Run Random Forest on all data: training and the best test result so far


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('..')

Read precomputed features

uncommoent the relevant pipeline in ../seizure_detection.py and run

cd ..
./doall data

or

./doall td
./doall tt

In [3]:
FEATURES = 'gen-8_medianwindow-bands2-usf-w60-b0.2-b4-b8-b12-b30-b70-0.1-0.5-0.9'

In [4]:
from common.data import CachedDataLoader
cached_data_loader = CachedDataLoader('../data-cache')

In [5]:
def read_data(target, data_type, features):
    fname = 'data_%s_%s_%s'%(data_type,target,features)
    print fname
    return cached_data_loader.load(fname,None)

In [6]:
best = pd.read_csv('../submissions/141029-predict.10.csv', index_col='clip', squeeze=True)

In [7]:
best.hist(bins=50)


Out[7]:
<matplotlib.axes._subplots.AxesSubplot at 0x11394e090>

Predict


In [8]:
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, bootstrap=False,max_depth=10,
                             n_jobs=-1)#, max_features=15

In [9]:
fpout = open('../submissions/141101-predict.3.csv','w')
print >>fpout,'clip,preictal'

In [10]:
def prb2logit(x):
    return np.log(x/(1.-x))
def logit2prb(x):
    return 1./(1+np.exp(-x))
SMOOTH = 0.3

for target in ['Dog_1', 'Dog_2', 'Dog_3', 'Dog_4', 'Dog_5', 'Patient_1', 'Patient_2']:
    pdata0 = read_data(target, 'preictal', FEATURES) # positive examples
    ndata0 = read_data(target, 'interictal', FEATURES) # negative examples
    X0 = np.concatenate((pdata0.X, ndata0.X))
    y0 = np.zeros(X0.shape[0])
    y0[:pdata0.X.shape[0]] = 1

    # predict
    tdata = read_data(target, 'test', FEATURES) # test examples
    Xt = tdata.X
    Nt = Xt.shape[0]
    yt = np.array([best['%s_test_segment_%04d.mat' % (target, i+1)] for i in range(Nt)])
    yt = prb2logit(np.clip(yt,0.01,0.99))
    yt = yt*(1.-SMOOTH) + SMOOTH*prb2logit(y0.mean())
    yt = logit2prb(yt)
    
    X = np.concatenate((X0,Xt))
    
    y_proba = []
    for j in range(10):
        y1 = np.array([np.random.random(Nt) < yt],dtype=int).ravel()

        y = np.concatenate((y0,y1))

        clf.fit(X,y)

        y_proba.append(clf.predict_proba(Xt)[:,1])

    y_proba = np.array(y_proba).mean(axis=0)
    
    # write results
    for i,p in enumerate(y_proba):
        print >>fpout,'%s_test_segment_%04d.mat,%.15f' % (target, i+1, p)


data_preictal_Dog_1_gen-8_medianwindow-bands2-usf-w60-b0.2-b4-b8-b12-b30-b70-0.1-0.5-0.9
data_interictal_Dog_1_gen-8_medianwindow-bands2-usf-w60-b0.2-b4-b8-b12-b30-b70-0.1-0.5-0.9
data_test_Dog_1_gen-8_medianwindow-bands2-usf-w60-b0.2-b4-b8-b12-b30-b70-0.1-0.5-0.9
data_preictal_Dog_2_gen-8_medianwindow-bands2-usf-w60-b0.2-b4-b8-b12-b30-b70-0.1-0.5-0.9
data_interictal_Dog_2_gen-8_medianwindow-bands2-usf-w60-b0.2-b4-b8-b12-b30-b70-0.1-0.5-0.9
data_test_Dog_2_gen-8_medianwindow-bands2-usf-w60-b0.2-b4-b8-b12-b30-b70-0.1-0.5-0.9
data_preictal_Dog_3_gen-8_medianwindow-bands2-usf-w60-b0.2-b4-b8-b12-b30-b70-0.1-0.5-0.9
data_interictal_Dog_3_gen-8_medianwindow-bands2-usf-w60-b0.2-b4-b8-b12-b30-b70-0.1-0.5-0.9
data_test_Dog_3_gen-8_medianwindow-bands2-usf-w60-b0.2-b4-b8-b12-b30-b70-0.1-0.5-0.9
data_preictal_Dog_4_gen-8_medianwindow-bands2-usf-w60-b0.2-b4-b8-b12-b30-b70-0.1-0.5-0.9
data_interictal_Dog_4_gen-8_medianwindow-bands2-usf-w60-b0.2-b4-b8-b12-b30-b70-0.1-0.5-0.9
data_test_Dog_4_gen-8_medianwindow-bands2-usf-w60-b0.2-b4-b8-b12-b30-b70-0.1-0.5-0.9
data_preictal_Dog_5_gen-8_medianwindow-bands2-usf-w60-b0.2-b4-b8-b12-b30-b70-0.1-0.5-0.9
data_interictal_Dog_5_gen-8_medianwindow-bands2-usf-w60-b0.2-b4-b8-b12-b30-b70-0.1-0.5-0.9
data_test_Dog_5_gen-8_medianwindow-bands2-usf-w60-b0.2-b4-b8-b12-b30-b70-0.1-0.5-0.9
data_preictal_Patient_1_gen-8_medianwindow-bands2-usf-w60-b0.2-b4-b8-b12-b30-b70-0.1-0.5-0.9
data_interictal_Patient_1_gen-8_medianwindow-bands2-usf-w60-b0.2-b4-b8-b12-b30-b70-0.1-0.5-0.9
data_test_Patient_1_gen-8_medianwindow-bands2-usf-w60-b0.2-b4-b8-b12-b30-b70-0.1-0.5-0.9
data_preictal_Patient_2_gen-8_medianwindow-bands2-usf-w60-b0.2-b4-b8-b12-b30-b70-0.1-0.5-0.9
data_interictal_Patient_2_gen-8_medianwindow-bands2-usf-w60-b0.2-b4-b8-b12-b30-b70-0.1-0.5-0.9
data_test_Patient_2_gen-8_medianwindow-bands2-usf-w60-b0.2-b4-b8-b12-b30-b70-0.1-0.5-0.9

In [11]:
fpout.close()