pd.read_sql("select * from all_data where cycle = %s" % (int(number) - 1), coon)
        now_time = data1.date_info.unique()[0] + " " + data1.detail_time.unique()[0]  # 查询数据收集时间
        week_info = self.get_week_day(datetime.date.today())
        weather = self.get_window()  # 天气数据
        all_num = data1["confirmedCount"].sum()  # 目前总人数
        add_all_num = int(data1["confirmedCount"].sum()) - int(data2["confirmedCount"].sum())  # 总新增人数

        sx_all = data1[data1["province_name"] == importance_province]["confirmedCount"].sum()
        add_xian = int(data1[data1["cityName"] == importance_city]["confirmedCount"]) -                    int(data2[data2["cityName"] == importance_city]["confirmedCount"])  # 西安新增人数
        xian_all = int(data1[data1["cityName"] == importance_city]["confirmedCount"])

        temp_a1 = data1.groupby("province_name")["confirmedCount"].sum()
        temp_a2 = data2.groupby("province_name")["confirmedCount"].sum()
        add_city = (temp_a1 - temp_a2).sort_values(ascending=False)
        add_city = add_city[add_city.values != 0]  # 新增地区及人数
        result_str = "
"
        for city_name, number in zip(add_city.index.tolist(), add_city.values.tolist()):
            str_data = str(city_name) + "新增病例: " + str(number) + "
"
            result_str += str_data

        danger_area = data2.groupby("province_name")["confirmedCount"].sum().sort_values(ascending=False)[: 10]
        danger_str = "
"  # 疫情严重地区可以自己添加
        for city_name, number in zip(danger_area.index.tolist(), danger_area.values.tolist()):
            str_data = str(city_name) + "出现病例: " + str(number) + "
"
            danger_str += str_data

        result = result % (str(now_time).split(" ")[1], week_info, weather, all_num, add_all_num,
                           add_xian, xian_all, sx_all, result_str)
        coon.close()
        return result

    @staticmethod
    def get_week_day(date):
        week_day = {
            0: 星期一,
            1: 星期二,
            2: 星期三,
            3: 星期四,
            4: 星期五,
            5: 星期六,
            6: 星期日,
        }
        day = date.weekday()  # weekday()可以获得是星期几
        return week_day[day]

    @staticmethod
    def get_window():
        url = "http://api.qingyunke.com/api.php?key=free&appid=0&msg=%E8%A5%BF%E5%AE%89%E5%A4%A9%E6%B0%94"
        response = requests.get(url)
        content = json.loads(response.content.decode())
        if content["result"]:
            return "未获取到天气信息"
        else:
            return content["content"]


if __name__ == __main__:
    sup = VirusSupervise()
    print(sup.data_analysis())

在数据库建立完成之后,报错如下:

技术图片

是不匹配的原因,解决方法:都用了int类型,

就报下面错了:

技术图片

 暂无解决方法

import re
import time
import json
import datetime
import requests
import pymysql
import pandas as pd


class VirusSupervise(object):
def __init__(self):
self.url = ‘https://3g.dxy.cn/newh5/view/pneumonia?scene=2&clicktime=1579582238&enterid=1579582238&from=timeline&isappinstalled=0‘
self.all_data = list()
self.host_ip = "localhost" # 数据库地图
self.host_user = "root" # 用户
self.password = "root" # 数据库密码

def request_page(self):
"""
请求页面数据
"""
res = requests.get(self.url)
res.encoding = ‘utf-8‘
pat0 = re.compile(‘window.getAreaStat = ([sS]*?)</script>‘)
data_list = pat0.findall(res.text)
data = data_list[0].replace(‘}catch(e){}‘, ‘‘)
data = eval(data)
return data

def deep_spider(self, data, province_name):
"""
深度提取出标签里详细的数据
:param data:
:param province_name:
:return:
"""
for temp_data in data:
self.all_data.append([temp_data["cityName"], temp_data["confirmedCount"], temp_data["curedCount"],
temp_data["deadCount"], province_name, datetime.date.today(),
datetime.datetime.now().strftime(‘%H:%M:%S‘)])

def filtration_data(self):
"""
过滤数据
"""
temp_data = self.request_page()
province_short_names, confirmed_counts, cured_counts, dead_counts = list(), list(), list(), list()
for i in temp_data:
province_short_names.append(i[‘provinceShortName‘]) # 省份
confirmed_counts.append(i[‘confirmedCount‘]) # 确诊
cured_counts.append(i[‘curedCount‘]) # 治愈
dead_counts.append(i[‘deadCount‘]) # 死亡
self.deep_spider(i[‘cities‘], i["provinceShortName"]) # 深度解析数据添加到实例属性中

data_all = pd.DataFrame(self.all_data, columns=["城市", "确诊", "治愈", "死亡", "省份", "日期", "时间"])
# print(data_all[data_all["省份"] == "陕西"])
df = pd.DataFrame()
df[‘省份‘] = province_short_names
df[‘确诊‘] = confirmed_counts
df[‘治愈‘] = cured_counts
df[‘死亡‘] = dead_counts
print(df)
data_all.to_csv("疫情数据_1.csv", encoding="utf_8_sig")
return data_all



def data_analysis(self):
"""
数据分析返回结果
:return:
"""
importance_province = "陕西" # 你所在的省市(注意数据库里是否有此数据)
importance_city = "西安" # 你所在的城市(同上) result中的需要自己修改
result = "您好! 我是你的智能疫情监控机器人ABL 现在是北京时间: %s %s %s 在十二小时内 全国内陆"
"30个地区: 总病例:%s 全国新增病例:%s 西安新增病例:%s 积累病例:%s 陕西积累病例:%s 下面是新增疫情详细数据:%s疫情期间,注意保护好自己和家"
"人的健康 如什么问题可以问我哦" # 时间 天气 昨天时间 今日时间 疫情数据
coon = pymysql.connect(host=self.host_ip, user=self.host_user, password=self.password, database="epidemic_data",
charset="utf8")
number = pd.read_sql("select cycle from all_data order by id DESC limit 1", coon)["cycle"].to_list()[0]
data1 = pd.read_sql("select * from all_data where cycle = %s" % number, coon)
data2 = pd.read_sql("select * from all_data where cycle = %s" % (int(number) - 1), coon)
now_time = data1.date_info.unique()[0] + " " + data1.detail_time.unique()[0] # 查询数据收集时间
week_info = self.get_week_day(datetime.date.today())
weather = self.get_window() # 天气数据
all_num = data1["confirmedCount"].sum() # 目前总人数
add_all_num = int(data1["confirmedCount"].sum()) - int(data2["confirmedCount"].sum()) # 总新增人数

sx_all = data1[data1["province_name"] == importance_province]["confirmedCount"].sum()
add_xian = int(data1[data1["cityName"] == importance_city]["confirmedCount"]) -
int(data2[data2["cityName"] == importance_city]["confirmedCount"]) # 西安新增人数
xian_all = int(data1[data1["cityName"] == importance_city]["confirmedCount"])

temp_a1 = data1.groupby("province_name")["confirmedCount"].sum()
temp_a2 = data2.groupby("province_name")["confirmedCount"].sum()
add_city = (temp_a1 - temp_a2).sort_values(ascending=False)
add_city = add_city[add_city.values != 0] # 新增地区及人数
result_str = " "
for city_name, number in zip(add_city.index.tolist(), add_city.values.tolist()):
str_data = str(city_name) + "新增病例: " + str(number) + " "
result_str += str_data

danger_area = data2.groupby("province_name")["confirmedCount"].sum().sort_values(ascending=False)[: 10]
danger_str = " " # 疫情严重地区可以自己添加
for city_name, number in zip(danger_area.index.tolist(), danger_area.values.tolist()):
str_data = str(city_name) + "出现病例: " + str(number) + " "
danger_str += str_data

result = result % (str(now_time).split(" ")[1], week_info, weather, all_num, add_all_num,
add_xian, xian_all, sx_all, result_str)
coon.close()
return result

@staticmethod
def get_week_day(date):
week_day = {
0: ‘星期一‘,
1: ‘星期二‘,
2: ‘星期三‘,
3: ‘星期四‘,
4: ‘星期五‘,
5: ‘星期六‘,
6: ‘星期日‘,
}
day = date.weekday() # weekday()可以获得是星期几
return week_day[day]

@staticmethod
def get_window():
url = "http://api.qingyunke.com/api.php?key=free&appid=0&msg=%E8%A5%BF%E5%AE%89%E5%A4%A9%E6%B0%94"
response = requests.get(url)
content = json.loads(response.content.decode())
if content["result"]:
return "未获取到天气信息"
else:
return content["content"]


if __name__ == ‘__main__‘:
sup = VirusSupervise()
print(sup.data_analysis())

以上是关于学习进度2020.02.10的主要内容,如果未能解决你的问题,请参考以下文章

自定义对话框片段内的进度条 - 如何从 AsyncTask 传递进度?

当片段视图加载是异步任务的一部分时,如何在片段加载之前显示进度条?

在recyclerview片段Reandroid中屏幕旋转后进度条不显示

css Bootstrap 3进度条片段

Seekbar进度drawable异常行为onPause

第一次进入片段ListView时AsyncTask更新progressBar的进度失败,滚动ListView后就ok了