# -*- coding: utf-8 -*-
__Author__ = 'zhangbaojun'
__Time__ = '2018/6/6 14:00'
__File__ = 'data_volumn.py'
import pandas as pd
# time='DTCOLLECTTIME'
# volumn = 'SUM(D.NVOLUME)'
data = 'D:/Hisense/TrafficFlowPrediction/data/100211gaizao.csv'
df1 = pd.read_csv(data, encoding='utf-8', header=None, ).fillna(0)
df1.columns = ['time', 'volumn']
a = []
b=[]
# print(df1['time'].values[0][0:9])
for i in range(0, len(df1)):
if df1['time'].values[i][0:9] == '2018/1/20' or df1['time'].values[i][0:9] == '2018/1/21'\
or df1['time'].values[i][0:9] == '2018/1/27'or df1['time'].values[i][0:9] == '2018/1/28'\
or df1['time'].values[i][0:8] == '2018/2/3'or df1['time'].values[i][0:8] == '2018/2/4'\
or df1['time'].values[i][0:9] == '2018/2/10'or df1['time'].values[i][0:9] == '2018/2/15'\
or df1['time'].values[i][0:9] == '2018/2/16'or df1['time'].values[i][0:9] == '2018/2/17'\
or df1['time'].values[i][0:9] == '2018/2/18'or df1['time'].values[i][0:9] == '2018/2/19'\
or df1['time'].values[i][0:9] == '2018/2/20'or df1['time'].values[i][0:9] == '2018/2/21'\
or df1['time'].values[i][0:9] == '2018/2/25'\
or df1['time'].values[i][0:8] == '2018/3/3'or df1['time'].values[i][0:8] == '2018/3/4'\
or df1['time'].values[i][0:9] == '2018/3/10'or df1['time'].values[i][0:9] == '2018/3/11'\
or df1['time'].values[i][0:9] == '2018/3/17'or df1['time'].values[i][0:9] == '2018/3/18'\
or df1['time'].values[i][0:9] == '2018/3/24'or df1['time'].values[i][0:9] == '2018/3/25'\
or df1['time'].values[i][0:9] == '2018/3/31'or df1['time'].values[i][0:8] == '2018/4/1'\
or df1['time'].values[i][0:8] == '2018/4/5'or df1['time'].values[i][0:8] == '2018/4/6'\
or df1['time'].values[i][0:8] == '2018/4/7'or df1['time'].values[i][0:9] == '2018/4/14'\
or df1['time'].values[i][0:9] == '2018/4/15'or df1['time'].values[i][0:9] == '2018/4/21'\
or df1['time'].values[i][0:9] == '2018/4/22'or df1['time'].values[i][0:9] == '2018/4/29'\
or df1['time'].values[i][0:9] == '2018/4/28'or df1['time'].values[i][0:9] == '2018/4/30'\
or df1['time'].values[i][0:8] == '2018/5/1'or df1['time'].values[i][0:8] == '2018/5/5'\
or df1['time'].values[i][0:9] == '2018/5/6':
a.append([df1['time'].values[i],df1['volumn'].values[i]])
zhoumo=pd.DataFrame(a)
zhoumo.to_csv('100211_jiejiari.csv',index=None)
for i in range(0, len(df1)):
if df1['time'].values[i][0:9] != '2018/1/20' and df1['time'].values[i][0:9] != '2018/1/21'\
and df1['time'].values[i][0:9] != '2018/1/27'or df1['time'].values[i][0:9] != '2018/1/28'\
and df1['time'].values[i][0:8] != '2018/2/3'or df1['time'].values[i][0:8] != '2018/2/4'\
and df1['time'].values[i][0:9] != '2018/2/10'or df1['time'].values[i][0:9] != '2018/2/15'\
and df1['time'].values[i][0:9] != '2018/2/16'or df1['time'].values[i][0:9] != '2018/2/17'\
and df1['time'].values[i][0:9] != '2018/2/18'or df1['time'].values[i][0:9] != '2018/2/19'\
and df1['time'].values[i][0:9] != '2018/2/20'or df1['time'].values[i][0:9] != '2018/2/21'\
and df1['time'].values[i][0:9] != '2018/2/25'\
and df1['time'].values[i][0:8] != '2018/3/3'and df1['time'].values[i][0:8] != '2018/3/4'\
and df1['time'].values[i][0:9] != '2018/3/10'and df1['time'].values[i][0:9] != '2018/3/11'\
and df1['time'].values[i][0:9] != '2018/3/17'and df1['time'].values[i][0:9] != '2018/3/18'\
and df1['time'].values[i][0:9] != '2018/3/24'and df1['time'].values[i][0:9] != '2018/3/25'\
and df1['time'].values[i][0:9] != '2018/3/31'and df1['time'].values[i][0:8] != '2018/4/1'\
and df1['time'].values[i][0:8] != '2018/4/5'and df1['time'].values[i][0:8] != '2018/4/6'\
and df1['time'].values[i][0:8] != '2018/4/7'and df1['time'].values[i][0:9] != '2018/4/14'\
and df1['time'].values[i][0:9] != '2018/4/15'and df1['time'].values[i][0:9] != '2018/4/21'\
and df1['time'].values[i][0:9] != '2018/4/22'and df1['time'].values[i][0:9] != '2018/4/29'\
and df1['time'].values[i][0:9] != '2018/4/28'and df1['time'].values[i][0:9] != '2018/4/30'\
and df1['time'].values[i][0:8] != '2018/5/1'and df1['time'].values[i][0:8] != '2018/5/5'\
and df1['time'].values[i][0:9] != '2018/5/6':
b.append([df1['time'].values[i],df1['volumn'].values[i]])
zhoumo=pd.DataFrame(b)
zhoumo.to_csv('100211_gongzuori.csv',index=None)
# print(a)
# print(df1['time'].values[0])
城市交通道路流量预测.rar （80个子文件） 
城市交通道路流量预测 data 
100211_jiejiari.csv 240KB gongzuori.csv 66KB 5.7-5.9数据 8KB zhoumo_test.csv 45KB volumn-gaizao.csv 481KB volumn.csv 554KB 100211_jiejiari_buhanling.csv 214KB 100211_jiejiari_buhanling_train.csv 121KB zhoumo_train.csv 124KB gongzuori_train.csv 202KB 100211_buhanling_train.csv 357KB 100211_gongzuori_buhanling_train.csv 236KB gongzuori_test.csv 85KB 100211_gongzuori.csv 586KB data.py 1KB 100211_gongzuori_buhanling_test.csv 118KB 100211data 100211_weekend_test.csv 60KB 100211_weekend_train.csv 121KB 100211_all_train.csv 357KB 100211_all_test.csv 178KB 100211_workdays_train.csv 236KB 100211_workdays_test(1).csv 118KB 100211gaizao.csv 586KB train.csv 195KB __pycache__ data.cpython-37.pyc 1KB 100211_gongzuori_buhanling.csv 524KB data_volumn.py 5KB 100211_jiejiari_buhanling_test.csv 60KB zhoumo.csv 43KB test.csv 108KB 100211_buhanling_test.csv 178KB .idea 城市交通道路流量预测.iml 408B workspace.xml 15KB misc.xml 294B modules.xml 319B encodings.xml 138B data.py 1KB model 100211_all saes.h5 2.52MB lstm.h5 414KB gru loss.csv 47KB gru.h5 316KB saes loss.csv 47KB lstm loss.csv 48KB lstm.h5 414KB 100211_weekend saes.h5 2.52MB lstm.h5 414KB gru loss.csv 47KB gru.h5 316KB saes loss.csv 47KB lstm loss.csv 47KB model.py 2KB 原始模型 saes.h5 2.52MB lstm.h5 414KB gru loss.csv 47KB gru.h5 316KB saes loss.csv 47KB lstm loss.csv 47KB lstm_loss.csv 47KB __pycache__ model.cpython-37.pyc 2KB 100211_workdays saes.h5 2.52MB lstm.h5 414KB gru loss.csv 48KB gru.h5 316KB saes loss.csv 48KB lstm loss.csv 48KB lstm loss.csv 47KB images 
pre_workdays_daily.png 49KB 原始图片 GRU.png 19KB LSTM.png 19KB SAEs.png 37KB eva.png 69KB GRU.png 19KB LSTM.png 19KB pre_weekend.png 51KB SAEs.png 37KB pre_weekend_daily.png 48KB pre_workdays.png 66KB train.py 3KB __pycache__ data.cpython-37.pyc 1KB test.py 4KB资源评论
一枚爱吃大蒜的程序员
- 粉丝: 1w+
- 资源: 86
