def __init__(self, xs, ys, args, xs_pair=None, moco=True):
if moco:
assert xs_pair is not None
self.xs = xs
self.xs_pair = xs_pair
self.ys = ys
self.is_moco = moco
self.sample_len = len(self.xs[0])
if args.augment_type == 'warp':
self.aug_for_query_moco = (
TimeWarp(seed=10) * 1 # random time warping
)
self.aug_for_key_moco = (
TimeWarp(seed=20) * 1 # random time warping
)
self.aug_train = (
TimeWarp(seed=30) * 1 # random time warping
)
elif args.augment_type == 'noise':
self.aug_for_query_moco = (AddNoise(scale=0.01, seed=10))
self.aug_for_key_moco = (AddNoise(scale=0.01, seed=20))
self.aug_train = (AddNoise(scale=0.01, seed=30))
elif args.augment_type == 'drift':
self.aug_for_query_moco = (Drift(max_drift=0.7,
n_drift_points=5,
seed=10))
self.aug_for_key_moco = (Drift(max_drift=0.7,
n_drift_points=5,
seed=20))
self.aug_train = (Drift(max_drift=0.7, n_drift_points=5, seed=30))
elif args.augment_type == 'crop':
crop_size = int(self.sample_len * 0.05)
self.aug_for_query_moco = (Crop(size=crop_size, seed=10))
self.aug_for_key_moco = (Crop(size=crop_size, seed=20))
self.aug_train = (Crop(size=crop_size, seed=30))
elif args.augment_type == 'dropout':
self.aug_for_query_moco = (Dropout(p=0.1, fill=0, seed=10))
self.aug_for_key_moco = (Dropout(p=0.1, fill=0, seed=20))
self.aug_train = (Dropout(p=0.1, fill=0, seed=30))
elif args.augment_type == 'dropout_0.2':
self.aug_for_query_moco = (Dropout(p=0.2, fill=0, seed=10))
self.aug_for_key_moco = (Dropout(p=0.2, fill=0, seed=20))
self.aug_train = (Dropout(p=0.2, fill=0, seed=30))
if self.is_moco:
self.d_aug_query = self.aug_for_query_moco.augment(xs)
self.d_aug_key = self.aug_for_key_moco.augment(xs_pair)
else:
self.d_aug_train = self.aug_train.augment(xs)
def test_pipe():
augmenter = (
AddNoise() * 2 @ 0.5
+ (Crop(size=int(T / 2)) * 2 + Drift())
+ (Dropout() @ 0.5 + Pool())
+ Quantize() * 2
)
augmenter.augment(X1)
augmenter.augment(X1, Y1)
augmenter.augment(X2)
augmenter.augment(X2, Y2)
augmenter.augment(X2, Y3)
augmenter.augment(X3)
augmenter.augment(X3, Y2)
augmenter.augment(X3, Y3)
augmenter.summary()
assert len(augmenter) == 6
exchange = Resize(size=int(T / 2)) * 2 @ 0.5
augmenter[3] = exchange
assert augmenter[3] is exchange
exchange.resize = int(T / 3)
exchange.repeats = 3
exchange.prob = 0.4
assert isinstance(augmenter[3], Resize)
assert augmenter[3].resize == int(T / 3)
assert augmenter[3].repeats == 3
assert augmenter[3].prob == 0.4
def augment_tsaug(filename):
y, sr = librosa.load(filename, mono=False)
duration = int(librosa.core.get_duration(y, sr))
print(y.shape)
# y=np.expand_dims(y.swapaxes(0,1), 0)
# N second splice between 1 second to N-1 secondsd
splice = random.randint(1, duration - 1)
my_augmenter = (
Crop(size=sr * splice) *
5 # random crop subsequences of splice seconds
+ AddNoise(scale=(0.01, 0.05))
@ 0.5 # with 50% probability, add random noise up to 1% - 5%
+ Dropout(
p=0.1,
fill=0,
size=[int(0.001 * sr),
int(0.01 * sr),
int(0.1 * sr)]
) # drop out 10% of the time points (dropped out units are 1 ms, 10 ms, or 100 ms) and fill the dropped out points with zeros
)
y_aug = my_augmenter.augment(y)
newfile = 'tsaug_' + filename
sf.write(newfile, y_aug.T, sr)
return [newfile]
def test_crop_X3():
X = np.concatenate(
[
np.arange(200).reshape(2, -1, 1),
-1 * np.arange(200).reshape(2, -1, 1),
],
axis=2,
)
X_crops = Crop(crop_start=[[0, 90, 20], [10, 30, 15]], crop_size=5).run(X)
assert X_crops.shape == (6, 5, 2)
assert (X_crops[3, :, 0] == np.arange(110, 115)).all()
assert (X_crops[1, :, 1] == -np.arange(90, 95)).all()
def test_crop_X1():
X = np.arange(100)
X_crops = Crop(crop_start=[[0, 90, 20]], crop_size=5).run(X)
assert X_crops.shape == (3, 5)
assert (X_crops[0, :] == np.arange(5)).all()
assert (X_crops[1, :] == np.arange(90, 95)).all()
def test_crop_X2():
X = np.arange(200).reshape(2, -1)
X_crops = Crop(crop_start=[[0, 90, 20], [10, 30, 15]], crop_size=5).run(X)
assert X_crops.shape == (6, 5)
assert (X_crops[3, :] == np.arange(110, 115)).all()
assert (X_crops[1, :] == np.arange(90, 95)).all()
AddNoise,
Convolve,
Crop,
Drift,
Dropout,
Pool,
Quantize,
Resize,
Reverse,
TimeWarp,
)
augmenters = [
AddNoise(),
Convolve(size=(7, 10)) * 10,
Crop(size=10),
Drift(),
Dropout(),
Pool(size=[2, 4, 8]) * 10,
Quantize(n_levels=[10, 20, 30]) * 10,
Reverse() @ 0.5 * 10,
TimeWarp(),
]
N = 10
T = 1000
C = 3
L = 2
M = 4
X1 = np.random.uniform(size=T)
from tsaug import TimeWarp, Crop, Quantize, Drift, Reverse
from pandas import read_csv, DataFrame
dataset = read_csv('CLEANED_ECX_EUA_.csv', delimiter=",", engine='python')
dataset.columns = [
'Date', 'Open', 'High', 'Low', 'Settle', 'Change', 'CloseToPredict'
]
dataset = dataset.drop(columns=['Date', 'Change', 'CloseToPredict'])
X = dataset.to_numpy()
X = X.reshape(len(dataset.columns), len(dataset))
print(len(X))
print(X.shape)
my_augmenter = (TimeWarp() * 1 + Crop(size=3000) +
Quantize(n_levels=[10, 20, 30]) +
Drift(max_drift=(0.1, 0.5)) @ 0.8 + Reverse() @ 0.5)
X_aug = my_augmenter.augment(X)
print(X)
print(X_aug)
test = X_aug.reshape(-1, 4)
new = DataFrame(test)
print(new)
new.to_csv("SYNTHETIC_DATA_3K_SAMPLE.csv", index=False, header=False)
AddNoise(distr="laplace", seed=0),
AddNoise(distr="uniform", seed=0),
AddNoise(kind="multiplicative", seed=0),
AddNoise(per_channel=False, normalize=False, seed=0),
Convolve(repeats=M, prob=0.5, seed=0),
Convolve(window=["hann", "blackman", ("gaussian", 1)], seed=0),
Convolve(
window=["hann", "blackman", ("gaussian", 1)], per_channel=True, seed=0
),
Convolve(window=("gaussian", 1), seed=0),
Convolve(size=(7, 11), seed=0),
Convolve(size=(7, 11), per_channel=True, seed=0),
Convolve(size=[7, 11], seed=0),
Convolve(size=[7, 11], per_channel=True, seed=0),
Convolve(per_channel=True, seed=0),
Crop(size=int(T / 2), repeats=M, seed=0),
Crop(size=(int(T / 3), T), resize=int(T / 2), seed=0),
Crop(size=[int(T / 3), T], resize=int(T / 2), seed=0),
Drift(repeats=M, prob=0.5, seed=0),
Drift(max_drift=(0.5, 1.0), seed=0),
Drift(n_drift_points=[3, 8], seed=0),
Drift(kind="multiplicative", seed=0),
Drift(per_channel=False, normalize=False, seed=0),
Dropout(repeats=M, prob=0.5, seed=0),
Dropout(p=(0.01, 0.1), size=(1, 5), seed=0),
Dropout(p=[0.01, 0.02, 0.03], size=[1, 2, 3], seed=0),
Dropout(fill="bfill", seed=0),
Dropout(fill="mean", seed=0),
Dropout(fill=0, seed=0),
Dropout(per_channel=True, seed=0),
Pool(repeats=M, prob=0.5, seed=0),