def find_best_parameter(self, ratio, hdn_nstates_list, niter, nrepetitions, data, labels):
"""
parameter search over number of hidden states
@param hdn_nstates_list: list of number of hidden states to try, e.g. range(2,10)
@param ratio: ratio of the dataset split for train, e.g. 0.7
@param niter: number of iterations for hmm model to perform, e.g. 10
@param nrepetitions: number of repeated runs for the same hidden state, but for the different split, e.g. 5
"""
accuracy_results = {}
for nstates in hdn_nstates_list:
print 'state' + str(nstates)
accuracy_results[nstates] = []
for run in range(nrepetitions):
print 'repetition' + ' ' + str(run)
# make new random split
train_data, train_labels, val_data, val_labels = DataHandler.split(ratio, data, labels)
# train a model on this split
model_pos, model_neg = self.train(nstates, niter, train_data, train_labels)
# test the model and store the results
acc = self.test(model_pos, model_neg, val_data, val_labels)
print nstates, acc
accuracy_results[nstates].append(acc)
with open("../../Results/crossvalidated_accuracy.txt","w") as f:
for nstates in hdn_nstates_list:
print nstates, np.mean(accuracy_results[nstates]), np.std(accuracy_results[nstates])
f.write("%d, %s\n" % (nstates, ", ".join([str(x) for x in accuracy_results[nstates]])))
def find_best_parameter(self, ratio, hdn_nstates_list, niter, nrepetitions,
data, labels):
"""
parameter search over number of hidden states
@param hdn_nstates_list: list of number of hidden states to try, e.g. range(2,10)
@param ratio: ratio of the dataset split for train, e.g. 0.7
@param niter: number of iterations for hmm model to perform, e.g. 10
@param nrepetitions: number of repeated runs for the same hidden state, but for the different split, e.g. 5
"""
accuracy_results = {}
for nstates in hdn_nstates_list:
print 'state' + str(nstates)
accuracy_results[nstates] = []
for run in range(nrepetitions):
print 'repetition' + ' ' + str(run)
# make new random split
train_data, train_labels, val_data, val_labels = DataHandler.split(
ratio, data, labels)
# train a model on this split
model_pos, model_neg = self.train(nstates, niter, train_data,
train_labels)
# test the model and store the results
acc = self.test(model_pos, model_neg, val_data, val_labels)
print nstates, acc
accuracy_results[nstates].append(acc)
with open("../../Results/crossvalidated_accuracy.txt", "w") as f:
for nstates in hdn_nstates_list:
print nstates, np.mean(accuracy_results[nstates]), np.std(
accuracy_results[nstates])
f.write("%d, %s\n" % (nstates, ", ".join(
[str(x) for x in accuracy_results[nstates]])))
def ecoglstm(lstmsize, fcsize, dropout, optim):
print("Reading data...")
data = np.load(
"/storage/hpc_anna/GMiC/Data/ECoGmixed/preprocessed/train_data.npy")
labels = np.load(
"/storage/hpc_anna/GMiC/Data/ECoGmixed/preprocessed/train_labels.npy")
train_data, train_labels, val_data, val_labels = DataHandler.split(
0.7, data, labels)
lstmcl = LSTMDiscriminative(lstmsize[0], fcsize[0], dropout[0], optim[0],
10, 128)
model = lstmcl.train(train_data, train_labels)
result = -lstmcl.test(model, val_data, val_labels)
print('Result = %f' % result)
return result
# parameters
NSTATES = 2
NITERS = 2
# load the data
print "Reading data..."
train_data = np.load("/storage/hpc_anna/GMiC/Data/ECoG/preprocessed/train_data.npy")
train_labels = np.load("/storage/hpc_anna/GMiC/Data/ECoG/preprocessed/train_labels.npy")
test_data = np.load("/storage/hpc_anna/GMiC/Data/ECoG/preprocessed/test_data.npy")
test_labels = np.load("/storage/hpc_anna/GMiC/Data/ECoG/preprocessed/test_labels.npy")
# split the training data into two halves
# fh stands for first half
# sh stands for second half
print "Splitting data in two halves..."
fh_data, fh_labels, sh_data, sh_labels = DataHandler.split(0.5, train_data, train_labels)
# train HMM on first 50% of the training set
print "Training HMM classifier..."
hmmcl = HMMClassifier()
model_pos, model_neg = hmmcl.train(NSTATES, NITERS, fh_data, fh_labels)
# feed second 50% of the training set into the HMM to obtain
# pos/neg ratio for every sequence in the second half of the training set
print "Extracting ratios based on the HMM model..."
sh_ratios = hmmcl.pos_neg_ratios(model_pos, model_neg, sh_data)
test_ratios = hmmcl.pos_neg_ratios(model_pos, model_neg, test_data)
# apply fourier transform on the second 50% of the training set
print "Fouriering the second half of the dataset..."
fourier_sh_data = Fourier.data_to_fourier(sh_data)
# load the data
print "Reading data..."
train_data = np.load(
"/storage/hpc_anna/GMiC/Data/ECoG/preprocessed/train_data.npy")
train_labels = np.load(
"/storage/hpc_anna/GMiC/Data/ECoG/preprocessed/train_labels.npy")
test_data = np.load(
"/storage/hpc_anna/GMiC/Data/ECoG/preprocessed/test_data.npy")
test_labels = np.load(
"/storage/hpc_anna/GMiC/Data/ECoG/preprocessed/test_labels.npy")
# split the training data into two halves
# fh stands for first half
# sh stands for second half
print "Splitting data in two halves..."
fh_data, fh_labels, sh_data, sh_labels = DataHandler.split(
0.5, train_data, train_labels)
# train HMM on first 50% of the training set
print "Training HMM classifier..."
hmmcl = HMMClassifier()
model_pos, model_neg = hmmcl.train(NSTATES, NITERS, fh_data, fh_labels)
# feed second 50% of the training set into the HMM to obtain
# pos/neg ratio for every sequence in the second half of the training set
print "Extracting ratios based on the HMM model..."
sh_ratios = hmmcl.pos_neg_ratios(model_pos, model_neg, sh_data)
test_ratios = hmmcl.pos_neg_ratios(model_pos, model_neg, test_data)
# apply fourier transform on the second 50% of the training set
print "Fouriering the second half of the dataset..."
fourier_sh_data = Fourier.data_to_fourier(sh_data)
