notebook.community

Edit and run



In [132]:

    
import csv
import pandas as pd
import numpy as np
import src.Paths as path

import sys
import os

print(os.getcwd())
print(sys.version_info)









    



C:\Users\Chrisi\Desktop\Studium\BigDataScience\sose17-small-data\python\traffic-prediction
sys.version_info(major=3, minor=5, micro=2, releaselevel='final', serial=0)



In [133]:

    
path.trajectories_training_file









    Out[133]:





'../../new_dataset/training/trajectories(table 5)_training.csv'



In [134]:

    
training_files = "../../dataset/training/"
links_file = "links (table 3).csv"
routes_file = "routes (table 4).csv"
trajectories_file = "trajectories(table 5)_training.csv"
volume_file = "volume(table 6)_training.csv"
weather_file = "weather (table 7)_training.csv"

routes_df = pd.read_csv(training_files+routes_file)
links_df = pd.read_csv(training_files+links_file)
weather_df = pd.read_csv(training_files+weather_file)
volume_df = pd.read_csv(training_files+volume_file)

training_files = "../../new_dataset/training/"
trajectories_df = pd.read_csv(training_files+trajectories_file)



In [135]:

    
routes_df









    Out[135]:






  
    
      
      intersection_id
      tollgate_id
      link_seq
    
  
  
    
      0
      A
      2
      110,123,107,108,120,117
    
    
      1
      A
      3
      110,123,107,108,119,114,118,122
    
    
      2
      B
      1
      105,100,111,103,116,101,121,106,113
    
    
      3
      B
      3
      105,100,111,103,122
    
    
      4
      C
      1
      115,102,109,104,112,111,103,116,101,121,106,113
    
    
      5
      C
      3
      115,102,109,104,112,111,103,122



In [136]:

    
from datetime import time
df3 = trajectories_df
df3 = df3.set_index(['intersection_id', 'tollgate_id', 'vehicle_id'])

df3['starting_time'] = pd.to_datetime(df3['starting_time'])
df3 = df3[df3['starting_time'].dt.dayofweek == 1]
df3 = df3[(df3['starting_time'].dt.hour >= 14) & (df3['starting_time'].dt.hour <= 14) & 
          (df3['starting_time'].dt.minute >= 49) & (df3['starting_time'].dt.minute <= 50)]
print( len(df3))
df3









    Out[136]:






C               1           1070045          205.36  
A               2           1064563           55.66  
B               3           1070066          161.04  
C               1           1076854          135.73  
A               2           1084497           38.69  
                3           1014161           99.26  
                            1012763          118.68  
                            1057709           71.90  
                            1069044          122.80  
B               3           1082678          120.83  
A               2           1081411           78.71  
                            1036997           93.25  
C               3           1059460          180.40  
A               2           1007462           48.53  
                3           1005569          172.82  
C               3           1033579          116.50  
A               2           1021625           89.36  
                3           1020754           68.13  
B               1           1045425          144.34  
                3           1034418          115.95  
C               1           1017548          196.71  
A               2           1032612           66.18  
                            1014027           12.67  
                            1051728           66.24  
C               1           1022536          132.21  
A               2           1022842           57.31  
                            1006481           59.04  
B               3           1047561           86.82  
A               3           1011494           93.25  
C               1           1025289          176.43  
                            1029065          131.24  
A               3           1029382          148.62  
                2           1009092          111.42  

  
    
      
      link_id
      length
      width
      lanes
      in_top
      out_top
      lane_width
    
  
  
    
      0
      100
      58
      3
      1
      105
      111
      3
    
    
      1
      101
      84
      3
      1
      116
      121
      3
    
    
      2
      102
      131
      9
      3
      115
      109
      3
    
    
      3
      103
      23
      12
      4
      111
      122,116
      3
    
    
      4
      104
      293
      9
      3
      109
      112
      3
    
    
      5
      105
      78
      6
      2
      NaN
      100
      3
    
    
      6
      106
      15
      3
      1
      121
      113
      3
    
    
      7
      107
      34
      9
      3
      123
      108
      3
    
    
      8
      108
      40
      9
      3
      107
      119,120
      3
    
    
      9
      109
      135
      9
      3
      102
      104
      3
    
    
      10
      110

	intersection_id	tollgate_id	link_seq
0	A	2	110,123,107,108,120,117
1	A	3	110,123,107,108,119,114,118,122
2	B	1	105,100,111,103,116,101,121,106,113
3	B	3	105,100,111,103,122
4	C	1	115,102,109,104,112,111,103,116,101,121,106,113
5	C	3	115,102,109,104,112,111,103,122

	link_id	length	width	lanes	in_top	out_top	lane_width
0	100	58	3	1	105	111	3
1	101	84	3	1	116	121	3
2	102	131	9	3	115	109	3
3	103	23	12	4	111	122,116	3
4	104	293	9	3	109	112	3
5	105	78	6	2	NaN	100	3
6	106	15	3	1	121	113	3
7	107	34	9	3	123	108	3
8	108	40	9	3	107	119,120	3
9	109	135	9	3	102	104	3
10	110