In [1]:

    

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


    

In [2]:

    

import sys
sys.path.append('..')


    

In [3]:

    

FEATURES = 'gen-8_maxdiff-60'


    

In [15]:

    

nwindows = 60


    

In [5]:

    

from common.data import CachedDataLoader
cached_data_loader = CachedDataLoader('../data-cache')


    

In [6]:

    

def read_data(target, data_type):
    fname = 'data_%s_%s_%s'%(data_type,target,FEATURES)
    print fname
    return cached_data_loader.load(fname,None)


    

In [8]:

    

def process(X):
    return X


    

In [29]:

    

def stat(target, data_type):
    data = read_data(target, data_type) # positive examples
    X = process(data.X)
    N, NF = X.shape
    print X.mean(),X.std()
    print X.reshape(N,nwindows,-1).reshape(N*nwindows,-1).max(axis=0)
    pl.hist(X.ravel(),bins=50,normed=True)


    

In [32]:

    

iplot = 0
for target in ['Dog_1', 'Dog_2', 'Dog_3', 'Dog_4', 'Dog_5', 'Patient_1', 'Patient_2']:
    for data_type in ['preictal', 'interictal', 'test']:
        print target, data_type
        iplot += 1
        pl.subplot(7,3,iplot)
        stat(target, data_type)
        pl.title(target+data_type)
pl.gcf().set_size_inches(18,18);


    

    




Dog_1 preictal
data_preictal_Dog_1_gen-8_maxdiff-60
49.367040308 44.4412507659
[ 764.  406.  270.  282.  603.  318.  557.  453.  335.  186.  246.  213.
  900.  371.  389.  396.]
Dog_1 interictal
data_interictal_Dog_1_gen-8_maxdiff-60
51.7417730035 59.3569041195
[  784.   961.   847.  1374.   903.  1632.  1301.  1892.  1608.   541.
   874.   868.  1584.   625.  1092.  2090.]
Dog_1 test
data_test_Dog_1_gen-8_maxdiff-60
57.8456797809 61.9153108459
[  862.   509.   887.  1044.   919.   686.  1294.  2133.   626.   652.
   760.   577.  1565.   727.  1247.   856.]
Dog_2 preictal
data_preictal_Dog_2_gen-8_maxdiff-60
35.7918057712 17.4739315455
[ 268.  127.  141.  271.  369.  207.  124.  212.  207.  106.  238.  344.
  245.  114.  143.  311.]
Dog_2 interictal
data_interictal_Dog_2_gen-8_maxdiff-60
42.5840625 34.944658929
[  337.   219.   221.   291.   484.   408.   548.  1056.   287.   225.
   390.   536.   517.   405.   405.   463.]
Dog_2 test
data_test_Dog_2_gen-8_maxdiff-60
41.8349833333 32.9908364916
[  732.   992.  1476.  1154.  1639.  1157.   681.  1128.   974.   653.
   558.   784.   478.   294.   780.   932.]
Dog_3 preictal
data_preictal_Dog_3_gen-8_maxdiff-60
59.3084258001 46.5582179073
[ 524.  327.  576.  794.  943.  762.  383.  629.  281.  240.  567.  956.
  571.  265.  463.  916.]
Dog_3 interictal
data_interictal_Dog_3_gen-8_maxdiff-60
63.7801338252 55.5556880915
[ 4074.  2003.  1992.  1167.  1503.  1955.  2094.  2107.  1940.   721.
  1655.  1411.   696.  2106.   589.  1424.]
Dog_3 test
data_test_Dog_3_gen-8_maxdiff-60
42.4536544469 49.7972171882
[ 2990.   825.  1016.  1300.  1024.   841.   758.  1057.   286.  1060.
  1069.  1277.   539.  2730.  1578.  1091.]
Dog_4 preictal
data_preictal_Dog_4_gen-8_maxdiff-60
169.662810945 115.645473015
[ 2129.  2079.  1771.  2283.  2011.  2009.  2045.  2328.  2228.  2059.
  2002.  1755.  2036.  2237.  2278.  3063.]
Dog_4 interictal
data_interictal_Dog_4_gen-8_maxdiff-60
232.564033997 140.552075634
[  958.   843.  1539.  1425.  1273.   885.  1059.  1689.  1745.  1953.
  1065.  1792.  1471.  1950.  1310.   848.]
Dog_4 test
data_test_Dog_4_gen-8_maxdiff-60
268.639588594 162.613012449
[ 2715.  2049.  2229.  1872.  2880.  2585.  2959.  2218.  2193.  2096.
  2934.  1999.  2210.  2512.  2184.  2263.]
Dog_5 preictal
data_preictal_Dog_5_gen-8_maxdiff-60
42.6067198068 20.5622331506
[ 288.  191.  190.  369.  479.  223.  878.  277.  124.  198.  299.  295.
  253.  337.  633.]
Dog_5 interictal
data_interictal_Dog_5_gen-8_maxdiff-60
65.4205308642 67.0268101194
[ 2021.  2056.  2047.  2067.  2057.  1990.  2147.  1330.  2063.  2022.
   949.  1977.  2023.  1731.  2221.]
Dog_5 test
data_test_Dog_5_gen-8_maxdiff-60
147.335456661 322.690898742
[ 4073.  4071.  2920.  3045.  3090.  3078.  4072.  4058.  3312.  3698.
  3199.  3479.  3698.  3520.  4050.]
Patient_1 preictal
data_preictal_Patient_1_gen-8_maxdiff-60
3638.06307568 6545.69311895
[ 87503.  86145.  87722.  84526.  85285.  85099.  85592.  89135.  87334.
  87810.  86818.  86773.  86283.  85798.  87822.]
Patient_1 interictal
data_interictal_Patient_1_gen-8_maxdiff-60
142.355711111 1106.24266634
[ 41332.  41385.  41396.  41337.  41340.  41330.  41355.  41426.  41441.
  41406.  41433.  41435.  41395.  41387.  41408.]
Patient_1 test
data_test_Patient_1_gen-8_maxdiff-60
141.305754986 745.894380374
[ 51609.  51532.  51547.  51482.  51482.  51497.  51512.  51577.  51596.
  51580.  51616.  51596.  51553.  51546.  51576.]
Patient_2 preictal
data_preictal_Patient_2_gen-8_maxdiff-60
26.8959188808 719.118582586
[  1759.  16737.   8034.   4157.  10462.  11813.  32427.  13423.  23090.
  25354.  22762.  56751.  21825.  26011.  12180.  21875.  14286.   6072.
  19268.  19994.  11652.  23410.  10118.  33057.]
Patient_2 interictal
data_interictal_Patient_2_gen-8_maxdiff-60
5.9660218254 14.0553558719
[   99.   312.   500.   226.   605.   547.   928.   625.   858.   857.
  1181.   974.  1138.   948.   534.   423.   623.   563.   121.   689.
   608.   687.   372.   823.]
Patient_2 test
data_test_Patient_2_gen-8_maxdiff-60
108.885986111 2478.21851968
[  10108.   12338.   28323.   32527.   34383.   22544.   10912.    6427.
   30492.   31652.   37567.  123674.  124514.   38834.   18293.    8479.
   37808.  119850.  128651.  126580.  118706.   35956.    9954.    5437.]






    

In [16]:

    

Xp.reshape(184,60,-1).shape


    

    
Out[16]:





(184, 60, 16)

In [22]:

    

nwindows


    

    
Out[22]:





60

In [ ]: