In [42]:
import numpy as np
In [43]:
import pandas as pd
In [44]:
c_names = ['vID', 'frID', 'tFr','Timestamp', 'localX', 'localY', 'globalX','globalY', 'vLenght', 'vWidth', 'vType', 'veloc','accel', 'line', 'pred', 'foll', 'spac', 'headway', 'dateTime']
data = pd.read_table('D:\\zzzLola\\PhD\\DataSet\\US101\\test\\100ts.txt', sep='\t', header=None, names=c_names)
In [45]:
data.count
Out[45]:
<bound method DataFrame.count of vID frID tFr Timestamp localX localY globalX \
0 1073 3211 587 1118847300000 20.097 1999.367 6452595.286
1 1073 3212 587 1118847300100 20.025 2005.368 6452600.004
2 1073 3213 587 1118847300200 19.973 2011.314 6452604.649
3 1073 3214 587 1118847300300 19.886 2017.183 6452609.253
4 1073 3215 587 1118847300400 19.817 2023.016 6452613.792
5 1073 3216 587 1118847300500 19.731 2028.885 6452618.396
6 1073 3217 587 1118847300600 19.678 2034.831 6452623.041
7 1073 3218 587 1118847300700 19.606 2040.831 6452627.759
8 1073 3219 587 1118847300800 19.535 2046.858 6452632.453
9 1073 3220 587 1118847300900 19.464 2052.849 6452637.148
10 1073 3221 587 1118847301000 19.393 2058.777 6452641.843
11 1073 3222 587 1118847301100 19.383 2064.687 6452646.538
12 1073 3223 587 1118847301200 19.382 2070.617 6452651.233
13 1073 3224 587 1118847301300 19.383 2076.605 6452655.927
14 1073 3225 587 1118847301400 19.383 2082.618 6452660.622
15 1073 3226 587 1118847301500 19.382 2088.617 6452665.317
16 1073 3227 587 1118847301600 19.382 2094.618 6452670.012
17 1073 3228 587 1118847301700 19.381 2100.622 6452674.707
18 1073 3229 587 1118847301800 19.380 2106.627 6452679.402
19 1073 3230 587 1118847301900 19.376 2112.631 6452684.096
20 1073 3231 587 1118847302000 19.372 2118.632 6452688.791
21 1073 3232 587 1118847302100 19.367 2124.632 6452693.486
22 1077 3211 637 1118847300000 7.393 2086.090 6452670.807
23 1077 3212 637 1118847300100 7.393 2092.585 6452675.893
24 1077 3213 637 1118847300200 7.392 2099.058 6452680.957
25 1077 3214 637 1118847300300 7.375 2105.593 6452686.092
26 1077 3215 637 1118847300400 7.387 2112.099 6452691.152
27 1077 3216 637 1118847300500 7.381 2119.098 6452696.629
28 1077 3217 637 1118847300600 7.377 2125.598 6452701.715
29 1080 3211 559 1118847300000 31.113 1969.918 6452565.130
... ... ... ... ... ... ... ...
124625 3108 3699 359 1118847348800 13.705 1912.844 6452532.863
124626 3108 3700 359 1118847348900 13.671 1920.024 6452538.357
124627 3108 3701 359 1118847349000 13.715 1927.329 6452543.909
124628 3108 3702 359 1118847349100 13.774 1934.705 6452549.520
124629 3108 3703 359 1118847349200 13.816 1942.094 6452555.112
124630 3108 3704 359 1118847349300 13.858 1949.466 6452560.704
124631 3108 3705 359 1118847349400 13.901 1956.853 6452566.296
124632 3108 3706 359 1118847349500 13.944 1964.221 6452571.888
124633 3108 3707 359 1118847349600 13.986 1971.500 6452577.503
124634 3108 3708 359 1118847349700 14.062 1978.699 6452583.053
124635 3108 3709 359 1118847349800 14.244 1985.878 6452588.536
124636 3108 3710 359 1118847349900 14.406 1993.149 6452594.076
124637 3108 3711 359 1118847350000 14.595 2000.561 6452599.690
124638 3108 3712 359 1118847350100 14.847 2008.085 6452605.362
124639 3108 3713 359 1118847350200 15.064 2015.686 6452611.145
124640 3108 3714 359 1118847350300 15.275 2023.307 6452616.905
124641 3108 3715 359 1118847350400 15.485 2030.915 6452622.665
124642 3108 3716 359 1118847350500 15.694 2038.533 6452628.425
124643 3108 3717 359 1118847350600 15.904 2046.147 6452634.185
124644 3108 3718 359 1118847350700 16.125 2053.696 6452639.969
124645 3108 3719 359 1118847350800 16.369 2061.138 6452645.665
124646 3108 3720 359 1118847350900 16.574 2068.451 6452651.306
124647 3108 3721 359 1118847351000 16.739 2075.683 6452656.853
124648 3108 3722 359 1118847351100 16.711 2082.911 6452662.508
124649 3108 3723 359 1118847351200 16.686 2090.260 6452668.234
124650 3108 3724 359 1118847351300 16.687 2097.765 6452674.097
124651 3108 3725 359 1118847351400 16.689 2105.418 6452680.103
124652 3108 3726 359 1118847351500 16.746 2113.184 6452686.167
124653 3108 3727 359 1118847351600 16.741 2121.184 6452692.426
124654 3108 3728 359 1118847351700 16.734 2129.183 6452698.686
globalY vLenght vWidth vType veloc accel line pred foll \
0 1872026.290 12.5 5.0 2 59.92 -1.71 2 0 1083
1 1872022.536 12.5 5.0 2 59.60 -4.46 2 0 1083
2 1872018.817 12.5 5.0 2 59.14 -5.47 2 0 1083
3 1872015.175 12.5 5.0 2 58.78 -2.54 2 0 1083
4 1872011.563 12.5 5.0 2 58.78 2.52 2 0 1083
5 1872007.921 12.5 5.0 2 59.14 5.47 2 0 1083
6 1872004.202 12.5 5.0 2 59.60 4.46 2 0 1083
7 1872000.448 12.5 5.0 2 59.91 1.71 2 0 1083
8 1871996.712 12.5 5.0 2 59.90 -2.03 2 0 1083
9 1871992.976 12.5 5.0 2 59.60 -3.95 2 0 1083
10 1871989.240 12.5 5.0 2 59.39 -1.76 2 0 1083
11 1871985.504 12.5 5.0 2 59.39 1.79 2 0 1083
12 1871981.768 12.5 5.0 2 59.59 3.72 2 0 1083
13 1871978.031 12.5 5.0 2 59.88 1.98 2 0 1083
14 1871974.295 12.5 5.0 2 60.00 0.00 2 0 1083
15 1871970.559 12.5 5.0 2 60.01 0.12 2 0 1083
16 1871966.823 12.5 5.0 2 60.02 0.22 2 0 1083
17 1871963.087 12.5 5.0 2 60.04 0.10 2 0 1083
18 1871959.351 12.5 5.0 2 60.04 -0.10 2 0 1083
19 1871955.615 12.5 5.0 2 60.04 0.00 2 0 1083
20 1871951.878 12.5 5.0 2 60.04 0.00 2 0 1083
21 1871948.142 12.5 5.0 2 60.04 0.00 2 0 1083
22 1871981.512 13.0 5.9 2 64.98 -0.04 1 0 1082
23 1871977.465 13.0 5.9 2 65.00 0.46 1 0 1082
24 1871973.436 13.0 5.9 2 65.30 4.71 1 0 1082
25 1871969.370 13.0 5.9 2 65.93 8.08 1 0 1082
26 1871965.322 13.0 5.9 2 65.93 0.00 1 0 1082
27 1871960.964 13.0 5.9 2 65.93 0.00 1 0 1082
28 1871956.916 13.0 5.9 2 65.93 0.00 1 0 1082
29 1872036.857 13.0 5.9 2 56.89 -5.70 3 0 1084
... ... ... ... ... ... ... ... ... ...
124625 1872087.050 7.0 3.0 1 71.44 9.02 2 1215 1219
124626 1872082.435 7.0 3.0 1 72.34 10.02 2 1215 1219
124627 1872077.669 7.0 3.0 1 73.14 6.54 2 1215 1219
124628 1872072.833 7.0 3.0 1 73.59 2.22 2 1215 1219
124629 1872068.034 7.0 3.0 1 73.73 -0.17 2 1215 1219
124630 1872063.236 7.0 3.0 1 73.72 -0.07 2 1215 1219
124631 1872058.437 7.0 3.0 1 73.57 -2.32 2 1215 1219
124632 1872053.638 7.0 3.0 1 73.11 -6.29 2 1215 1219
124633 1872048.821 7.0 3.0 1 72.59 -5.91 2 1215 1219
124634 1872044.050 7.0 3.0 1 72.34 -0.30 2 1215 1219
124635 1872039.346 7.0 3.0 1 72.63 7.25 2 1215 1219
124636 1872034.620 7.0 3.0 1 73.51 10.97 2 1215 1219
124637 1872029.799 7.0 3.0 1 74.55 10.14 2 1215 1219
124638 1872024.849 7.0 3.0 1 75.37 7.05 2 1215 1219
124639 1872019.854 7.0 3.0 1 75.87 2.79 2 1215 1219
124640 1872014.886 7.0 3.0 1 76.05 0.10 2 1215 1219
124641 1872009.919 7.0 3.0 1 76.07 0.03 2 0 1215
124642 1872004.952 7.0 3.0 1 75.96 -1.63 2 0 1215
124643 1871999.985 7.0 3.0 1 75.54 -5.97 2 0 1215
124644 1871994.985 7.0 3.0 1 74.81 -9.44 2 0 1215
124645 1871990.050 7.0 3.0 1 73.88 -10.07 2 0 1215
124646 1871985.299 7.0 3.0 1 73.07 -6.37 2 0 1215
124647 1871980.673 7.0 3.0 1 72.79 0.00 2 0 1215
124648 1871976.208 7.0 3.0 1 73.19 7.82 2 0 1215
124649 1871971.683 7.0 3.0 1 74.25 11.20 2 0 1215
124650 1871967.016 7.0 3.0 1 75.77 11.20 2 0 1215
124651 1871962.233 7.0 3.0 1 77.35 11.20 2 0 1215
124652 1871957.327 7.0 3.0 1 77.35 0.00 2 0 1215
124653 1871952.345 7.0 3.0 1 77.35 0.00 2 0 1215
124654 1871947.364 7.0 3.0 1 77.35 0.00 2 0 1215
spac headway dateTime
0 0.00 0.00 NaN
1 0.00 0.00 NaN
2 0.00 0.00 NaN
3 0.00 0.00 NaN
4 0.00 0.00 NaN
5 0.00 0.00 NaN
6 0.00 0.00 NaN
7 0.00 0.00 NaN
8 0.00 0.00 NaN
9 0.00 0.00 NaN
10 0.00 0.00 NaN
11 0.00 0.00 NaN
12 0.00 0.00 NaN
13 0.00 0.00 NaN
14 0.00 0.00 NaN
15 0.00 0.00 NaN
16 0.00 0.00 NaN
17 0.00 0.00 NaN
18 0.00 0.00 NaN
19 0.00 0.00 NaN
20 0.00 0.00 NaN
21 0.00 0.00 NaN
22 0.00 0.00 NaN
23 0.00 0.00 NaN
24 0.00 0.00 NaN
25 0.00 0.00 NaN
26 0.00 0.00 NaN
27 0.00 0.00 NaN
28 0.00 0.00 NaN
29 0.00 0.00 NaN
... ... ... ...
124625 24.05 0.34 NaN
124626 22.55 0.31 NaN
124627 20.93 0.29 NaN
124628 19.24 0.26 NaN
124629 17.58 0.24 NaN
124630 16.01 0.22 NaN
124631 14.43 0.20 NaN
124632 12.77 0.17 NaN
124633 11.17 0.15 NaN
124634 9.72 0.13 NaN
124635 8.45 0.12 NaN
124636 7.19 0.10 NaN
124637 5.79 0.08 NaN
124638 4.28 0.06 NaN
124639 2.67 0.04 NaN
124640 1.05 0.01 NaN
124641 0.00 0.00 NaN
124642 0.00 0.00 NaN
124643 0.00 0.00 NaN
124644 0.00 0.00 NaN
124645 0.00 0.00 NaN
124646 0.00 0.00 NaN
124647 0.00 0.00 NaN
124648 0.00 0.00 NaN
124649 0.00 0.00 NaN
124650 0.00 0.00 NaN
124651 0.00 0.00 NaN
124652 0.00 0.00 NaN
124653 0.00 0.00 NaN
124654 0.00 0.00 NaN
[124655 rows x 19 columns]>
In [46]:
data[:10]
Out[46]:
vID
frID
tFr
Timestamp
localX
localY
globalX
globalY
vLenght
vWidth
vType
veloc
accel
line
pred
foll
spac
headway
dateTime
0
1073
3211
587
1118847300000
20.097
1999.367
6452595.286
1872026.290
12.5
5
2
59.92
-1.71
2
0
1083
0
0
NaN
1
1073
3212
587
1118847300100
20.025
2005.368
6452600.004
1872022.536
12.5
5
2
59.60
-4.46
2
0
1083
0
0
NaN
2
1073
3213
587
1118847300200
19.973
2011.314
6452604.649
1872018.817
12.5
5
2
59.14
-5.47
2
0
1083
0
0
NaN
3
1073
3214
587
1118847300300
19.886
2017.183
6452609.253
1872015.175
12.5
5
2
58.78
-2.54
2
0
1083
0
0
NaN
4
1073
3215
587
1118847300400
19.817
2023.016
6452613.792
1872011.563
12.5
5
2
58.78
2.52
2
0
1083
0
0
NaN
5
1073
3216
587
1118847300500
19.731
2028.885
6452618.396
1872007.921
12.5
5
2
59.14
5.47
2
0
1083
0
0
NaN
6
1073
3217
587
1118847300600
19.678
2034.831
6452623.041
1872004.202
12.5
5
2
59.60
4.46
2
0
1083
0
0
NaN
7
1073
3218
587
1118847300700
19.606
2040.831
6452627.759
1872000.448
12.5
5
2
59.91
1.71
2
0
1083
0
0
NaN
8
1073
3219
587
1118847300800
19.535
2046.858
6452632.453
1871996.712
12.5
5
2
59.90
-2.03
2
0
1083
0
0
NaN
9
1073
3220
587
1118847300900
19.464
2052.849
6452637.148
1871992.976
12.5
5
2
59.60
-3.95
2
0
1083
0
0
NaN
In [47]:
counts = data.groupby('vID').size()
In [48]:
counts
Out[48]:
vID
1073 22
1077 7
1080 28
1081 14
1082 31
1083 55
1084 46
1086 50
1087 12
1088 71
1089 28
1090 67
1091 61
1092 44
1093 77
1094 108
1095 80
1096 107
1097 86
1098 48
1099 100
1100 119
1101 124
1102 94
1103 60
1104 109
1105 127
1106 135
1107 109
1108 143
...
1518 89
1519 126
1520 95
1521 195
1522 73
1523 74
1524 170
1525 59
1526 108
1527 26
1528 45
1529 146
1530 4
1531 23
1533 111
1534 90
1535 50
1536 9
1537 23
1538 70
1539 77
1540 7
1548 43
1549 50
1551 10
1554 29
1556 2
3106 275
3107 227
3108 359
dtype: int64
In [49]:
ids = pd.DataFrame(counts, columns = ['size'])
In [50]:
ids = ids[ids['size']>1]
In [51]:
ids.index
Out[51]:
Int64Index([1073, 1077, 1080, 1081, 1082, 1083, 1084, 1086, 1087, 1088,
...
1539, 1540, 1548, 1549, 1551, 1554, 1556, 3106, 3107, 3108],
dtype='int64', name=u'vID', length=369)
In [52]:
ids
Out[52]:
size
vID
1073
22
1077
7
1080
28
1081
14
1082
31
1083
55
1084
46
1086
50
1087
12
1088
71
1089
28
1090
67
1091
61
1092
44
1093
77
1094
108
1095
80
1096
107
1097
86
1098
48
1099
100
1100
119
1101
124
1102
94
1103
60
1104
109
1105
127
1106
135
1107
109
1108
143
...
...
1518
89
1519
126
1520
95
1521
195
1522
73
1523
74
1524
170
1525
59
1526
108
1527
26
1528
45
1529
146
1530
4
1531
23
1533
111
1534
90
1535
50
1536
9
1537
23
1538
70
1539
77
1540
7
1548
43
1549
50
1551
10
1554
29
1556
2
3106
275
3107
227
3108
359
369 rows × 1 columns
In [53]:
ids.describe()
Out[53]:
size
count
369.000000
mean
337.818428
std
168.073150
min
2.000000
25%
195.000000
50%
369.000000
75%
489.000000
max
600.000000
In [54]:
counts2 = data.groupby('Timestamp').size()
In [55]:
counts2.index
Out[55]:
Int64Index([1118847300000, 1118847300100, 1118847300200, 1118847300300,
1118847300400, 1118847300500, 1118847300600, 1118847300700,
1118847300800, 1118847300900,
...
1118847399000, 1118847399100, 1118847399200, 1118847399300,
1118847399400, 1118847399500, 1118847399600, 1118847399700,
1118847399800, 1118847399900],
dtype='int64', name=u'Timestamp', length=1000)
In [56]:
counts2.max()
Out[56]:
138
In [58]:
counts2.min()
Out[58]:
116
In [57]:
counts2.mean()
Out[57]:
124.655
In [29]:
counts3 = data.groupby(['Timestamp','vID']).mean()
In [30]:
counts3[350:351]
Out[30]:
frID
tFr
localX
localY
globalX
globalY
vLenght
vWidth
vType
veloc
accel
line
pred
foll
spac
headway
dateTime
Timestamp
vID
1118846985300
14
64
515
50.008
175.623
6451208.678
1873218.081
24
8.5
3
39.54
7.76
5
0
18
0
0
NaN
In [31]:
t_v = pd.DataFrame(counts3, columns = ['frID', 'tFr', 'localX', 'localY', 'globalX','globalY', 'vLenght', 'vWidth',
'vType', 'veloc','accel', 'line', 'pred', 'foll', 'spac', 'headway'])
In [41]:
t_v[67777:67779]
Out[41]:
frID
tFr
localX
localY
globalX
globalY
vLenght
vWidth
vType
veloc
accel
line
pred
foll
spac
headway
Timestamp
vID
1118847058800
232
799
606
7.505
998.287
6451847.821
1872693.234
17
6.4
2
21.15
-0.06
1
223
239
48.93
2.31
233
799
438
50.605
1099.633
6451895.926
1872594.168
15
5.4
2
50.00
0.00
5
231
246
64.10
1.28
In [36]:
time_pres = data.groupby('tFr').size()
In [37]:
time_pres.describe
Out[37]:
<bound method Series.describe of tFr
177 177
178 178
245 245
246 246
250 250
251 251
253 253
254 254
255 510
258 258
259 518
260 260
261 261
263 789
264 264
268 804
269 269
270 270
271 813
273 273
275 275
276 1104
277 277
279 279
280 1120
282 282
283 566
284 284
286 858
287 287
...
933 2799
935 1870
936 936
937 937
939 939
941 1882
942 1884
944 944
945 945
946 2838
947 1894
948 2844
951 951
952 952
954 2862
956 956
957 957
958 958
960 2880
961 961
962 962
964 964
965 965
967 967
968 968
975 975
977 977
979 979
986 986
1010 1010
dtype: int64>
In [38]:
time_pres.mean()
Out[38]:
1984.198319327731
In [ ]:
Content source: lalonica/PhD
Similar notebooks: