Run Random Forest after combining two feature sets
In [16]:
%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 [17]:
import sys
sys.path.append('..')
uncommoent the relevant pipeline in ../seizure_detection.py
and run
cd ..
./doall data
or
./doall td
./doall tt
In [18]:
FEATURES0 = 'gen-8_medianwindow1-bands2-usf-w60-b0.2-b4-b8-b12-b30-b70-0.1-0.5-0.9'
FEATURES1 = 'gen-8_medianwindow1-bands2--w60-b0.2-b4-b8-b12-b30-b70-0.1-0.5-0.9'
In [19]:
from common.data import CachedDataLoader
cached_data_loader = CachedDataLoader('../data-cache')
In [20]:
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 [21]:
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 [22]:
fpout = open('../submissions/141026-predict.3.csv','w')
print >>fpout,'clip,preictal'
In [23]:
for target in ['Dog_1', 'Dog_2', 'Dog_3', 'Dog_4', 'Dog_5', 'Patient_1', 'Patient_2']:
pdata0 = read_data(target, 'preictal', FEATURES0) # positive examples
ndata0 = read_data(target, 'interictal', FEATURES0) # negative examples
X0 = np.concatenate((pdata0.X, ndata0.X))
y0 = np.zeros(X0.shape[0])
y0[:pdata0.X.shape[0]] = 1
pdata1 = read_data(target, 'preictal', FEATURES1) # positive examples
ndata1 = read_data(target, 'interictal', FEATURES1) # negative examples
X1 = np.concatenate((pdata1.X, ndata1.X))
y1 = np.zeros(X1.shape[0])
y1[:pdata1.X.shape[0]] = 1
X = np.hstack((X0,X1))
assert np.all(y0 == y1)
y = y0
# shuffle
idxs=range(len(y))
random.shuffle(idxs)
X = X[idxs,:]
y = y[idxs]
clf.fit(X,y)
# predict
tdata0 = read_data(target, 'test', FEATURES0) # test examples
Xt0 = tdata0.X
tdata1 = read_data(target, 'test', FEATURES1) # test examples
Xt1 = tdata1.X
Xt = np.hstack((Xt0, Xt1))
y_proba = clf.predict_proba(Xt)[:,1]
# write results
for i,p in enumerate(y_proba):
print >>fpout,'%s_test_segment_%04d.mat,%.15f' % (target, i+1, p)
In [24]:
fpout.close()
In [24]: