def bpic(nhmmstates, nhmmiter):
nhmmstates = nhmmstates[0]
nhmmiter = nhmmiter[0] * 10
nfolds = 5
hmmcovtype = 'full'
print nhmmstates, nhmmiter
# Load the dataset
static_train = np.load(
'/storage/hpc_anna/GMiC/Data/BPIChallenge/f1/preprocessed/train_static.npy'
)
dynamic_train = np.load(
'/storage/hpc_anna/GMiC/Data/BPIChallenge/f1/preprocessed/train_dynamic.npy'
)
static_val = np.load(
'/storage/hpc_anna/GMiC/Data/BPIChallenge/f1/preprocessed/test_static.npy'
)
dynamic_val = np.load(
'/storage/hpc_anna/GMiC/Data/BPIChallenge/f1/preprocessed/test_dynamic.npy'
)
labels_train = np.load(
'/storage/hpc_anna/GMiC/Data/BPIChallenge/f1/preprocessed/train_labels.npy'
)
labels_val = np.load(
'/storage/hpc_anna/GMiC/Data/BPIChallenge/f1/preprocessed/test_labels.npy'
)
# Merge train and test
static_all = np.concatenate((static_train, static_val), axis=0)
dynamic_all = np.concatenate((dynamic_train, dynamic_val), axis=0)
labels_all = np.concatenate((labels_train, labels_val), axis=0)
nsamples = static_all.shape[0]
# k-fold cross validation to obtain accuracy
val_idx_list = np.array_split(range(nsamples), nfolds)
scores = []
for fid, val_idx in enumerate(val_idx_list):
train_idx = list(set(range(nsamples)) - set(val_idx))
# extract predictions using HMM on dynamic
hmmcl = HMMClassifier()
model_pos, model_neg = hmmcl.train(nhmmstates, nhmmiter, hmmcovtype,
dynamic_all[train_idx],
labels_all[train_idx])
scores.append(
hmmcl.test(model_pos, model_neg, dynamic_all[val_idx],
labels_all[val_idx]))
print 'Result: %.4f' % np.mean(scores)
return -np.mean(scores)
def modelopt(nhmmstates, nhmmiter):
nhmmstates = nhmmstates[0]
nhmmiter = nhmmiter[0] * 10
nfolds = 5
hmmcovtype = 'full'
print nhmmstates, nhmmiter
# Load the dataset
#static_train = np.load('/storage/hpc_anna/GMiC/Data/ECoGmixed/fourier/train_data.npy')
dynamic_train = np.load(
'/storage/hpc_anna/GMiC/Data/ECoGmixed/preprocessed/train_data.npy')
#static_test = np.load('/storage/hpc_anna/GMiC/Data/ECoGmixed/fourier/test_data.npy')
#dynamic_test = np.load('/storage/hpc_anna/GMiC/Data/ECoGmixed/preprocessed/test_data.npy')
labels_train = np.load(
'/storage/hpc_anna/GMiC/Data/ECoGmixed/preprocessed/train_labels.npy')
#labels_test = np.load('/storage/hpc_anna/GMiC/Data/ECoGmixed/preprocessed/test_labels.npy')
nsamples = dynamic_train.shape[0]
# k-fold cross validation to obtain accuracy
val_idx_list = np.array_split(range(nsamples), nfolds)
scores = []
for fid, val_idx in enumerate(val_idx_list):
train_idx = list(set(range(nsamples)) - set(val_idx))
print "Current fold is %d / %d" % (fid + 1, nfolds)
# extract predictions using HMM on dynamic
hmmcl = HMMClassifier()
model_pos, model_neg = hmmcl.train(nhmmstates, nhmmiter, hmmcovtype,
dynamic_train[train_idx],
labels_train[train_idx])
scores.append(
hmmcl.test(model_pos, model_neg, dynamic_train[val_idx],
labels_train[val_idx]))
print 'Result: %.4f' % np.mean(scores)
return -np.mean(scores)
#
# Prepare combined datasets for the future experiments
#
# dataset to check how generative models perform if provided with static features along with dynamic
static_as_dynamic = np.zeros((static_all.shape[0], static_all.shape[1], dynamic_all.shape[2]))
for i in range(static_all.shape[0]):
static_as_dynamic[i, :, :] = np.tile(static_all[i, :], (dynamic_all.shape[2], 1)).T
dynamic_and_static_as_dynamic = np.concatenate((dynamic_all, static_as_dynamic + np.random.uniform(-0.0001, 0.0001, static_as_dynamic.shape)), axis=1)
#
# k-fold CV for performance estimation
#
val_idx_list = np.array_split(range(nsamples), nfolds)
scores = {1: [], 2: [], 3: [], 4: [], 5: [], 6: [], 7: [], 8: [], 9: [], 10: [], 11: []}
for fid, val_idx in enumerate(val_idx_list):
print "Current fold is %d / %d" % (fid + 1, nfolds)
train_idx = list(set(range(nsamples)) - set(val_idx))
# HMM on dynamic and static (turned into fake sequences) (9)
hmmcl = HMMClassifier()
model_pos, model_neg = hmmcl.train(nhmmstates, nhmmiter, hmmcovtype, dynamic_and_static_as_dynamic[train_idx], labels_all[train_idx])
acc, auc = hmmcl.test(model_pos, model_neg, dynamic_and_static_as_dynamic[val_idx], labels_all[val_idx])
scores[9].append(acc)
print "===> (9) HMM on dynamic and static features: %.4f (+/- %.4f) %s" % (np.mean(scores[9]), np.std(scores[9]), scores[9])
def bpic(nhmmstates, nestimators, nhmmiter):
nhmmstates = nhmmstates[0]
nestimators = nestimators[0] * 100
nhmmiter = nhmmiter[0] * 10
nfolds = 5
hmmcovtype = 'full'
print nhmmstates, nestimators, nhmmiter
# Load the dataset
static_train = np.load(
'/storage/hpc_anna/GMiC/Data/BPIChallenge/f1/preprocessed/train_static.npy'
)
dynamic_train = np.load(
'/storage/hpc_anna/GMiC/Data/BPIChallenge/f1/preprocessed/train_dynamic.npy'
)
static_val = np.load(
'/storage/hpc_anna/GMiC/Data/BPIChallenge/f1/preprocessed/test_static.npy'
)
dynamic_val = np.load(
'/storage/hpc_anna/GMiC/Data/BPIChallenge/f1/preprocessed/test_dynamic.npy'
)
labels_train = np.load(
'/storage/hpc_anna/GMiC/Data/BPIChallenge/f1/preprocessed/train_labels.npy'
)
labels_val = np.load(
'/storage/hpc_anna/GMiC/Data/BPIChallenge/f1/preprocessed/test_labels.npy'
)
# Merge train and test
static_all = np.concatenate((static_train, static_val), axis=0)
dynamic_all = np.concatenate((dynamic_train, dynamic_val), axis=0)
labels_all = np.concatenate((labels_train, labels_val), axis=0)
nsamples = static_all.shape[0]
# prepare where to store the ratios
ratios_all_hmm = np.empty(len(labels_all))
# split indices into folds
enrich_idx_list = np.array_split(range(nsamples), nfolds)
# run CV
for fid, enrich_idx in enumerate(enrich_idx_list):
train_idx = list(set(range(nsamples)) - set(enrich_idx))
# extract predictions using HMM on dynamic
hmmcl = HMMClassifier()
model_pos, model_neg = hmmcl.train(nhmmstates, nhmmiter, hmmcovtype,
dynamic_all[train_idx],
labels_all[train_idx])
ratios_all_hmm[enrich_idx] = hmmcl.pos_neg_ratios(
model_pos, model_neg, dynamic_all[enrich_idx])
# dataset for hybrid learning
enriched_by_hmm = np.concatenate((static_all, np.matrix(ratios_all_hmm).T),
axis=1)
# (2.) k-fold cross validation to obtain accuracy
val_idx_list = np.array_split(range(nsamples), nfolds)
scores = []
for fid, val_idx in enumerate(val_idx_list):
train_idx = list(set(range(nsamples)) - set(val_idx))
# Hybrid on features enriched by HMM (3)
rf = RandomForestClassifier(n_estimators=nestimators)
rf.fit(enriched_by_hmm[train_idx], labels_all[train_idx])
scores.append(rf.score(enriched_by_hmm[val_idx], labels_all[val_idx]))
print 'Result: %.4f' % np.mean(scores)
return -np.mean(scores)
