208 lines
5.5 KiB
Python
208 lines
5.5 KiB
Python
import random
|
|
import time
|
|
import datetime
|
|
import pandas as pd
|
|
|
|
|
|
def get_uid():
|
|
return hex(int(time.time() * 10 ** 7) + random.randint(0, 10000))[2:]
|
|
|
|
|
|
# 获取筛选条件的包含关系
|
|
def get_bijiao(bijiao):
|
|
if bijiao == '==' or bijiao == 'in' or bijiao == 'like' or bijiao == 'is not null':
|
|
return "IN"
|
|
elif bijiao == '!=' or bijiao == 'not like' or bijiao == 'is null':
|
|
return 'NOT LIKE'
|
|
|
|
|
|
# 判断传入的数据类型
|
|
def estimate_data(data_type):
|
|
if data_type == 'int':
|
|
return "Nullable(Int64)"
|
|
elif data_type == 'ip':
|
|
return "Nullable(DateTime('UTC'))"
|
|
else:
|
|
return "Nullable(String)"
|
|
|
|
|
|
# 将字典变成字符串
|
|
def dict_to_str(dic):
|
|
c = str()
|
|
b = 0
|
|
for k, v in dic.items():
|
|
b += 1
|
|
if b == 1:
|
|
c += "{\"%s\":\"%s\"," % (k, v)
|
|
elif b != len(dic):
|
|
c += "\"%s\":\"%s\"," % (k, v)
|
|
else:
|
|
c += "\"%s\":\"%s\"}" % (k, v)
|
|
return c
|
|
|
|
|
|
def getEveryDay(begin_date, end_date):
|
|
# 前闭后闭
|
|
date_list = []
|
|
begin_date = datetime.datetime.strptime(begin_date, "%Y-%m-%d")
|
|
end_date = datetime.datetime.strptime(end_date, "%Y-%m-%d")
|
|
while begin_date <= end_date:
|
|
date_str = begin_date.strftime("%Y-%m-%d")
|
|
date_list.append(date_str)
|
|
begin_date += datetime.timedelta(days=1)
|
|
return date_list
|
|
|
|
|
|
# print(getEveryDay('2016-01-01','2017-05-11'))
|
|
def Download_xlsx(df, name):
|
|
"""
|
|
下载功能
|
|
name为文件名
|
|
"""
|
|
from urllib.parse import quote
|
|
import mimetypes
|
|
from utils import DfToStream
|
|
from fastapi.responses import StreamingResponse
|
|
file_name = quote(f'{name}.xlsx')
|
|
mime = mimetypes.guess_type(file_name)[0]
|
|
df_to_stream = DfToStream((df, name))
|
|
with df_to_stream as d:
|
|
export = d.to_stream()
|
|
Download = StreamingResponse(export, media_type=mime, headers={'Content-Disposition': f'filename="{file_name}"'})
|
|
return Download
|
|
|
|
|
|
def jiange_insert(list_date):
|
|
"""
|
|
间隔1条插入一条数据插入数据
|
|
:param day: list数据
|
|
:return: list
|
|
"""
|
|
i = 1
|
|
while i <= len(list_date):
|
|
list_date.insert(i, '-')
|
|
i += 2
|
|
return list_date
|
|
|
|
|
|
def create_df(resp):
|
|
"""
|
|
分布分析外部下载功能的df数据
|
|
"""
|
|
columns = resp['label']
|
|
day = list(resp['list'].keys())
|
|
jiange_insert(day)
|
|
date = []
|
|
day_nu = 0
|
|
for i in day:
|
|
if i == '-':
|
|
av = day[day_nu - 1]
|
|
day_date = resp['list'][av]['总体']
|
|
else:
|
|
day_date = resp['list'][i]['总体']
|
|
date_dict = {}
|
|
n = 0
|
|
p = 0
|
|
if i == '-':
|
|
date_dict['事件发生时间'] = '-'
|
|
date_dict['总人数'] = '-'
|
|
for nu in range(len(columns)):
|
|
date_dict[columns[nu]] = day_date['p'][p]
|
|
p += 1
|
|
date.append(date_dict)
|
|
else:
|
|
date_dict['事件发生时间'] = i
|
|
date_dict['总人数'] = day_date['total']
|
|
for nu in range(len(columns)):
|
|
date_dict[columns[nu]] = day_date['n'][n]
|
|
n += 1
|
|
date.append(date_dict)
|
|
day_nu += 1
|
|
columns.insert(0, '总人数')
|
|
columns.insert(0, '事件发生时间')
|
|
df = pd.DataFrame(data=date, columns=columns)
|
|
return df
|
|
|
|
|
|
def create_neidf(resp, columnName):
|
|
"""
|
|
分布分析内部下载功能的df数据
|
|
"""
|
|
columns = resp['label']
|
|
day = list(resp['list'].keys())
|
|
jiange_insert(day)
|
|
date = []
|
|
day_nu = 0
|
|
for i in day:
|
|
if i == '-':
|
|
av = day[day_nu - 1]
|
|
day_date = resp['list'][av]
|
|
else:
|
|
day_date = resp['list'][i]
|
|
date_dict = {}
|
|
n = 0
|
|
p = 0
|
|
if i == '-':
|
|
date_dict[columnName] = '-'
|
|
date_dict['全部用户数'] = '-'
|
|
for nu in range(len(columns)):
|
|
date_dict[columns[nu]] = day_date['p'][p]
|
|
p += 1
|
|
date.append(date_dict)
|
|
else:
|
|
date_dict[columnName] = i
|
|
date_dict['全部用户数'] = day_date['total']
|
|
for nu in range(len(columns)):
|
|
date_dict[columns[nu]] = day_date['n'][n]
|
|
n += 1
|
|
date.append(date_dict)
|
|
day_nu += 1
|
|
columns.insert(0, '全部用户数')
|
|
columns.insert(0, columnName)
|
|
df = pd.DataFrame(data=date, columns=columns)
|
|
return df
|
|
|
|
|
|
def random_hex():
|
|
"""
|
|
生成16位随机数
|
|
:return: 随机数
|
|
"""
|
|
result = hex(random.randint(0, 16 ** 16)).replace('0x', '').upper()
|
|
if (len(result) < 16):
|
|
result = '0' * (16 - len(result)) + result
|
|
return result
|
|
|
|
|
|
def get_time(fmt: str = '%Y-%m-%d') -> str:
|
|
'''
|
|
获取当前时间
|
|
'''
|
|
ts = time.time()
|
|
ta = time.localtime(ts)
|
|
t = time.strftime(fmt, ta)
|
|
return t
|
|
|
|
|
|
def import_excel(data, columns, name):
|
|
"""
|
|
导出数据到xlsx表里面
|
|
:param data: 需要导出的数据
|
|
:param columns: df的表名 例：['a','b','c']
|
|
:param name: 文件名。例：'随机数'
|
|
:return:
|
|
"""
|
|
zh = pd.DataFrame(data, columns=columns)
|
|
zh.to_excel(f'{name}.xlsx', index=False, header=True)
|
|
|
|
|
|
def qujian_time(start_time, end_time):
|
|
"""
|
|
把两个时间变成区间
|
|
:param start_time: '2022-07-01 10:00:00'
|
|
:param end_time: '2022-07-01 10:30:00'
|
|
:return: '2022-07-01 10:00:00~10:30:00'
|
|
"""
|
|
timess = str(end_time).split(' ')[-1]
|
|
return str(start_time) + '~' + timess
|