Use nolearn's DBN https://pythonhosted.org/nolearn/dbn.html
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('..')
uncommoent the relevant pipeline in ../seizure_detection.py and run
cd ..
./doall data
or
./doall td
./doall tt
In [3]:
FEATURES = 'gen-8_medianwindow1-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):
fname = 'data_%s_%s_%s'%(data_type,target,FEATURES)
print fname
return cached_data_loader.load(fname,None)
In [10]:
from sklearn import preprocessing
from nolearn.dbn import DBN
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
scale = StandardScaler()
min_max_scaler = preprocessing.MinMaxScaler() # scale features to be [0..1] which is DBN requirement
dbn = DBN(
[-1, 300, -1], # first layer has size X.shape[1], hidden layer(s), last layer will have number of classes in y (2))
learn_rates=0.3,
learn_rate_decays=0.9,
epochs=1000,
dropouts=[0.1,0.5],
verbose=0,
)
clf = Pipeline([('min_max_scaler', min_max_scaler), ('dbn', dbn)])
In [11]:
fpout = open('../submissions/141003-predict.4.csv','w')
print >>fpout,'clip,preictal'
In [12]:
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))
_, NF = X.shape
X = scale.fit_transform(X)
X = np.clip(X,-3,3)
clf.set_params(dbn__layer_sizes=[NF,300,2]) # we need to reset each time because NF is different
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)
# predict
tdata = read_data(target, 'test') # test examples
Xt = scale.transform(tdata.X)
Xt = np.clip(Xt,-3,3)
y_proba = clf.predict_proba(tdata.X)[:,1]
# write results
for i,p in enumerate(y_proba):
print >>fpout,'%s_test_segment_%04d.mat,%.15f' % (target, i+1, p)
In [13]:
fpout.close()
In [ ]: