def main(argv):
# wandb.init(project="WME-Nyst and CUR")
# wandb.config.update(flags.FLAGS)
# logging.info('Running with args %s', str(argv))
# get dataset
dataset = FLAGS.dataset
if dataset == "ohsumed":
filename = "oshumed_K_set1.mat"
if FLAGS.run_mode == "test":
test_filename = "oshumed_K_set1.mat"
version = "v7.3"
if dataset == "twitter":
filename = "twitter_K_set1.mat"
if FLAGS.run_mode == "test":
test_filename = "twitter_K_set1.mat"
version = "default"
if dataset == "news":
filename = "20ng2_new_K_set1.mat"
if FLAGS.run_mode == "test":
test_filename = "20ng2_new_K_set1.mat"
version = "v7.3"
if dataset == "recipe":
filename = "recipe_trainData.mat"
if FLAGS.run_mode == "test":
test_filename = "recipe_K_set1"
version = "v7.3"
approximator = FLAGS.method
if approximator not in ["nystrom", "CUR"]:
print("please choose between nystrom and CUR for approximator")
return None
# get EMD matrix
# similarity_matrix, labels = read_mat_file(\
# file_="/mnt/nfs/work1/elm/ray/"+filename,\
# version=version, return_type="all")
similarity_matrix, labels = read_mat_file(\
file_="./WordMoversEmbeddings/mat_files/"+filename,\
version=version, return_type="all")
# set hyperparameters
config = {"samples":FLAGS.sample_size,\
"CV":10, \
"gamma": FLAGS.gamma,\
"lambda_inverse":FLAGS.lambda_inverse,\
"approximator":approximator,
"run_mode":FLAGS.run_mode}
if config["run_mode"] == "test":
test_sim_mat, test_labels = read_mat_file(\
file_="./WordMoversEmbeddings/mat_files/"+test_filename,\
version=version, return_type="all", mode="test")
if config["run_mode"] == "validate":
train_all(similarity_matrix, labels, config)
else:
train_all(similarity_matrix, labels, config, \
X_test=test_sim_mat, Y_test=test_labels)
return None
def create_spectrogram_images(mat_file_path):
data, properties = utils.read_mat_file(mat_file_path)
spectrograms = []
for data_channel in data.T:
spectrograms.append(utils.convert_to_spectrogram(data_channel))
return np.array(spectrograms)
def get_features(mat_file):
d, _ = ut.read_mat_file(mat_file)
# 5 seconds = 600/5 = 120 windows
window_size = d.shape[0] / 120
for i in range(0, d.shape[0], window_size):
wd = d[i:i + window_size, :].T
bf_feats = np.array(map(get_butter_features, wd))
ff_feats = np.array(map(get_fft_features, wd))
xcorr_feats = get_corr_features(wd)
yield np.append(np.append(bf_feats, ff_feats), xcorr_feats)
distorts = [0, 10, 20, 30, 40] evaluator = StructuredAccuracy() for distort in distorts: print 'data with ' + str(distort) + '% of total labels distorted' ### prepare training, test data and evaluator train_data_file = 'hmsvm_%d_distort_data_fold' % distort train_num_examples_fold = 20 train_num_folds = 5 train_labels, train_features = utils.unfold_data(train_data_file) test_data_file = 'hmsvm_%d_distort_data_test' % distort test_num_examples = 100 test_labels, test_features = utils.read_mat_file(test_data_file, test_num_examples) ### train ML-HMM and evaluate in training data model = HMSVMModel(train_features, train_labels, SMT_TWO_STATE) model.set_use_plifs(True) mlhmm = MLHMM(model) mlhmm.train() prediction = mlhmm.apply() accuracy = evaluator.evaluate(prediction, train_labels) print '\ttraining accuracy:\t' + str(accuracy*100) + '%' utils.print_statistics(train_labels, prediction) ### evaluate in test data
def main(variables):
data = read_mat_file(variables["data_path"])
f1_data, f2_data = np.array(data['F1']), np.array(data['F2'])
n_samples = f1_data.shape[0]
ground_truth = np.array([[0, 1, 2, 3, 4] for _ in range(n_samples)])
print("About the data")
print("Source of data: ", variables["data_path"])
print("Classes of data: 0,1,2,3,4")
print("No. of samples: ", n_samples, "\n")
#Training on 100 samples
#m_std is dictionary of f1, f2 for each column, c1 c2 c3 c4 and c5.
print("\n---------- Section 1: Training -------------")
print("\n Calculating the means and standard deviations for 100 samples\n")
train_size = variables['training_size']
b1 = Bayes_Classifier(f1_data, train_size)
m_std_train = b1.train()
## Section 2.1: Testing
print("\n---------- Section 2.1: Testing -------------")
print("\n Predicting the classes for 101: 1000 samples")
predicted = b1.predict()
## Section 2.2: Calculating accuracy and error rate
print(
"\n---------- Section 2.2: Calculating accuracy for the classifier -------------"
)
print("\nAccuracy for the Bayes classifier: ")
acc = b1.validate(predicted)
## Section 3: Standard Normal (z score)
print("---------- Section 3: Standard normal(Z Score) -------------")
# z1_data is the standard normalized data.
z1_data=np.swapaxes(np.array([std_normalize(f1_data[:,i],m_std_train['f1'][i]['m'],\
m_std_train['f1'][i]['std'])
for i in range(5)]),0,1)
print("Plot of Z1 vs F2")
plot_clustered_graph(z1_data.flatten(),
f2_data.flatten(),
ground_truth.flatten(),
name="z1vsf2.png",
labels=['z1', 'f2'])
# z1_data is the standard normalized data.
print("\n Plot of F1 vs F2")
plot_clustered_graph(f1_data.flatten(),
f2_data.flatten(),
ground_truth.flatten(),
name="f1vsf2.png",
labels=['f1', 'f2'])
## Section 4
### Case 1: Training with the z1 data
print(
"\n---------- Section 4, Case 2: Training with the z1 data -------------"
)
b = Bayes_Classifier(z1_data)
b.train()
predicted = b.predict()
acc = b.validate(predicted)
print(
"\n---------- Section 4, Case 3: Training with the f2 data -------------"
)
b = Bayes_Classifier(f2_data)
b.train()
predicted = b.predict()
acc = b.validate(predicted)
print(
"\n---------- Section 4, Case 4: Training with the [z1, f2] data -------------"
)
data = {'z1': z1_data, 'f2': f2_data}
b = Multivariate_Bayes_Classifier(data)
b.train()
predicted = b.predict()
acc = b.validate(predicted)
K = 5
# number of examples per fold
num_fold_examples = 20
# length of each example
example_len = 250
# number of features per example
num_features = 10
# the number different label values
num_states = 2
# K models that will contain the data of each fold
models = []
# load each data fold in a HMSVMModel
data_file = 'hmsvm_30_distort_data_fold'
for k in xrange(K):
labels, features = utils.read_mat_file('%s_%d' % (data_file, k), num_fold_examples)
models.append(HMSVMModel(features, labels, SMT_TWO_STATE))
# put together folds, leaving out one of them for each set
labels_no_fold = []
features_no_fold = []
# for each fold
for k1 in xrange(K):
# put all labels/features together except the ones of the current fold
labels_no_kfold = SequenceLabels(num_fold_examples*(K-1), num_states)
features_no_kfold = RealMatrixFeatures(num_fold_examples*(K-1), num_features)
# index for the next feature vector to set
idx = 0
for k2 in xrange(K):
def compute_min_eig(Z):
min_eigs = np.linalg.eigvals(Z)
return min_eigs
# read mat
filetype = None
dataset = sys.argv[1]
if dataset == "PSD":
feats = np.random.random((1000,1000))
similarity_matrix = feats @ feats.T
filetype = "numpy"
if dataset == "mrpc" or dataset == "rte" or dataset == "stsb":
filename = "../GYPSUM/"+dataset+"_predicts_0.npy"
filetype = "python"
if dataset == "twitter":
similarity_matrix = read_mat_file(file_="./WordMoversEmbeddings/mat_files/twitter_K_set1.mat")
if filetype == "python":
similarity_matrix = read_file(filename)
sample_size = int(sys.argv[2])
runs = 50
n_bins = 50
# check for similar rows or columns
if dataset != "PSD":
unique_rows, indices = np.unique(similarity_matrix, axis=0, return_index=True)
similarity_matrix_O = similarity_matrix[indices][:, indices]
# symmetrization
similarity_matrix = (similarity_matrix_O + similarity_matrix_O.T) / 2.0
if return_type == "error":
return np.linalg.norm(\
similarity_matrix - \
KS @ np.linalg.pinv(A) @ KS.T)\
/ np.linalg.norm(similarity_matrix), min_eig
##########################################################################################
step = 50
runs_ = 3
"""
20ng2_new_K_set1.mat oshumed_K_set1.mat recipe_K_set1.mat recipe_trainData.mat twitter_K_set1.mat twitter_set1.mat
"""
# filename = "stsb"
id_count = 500 #len(similarity_matrix) #1000
similarity_matrix = read_mat_file(file_="WordMoversEmbeddings/mat_files/recipe_trainData.mat",\
version="v7.3")
# similarity_matrix = read_file("../GYPSUM/"+filename+"_predicts_0.npy")
# check for similar rows or columns
unique_rows, indices = np.unique(similarity_matrix, axis=0, return_index=True)
similarity_matrix_O = similarity_matrix[indices][:, indices]
# symmetrization
similarity_matrix = (similarity_matrix_O + similarity_matrix_O.T) / 2.0
multipliers = list(np.arange(1.0, 2.3, 0.5))
list_of_list_of_errors = []
list_of_min_eig_scaling = []
z_range = [1, 2, 5, 10]
# eps=1e-16
from mlhmm import MLHMM
from itertools import product
from modshogun import StructuredAccuracy, HMSVMModel, SMT_TWO_STATE
### prepare training, test data and evaluator
distort = 40
train_data_file = 'hmsvm_%d_distort_data_fold' % distort
train_num_examples_fold = 20
train_num_folds = 5
train_labels, train_features = utils.unfold_data(train_data_file)
test_data_file = 'hmsvm_%d_distort_data_test' % distort
test_num_examples = 100
test_labels, test_features = utils.read_mat_file(test_data_file,
test_num_examples)
evaluator = StructuredAccuracy()
### train ML-HMM and evaluate in training data
print 'training ML-HMM'
model = HMSVMModel(train_features, train_labels, SMT_TWO_STATE)
model.set_use_plifs(True)
mlhmm = MLHMM(model)
mlhmm.train()
'''
print '\n\tmodel parameters:'
print '\t- transition scores: ' + str(numpy.exp(mlhmm.transition_scores))
print '\t- feature scores:'
for s,f in product(xrange(mlhmm.num_free_states), xrange(mlhmm.num_features)):
# number of features per example
num_features = 10
# the number different label values
num_states = 2
distorts = [0, 10, 20, 30, 40]
for distort in distorts:
# K models that will contain the data of each fold
models = []
print '>>>> data with ' + str(distort) + '% of total labels distorted'
data_file = 'hmsvm_%d_distort_data_fold' % distort
for k in xrange(K):
fold_data_file = '%s_%d' % (data_file, k)
labels, features = utils.read_mat_file(fold_data_file,
num_fold_examples)
models.append(HMSVMModel(features, labels, SMT_TWO_STATE))
# check
if checks:
print 'running checks on simulated data'
for k in xrange(K):
labels = models[k].get_labels()
features = RealMatrixFeatures.obtain_from_generic(
models[k].get_features())
print '\tmodel %d with %d labels and %d features' % (
k, labels.get_num_labels(), features.get_num_vectors())
assert (labels.get_num_labels() == features.get_num_vectors())
for i in xrange(labels.get_num_labels()):
# number of features per example num_features = 10 # the number different label values num_states = 2 distorts = [0, 10, 20, 30, 40] for distort in distorts: # K models that will contain the data of each fold models = [] print '>>>> data with ' + str(distort) + '% of total labels distorted' data_file = 'hmsvm_%d_distort_data_fold' % distort; for k in xrange(K): fold_data_file = '%s_%d' % (data_file, k) labels, features = utils.read_mat_file(fold_data_file, num_fold_examples) models.append(HMSVMModel(features, labels, SMT_TWO_STATE)) # check if checks: print 'running checks on simulated data' for k in xrange(K): labels = models[k].get_labels() features = RealMatrixFeatures.obtain_from_generic(models[k].get_features()) print '\tmodel %d with %d labels and %d features' % (k, labels.get_num_labels(), features.get_num_vectors()) assert(labels.get_num_labels() == features.get_num_vectors()) for i in xrange(labels.get_num_labels()): label = Sequence.obtain_from_generic(labels.get_label(i))
step = 50
runs_ = 3
"""
20ng2_new_K_set1.mat oshumed_K_set1.mat recipe_K_set1.mat recipe_trainData.mat twitter_K_set1.mat twitter_set1.mat
"""
filetype = None
dataset = sys.argv[1]
if dataset == "PSD":
feats = np.random.random((1000,1000))
similarity_matrix = feats @ feats.T
filetype = "numpy"
if dataset == "mrpc" or dataset == "rte" or dataset == "stsb":
filename = "../GYPSUM/"+dataset+"_predicts_0.npy"
filetype = "python"
if dataset == "twitter":
similarity_matrix = read_mat_file(file_="./WordMoversEmbeddings/mat_files/twitter_K_set1.mat")
if dataset == "ohsumed":
similarity_matrix = read_mat_file(file_="./WordMoversEmbeddings/mat_files/oshumed_K_set1.mat", version="v7.3")
if dataset == "recipe":
similarity_matrix = read_mat_file(file_="/mnt/nfs/work1/elm/ray/recipe_trainData.mat", version="v7.3")
if dataset == "news":
similarity_matrix = read_mat_file(file_="/mnt/nfs/work1/elm/ray/20ng2_new_K_set1.mat", version="v7.3")
if filetype == "python":
similarity_matrix = read_file(filename)
# similarity_matrix = read_file("../GYPSUM/"+filename+"_predicts_0.npy")
true_error = []
KS_corrected_error_list = []
KS_ncorrected_error_list = []
scaling_error_list = []
