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 = 'gen8_medianwindow-fft-with-time-freq-corr-1-48-r400-usf-w600'


    

In [4]:

    

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


    

In [5]:

    

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 [9]:

    

from sklearn.ensemble import RandomForestClassifier
from sklearn.cross_validation import StratifiedKFold
from sklearn.metrics import roc_auc_score
from sklearn.linear_model import LogisticRegression as LR

clf = RandomForestClassifier(n_estimators=3000, min_samples_split=1, max_depth=10,bootstrap=True,
                             oob_score=True,
                             n_jobs=-1)


    

In [16]:

    

y_proba = None
all_y = None
for target in ['Dog_1', 'Dog_2', 'Dog_3', 'Dog_4', 'Dog_5', 'Patient_1', 'Patient_2']:
    pdata = read_data(target, 'preictal') # positive examples
    ndata = read_data(target, 'interictal') # negative examples
    X = np.concatenate((pdata.X, ndata.X))
    y = np.zeros(X.shape[0])
    y[:pdata.X.shape[0]] = 1
    # shuffle
    idxs=range(len(y))
    random.shuffle(idxs)
    X = X[idxs,:]
    y = y[idxs]
    # model
    clf.fit(X,y)
    if y_proba is None:
        y_proba = clf.oob_decision_function_[:,1]
        all_y = y
    else:
        y_proba = np.hstack((y_proba, clf.oob_decision_function_[:,1]))
        all_y = np.hstack((all_y, y))


    

    




data_preictal_Dog_1_gen8_medianwindow-fft-with-time-freq-corr-1-48-r400-usf-w600
data_interictal_Dog_1_gen8_medianwindow-fft-with-time-freq-corr-1-48-r400-usf-w600
data_preictal_Dog_2_gen8_medianwindow-fft-with-time-freq-corr-1-48-r400-usf-w600
data_interictal_Dog_2_gen8_medianwindow-fft-with-time-freq-corr-1-48-r400-usf-w600
data_preictal_Dog_3_gen8_medianwindow-fft-with-time-freq-corr-1-48-r400-usf-w600
data_interictal_Dog_3_gen8_medianwindow-fft-with-time-freq-corr-1-48-r400-usf-w600
data_preictal_Dog_4_gen8_medianwindow-fft-with-time-freq-corr-1-48-r400-usf-w600
data_interictal_Dog_4_gen8_medianwindow-fft-with-time-freq-corr-1-48-r400-usf-w600
data_preictal_Dog_5_gen8_medianwindow-fft-with-time-freq-corr-1-48-r400-usf-w600
data_interictal_Dog_5_gen8_medianwindow-fft-with-time-freq-corr-1-48-r400-usf-w600
data_preictal_Patient_1_gen8_medianwindow-fft-with-time-freq-corr-1-48-r400-usf-w600
data_interictal_Patient_1_gen8_medianwindow-fft-with-time-freq-corr-1-48-r400-usf-w600
data_preictal_Patient_2_gen8_medianwindow-fft-with-time-freq-corr-1-48-r400-usf-w600
data_interictal_Patient_2_gen8_medianwindow-fft-with-time-freq-corr-1-48-r400-usf-w600

In [20]:

    

all_y.shape, all_y.mean()


    

    
Out[20]:





((6067,), 0.37926487555628813)

In [17]:

    

from sklearn.metrics import roc_auc_score


    

In [18]:

    

roc_auc_score(all_y, y_proba)


    

    
Out[18]:





0.9951251885912582

In [ ]: