def make_model(input_shape, nb_epochs=100, batch_size=128, lr=0.01, n_layers=1, n_hidden=16, rate_dropout=0.3):
model_path = '/output/model.{}.{}c.{}l.{}'.format(input_shape[0], n_hidden, n_layers, nb_epochs)
wp = WindPuller(input_shape=input_shape, lr=lr, n_layers=n_layers, n_hidden=n_hidden, rate_dropout=rate_dropout)
train_set, test_set = read_ultimate("/dataset/", input_shape)
wp.fit(train_set.images, train_set.labels, batch_size=batch_size,
nb_epoch=nb_epochs, shuffle=False, verbose=1,
# validation_split=0.02,
validation_data=(test_set.images, test_set.labels),
callbacks=[
TensorBoard(log_dir='/output/logs', histogram_freq=100),
ModelCheckpoint(filepath=model_path + '.best', save_best_only=True, mode='min')
])
scores = wp.evaluate(test_set.images, test_set.labels, verbose=0)
print('Test loss:', scores[0])
print('Test accuracy:', scores[1])
wp.model.save(model_path)
saved_wp = wp.load_model(model_path)
scores = saved_wp.evaluate(test_set.images, test_set.labels, verbose=0)
print('Test loss:', scores[0])
print('test accuracy:', scores[1])
pred = saved_wp.predict(test_set.images, 1024)
# print(pred)
# print(test_set.labels)
pred = numpy.reshape(pred, [-1])
result = numpy.array([pred, test_set.labels]).transpose()
with open('output.' + str(input_shape[0]), 'w') as fp:
for i in range(result.shape[0]):
for val in result[i]:
fp.write(str(val) + "\t")
fp.write('\n')
def evaluate_model(model_path, code, output_dir, input_shape=[30, 61]):
extract_from_file("dataset/%s.csv" % code, output_dir, code)
train_set, test_set = read_feature(output_dir, input_shape, code)
saved_wp = WindPuller(input_shape).load_model(model_path)
scores = saved_wp.evaluate(test_set.images, test_set.labels, verbose=0)
print('Test loss:', scores[0])
print('test accuracy:', scores[1])
pred = saved_wp.predict(test_set.images, 1024)
[cr, cap] = calculate_cumulative_return(test_set.labels, pred)
# Output to a csv file
# Read in the date, close from original data file.
days_for_test = 700
tmp = pd.read_csv('dataset/%s.csv' % code, delimiter='\t')
# tmp.columns = ['date', 'open', 'high', 'low', 'close', 'volume']
date = tmp['date'][-days_for_test:]
close = tmp['close'][-days_for_test:]
output = pd.DataFrame(
{
'Return': test_set.labels,
'Position': pred.reshape(-1),
'Capital': cap.reshape(-1),
'Close': close.values
},
index=date,
columns=['Close', 'Return', 'Position', 'Capital'])
output.to_csv('output/%s.csv' % code)
def make_model_type3(input_shape,
nb_epochs=100,
batch_size=128,
lr=0.01,
n_layers=1,
n_hidden=16,
rate_dropout=0.3):
model_path = 'model.%s' % input_shape[0]
windowSize = input_shape[0] # num minutes
X_train, y_train, X_val, Y_val, X_test, y_test, numFeatures = ft.generateDataSetTXF(
os.getcwd(), input_wind_size=input_shape[0], toDataSet=False)
input_shape[0] = numFeatures
wp = WindPuller(input_shape=input_shape,
modelType=3,
lr=lr,
n_layers=n_layers,
n_hidden=n_hidden,
rate_dropout=rate_dropout)
wp.fit(X_train,
y_train,
batch_size=batch_size,
nb_epoch=nb_epochs,
shuffle=True,
verbose=1,
validation_data=(X_val, Y_val))
scores = wp.evaluate(X_test, y_test, verbose=0)
print('Test loss:', scores[0])
print('Test accuracy:', scores[1])
wp.model.save(model_path)
def make_model_type(input_shape,
_modelTyp=0,
nb_epochs=100,
batch_size=128,
lr=0.01,
n_layers=1,
n_hidden=16,
rate_dropout=0.3):
model_path = 'model.%s' % input_shape[0]
train_set, validation_set, test_set, numFeatures = ft.generateDataSetTXF(
os.getcwd(), input_wind_size=input_shape[0], toDataSet=True)
input_shape[1] = numFeatures
wp = WindPuller(input_shape=input_shape,
modelType=_modelTyp,
lr=lr,
n_layers=n_layers,
n_hidden=n_hidden,
rate_dropout=rate_dropout)
wp.fit(train_set.images,
train_set.labels,
batch_size=batch_size,
nb_epoch=nb_epochs,
shuffle=True,
verbose=1,
validation_data=(validation_set.images, validation_set.labels))
scores = wp.evaluate(test_set.images, test_set.labels, verbose=0)
print('Test loss:', scores[0])
print('Test accuracy:', scores[1])
wp.model.save(model_path)
def make_separate_model(nb_epochs=100,
batch_size=128,
lr=0.01,
n_layers=1,
n_hidden=14,
rate_dropout=0.3,
input_shape=[30, 73]):
train_sets, test_sets = read_separate_feature("./ultimate_feature")
wp = WindPuller(input_shape=input_shape,
lr=lr,
n_layers=n_layers,
n_hidden=n_hidden,
rate_dropout=rate_dropout)
wp.build_model()
for code, train_set in train_sets.items():
test_set = test_sets[code]
input_shape = [train_set.images.shape[1], train_set.images.shape[2]]
print(input_shape)
model_path = 'model.%s' % code
print(train_set.images.shape)
wp.fit(train_set.images,
train_set.labels,
batch_size=batch_size,
nb_epoch=nb_epochs,
shuffle=False,
verbose=1,
validation_data=(test_set.images, test_set.labels),
callbacks=[
TensorBoard(histogram_freq=1000),
ModelCheckpoint(filepath=model_path + '.best.checkpoints',
save_best_only=True,
mode='min')
])
scores = wp.evaluate(test_set.images, test_set.labels, verbose=0)
print('Test loss:', scores[0])
print('Test accuracy:', scores[1])
wp.model.save(model_path)
saved_wp = wp.load_model(model_path)
scores = saved_wp.evaluate(test_set.images, test_set.labels, verbose=0)
print('Test loss:', scores[0])
print('test accuracy:', scores[1])
pred = saved_wp.predict(test_set.images, 1024)
# print(pred)
# print(test_set.labels)
pred = numpy.reshape(pred, [-1])
result = numpy.array([pred, test_set.labels]).transpose()
with open('output.' + str(input_shape[0]), 'w') as fp:
for i in range(result.shape[0]):
for val in result[i]:
fp.write(str(val) + "\t")
fp.write('\n')
def evaluate_model(model_path, code, input_shape=[30, 83]):
extract_from_file("dataset/%s.csv" % code, code)
train_set, test_set = read_feature(".", input_shape, code)
saved_wp = WindPuller(input_shape).load_model(model_path)
scores = saved_wp.evaluate(test_set.images, test_set.labels, verbose=0)
print('Test loss:', scores[0])
print('test accuracy:', scores[1])
pred = saved_wp.predict(test_set.images, 1024)
cr = calculate_cumulative_return(test_set.labels, pred)
print("changeRate\tpositionAdvice\tprincipal\tcumulativeReturn")
for i in range(len(test_set.labels)):
print(str(test_set.labels[i]) + "\t" + str(pred[i]) + "\t" + str(cr[i] + 1.) + "\t" + str(cr[i]))