matplotlib.rcParams.update({'axes.labelsize': 12,
'text.fontsize': 10,
'legend.fontsize': 10,
'xtick.labelsize': 10,
'ytick.labelsize': 10,
'text.usetex': False,
'figure.figsize': [4.5, 4.5]})
import pscgen
def num_ops(N, M):
return N * (2 * M - 1)
args = json.loads(sys.argv[1])
storage = pscgen.name_to_storage(args['storage'])
comp_scheme = pscgen.name_to_comp_scheme('pca')
X, Y, X_flat = util.wav_to_np(args['tr_folder_path'], window_size=50)
assert False
num_folds = 5
acc = 0.0
max_atoms = 1000
sss = StratifiedShuffleSplit(Y, num_folds, test_size=0.7, random_state=0)
alphas = [1, 2, 3, 4, 5, 5, 5, 5, 5, 10, 10, 10, 15, 20, 20, 20, 20, 25]
betas = [1, 1, 1, 1, 1, 2, 3, 4, 5, 5, 7, 10, 10, 10, 12, 15, 20, 20]
Ns = [1, 2, 3, 4, 5, 10, 15, 20, 25, 50, 70, 100, 150, 200, 240, 300, 400, 500]
alphas = [1, 2, 3, 4, 5, 5, 5, 5, 5, 10, 10, 10, 15, 20, 20]
betas = [1, 1, 1, 1, 1, 2, 3, 4, 5, 5, 7, 10, 10, 10, 12]
Ns = [1, 2, 3, 4, 5, 10, 15, 20, 25, 50, 70, 100, 150, 200, 240]
return json.dumps(chunk_dict)
'''
Updater:
dtype (e.g. wav)
tr_folder_path (containing files of format classlabel_XXXXX.dtype)
D_atoms
alpha
beta
storage (e.g. 'mini' or 'half')
output_path
chunk_size (size in bytes, -1 for no chunks)
'''
args = json.loads(sys.argv[1])
storage = name_to_storage(args['storage'])
KMeans_tr_size = 200000
X, Y, X_normal = read_dataset(args['tr_folder_path'], args['dtype'])
pipe = pscgen.Pipeline(100, 12)
pipe.fit(X, Y, args['D_atoms'], args['alpha'], args['beta'], storage)
cl1, cl2, cl3 = [], [], []
for i in xrange(len(X)):
x = util.bow(pipe.nnu.index(X[i]), args['D_atoms'])
cl1.append(pipe.svm.predict(x)[0])
cl2.append(pipe.svm.classes_[classify(x, pipe.svm.coef_,
pipe.svm.intercept_, 13)])
cl3.append(pipe.classify(X_normal[i]))
