np.random.seed(90210)
num_classes = 5
batch_size = 256
epochs = 7500
crop_future = -20
input_size = 128
#savePath = r'/home/suroot/Documents/train/daytrader/'
#path =r'/home/suroot/Documents/train/daytrader/ema-crossover' # path to data
savePath = r'/home/suroot/Documents/train/raw/'
path = r'/home/suroot/Documents/train/raw/22222c82-59d1-4c56-a661-3e8afa594e9a' # path to data
(data, labels_classed, _) = dt.cacheLoadData(path,
crop_future,
num_classes,
input_size,
symbols=dt.CA_EXTRA)
print(data.shape)
x_train, x_test, y_train, y_test = train_test_split(data,
labels_classed,
test_size=0.1)
model = Sequential()
model.add(
Dense(128,
activation='relu',
input_dim=data.shape[1],
kernel_regularizer=regularizers.l2(0.01)))
#model.add(Dropout(0.2))
# fix random seed for reproducibility
np.random.seed(90210)
num_classes = 5
batch_size = 256
epochs = 7500
input_size = 256
subset = -1 # -1 to use the entire data set
savePath = r'/home/suroot/Documents/train/daytrader/'
path = r'/home/suroot/Documents/train/daytrader/encoder-' + str(
input_size) + '.npy' # path to data
(data, labels_classed) = dt.cacheLoadData(path, num_classes,
-1) # just to load labels
data = np.load(path)
ss = StratifiedShuffleSplit(n_splits=1, test_size=0.1)
for train_index, test_index in ss.split(data, labels_classed):
print("TRAIN:", train_index, "TEST:", test_index)
x_train, x_test = data[train_index], data[test_index]
y_train, y_test = labels_classed[train_index], labels_classed[test_index]
dt.plotTrainingExample(x_train[15, :])
model = Sequential()
model.add(
Dense(128,
activation='relu',
input_dim=data.shape[1],
# num of input signals
input_dim = 1
# num of output signals
output_dim = 1
# num of stacked lstm layers
num_stacked_layers = 2
# gradient clipping - to avoid gradient exploding
GRADIENT_CLIPPING = 2.5
scaler = StandardScaler()
savePath = r'/home/suroot/Documents/train/daytrader/'
path = r'/home/suroot/Documents/train/daytrader/ema-crossover' # path to data
savePath = r'/home/suroot/Documents/train/daytrader/'
path = r'/home/suroot/Documents/train/daytrader/ema-crossover' # path to data
(data, labels_classed, _) = dt.cacheLoadData(path, crop_future, num_classes,
input_size)
print("data: " + str(data.shape))
ss = StratifiedShuffleSplit(test_size=0.1)
for train_index, test_index in ss.split(data, labels_classed):
print("TRAIN:", train_index, "TEST:", test_index)
x_train, x_test = data[train_index], data[test_index]
y_train, y_test = labels_classed[train_index], labels_classed[test_index]
print(x_train.shape)
def generate_train_samples(x,
y,
batch,
batch_size=10,
input_seq_len=input_seq_len,
from keras.models import Model # fix random seed for reproducibility np.random.seed(90210) num_classes = 5 batch_size = 256 epochs = 2500 input_size = -1 subset = -1 # -1 to use the entire data set savePath = r'/home/suroot/Documents/train/daytrader/' path = r'/home/suroot/Documents/train/daytrader/ema-crossover' # path to data (data, labels_classed) = dt.cacheLoadData(path, num_classes, input_size) x_train = data y_train = labels_classed # visualize some data from training #dt.plotTrainingExample(data[50,:]) #dt.plotTrainingExample(data[150,:]) #dt.plotTrainingExample(data[4500,:]) # this is the size of our encoded representations encoding_dim = 128 # this is our input placeholder input = Input(shape=(data.shape[1], )) # "encoded" is the encoded representation of the input