We will use distance between test segments computed in 140926-test-signal-jump to find sequence of segments that were likely together. Armed with this fact we can take the individual proababilities of each segment and combine it to form one probability that will be used to update the probabilites of all the segments in the sequence

the sequences are found using a greedy algoirthm that stops when a conflict is detected

the probabilities of segments should be combined by multiplying them, however this did not work well. Probably because the probabilites are not well calibrated. Taking the mean had a better effect.



In [1]:

    
%matplotlib inline
from matplotlib import pylab as pl
import cPickle as pickle
import pandas as pd
import numpy as np
import os

individual segment probablility file



In [2]:

    
FNAME_IN = '../submissions/140928-predict.2.csv'

updated probability file



In [3]:

    
FNAME_OUT = '../submissions/140928-predict.8.csv'



In [4]:

    
!head {FNAME_IN}









    



clip,preictal
Dog_1_test_segment_0001.mat,0.4133467551486389
Dog_1_test_segment_0002.mat,0.09224539061095215
Dog_1_test_segment_0003.mat,0.131194537821495
Dog_1_test_segment_0004.mat,0.18514265287316242
Dog_1_test_segment_0005.mat,0.1418730267251374
Dog_1_test_segment_0006.mat,0.14158106558901232
Dog_1_test_segment_0007.mat,0.05703624983301842
Dog_1_test_segment_0008.mat,0.194975158567898
Dog_1_test_segment_0009.mat,0.07618983261021842



In [5]:

    
scores = pd.read_csv(FNAME_IN, index_col='clip', squeeze=True) #64
out_scores = scores.copy()



In [6]:

    
scores['Dog_2_test_segment_0004.mat']









    Out[6]:





0.19903732735990687



In [7]:

    
targets = set(['_'.join(f.split('_')[:2]) for f in scores.index.values])
targets









    Out[7]:





{'Dog_1', 'Dog_2', 'Dog_3', 'Dog_4', 'Dog_5', 'Patient_1', 'Patient_2'}



In [8]:

    
for target in targets:
    print
    d = np.load('../data-cache/%s-test-jump-distance.npy'%target)
    N = d.shape[0]
    print target, N
    dord = np.unravel_index(d.ravel().argsort(),d.shape)
    Nsequences = N/6
    
    # find good pairs of segments that are likely to be paired in time
    next_segment = [-1]*N
    previous_segment = [-1]*N
    for i,(s1,s2) in enumerate(np.array(dord).T):
        dist = d[s1,s2]
        if next_segment[s1] != -1:
            print i,'right conflict',dist
            break
        if previous_segment[s2] != -1:
            print i,'left conflict',dist
            break
        next_segment[s1] = s2
        previous_segment[s2] = s1
#     if i < Nsequences:
#         print 'skip'
#         continue
    # check code
    for i in range(N):
        if next_segment[i] != -1:
            assert previous_segment[next_segment[i]] == i

    # find good sequences
    sequences = []
    for i in range(N):
        if previous_segment[i] == -1 and next_segment[i] != -1:
            j = i
            sequence = [j]
            while next_segment[j] != -1:
                j = next_segment[j]
                sequence.append(j)
            sequences.append(sequence)
    len_sequences = [len(sequence) for sequence in sequences]
    print '#sequences',len(sequences), '%segments that was sequenced',sum(len_sequences)/float(N), 'longest sequence', max(len_sequences)
    print sequences

    #compute probability for sequences
    sequences_prb = []
    for sequence in sequences:
        p1 =0.
        p = 1.
        q = 1.
        p2 = 0.
        for s in sequence:
            P = scores['%s_test_segment_%04d.mat'%(target,s+1)]
            p1 += P
            p *= P
            q *= 1. - P
            if P > p2:
                p2 = P
        p1 = p1 / len(sequence)
        p = p / (p+q)
#         print p, p1
        sequences_prb.append(p2)
    # fix probability for segments in sequences
    for p,sequence in zip(sequences_prb,sequences):
        # all segments in the same sequence will be assigned the same probability
        for s in sequence:
            out_scores['%s_test_segment_%04d.mat'%(target,s+1)] = p









    



Dog_2 1000
324 right conflict -0.932151727252
#sequences 193 %segments that was sequenced 0.517 longest sequence 6
[[3, 226, 140], [6, 386], [16, 862], [23, 956, 935], [26, 37, 276], [28, 489], [31, 614], [34, 143], [35, 175], [44, 346], [48, 552, 542], [52, 737, 268], [58, 315, 772, 124], [64, 435], [66, 938, 17], [67, 254], [74, 302, 775, 588, 673, 184], [80, 776], [86, 387, 641], [90, 265], [92, 306], [93, 598, 695, 699, 638], [95, 131, 941], [97, 907], [100, 507], [102, 865, 604], [104, 889, 798, 733, 50, 72], [109, 63], [114, 79, 87, 216], [127, 998, 170, 32], [130, 10], [133, 30], [146, 634, 281, 498], [152, 340, 606], [157, 731], [162, 213], [169, 257], [173, 954], [180, 20], [185, 341], [194, 877], [202, 600, 277, 196, 296], [206, 71], [209, 509], [214, 419], [222, 990, 203, 275], [225, 384, 582, 251], [232, 792], [233, 292], [234, 352, 820, 14], [235, 118], [236, 783, 291], [238, 578], [239, 122], [245, 546, 514, 657, 323], [250, 892, 702, 555], [253, 405], [264, 317, 939, 645], [267, 347, 46], [274, 248, 227], [284, 663], [289, 616], [293, 9], [295, 332, 466, 24, 558, 853], [297, 45], [305, 283, 917, 136, 510], [325, 545], [327, 438], [334, 298, 452], [336, 161], [339, 846], [342, 730], [348, 240], [357, 221, 764], [360, 413], [370, 608], [393, 2], [400, 139], [402, 121], [404, 447, 365, 763], [408, 707], [409, 218, 622], [411, 750, 511], [415, 841, 832, 255, 612, 581], [424, 312, 160], [430, 910], [431, 824], [440, 839], [448, 619, 810], [454, 412], [455, 101], [456, 874], [461, 423], [463, 960, 613], [467, 911], [469, 977], [474, 471], [480, 880, 304, 421, 569], [484, 392], [494, 147], [501, 278], [504, 760, 630], [506, 199, 426], [512, 401], [537, 995, 77, 442], [551, 629], [567, 75, 53], [568, 468], [570, 924], [571, 599], [572, 60], [575, 682], [580, 927], [583, 107, 905], [584, 549, 916, 285], [585, 261, 43, 754], [586, 991], [587, 154], [601, 262], [631, 125], [633, 273, 807, 150], [642, 126], [648, 453], [653, 688], [654, 186, 487], [658, 652, 566], [665, 538], [666, 177], [672, 476], [678, 635, 208], [686, 718, 649], [689, 492], [691, 908, 741], [703, 19], [705, 590, 15], [719, 345], [725, 369], [732, 906], [734, 970, 866], [740, 519], [742, 428], [748, 318], [753, 379], [755, 465, 459, 550], [758, 462, 174], [766, 714, 418, 815, 316, 851], [771, 932, 972, 191, 138, 524], [774, 816, 868], [789, 948], [794, 751], [795, 690], [803, 362, 562, 767, 508], [804, 576, 182], [812, 382], [835, 385], [838, 301], [842, 921, 770, 377], [844, 738], [845, 505, 746, 172, 724, 320], [848, 372, 592, 872], [849, 88], [850, 560], [854, 934, 231, 704], [855, 836], [857, 515], [859, 858, 785], [879, 813, 333], [884, 898, 137], [891, 171], [894, 12], [897, 117], [899, 368, 110, 779], [902, 944, 490, 488, 337], [903, 187], [904, 609], [912, 151], [915, 134], [925, 636, 444], [940, 244], [952, 540, 679, 119], [953, 356], [964, 78], [966, 39], [968, 324], [969, 266, 532], [975, 364], [976, 314], [979, 594], [981, 155], [985, 29, 801], [988, 864, 527, 800], [994, 331], [997, 811]]

Dog_3 907
33 left conflict -0.989490150071
#sequences 30 %segments that was sequenced 0.0694597574421 longest sequence 3
[[35, 445], [63, 432], [70, 368], [103, 136], [104, 325], [116, 537, 654], [133, 676], [177, 770], [318, 337], [341, 639], [344, 94], [361, 265], [370, 527], [380, 417], [436, 403], [472, 399], [515, 141], [524, 11], [557, 765], [587, 662], [613, 836, 422], [648, 698], [678, 233], [695, 840], [713, 86], [784, 441], [785, 356, 726], [855, 84], [879, 80], [890, 105]]

Dog_1 502
108 left conflict -0.9611050735
#sequences 74 %segments that was sequenced 0.362549800797 longest sequence 5
[[21, 32], [43, 20], [51, 497], [56, 24], [58, 371], [62, 42], [66, 134], [70, 495], [76, 127, 146, 106, 389], [77, 204], [79, 48], [93, 321], [95, 452], [97, 107, 219], [120, 141], [124, 88], [158, 140], [162, 287], [163, 131], [179, 194, 377, 99], [186, 473], [188, 259], [190, 463], [209, 263], [211, 117], [215, 197], [224, 31], [235, 37, 84], [236, 199], [239, 67], [240, 394], [247, 223, 249, 102], [248, 416, 132], [256, 262, 361], [260, 490], [291, 381, 92, 268], [301, 366, 342], [302, 343, 232], [303, 19], [304, 230], [307, 376], [310, 456], [320, 57, 413], [331, 424], [339, 153, 174], [340, 281, 229, 333], [341, 176, 245], [346, 26], [350, 319], [354, 181, 431, 338, 200], [360, 441, 4], [369, 439], [370, 316, 300], [375, 227, 109], [390, 383, 309], [392, 164], [393, 145], [406, 282, 161], [412, 154], [419, 195], [432, 332], [434, 267, 293, 442, 221], [445, 115], [450, 395], [453, 425], [455, 34], [459, 45], [461, 193], [476, 44], [479, 185], [481, 489, 430], [487, 206], [494, 63, 189], [499, 446, 182]]

Dog_4 990
556 right conflict -0.960661574506
#sequences 241 %segments that was sequenced 0.805050505051 longest sequence 6
[[0, 399], [1, 260, 101, 478, 415, 236], [7, 759, 635, 264], [11, 10], [13, 321, 132, 889], [14, 581, 429], [15, 24], [25, 315], [28, 8], [33, 631], [36, 964, 75, 141, 790], [38, 978, 678], [44, 875, 116], [45, 462], [46, 402, 971, 446], [48, 70, 483, 840, 986], [55, 170, 319, 767], [60, 127, 847], [63, 528], [67, 937, 987, 148, 948], [79, 126, 249], [86, 789], [87, 584], [98, 144], [103, 737, 721], [107, 664, 546, 18], [112, 827, 155, 106, 890, 244], [120, 122], [121, 573, 324, 544], [123, 383, 809, 970, 82, 333], [125, 647, 374], [128, 134], [129, 915], [135, 311], [136, 853, 417, 230], [138, 235, 613], [140, 499, 604], [142, 341, 860, 409, 655], [147, 200], [161, 896, 76], [163, 817, 648], [172, 680, 295, 68, 214], [174, 508, 488], [175, 976, 16], [177, 795, 520, 713], [179, 495], [184, 479, 829, 139, 724], [186, 22, 444, 859], [187, 585, 728, 154], [189, 855], [190, 682], [191, 89, 364], [193, 885], [197, 545, 531, 17], [203, 760], [207, 878], [208, 349, 413], [209, 143], [211, 638, 376, 102, 373], [216, 848], [220, 502, 770, 908, 985, 828], [225, 813], [233, 231, 459, 612], [251, 618], [253, 956], [255, 224, 47, 195], [256, 516, 473], [257, 658, 954], [263, 288], [268, 442, 934, 171, 241], [273, 932, 73], [279, 222, 327, 448, 729, 504], [281, 727, 406, 820], [282, 957, 497, 269, 656, 426], [283, 717], [289, 50], [294, 156], [297, 940, 455, 284], [299, 152, 183, 456], [300, 239, 926, 851], [307, 753, 862], [309, 361], [310, 377], [312, 730], [313, 662, 272], [316, 487], [318, 229, 731], [328, 740, 637, 167, 942], [329, 685, 523, 673], [335, 501], [338, 768, 703, 927, 511, 893], [340, 532], [343, 951, 943], [344, 907, 465, 652], [348, 562, 416], [350, 766, 835, 807, 837, 365], [356, 782], [357, 733, 698, 891], [362, 359], [366, 454, 428, 438], [372, 165, 923], [379, 720], [384, 640, 557], [385, 726, 526, 250], [386, 708, 911, 856, 792], [389, 355], [390, 578, 599, 706], [394, 51], [395, 110, 419, 606, 977, 217], [396, 984], [401, 286, 514, 398], [403, 162, 659, 754], [404, 846], [405, 118, 565], [407, 339, 457, 363], [422, 716], [430, 894, 711], [434, 27, 748], [441, 619], [443, 794, 843, 77, 234, 808], [450, 221, 521], [451, 449, 935, 873, 19, 592], [461, 906], [468, 470], [469, 796, 146, 226], [472, 958, 834, 761], [475, 677, 205, 601], [481, 877, 826, 973, 969, 247], [486, 825], [489, 322, 292, 552], [492, 188, 2, 505, 306, 3], [493, 561, 421, 74], [494, 966], [500, 301], [506, 901], [507, 824, 895], [509, 423], [513, 630], [515, 547, 605, 553, 52, 683], [522, 182], [524, 850, 670, 797], [527, 323], [535, 278], [536, 836, 869, 115, 503], [537, 248, 572, 905, 886, 477], [555, 920], [558, 484, 266, 979, 181], [559, 903], [564, 739], [566, 815, 124, 296], [575, 151, 71, 574], [577, 81, 653, 550], [583, 569], [589, 725, 801], [591, 803], [593, 331], [596, 694], [597, 485], [602, 265], [615, 369, 228, 892, 784, 368], [616, 517, 408], [620, 178, 567], [628, 261], [632, 883, 518], [642, 96, 665, 414, 270, 317], [643, 212], [649, 32], [650, 158, 427], [651, 668, 736, 833, 510, 149], [667, 594, 342, 360], [675, 936, 97], [684, 914], [686, 543], [688, 924, 262], [692, 83, 245, 695, 746, 541], [699, 622, 666], [700, 772, 201], [704, 482], [714, 660, 582], [715, 378], [719, 928, 435, 922, 237, 804], [723, 206], [735, 35, 466], [743, 196, 972, 702, 173], [745, 351, 391], [747, 988, 554], [749, 876, 471, 114, 866], [750, 982, 352, 744], [751, 287, 274, 5], [755, 718, 453, 168, 223], [756, 674], [757, 336], [758, 345, 491], [762, 865], [773, 669], [777, 912], [778, 285], [779, 732, 64], [780, 549, 609, 293], [781, 705, 467], [783, 830, 672, 412], [786, 533, 410, 939], [787, 290], [798, 53], [810, 690, 930, 679], [811, 938, 347], [812, 326, 219, 989, 62, 420], [814, 802], [816, 400, 246, 277, 192, 334], [818, 304, 397, 874], [819, 563, 26, 243, 325], [821, 6, 104, 105], [823, 480, 180, 199, 57, 841], [831, 463, 539], [838, 576, 579], [844, 393, 113], [845, 981, 254, 884, 381, 198], [861, 880], [863, 460, 21, 799], [864, 512, 43, 882, 267, 769], [867, 946, 707, 84], [871, 100], [879, 227, 358], [888, 644], [904, 963, 117, 587, 600, 69], [910, 742], [919, 354, 90, 625, 548], [921, 375, 586], [929, 476, 534, 218, 94, 59], [944, 909, 380, 160, 788], [949, 150, 153], [950, 629, 917, 854], [952, 785, 91], [953, 42, 298], [955, 621, 611], [959, 897, 388], [960, 519, 931], [961, 66, 464], [962, 580], [967, 654], [974, 542]]

Dog_5 191
42 left conflict -0.959496774214
#sequences 33 %segments that was sequenced 0.392670157068 longest sequence 4
[[1, 131, 105, 139], [6, 36, 140], [10, 7], [22, 112], [32, 74], [33, 23, 190], [34, 49], [38, 84, 107], [41, 21], [42, 160], [57, 133], [62, 51], [69, 188], [77, 113], [78, 158], [79, 119, 55, 2], [90, 159], [91, 115], [93, 148], [99, 43], [116, 16], [120, 180], [128, 48], [129, 75], [138, 92, 109], [144, 14], [145, 130], [147, 154], [152, 5], [161, 171], [166, 182], [177, 26, 143], [179, 187]]

Patient_2 150
1 right conflict -0.999516626264
#sequences 1 %segments that was sequenced 0.0133333333333 longest sequence 2
[[102, 24]]

Patient_1 195
10 left conflict -0.909383819823
#sequences 9 %segments that was sequenced 0.0974358974359 longest sequence 3
[[3, 54], [13, 179, 19], [86, 15], [97, 72], [124, 127], [147, 172], [183, 160], [185, 2], [189, 113]]



In [9]:

    
out_scores.to_csv(FNAME_OUT, header=True)



In [10]:

    
!paste {FNAME_IN} {FNAME_OUT} | head









    



clip,preictal	clip,preictal
Dog_1_test_segment_0001.mat,0.4133467551486389	Dog_1_test_segment_0001.mat,0.4133467551486389
Dog_1_test_segment_0002.mat,0.09224539061095215	Dog_1_test_segment_0002.mat,0.09224539061095216
Dog_1_test_segment_0003.mat,0.131194537821495	Dog_1_test_segment_0003.mat,0.13119453782149498
Dog_1_test_segment_0004.mat,0.18514265287316242	Dog_1_test_segment_0004.mat,0.1851426528731624
Dog_1_test_segment_0005.mat,0.1418730267251374	Dog_1_test_segment_0005.mat,0.17257023937670513
Dog_1_test_segment_0006.mat,0.14158106558901232	Dog_1_test_segment_0006.mat,0.14158106558901232
Dog_1_test_segment_0007.mat,0.05703624983301842	Dog_1_test_segment_0007.mat,0.05703624983301842
Dog_1_test_segment_0008.mat,0.194975158567898	Dog_1_test_segment_0008.mat,0.19497515856789802
Dog_1_test_segment_0009.mat,0.07618983261021842	Dog_1_test_segment_0009.mat,0.07618983261021843



In [11]:

    
out_scores['Dog_2_test_segment_0004.mat']









    Out[11]:





0.24813544779440744



In [12]:

    
df = pd.DataFrame()
df['in'] = pd.read_csv(FNAME_IN, index_col='clip', squeeze=True) #64
df['out'] = pd.read_csv(FNAME_OUT, index_col='clip', squeeze=True)



In [13]:

    
pd.scatter_matrix(df,figsize=(6, 6), diagonal='kde');



In [ ]: