PCL-SZ-volume 数据说明
数据集共包含六个文件:
- sz_traffic.h5 主数据文件
- sz_cleaned.csv 填充缺失值后的主数据文件
- locations.txt 可明确标记点的坐标(基于google坐标系)
- from_to_table.csv 可明确标记点间的驾车行驶距离
- adj_mx_sz.pkl 将from_to_table利用z-score标准化后产生的邻接矩阵
- weather.csv 天气文件
sz_traffic.h5
包含一个dataframe,包含从原始数据当中提取的136个数据采集点,从2019年2月1日到2019年4月30日以每5min为间隔的流量数据,若在原始数据集中某时刻某采集点没有条目,则赋值为NaN。
#横轴为采集点id
#纵轴为5min时间区间开始点
4341 4342 5141 ... 20501805 20503401 20503402
2019-02-01 00:00:00 NaN NaN NaN ... NaN NaN NaN
2019-02-01 00:05:00 NaN NaN NaN ... NaN NaN NaN
2019-02-01 00:10:00 NaN NaN NaN ... NaN NaN NaN
2019-02-01 00:15:00 NaN NaN NaN ... NaN NaN NaN
2019-02-01 00:20:00 NaN NaN NaN ... NaN NaN NaN
2019-02-01 00:25:00 NaN NaN NaN ... NaN NaN NaN
2019-02-01 00:30:00 NaN NaN NaN ... NaN NaN NaN
2019-02-01 00:35:00 NaN NaN NaN ... NaN NaN NaN
2019-02-01 00:40:00 NaN NaN NaN ... NaN NaN NaN
2019-02-01 00:45:00 NaN NaN NaN ... NaN NaN NaN
2019-02-01 00:50:00 NaN NaN NaN ... NaN NaN NaN
2019-02-01 00:55:00 NaN NaN NaN ... NaN NaN NaN
2019-02-01 01:00:00 NaN NaN NaN ... NaN NaN NaN
2019-02-01 01:05:00 NaN NaN NaN ... NaN NaN NaN
2019-02-01 01:10:00 NaN NaN NaN ... NaN NaN NaN
2019-02-01 01:15:00 NaN NaN NaN ... NaN NaN NaN
2019-02-01 01:20:00 NaN NaN NaN ... NaN NaN NaN
2019-02-01 01:25:00 NaN NaN NaN ... NaN NaN NaN
2019-02-01 01:30:00 NaN NaN NaN ... NaN NaN NaN
2019-02-01 01:35:00 NaN NaN NaN ... NaN NaN NaN
2019-02-01 01:40:00 NaN NaN NaN ... NaN NaN NaN
2019-02-01 01:45:00 NaN NaN NaN ... NaN NaN NaN
2019-02-01 01:50:00 NaN NaN NaN ... NaN NaN NaN
2019-02-01 01:55:00 NaN NaN NaN ... NaN NaN NaN
2019-02-01 02:00:00 NaN NaN NaN ... NaN NaN NaN
2019-02-01 02:05:00 NaN NaN NaN ... NaN NaN NaN
2019-02-01 02:10:00 NaN NaN NaN ... NaN NaN NaN
2019-02-01 02:15:00 NaN NaN NaN ... NaN NaN NaN
2019-02-01 02:20:00 NaN NaN NaN ... NaN NaN NaN
2019-02-01 02:25:00 NaN NaN NaN ... NaN NaN NaN
... ... ... ... ... ... ...
2019-04-30 21:30:00 37.0 69.0 119.0 ... 383.0 85.0 140.0
2019-04-30 21:35:00 30.0 37.0 91.0 ... 372.0 93.0 114.0
2019-04-30 21:40:00 28.0 63.0 84.0 ... 397.0 57.0 137.0
2019-04-30 21:45:00 38.0 79.0 133.0 ... 344.0 116.0 111.0
2019-04-30 21:50:00 26.0 111.0 99.0 ... 391.0 74.0 138.0
2019-04-30 21:55:00 45.0 65.0 105.0 ... 328.0 87.0 116.0
2019-04-30 22:00:00 36.0 107.0 82.0 ... 341.0 94.0 128.0
2019-04-30 22:05:00 36.0 87.0 93.0 ... 260.0 62.0 127.0
2019-04-30 22:10:00 39.0 78.0 96.0 ... 310.0 82.0 135.0
2019-04-30 22:15:00 28.0 74.0 121.0 ... 280.0 73.0 96.0
2019-04-30 22:20:00 67.0 96.0 129.0 ... 291.0 60.0 80.0
2019-04-30 22:25:00 30.0 84.0 126.0 ... 242.0 47.0 83.0
2019-04-30 22:30:00 44.0 81.0 125.0 ... 246.0 89.0 100.0
2019-04-30 22:35:00 37.0 62.0 112.0 ... 204.0 80.0 90.0
2019-04-30 22:40:00 34.0 63.0 62.0 ... 259.0 62.0 63.0
2019-04-30 22:45:00 25.0 82.0 169.0 ... 261.0 91.0 111.0
2019-04-30 22:50:00 45.0 40.0 111.0 ... 175.0 60.0 69.0
2019-04-30 22:55:00 50.0 64.0 129.0 ... 230.0 72.0 92.0
2019-04-30 23:00:00 40.0 91.0 127.0 ... 174.0 37.0 103.0
2019-04-30 23:05:00 35.0 75.0 101.0 ... 224.0 74.0 95.0
2019-04-30 23:10:00 49.0 62.0 100.0 ... 170.0 63.0 74.0
2019-04-30 23:15:00 28.0 96.0 134.0 ... 222.0 68.0 69.0
2019-04-30 23:20:00 35.0 45.0 126.0 ... 177.0 68.0 56.0
2019-04-30 23:25:00 20.0 63.0 89.0 ... 219.0 60.0 70.0
2019-04-30 23:30:00 38.0 28.0 105.0 ... 197.0 60.0 63.0
2019-04-30 23:35:00 27.0 33.0 87.0 ... 194.0 55.0 70.0
2019-04-30 23:40:00 20.0 61.0 137.0 ... 176.0 48.0 57.0
2019-04-30 23:45:00 44.0 60.0 109.0 ... 229.0 61.0 57.0
2019-04-30 23:50:00 23.0 82.0 154.0 ... 183.0 58.0 69.0
2019-04-30 23:55:00 23.0 50.0 98.0 ... 240.0 43.0 58.0
[25632 rows x 136 columns]
sz_cleaned.scv
鉴于sz_traffic.h5中存在较多缺失值,根据线性插值法对原数据进行了填充,程序运行实际使用该数据
4341 4342 5141 5142 5143 5144 6041 6042 ... 10103502 20501401 20501402 20501403 20501803 20501805 20503401 20503402
0 18.397727 30.454545 62.179487 43.384615 21.846154 19.128205 22.569767 15.953488 ... 64.592593 160.862069 95.863636 35.954545 144.827586 88.574713 35.750000 39.965909
1 18.784091 28.261364 57.205128 43.307692 20.692308 19.307692 21.755814 16.406977 ... 63.651163 152.666667 93.590909 34.102273 143.149425 88.505747 37.170455 36.022727
2 18.056818 28.727273 64.128205 41.230769 20.333333 17.025641 19.430233 13.395349 ... 65.428571 158.402299 92.772727 35.829545 147.290698 83.873563 37.170455 36.659091
3 18.227273 26.181818 61.512821 44.384615 21.743590 16.435897 19.802326 14.360465 ... 63.000000 152.448276 92.511364 34.568182 144.720930 81.011628 36.943182 34.920455
4 18.261364 26.125000 63.589744 40.641026 21.974359 16.461538 19.627907 15.034884 ... 60.658824 153.919540 88.352273 35.068966 141.282353 80.977011 35.886364 34.772727
5 17.727273 26.568182 60.282051 38.769231 17.000000 15.205128 17.470588 12.906977 ... 60.388235 149.000000 83.568182 33.329545 135.488372 79.402299 31.897727 32.238636
6 18.295455 26.147727 51.769231 39.282051 17.743590 12.692308 17.720930 11.988372 ... 57.694118 146.183908 81.375000 31.659091 139.068966 78.931034 31.420455 31.818182
7 15.000000 24.625000 57.179487 38.000000 18.102564 13.564103 15.860465 11.372093 ... 53.639535 141.436782 78.147727 30.170455 134.873563 73.953488 32.340909 30.886364
8 14.909091 23.852273 54.461538 37.000000 16.717949 12.948718 16.453488 11.200000 ... 51.848837 137.701149 74.420455 29.409091 131.287356 67.372093 29.022727 31.136364
9 16.863636 22.556818 53.435897 37.794872 15.128205 14.153846 14.372093 9.571429 ... 51.906977 132.321839 72.613636 26.215909 136.517241 67.574713 28.909091 28.875000
10 15.488636 20.310345 44.564103 35.051282 15.871795 12.538462 15.232558 10.244186 ... 49.011765 130.390805 67.090909 26.181818 132.091954 66.873563 27.715909 28.522727
11 14.818182 20.590909 46.384615 34.000000 15.256410 11.384615 12.360465 10.069767 ... 48.670588 127.517241 63.647727 25.306818 126.705882 61.931034 24.477273 26.488636
12 16.056818 18.363636 43.641026 34.153846 14.153846 13.102564 12.604651 9.011765 ... 44.651163 124.770115 61.454545 24.659091 129.541176 62.103448 26.896552 27.465909
13 15.806818 20.057471 44.307692 31.461538 13.923077 11.666667 12.104651 10.139535 ... 44.741176 121.735632 59.022727 24.329545 124.825581 57.689655 25.655172 26.488636
14 15.620690 19.852273 41.666667 29.384615 13.256410 13.179487 11.552941 8.404762 ... 44.720930 119.425287 57.329545 23.988636 121.290698 60.172414 24.390805 25.689655
15 15.091954 18.488636 43.282051 30.102564 11.794872 11.358974 11.800000 9.086420 ... 45.638554 118.494253 56.454545 22.454545 122.337209 52.862069 24.885057 24.149425
16 14.772727 19.068182 41.743590 27.512821 12.025641 8.692308 11.337209 7.952941 ... 43.890244 117.344828 55.250000 22.056818 120.627907 54.494253 21.790698 24.744186
17 13.670455 17.295455 41.205128 29.487179 10.923077 9.256410 10.558140 8.000000 ... 43.231707 114.045977 50.488636 21.678161 120.400000 52.252874 23.540230 23.627907
18 14.215909 17.636364 41.564103 25.615385 12.948718 8.846154 11.647059 6.647059 ... 40.903614 110.724138 51.113636 20.929412 117.390805 47.816092 21.701149 23.409091
19 13.113636 16.872093 40.333333 26.538462 9.948718 9.794872 10.639535 7.457831 ... 40.626506 105.459770 48.840909 20.227273 115.218391 44.620690 20.275862 20.908046
20 12.670455 18.348837 35.794872 26.128205 9.871795 8.512821 10.647059 7.364706 ... 37.950617 106.011494 46.340909 18.590909 111.264368 45.290698 19.908046 22.091954
21 13.670455 18.034091 37.410256 25.948718 10.076923 6.794872 9.465116 5.732558 ... 38.061728 108.494253 43.647727 19.379310 113.494253 43.379310 20.609195 21.229885
22 13.000000 15.772727 36.179487 25.051282 9.743590 7.871795 9.894118 5.901235 ... 37.604938 103.172414 42.840909 18.569767 106.770115 41.678161 18.636364 19.772727
23 13.103448 16.647727 34.384615 24.641026 8.179487 8.615385 9.493976 5.506494 ... 35.074074 100.816092 41.318182 17.448276 103.724138 39.827586 18.829545 18.659091
24 9.436782 11.811765 19.615385 14.052632 5.527778 5.052632 1.000000 1.571429 ... 35.011628 69.574713 30.534091 13.895349 106.310345 38.724138 17.886364 18.431818
25 12.674419 17.310345 36.684211 22.368421 8.368421 8.500000 6.464286 4.680000 ... 35.305882 97.197674 38.873563 17.166667 98.430233 36.953488 17.724138 18.988506
26 12.862069 16.147727 32.923077 25.102564 9.435897 7.076923 9.204545 5.154762 ... 36.238095 97.954023 38.534091 17.170455 97.701149 34.160920 19.465909 19.693182
27 13.159091 16.988636 33.282051 23.384615 8.794872 6.897436 9.147727 5.800000 ... 35.505882 97.839080 39.602273 16.852273 90.540230 34.712644 19.193182 17.909091
28 12.920455 16.397727 33.333333 26.538462 7.794872 7.342105 8.430233 4.432099 ... 34.988095 95.977011 37.670455 16.183908 89.825581 33.057471 17.897727 16.750000
29 14.170455 15.183908 33.974359 23.384615 7.820513 8.894737 7.627907 4.505882 ... 33.800000 95.356322 36.306818 15.941860 87.724138 32.229885 18.193182 17.284091
... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ...
25602 37.000000 69.000000 119.000000 100.000000 63.000000 70.000000 62.000000 38.000000 ... 168.000000 263.011494 312.000000 228.000000 352.000000 383.000000 85.000000 140.000000
25603 30.000000 37.000000 91.000000 82.000000 55.000000 51.000000 43.000000 36.000000 ... 152.000000 269.344828 341.000000 187.000000 252.000000 372.000000 93.000000 114.000000
25604 28.000000 63.000000 84.000000 72.000000 118.000000 54.000000 82.000000 42.000000 ... 180.000000 267.103448 339.000000 217.000000 333.000000 397.000000 57.000000 137.000000
25605 38.000000 79.000000 133.000000 94.000000 73.000000 43.000000 89.000000 43.000000 ... 163.000000 264.160920 362.000000 236.000000 297.000000 344.000000 116.000000 111.000000
25606 26.000000 111.000000 99.000000 98.000000 39.000000 50.000000 74.000000 50.000000 ... 182.000000 267.034483 381.000000 199.000000 386.000000 391.000000 74.000000 138.000000
25607 45.000000 65.000000 105.000000 116.000000 64.000000 69.000000 39.000000 38.000000 ... 208.000000 262.666667 317.000000 176.000000 260.000000 328.000000 87.000000 116.000000
25608 36.000000 107.000000 82.000000 87.000000 93.000000 67.000000 96.000000 37.000000 ... 228.000000 257.850575 432.000000 178.000000 315.000000 341.000000 94.000000 128.000000
25609 36.000000 87.000000 93.000000 73.000000 63.000000 53.000000 69.000000 54.000000 ... 234.000000 262.643678 352.000000 198.000000 252.000000 260.000000 62.000000 127.000000
25610 39.000000 78.000000 96.000000 82.000000 96.000000 29.000000 68.000000 32.000000 ... 227.000000 259.195402 343.000000 183.000000 334.000000 310.000000 82.000000 135.000000
25611 28.000000 74.000000 121.000000 111.000000 67.000000 62.000000 73.000000 58.000000 ... 201.000000 247.080460 357.000000 226.000000 311.000000 280.000000 73.000000 96.000000
25612 67.000000 96.000000 129.000000 92.000000 61.000000 24.000000 99.000000 60.000000 ... 194.000000 241.678161 323.000000 167.000000 358.000000 291.000000 60.000000 80.000000
25613 30.000000 84.000000 126.000000 122.000000 52.000000 26.000000 69.000000 36.000000 ... 191.000000 239.609195 349.000000 207.000000 244.000000 242.000000 47.000000 83.000000
25614 44.000000 81.000000 125.000000 81.000000 49.000000 50.000000 58.000000 28.000000 ... 189.000000 239.436782 360.000000 207.000000 242.000000 246.000000 89.000000 100.000000
25615 37.000000 62.000000 112.000000 73.000000 59.000000 26.000000 73.000000 27.000000 ... 199.000000 233.356322 336.000000 207.000000 293.000000 204.000000 80.000000 90.000000
25616 34.000000 63.000000 62.000000 86.000000 95.000000 42.000000 36.000000 41.000000 ... 185.000000 227.114943 345.000000 214.000000 324.000000 259.000000 62.000000 63.000000
25617 25.000000 82.000000 169.000000 73.000000 57.000000 48.000000 76.000000 21.000000 ... 166.000000 226.494253 351.000000 190.000000 328.000000 261.000000 91.000000 111.000000
25618 45.000000 40.000000 111.000000 117.000000 48.000000 30.000000 80.000000 56.000000 ... 158.000000 226.712644 359.000000 170.000000 262.000000 175.000000 60.000000 69.000000
25619 50.000000 64.000000 129.000000 88.000000 38.000000 45.000000 56.000000 35.000000 ... 141.000000 222.448276 351.000000 176.000000 237.000000 230.000000 72.000000 92.000000
25620 40.000000 91.000000 127.000000 79.000000 118.000000 41.000000 45.000000 38.000000 ... 138.000000 215.229885 301.000000 210.000000 282.000000 174.000000 37.000000 103.000000
25621 35.000000 75.000000 101.000000 78.000000 47.000000 38.000000 58.000000 31.000000 ... 144.000000 210.379310 308.000000 194.000000 336.000000 224.000000 74.000000 95.000000
25622 49.000000 62.000000 100.000000 54.000000 36.000000 30.000000 41.000000 23.000000 ... 134.000000 205.551724 291.000000 150.000000 356.000000 170.000000 63.000000 74.000000
25623 28.000000 96.000000 134.000000 85.000000 69.000000 27.000000 43.000000 41.000000 ... 126.000000 202.597701 309.000000 174.000000 321.000000 222.000000 68.000000 69.000000
25624 35.000000 45.000000 126.000000 77.000000 54.000000 37.000000 23.000000 18.000000 ... 132.000000 202.310345 306.000000 165.000000 414.000000 177.000000 68.000000 56.000000
25625 20.000000 63.000000 89.000000 46.000000 36.000000 36.000000 36.000000 20.000000 ... 129.000000 192.724138 291.000000 135.000000 380.000000 219.000000 60.000000 70.000000
25626 38.000000 28.000000 105.000000 38.000000 25.000000 30.000000 41.000000 40.000000 ... 135.000000 190.977011 287.000000 173.000000 300.000000 197.000000 60.000000 63.000000
25627 27.000000 33.000000 87.000000 57.000000 47.000000 27.000000 52.000000 33.000000 ... 136.000000 180.655172 299.000000 148.000000 343.000000 194.000000 55.000000 70.000000
25628 20.000000 61.000000 137.000000 59.000000 46.000000 22.000000 30.000000 13.000000 ... 121.000000 181.114943 319.000000 171.000000 263.000000 176.000000 48.000000 57.000000
25629 44.000000 60.000000 109.000000 57.000000 15.000000 22.000000 53.000000 19.000000 ... 117.000000 170.172414 274.000000 133.000000 236.000000 229.000000 61.000000 57.000000
25630 23.000000 82.000000 154.000000 49.000000 29.000000 11.000000 21.000000 15.000000 ... 106.000000 168.655172 312.000000 151.000000 330.000000 183.000000 58.000000 69.000000
25631 23.000000 50.000000 98.000000 49.000000 27.000000 20.000000 30.000000 11.000000 ... 100.000000 168.873563 244.000000 138.000000 187.000000 240.000000 43.000000 58.000000
[25632 rows x 136 columns]
locations.txt
包含一个字典,key=采集点id,data=采集点位置。利用google map手动根据采集点描述位置标注后整理得到的位置信息。因为无法准确定位高速卡口采集点位置,所以只通过街景手动标记了111个路口的摄像头位置信息。我们称这111个点为可明确标记点。
{"6221": [114.065767, 22.546825], "6222": [114.065076, 22.546747], "6223": [114.065445, 22.546407], "6224": [114.065335, 22.547169], "6251": [114.053193, 22.546606], "6252": [114.052362, 22.546531], "6254": [114.052721, 22.546989], "6261": [114.065898, 22.544835], "6262": [114.065027, 22.544686], "6263": [114.065498, 22.544357], "6264": [114.065374, 22.545194], "6271": [114.053098, 22.54464], "6272": [114.052343, 22.544457], "6273": [114.052834, 22.544019], "6291": [114.053194, 22.542623], "6292": [114.052424, 22.542543], "6293": [114.052887, 22.542169], "6294": [114.052788, 22.543003], "9244": [114.061038, 22.535286], "9291": [114.058827, 22.53684], "9293": [114.058515, 22.536432], "47261": [114.054168, 22.539912], "47262": [114.052508, 22.539628], "52551": [114.052246, 22.542608], "52552": [114.051373, 22.54253], "52553": [114.051955, 22.542022], "52554": [114.051854, 22.542973], "52561": [114.05229, 22.546579], "52562": [114.051352, 22.546523], "57161": [114.0533402, 22.5367538], "57162": [114.0524953, 22.5366433], "57163": [114.053021, 22.536295], "57164": [114.0529298, 22.537053], "57191": [114.0567195, 22.548586], "57192": [114.0555794, 22.5483719], "57193": [114.0562047, 22.5480636], "57271": [114.0639416, 22.5447646], "57272": [114.0620996, 22.5446648], "57273": [114.0631155, 22.5440059], "57274": [114.0629379, 22.5453924], "57282": [114.0622697, 22.5347043], "57283": [114.0633092, 22.5341493], "57284": [114.0630973, 22.5354305], "57291": [114.0637888, 22.5328005], "57292": [114.0626321, 22.5326725], "57294": [114.0631421, 22.5333464], "57381": [114.0573188, 22.5231002], "57382": [114.0557989, 22.522962], "57384": [114.0565034, 22.5236606], "57443": [114.0496453, 22.5479823], "57444": [114.0492477, 22.5481694], "57464": [114.0610823, 22.5331359], "57491": [114.0453678, 22.5396511], "57492": [114.0441769, 22.5391704], "57581": [114.0592705, 22.5327094], "57584": [114.058475, 22.5331169], "58621": [114.0659238, 22.5328416], "58622": [114.0653863, 22.5327227], "58623": [114.0657146, 22.5325347], "58624": [114.0656513, 22.5330601], "4341": [113.886505, 22.581726], "4342": [113.885964, 22.58114], "5141": [113.862058, 22.570307], "5142": [113.861178, 22.57084], "5143": [113.861415, 22.57026], "5144": [113.86192, 22.571032], "6041": [113.884448, 22.558307], "6042": [113.883428, 22.557219], "6043": [113.884266, 22.557504], "6044": [113.883917, 22.557796], "7891": [113.896046, 22.568396], "7893": [113.896026, 22.567728], "8132": [113.910272, 22.574173], "8133": [113.911092, 22.574223], "8134": [113.91033, 22.574852], "8172": [113.913779, 22.577733], "8173": [113.913898, 22.577293], "8601": [113.880716, 22.569236], "8602": [113.879851, 22.5681887], "8603": [113.880979, 22.568321], "8604": [113.8794165, 22.5692873], "42251": [113.8842755, 22.5798847], "42252": [113.8837334, 22.5793242], "42253": [113.8843562, 22.5794007], "42254": [113.8836931, 22.5798505], "42381": [113.919091, 22.576024], "42384": [113.918431, 22.576067], "42491": [113.858365, 22.567328], "42492": [113.857519, 22.566211], "42494": [113.857611, 22.567034], "42641": [113.873314, 22.553345], "42642": [113.872681, 22.55265], "42643": [113.873308, 22.552748], "42644": [113.872378, 22.553485], "55851": [113.875903, 22.56526], "55852": [113.8754239, 22.564202], "55853": [113.8763187, 22.5644256], "55854": [113.8752201, 22.5651584], "55871": [113.8691611, 22.5785586], "55872": [113.8678691, 22.5769847], "55873": [113.8692371, 22.5770193], "55874": [113.8672889, 22.578722], "55901": [113.9017252, 22.5670117], "55902": [113.9007971, 22.5660559], "55903": [113.9017813, 22.5660792], "55904": [113.9006847, 22.567062], "57082": [113.8899445, 22.5770461], "57084": [113.8898857, 22.5777168], "57083": [113.8906588, 22.5772085], "57123": [113.8714802, 22.5632541], "57124": [113.8701365, 22.5640767]}
from_to_table.csv
利用高德api得到的任意两个可明确标记点间的行车距离。from为起始点id,to为目的地点id,distance为行车距离。
from to distance
0 6221 6221 1
1 6221 6222 267
2 6221 6223 418
3 6221 6224 648
4 6221 6251 1288
5 6221 6252 1492
6 6221 6254 1990
7 6221 6261 642
8 6221 6262 684
9 6221 6263 632
10 6221 6264 207
11 6221 6271 1470
...
adj_mx_sz.pkl
为一个二进制文件可用python pickle包读取
with open('./PCL-SZ-volume-zip/adj_mx_sz.pkl','rb') as f:
adj_mx=pkl.load(f)
包含一个list。
第0位置是个list全部的可明确标记点id.
adj_mx[0]
Out[8]:
['6221',
'6222',
'6223',
'6224',
'6251',
'6252',
'6254',
'6261',
'6262',
'6263',
'6264',
'6271',
'6272',
'6273',
'6291',
'6292',
'6293',
'6294',
'9244',
'9291',
'9293',
'47261',
'47262',
'52551',
'52552',
'52553',
'52554',
'52561',
'52562',
'57161',
'57162',
'57163',
'57164',
'57191',
'57192',
'57193',
'57271',
'57272',
'57273',
'57274',
'57282',
'57283',
'57284',
'57291',
'57292',
'57294',
'57381',
'57382',
'57384',
'57443',
'57444',
'57464',
'57491',
'57492',
'57581',
'57584',
'58621',
'58622',
'58623',
'58624',
'4341',
'4342',
'5141',
'5142',
'5143',
'5144',
'6041',
'6042',
'6043',
'6044',
'7891',
'7893',
'8132',
'8133',
'8134',
'8172',
'8173',
'8601',
'8602',
'8603',
'8604',
'42251',
'42254',
'42381',
'42384',
'42491',
'42492',
'42494',
'42641',
'42642',
'42643',
'42644',
'55851',
'55852',
'55853',
'55854',
'55871',
'55872',
'55873',
'55874',
'55901',
'55902',
'55903',
'55904',
'57082',
'57084',
'57083',
'57123',
'57124',
'42252',
'42253']
第1位置是一个dict代表可标记点id在邻接矩阵当中的index
adj_mx[1]
Out[9]:
{'6221': 0,
'6222': 1,
'6223': 2,
'6224': 3,
'6251': 4,
'6252': 5,
'6254': 6,
'6261': 7,
'6262': 8,
'6263': 9,
'6264': 10,
'6271': 11,
'6272': 12,
'6273': 13,
'6291': 14,
'6292': 15,
'6293': 16,
'6294': 17,
'9244': 18,
'9291': 19,
'9293': 20,
'47261': 21,
'47262': 22,
'52551': 23,
'52552': 24,
'52553': 25,
'52554': 26,
'52561': 27,
'52562': 28,
'57161': 29,
'57162': 30,
'57163': 31,
'57164': 32,
'57191': 33,
'57192': 34,
'57193': 35,
'57271': 36,
'57272': 37,
'57273': 38,
'57274': 39,
'57282': 40,
'57283': 41,
'57284': 42,
'57291': 43,
'57292': 44,
'57294': 45,
'57381': 46,
'57382': 47,
'57384': 48,
'57443': 49,
'57444': 50,
'57464': 51,
'57491': 52,
'57492': 53,
'57581': 54,
'57584': 55,
'58621': 56,
'58622': 57,
'58623': 58,
'58624': 59,
'4341': 60,
'4342': 61,
'5141': 62,
'5142': 63,
'5143': 64,
'5144': 65,
'6041': 66,
'6042': 67,
'6043': 68,
'6044': 69,
'7891': 70,
'7893': 71,
'8132': 72,
'8133': 73,
'8134': 74,
'8172': 75,
'8173': 76,
'8601': 77,
'8602': 78,
'8603': 79,
'8604': 80,
'42251': 81,
'42254': 82,
'42381': 83,
'42384': 84,
'42491': 85,
'42492': 86,
'42494': 87,
'42641': 88,
'42642': 89,
'42643': 90,
'42644': 91,
'55851': 92,
'55852': 93,
'55853': 94,
'55854': 95,
'55871': 96,
'55872': 97,
'55873': 98,
'55874': 99,
'55901': 100,
'55902': 101,
'55903': 102,
'55904': 103,
'57082': 104,
'57084': 105,
'57083': 106,
'57123': 107,
'57124': 108,
'42252': 109,
'42253': 110}
第二位置是一个邻接矩阵在 $A$ 对于任意的一个元素 $a_{ij}$ 来说 $a_{ij}=zscore(distance_{ij})\quad if \quad zscore(distance_{ij})>0.8 \quad else \quad 0$ 其中$distnace_{ij}$就是在from_to_table.csv中i到j的距离。在这个邻接矩阵里zscore用的$\mu$和$\sigma$为全部距离的均值和方差。
adj_mx[2]
Out[10]:
array([[0.99999964, 0.9743761 , 0.9383606 , ..., 0. , 0. ,
0. ],
[0.9925817 , 0.99999964, 0.9400637 , ..., 0. , 0. ,
0. ],
[0.9923735 , 0.97512853, 0.99999964, ..., 0. , 0. ,
0. ],
...,
[0. , 0. , 0. , ..., 0.99999964, 0. ,
0. ],
[0. , 0. , 0. , ..., 0. , 0.99999964,
0.8089801 ],
[0. , 0. , 0. , ..., 0. , 0.63436824,
0.99999964]], dtype=float32)
weather.csv
天气信息,时间粒度为天,但为了和流量数据集的时间粒度匹配,处理成了每5分钟一个天气信息,一天中288个时间段的天气信息是相同的
weather
0 0.2
1 0.2
2 0.2
3 0.2
4 0.2
5 0.2
6 0.2
7 0.2
8 0.2
9 0.2
10 0.2
11 0.2
12 0.2
13 0.2
14 0.2
15 0.2
16 0.2
17 0.2
18 0.2
19 0.2
20 0.2
21 0.2
22 0.2
23 0.2
24 0.2
25 0.2
26 0.2
27 0.2
28 0.2
29 0.2
... ...
25602 1.0
25603 1.0
25604 1.0
25605 1.0
25606 1.0
25607 1.0
25608 1.0
25609 1.0
25610 1.0
25611 1.0
25612 1.0
25613 1.0
25614 1.0
25615 1.0
25616 1.0
25617 1.0
25618 1.0
25619 1.0
25620 1.0
25621 1.0
25622 1.0
25623 1.0
25624 1.0
25625 1.0
25626 1.0
25627 1.0
25628 1.0
25629 1.0
25630 1.0
25631 1.0
[25632 rows x 1 columns]