# -*- coding: utf-8 -*-

# 统计未来3小时将要起飞的人数

import os

import pandas as pd

import numpy as np

import matplotlib.pyplot as plt

from sklearn.preprocessing import MinMaxScaler

os.chdir('C:/Users\Administrator/Desktop/competition/1017')

df = pd.read_csv('airport_gz_departure_chusai_2ndround.csv',usecols = [2,3])

df = df.dropna(axis = 0)    # 删除含有空值的行

df = df[df.flight_time>df.checkin_time]    # 删除flighttime早于checktime的行

df = df.sort_values(by='flight_time')# 将数据按flight_time排序

df.flight_time = pd.to_datetime(df.flight_time)    #转换数据类型为Timestamp

df.checkin_time = pd.to_datetime(df.checkin_time)

df = df[(df.flight_time-df.checkin_time)<pd.Timedelta(hours=12)]    #去除间隔时间相差12个小时的，12这个参数需要自己调试

df = df.flight_time

dataset = pd.tseries.index.DatetimeIndex(df.values)        # 转换数据类型为DatetimeIndex

times = pd.date_range(start = '2016-09-10 19:00:00',end = '2016-9-25 15:00:00',freq ='10min')

contact_nums = []

for time in times:

    start = np.where(dataset>time)[0]

    time = time + pd.Timedelta(hours = 3)            # 统计当前时间后3小时将要起飞的乘客

    end = np.where(dataset<=time)[0]

    if len(end)==0:

        contact_nums.append(0)

    else:

        contact_nums.append(end[-1]-start[0]+1)

df = pd.DataFrame(contact_nums,index = times,columns = ['num'])

df.to_csv('C:/Users/Administrator/Desktop/competition/DataProcessing/Person_to_fly.csv',index_label = 'time_back')

scaler = MinMaxScaler(feature_range = (0,1))

contact_nums = scaler.fit_transform(np.reshape(np.array(contact_nums),(len(contact_nums),1)).astype('float32'))

plt.plot(scaler.inverse_transform(contact_nums))

plt.show()