def main():
configs = json.load(open('config.json', 'r'))
if not os.path.exists(configs['model']['save_dir']):
os.makedirs(configs['model']['save_dir'])
data = DataLoader(os.path.join('../data', configs['data']['filename']),
os.path.join('../data', configs['data']['VIMfile']),
configs['data']['train_test_split'],
configs['data']['columns'])
model = Model()
model.build_model(configs)
x, y = data.get_train_data(seq_len=configs['data']['sequence_length'],
normalise=configs['data']['normalise'])
'''
# in-memory training
model.train(
x,
y,
epochs = configs['training']['epochs'],
batch_size = configs['training']['batch_size'],
save_dir = configs['model']['save_dir']
)
'''
# Out-of memory generative training
steps_per_epoch = math.ceil(
(data.len_train - configs['data']['sequence_length']) /
configs['training']['batch_size'])
model.train_generator(data_gen=data.generate_train_batch(
seq_len=configs['data']['sequence_length'],
batch_size=configs['training']['batch_size'],
normalise=configs['data']['normalise']),
epochs=configs['training']['epochs'],
batch_size=configs['training']['batch_size'],
steps_per_epoch=steps_per_epoch,
save_dir=configs['model']['save_dir'])
x_test, y_test, p0_vec = data.get_test_data(
seq_len=configs['data']['sequence_length'],
normalise=configs['data']['normalise'])
#predictions = model.predict_sequences_multiple(x_test, configs['data']['sequence_length'], configs['data']['sequence_length'])
# predictions = model.predict_sequence_full(x_test, configs['data']['sequence_length'])
predictions = model.predict_point_by_point(x_test)
pred = predictions.reshape((predictions.size, 1))
#plot_results_multiple(predictions, y_test, configs['data']['sequence_length'])
#plot_results(pred, y_test) #normalised predictions
# De-normalise & plot
p_pred, p_true = denorm_transform(p0_vec, pred, y_test)
plot_results(p_pred, p_true) #de-normalised, i.e., original fex units
# Compute evaluation metrics
assess = EvalMetrics(p_true, p_pred)
MAE = assess.get_MAE()
RMSE = assess.get_RMSE()
print("MAE on validation set is: %f" % MAE)
print("RMSE on validation set is: %f" % RMSE)
def main():
configs = json.load(open("config.json", "r"))
if not os.path.exists(configs["model"]["save_dir"]):
os.makedirs(configs["model"]["save_dir"])
data = DataLoader(
os.path.join("data", configs["data"]["filename"]),
configs["data"]["train_test_split"],
configs["data"]["columns"],
)
model = Model()
model.build_model(configs)
x, y = data.get_train_data(
seq_len=configs["data"]["sequence_length"],
normalise=configs["data"]["normalise"],
)
"""
# in-memory training
model.train(
x,
y,
epochs = configs['training']['epochs'],
batch_size = configs['training']['batch_size'],
save_dir = configs['model']['save_dir']
)
"""
# out-of memory generative training
steps_per_epoch = math.ceil(
(data.len_train - configs["data"]["sequence_length"])
/ configs["training"]["batch_size"]
)
model.train_generator(
data_gen=data.generate_train_batch(
seq_len=configs["data"]["sequence_length"],
batch_size=configs["training"]["batch_size"],
normalise=configs["data"]["normalise"],
),
epochs=configs["training"]["epochs"],
batch_size=configs["training"]["batch_size"],
steps_per_epoch=steps_per_epoch,
save_dir=configs["model"]["save_dir"],
)
x_test, y_test = data.get_test_data(
seq_len=configs["data"]["sequence_length"],
normalise=configs["data"]["normalise"],
)
# predictions = model.predict_sequences_multiple(x_test, configs['data']['sequence_length'], configs['data']['sequence_length'])
# predictions = model.predict_sequence_full(x_test, configs['data']['sequence_length'])
predictions = model.predict_point_by_point(x_test)
# plot_results_multiple(predictions, y_test, configs["data"]["sequence_length"])
plot_results(predictions, y_test)
def main():
configs = json.load(open('config.json', 'r'))
if not os.path.exists(configs['model']['save_dir']):
os.makedirs(configs['model']['save_dir'])
if not os.path.exists(configs['model']['log_dir']):
os.makedirs(configs['model']['log_dir'])
data_loader = DataLoader(os.path.join('data',
configs['data']['filename_train']),
configs['data']['train_test_split'],
configs['data']['columns'],
is_training=True)
model = Model()
model.build_model(configs)
steps_per_epoch = math.ceil(
(data_loader.len_train - configs['data']['sequence_length']) /
configs['training']['batch_size'])
validation_steps = math.ceil(
(data_loader.len_val - configs['data']['sequence_length']) /
configs['training']['batch_size'])
model.train_generator(train_loader=data_loader.batch_generator(
seq_len=configs['data']['sequence_length'],
batch_size=configs['training']['batch_size'],
normalise=configs['data']['normalise'],
generator_type='train'),
val_loader=data_loader.batch_generator(
seq_len=configs['data']['sequence_length'],
batch_size=configs['training']['batch_size'],
normalise=configs['data']['normalise'],
generator_type='val'),
epochs=configs['training']['epochs'],
batch_size=configs['training']['batch_size'],
steps_per_epoch=steps_per_epoch,
validation_steps=validation_steps,
save_dir=configs['model']['save_dir'],
log_dir=configs['model']['log_dir'])
test_data_loader = DataLoader(os.path.join(
'data', configs['data']['filename_test']),
0,
configs['data']['columns'],
is_training=False)
x_test, y_test = test_data_loader.get_test_data(
seq_len=configs['data']['sequence_length'],
normalise=configs['data']['normalise'])
predictions = model.predict_sequences_multiple(
x_test, configs['data']['sequence_length'],
configs['data']['sequence_length'])
# predictions = model.predict_sequences_full(x_test, configs['data']['sequence_length'])
# predictions = model.predict_point_by_point(x_test)
plot = Plot()
plot.plot_results_multiple(predictions, y_test,
configs['data']['sequence_length'])
def main():
configs = json.load(open('config.json', 'r'))
if not os.path.exists(configs['model']['save_dir']):
os.makedirs(configs['model']['save_dir'])
#獲取數據
data = DataLoader(os.path.join('data', configs['data']['filename']),
configs['data']['train_test_split'],
configs['data']['columns'])
#建立模型
model = Model()
model.build_model(configs)
x, y = data.get_train_data(seq_len=configs['data']['sequence_length'],
normalise=configs['data']['normalise'])
'''
# in-memory training
model.train(
x,
y,
epochs = configs['training']['epochs'],
batch_size = configs['training']['batch_size'],
save_dir = configs['model']['save_dir']
)
'''
#out-of memory generative training
#每一輪的'前傳導-后傳導'組合數量
steps_per_epoch = math.ceil(
(data.len_train - configs['data']['sequence_length']) /
configs['training']['batch_size'])
model.train_generator(data_gen=data.generate_train_batch(
seq_len=configs['data']['sequence_length'],
batch_size=configs['training']['batch_size'],
normalise=configs['data']['normalise']),
epochs=configs['training']['epochs'],
batch_size=configs['training']['batch_size'],
steps_per_epoch=steps_per_epoch,
save_dir=configs['model']['save_dir'])
x_test, y_test = data.get_test_data(
seq_len=configs['data']['sequence_length'],
normalise=configs['data']['normalise'])
predictions = model.predict_sequences_multiple(
x_test, configs['data']['sequence_length'],
configs['data']['sequence_length'])
#predictions = model.predict_sequence_full(x_test, configs['data']['sequence_length'])
#predictions = model.predict_point_by_point(x_test)
plot_results_multiple(predictions, y_test,
configs['data']['sequence_length'])
#plot_results(predictions, y_test)
#if __name__=='__main__':
# main()
def main():
configs = json.load(open('config.json', 'r'))
if not os.path.exists(configs['model']['save_dir']):
os.makedirs(configs['model']['save_dir'])
rates_count = configs['data']['sequence_length'] * configs['data'][
'number_sequences']
#os.path.join('data', configs['data']['filename']),
data = DataLoader(configs['data']['symbol'],
configs['data']['train_test_split'],
configs['data']['columns'], rates_count)
model = Model()
model.build_model(configs)
x, y = data.get_train_data(seq_len=configs['data']['sequence_length'],
normalise=configs['data']['normalise'])
'''
# in-memory training
model.train(
x,
y,
epochs = configs['training']['epochs'],
batch_size = configs['training']['batch_size'],
save_dir = configs['model']['save_dir']
)
'''
# out-of memory generative training
steps_per_epoch = math.ceil(
(data.len_train - configs['data']['sequence_length']) /
configs['training']['batch_size'])
model.train_generator(data_gen=data.generate_train_batch(
seq_len=configs['data']['sequence_length'],
batch_size=configs['training']['batch_size'],
normalise=configs['data']['normalise']),
epochs=configs['training']['epochs'],
batch_size=configs['training']['batch_size'],
steps_per_epoch=steps_per_epoch,
save_dir=configs['model']['save_dir'])
x_test, y_test = data.get_test_data(
seq_len=configs['data']['sequence_length'],
normalise=configs['data']['normalise'])
predictions = model.predict_sequences_multiple(
x_test, configs['data']['sequence_length'],
configs['data']['sequence_length'])
#predictions = model.predict_sequence_full(x_test, configs['data']['sequence_length'], configs['data']['sequence_length'])
#predictions = model.predict_point_by_point(x_test)
plot_results_multiple(predictions, y_test,
configs['data']['sequence_length'])
#plot_results(predictions, y_test)
input("Press Enter to continue...")
def main():
configs = json.load(open('config.json', 'r'))
#create folder for save model params
if not os.path.exists(configs['model']['save_dir']): os.makedirs(configs['model']['save_dir'])
data = DataLoader(
os.path.join('data', configs['data']['filename']),
configs['data']['train_test_split'],
configs['data']['columns']
)
#plot true data
#plot_results(data.data_train,True)
#train model
model = Model()
model.build_model(configs)
x, y = data.get_train_data(
seq_len=configs['data']['sequence_length'],
normalise=configs['data']['normalise']
)
steps_per_epoch = math.ceil((data.len_train - configs['data']['sequence_length']) / configs['training']['batch_size'])
model.train_generator(
data_gen=data.generate_train_batch(
seq_len=configs['data']['sequence_length'],
batch_size=configs['training']['batch_size'],
normalise=configs['data']['normalise']
),
epochs=configs['training']['epochs'],
batch_size=configs['training']['batch_size'],
steps_per_epoch=steps_per_epoch,
save_dir=configs['model']['save_dir']
)
x_test, y_test = data.get_test_data(
seq_len=configs['data']['sequence_length'],
normalise=configs['data']['normalise']
)
predictions = model.predict_point_by_point(x_test)
# plot_results(predictions, y_test)
# print (predictions)
# plot_results(predictions, y_test)
data1 = pd.DataFrame(predictions)
data1.to_csv('predict.csv')
data2 = pd.DataFrame(y_test)
data2.to_csv('true.csv')
def main(model_name=None):
configs = json.load(open('config.json', 'r'))
if not os.path.exists(configs['model']['save_dir']):
os.makedirs(configs['model']['save_dir'])
data = DataLoader(os.path.join('data', configs['data']['filename']),
configs['data']['train_test_split'],
configs['data']['columns'])
model = Model()
if model_name:
saved_model = os.path.join(configs['model']['save_dir'], model_name)
model.load_model(saved_model)
else:
model.build_model(configs)
x, y = data.get_train_data(seq_len=configs['data']['sequence_length'],
normalise=configs['data']['normalise'])
'''
# in-memory training
model.train(
x,
y,
epochs = configs['training']['epochs'],
batch_size = configs['training']['batch_size'],
save_dir = configs['model']['save_dir']
)
'''
# out-of memory generative training
steps_per_epoch = math.ceil(
(data.len_train - configs['data']['sequence_length']) /
configs['training']['batch_size'])
if not model_name:
model.train_generator(data_gen=data.generate_train_batch(
seq_len=configs['data']['sequence_length'],
batch_size=configs['training']['batch_size'],
normalise=configs['data']['normalise']),
epochs=configs['training']['epochs'],
batch_size=configs['training']['batch_size'],
steps_per_epoch=steps_per_epoch,
save_dir=configs['model']['save_dir'])
x_test, y_test = data.get_test_data(
seq_len=configs['data']['sequence_length'],
normalise=configs['data']['normalise'])
predictions = model.predict_sequences_multiple(
x_test, configs['data']['sequence_length'],
configs['data']['sequence_length'])
plot_results_multiple(predictions, y_test,
configs['data']['sequence_length'])
def main():
configs = json.load(open('config.json', 'r'))
if not os.path.exists(configs['model']['save_dir']): os.makedirs(configs['model']['save_dir'])
data = DataLoader(
os.path.join('data', configs['data']['filename']),
configs['data']['train_test_split'],
configs['data']['columns']
)
model = Model()
model.build_model(configs)
x, y = data.get_train_data(
seq_len=configs['data']['sequence_length'],
normalise=configs['data']['normalise']
)
'''
# in-memory training
model.train(
x,
y,
epochs = configs['training']['epochs'],
batch_size = configs['training']['batch_size'],
save_dir = configs['model']['save_dir']
)
'''
# out-of memory generative training
steps_per_epoch = math.ceil((data.len_train - configs['data']['sequence_length']) / configs['training']['batch_size'])
model.train_generator(
data_gen=data.generate_train_batch(
seq_len=configs['data']['sequence_length'],
batch_size=configs['training']['batch_size'],
normalise=configs['data']['normalise']
),
epochs=configs['training']['epochs'],
batch_size=configs['training']['batch_size'],
steps_per_epoch=steps_per_epoch,
save_dir=configs['model']['save_dir']
)
x_test, y_test = data.get_test_data(
seq_len=configs['data']['sequence_length'],
normalise=configs['data']['normalise']
)
predictions = model.predict_sequences_multiple(x_test, configs['data']['sequence_length'], configs['data']['sequence_length'])
# predictions = model.predict_sequence_full(x_test, configs['data']['sequence_length'])
# predictions = model.predict_point_by_point(x_test)
plot_results_multiple(predictions, y_test, configs['data']['sequence_length'])
def main():
configs = json.load(open('config.json', 'r'))
data = DataLoader(
os.path.join('data', configs['data']['filename']),
configs['data']['train_test_split'],
configs['data']['columns']
)
model = Model()
model.build_model(configs)
x, y = data.get_train_data(
seq_len=configs['data']['sequence_length'],
normalise=configs['data']['normalise']
)
'''
# in-memory training
model.train(
x,
y,
epochs = configs['training']['epochs'],
batch_size = configs['training']['batch_size']
)
'''
# out-of memory generative training
# math.ceil(所有窗的个数 / batch_size)
steps_per_epoch = math.ceil((data.len_train - configs['data']['sequence_length']) / configs['training']['batch_size'])
model.train_generator(
data_gen=data.generate_train_batch(
seq_len=configs['data']['sequence_length'],
batch_size=configs['training']['batch_size'],
normalise=configs['data']['normalise']
),
epochs=configs['training']['epochs'],
batch_size=configs['training']['batch_size'],
steps_per_epoch=steps_per_epoch
)
x_test, y_test = data.get_test_data(
seq_len=configs['data']['sequence_length'],
normalise=configs['data']['normalise']
)
# predictions = model.predict_sequences_multiple(x_test, configs['data']['sequence_length'], configs['data']['sequence_length'])
predictions = model.predict_sequence_full(x_test, configs['data']['sequence_length'])
# predictions = model.predict_point_by_point(x_test)
# plot_results_multiple(predictions, y_test, configs['data']['sequence_length'])
plot_results(predictions, y_test)
def main():
configs = json.load(open('config.json', 'r'))
if not os.path.exists(configs['model']['save_dir']):
os.makedirs(configs['model']['save_dir'])
data = DataLoader(os.path.join('data', configs['data']['filename']),
configs['data']['train_test_split'],
configs['data']['columns'])
model = Model()
model.build_model(configs)
x, y = data.get_train_data(seq_len=configs['data']['sequence_length'],
normalise=configs['data']['normalise'])
'''
# in-memory training
model.train(
x,
y,
epochs = configs['training']['epochs'],
batch_size = configs['training']['batch_size'],
save_dir = configs['model']['save_dir']
)
'''
# out-of memory generative training
steps_per_epoch = math.ceil(
(data.len_train - configs['data']['sequence_length']) /
configs['training']['batch_size'])
model.train_generator(data_gen=data.generate_train_batch(
seq_len=configs['data']['sequence_length'],
batch_size=configs['training']['batch_size'],
normalise=configs['data']['normalise']),
epochs=configs['training']['epochs'],
batch_size=configs['training']['batch_size'],
steps_per_epoch=steps_per_epoch,
save_dir=configs['model']['save_dir'],
configs=configs)
x_test, y_test, p0 = data.get_test_data(
seq_len=configs['data']['sequence_length'],
normalise=configs['data']['normalise'])
# predictions = model.predict_sequences_multiple(x_test, configs['data']['sequence_length'], configs['data']['sequence_length'])
# predictions = model.predict_sequence_full(x_test, configs['data']['sequence_length'])
predictions = model.predict_point_by_point(x_test)
y_test = np.reshape(np.copy(y_test), -1)
plot_results((p0 * (predictions + 1))[-200:], (p0 * (y_test + 1))[-200:])
measure_performance(predictions, y_test)
def main():
configs = json.load(open('config.json', 'r'))
if not os.path.exists(configs['model']['save_dir']): os.makedirs(configs['model']['save_dir'])
data = DataLoader(
os.path.join('data', configs['data']['filename']),
configs['data']['train_test_split'],
configs['data']['columns']
)
model = Model()
model.build_model(configs)
x, y = data.get_train_data(
seq_len=configs['data']['sequence_length'],
normalise=configs['data']['normalise']
)
'''
# in-memory training
model.train(
x,
y,
epochs = configs['training']['epochs'],
batch_size = configs['training']['batch_size'],
save_dir = configs['model']['save_dir']
)
'''
# out-of memory generative training
steps_per_epoch = math.ceil((data.len_train - configs['data']['sequence_length']) / configs['training']['batch_size'])
model.train_generator(
data_gen=data.generate_train_batch(
seq_len=configs['data']['sequence_length'],
batch_size=configs['training']['batch_size'],
normalise=configs['data']['normalise']
),
epochs=configs['training']['epochs'],
batch_size=configs['training']['batch_size'],
steps_per_epoch=steps_per_epoch,
save_dir=configs['model']['save_dir']
)
x_test, y_test, onedot = data.get_test_data(
seq_len=configs['data']['sequence_length'],
normalise=configs['data']['normalise']
)
#predictions = model.predict_sequences_multiple(x_test, configs['data']['sequence_length'], configs['data']['sequence_length'])
#predictions = model.predict_sequence_full(x_test, configs['data']['sequence_length'])
predictions = model.predict_point_by_point(onedot)
with open('output.txt', 'w') as f:
f.write('预测下一时间的螺栓螺母消耗量为：' + str(int((predictions[-1] + 1) * data.last_raw_data(seq_len=configs['data']['sequence_length']))))
def main():
configs = json.load(open(CONFIG, 'r'))
data = DataLoader(DATA, configs['data']['train_test_split'],
configs['data']['columns'])
model = Model()
model.build_model(configs)
x, y = data.get_train_data(seq_len=configs['data']['sequence_length'],
normalise=configs['data']['normalise'])
'''
# in-memory training
model.train(
x,
y,
epochs = configs['training']['epochs'],
batch_size = configs['training']['batch_size']
)
'''
# out-of memory generative training
steps_per_epoch = math.ceil(
(data.len_train - configs['data']['sequence_length']) /
configs['training']['batch_size'])
model.train_generator(data_gen=data.generate_train_batch(
seq_len=configs['data']['sequence_length'],
batch_size=configs['training']['batch_size'],
normalise=configs['data']['normalise']),
epochs=configs['training']['epochs'],
batch_size=configs['training']['batch_size'],
steps_per_epoch=steps_per_epoch,
model_path=MODEL)
x_test, y_test = data.get_test_data(
seq_len=configs['data']['sequence_length'],
normalise=configs['data']['normalise'])
predictions = model.predict_sequences_multiple(
x_test, configs['data']['sequence_length'],
configs['data']['sequence_length'])
#predictions = model.predict_sequence_full(x_test, configs['data']['sequence_length'])
#predictions = model.predict_point_by_point(x_test)
plot_results_multiple(predictions, y_test,
configs['data']['sequence_length'])
#plot_results(predictions, y_test)
sys.stdout.write("--END--")
def main():
configs = json.load(open('config.json', 'r'))
if not os.path.exists(configs['model']['save_dir']):
os.makedirs(configs['model']['save_dir'])
data = DataLoader(os.path.join('data', configs['data']['filename']),
configs['data']['train_test_split'],
configs['data']['columns'])
model = Model()
model.build_model(configs)
x, y = data.get_train_data(seq_len=configs['data']['sequence_length'],
normalise=configs['data']['normalise'])
'''
# in-memory training (heavier computation)
model.train(
x,
y,
epochs = configs['training']['epochs'],
batch_size = configs['training']['batch_size'],
save_dir = configs['model']['save_dir']
)
'''
# out-of memory generative training
steps_per_epoch = math.ceil(
(data.len_train - configs['data']['sequence_length']) /
configs['training']['batch_size'])
model.train_generator(data_gen=data.generate_train_batch(
seq_len=configs['data']['sequence_length'],
batch_size=configs['training']['batch_size'],
normalise=configs['data']['normalise']),
epochs=configs['training']['epochs'],
batch_size=configs['training']['batch_size'],
steps_per_epoch=steps_per_epoch,
save_dir=configs['model']['save_dir'])
x_test, y_test = data.get_test_data(
seq_len=configs['data']['sequence_length'],
normalise=configs['data']['normalise'])
#predictions are made point by point with model.predict_point_by_point
predictions = model.predict_point_by_point(x_test)
plot_results(predictions, y_test)
def main():
configs = json.load(open('config.json', 'r'))
if not os.path.exists(configs['model']['save_dir']):
os.makedirs(configs['model']['save_dir'])
dataframe = pd.read_csv(configs['data']['filename'])
f = open('/Users/yucheng/Downloads/project2/stockIDs.txt', 'r')
stockIDs = [int(line.split('\n')[0]) for line in f.readlines()]
for id in stockIDs[377:378]:
# for id in stockIDs[444:500]:
print("index: ", stockIDs.index(id))
data = DataLoader(dataframe, id, configs['data']['train_test_split'],
configs['data']['columns'])
model = Model()
model.build_model(configs)
x, y = data.get_train_data(seq_len=configs['data']['sequence_length'],
normalise=configs['data']['normalise'])
'''
# in-memory training
model.train(
x,
y,
epochs = configs['training']['epochs'],
batch_size = configs['training']['batch_size'],
save_dir = configs['model']['save_dir']
)
'''
# out-of memory generative training
steps_per_epoch = math.ceil(
(data.len_train - configs['data']['sequence_length']) /
configs['training']['batch_size'])
model.train_generator(id=id,
data_gen=data.generate_train_batch(
seq_len=configs['data']['sequence_length'],
batch_size=configs['training']['batch_size'],
normalise=configs['data']['normalise']),
epochs=configs['training']['epochs'],
batch_size=configs['training']['batch_size'],
steps_per_epoch=steps_per_epoch,
save_dir=configs['model']['save_dir'])
plt.show()
# %% Build/Train the model
model = Model()
model.build_model(configs)
# out-of memory generative training
steps_per_epoch = math.ceil(
(data.len_train - configs['data']['sequence_length']) /
configs['training']['batch_size'])
model.train_generator(data_gen=data.generate_train_batch(
seq_len=configs['data']['sequence_length'],
batch_size=configs['training']['batch_size'],
normalise=configs['data']['normalise']),
epochs=configs['training']['epochs'],
batch_size=configs['training']['batch_size'],
steps_per_epoch=steps_per_epoch,
save_dir=configs['model']['save_dir'])
x_test, y_test = data.get_test_data(seq_len=configs['data']['sequence_length'],
normalise=configs['data']['normalise'])
predictions = model.predict_sequences_multiple(
x_test, configs['data']['sequence_length'],
configs['data']['sequence_length'])
plot_results_multiple(predictions, y_test, configs['data']['sequence_length'])
def main():
configs = json.load(open('config.json', 'r'))
if not os.path.exists(configs['model']['save_dir']):
os.makedirs(configs['model']['save_dir'])
data = DataLoader(os.path.join('data', configs['data']['filename']),
configs['data']['train_test_split'],
configs['data']['columns'])
model = Model()
# model.build_model(configs)
model.load_model("saved_models/dow_30_50%.h5")
x, y = data.get_train_data(seq_len=configs['data']['sequence_length'],
normalise=configs['data']['normalise'])
# out-of memory generative training
steps_per_epoch = math.ceil(
(data.len_train - configs['data']['sequence_length']) /
configs['training']['batch_size'])
model.train_generator(data_gen=data.generate_train_batch(
seq_len=configs['data']['sequence_length'],
batch_size=configs['training']['batch_size'],
normalise=configs['data']['normalise']),
epochs=configs['training']['epochs'],
batch_size=configs['training']['batch_size'],
steps_per_epoch=steps_per_epoch,
save_dir=configs['model']['save_dir'])
x_test, y_test = data.get_test_data(
seq_len=configs['data']['sequence_length'],
normalise=configs['data']['normalise'])
print("x_test.shape")
print(x_test.shape)
predictions = model.predict_point_by_point(x_test)
########################################################################
from sklearn.metrics import mean_squared_error
# loss_final = mean_squared_error(predictions, y_test)
# print("Testing Loss = " + str(loss_final))
########################################################################
# plot_results_multiple(predictions, y_test, configs['data']['sequence_length'])
print(predictions.shape)
print(y_test.shape)
m = pd.DataFrame(predictions)
n = pd.DataFrame(y_test)
m.to_csv("predictions.csv")
n.to_csv("y_test.csv")
p = 0
t = 0
t_1 = 0
count = 0
for a in range(len(predictions)):
if (a == 0):
t_1 = y_test[a]
continue
'''
1 1 1 1 1 1 1 1 1
1 1 1 1 1 1 1 1 1
'''
p = predictions[a]
t = y_test[a]
match = (t - t_1) * (p - t_1)
if (match > 0):
count += 1
t_1 = t
print("Good prediction rate = " + str(count / len(predictions)))
plot_results(predictions, y_test)
def main():
configs = json.load(open('config.json', 'r'))
if not os.path.exists(configs['model']['save_dir']):
os.makedirs(configs['model']['save_dir'])
if not os.path.exists(configs['data']['data picture save dir']):
os.makedirs(configs['data']['data picture save dir'])
data = DataLoader(os.path.join('data', configs['data']['filename']),
configs['data']['train_test_split'],
configs['data']['columns'], configs['data']['id'])
model = Model()
model.build_model(configs)
# x, y = data.get_train_data(
# seq_len=configs['data']['sequence_length'],
# normalise=configs['data']['normalise']
# )
'''
# in-memory training
model.train(
x,
y,
epochs = configs['training']['epochs'],
batch_size = configs['training']['batch_size'],
save_dir = configs['model']['save_dir']
)
'''
# out-of memory generative training
steps_per_epoch = math.ceil(
(data.len_train - configs['data']['sequence_length']) /
configs['training']['batch_size'])
model.train_generator(data_gen=data.generate_train_batch(
seq_len=configs['data']['sequence_length'],
batch_size=configs['training']['batch_size'],
normalise=configs['data']['normalise']),
epochs=configs['training']['epochs'],
batch_size=configs['training']['batch_size'],
steps_per_epoch=steps_per_epoch,
save_dir=configs['model']['save_dir'])
x_test, y_test = data.get_test_data(
seq_len=configs['data']['sequence_length'],
normalise=configs['data']['normalise'])
#predictions = model.predict_sequences_multiple(x_test, configs['data']['sequence_length'], configs['data']['sequence_length'])
# predictions = model.predict_sequence_full(x_test, configs['data']['sequence_length'])
predictions = model.predict_point_by_point(x_test)
sess = backend.get_session()
rmsee = backend.mean(rmse(y_test, predictions), axis=0)
msee = backend.mean(mse(y_test, predictions), axis=0)
with sess.as_default():
mse_val = msee.eval()
rmse_val = rmsee.eval()
print("mse:", mse_val)
print("rmse:", rmse_val)
#plot_results_multiple(predictions, y_test, configs['data']['sequence_length'])
plot_results(predictions, y_test, configs['data']['data picture save dir'],
configs['data']['id'])
with open("note.txt", 'a+') as f:
f.write(
'\n%s-e%s.h5:\n' %
(dt.datetime.now().strftime('%m%d-%H%M%S'), configs['data']['id']))
f.write("data split:%f\n" % configs["data"]["train_test_split"])
f.write("epochs:%d\n" % configs["training"]["epochs"])
f.write("batch size:%d\n" % configs["training"]["batch_size"])
f.write("mse:%f\n" % mse_val)
f.write("rmse:%f\n" % rmse_val)
f.write("notes:%s\n" % configs['data']['note'])
def main():
# instantiation
data = DataLoader(os.path.join('data', configs['data']['filename']),
configs['data']['train_test_split'],
configs['data']['columns'])
model = Model()
model.build_model(configs)
x, y = data.get_train_data(seq_len=configs['data']['sequence_length'],
normalise=configs['data']['normalise'])
'''
# in-memory training
model.train(
x,
y,
epochs = configs['training']['epochs'],
batch_size = configs['training']['batch_size']
)
'''
# out-of memory generative training
# 不懂为什么要自己算这个，LSTM不是自己自带batch参数吗，为什么要自己算出来一共要输多少次batch？？？
# 会出现：
# in data_generator_task， generator_output = next(self._generator)， StopIteration
# in fit_generator， str(generator_output))
# output of generator should be a tuple `(x, y, sample_weight)` or `(x, y)`. Found: None
# 所以出错的时候，手动减少steps_per_epoch
steps_per_epoch = math.ceil(
(data.len_train - configs['data']['sequence_length']) /
configs['training']['batch_size']) - 7
model.train_generator(data_gen=data.generate_train_batch(
seq_len=configs['data']['sequence_length'],
batch_size=configs['training']['batch_size'],
normalise=configs['data']['normalise']),
epochs=configs['training']['epochs'],
batch_size=configs['training']['batch_size'],
steps_per_epoch=steps_per_epoch)
x_test, y_test = data.get_test_data(
seq_len=configs['data']['sequence_length'],
normalise=configs['data']['normalise'])
predictions = model.predict_sequences_multiple(
x_test, configs['data']['sequence_length'],
configs['data']['sequence_length'])
plot_results_multiple(predictions, y_test,
configs['data']['sequence_length'])
# predictions = model.predict_sequence_full(x_test, configs['data']['sequence_length'])
# predictions = model.predict_point_by_point(x_test)
y_true_train, y_true_test = data.get_split_data()
unnorm_data = predict_unnorm_data(
y_true_test,
prediction_len=configs['data']['sequence_length'],
predictions=predictions)
# 计算RMSE并输出dataframe
begin_date = datetime(year=2018, month=9, day=18)
end_date = begin_date + timedelta(
days=(configs['data']['sequence_length'] - 1))
# y_true_test：（301，2）
y_true_test = pd.DataFrame(y_true_test)
file = pd.read_csv(os.path.join('data', configs['data']['filename']))
file = file['time'][len(y_true_train):]
file = pd.Series(file)
# 出现了无法新建列并赋值的error
# 因为dataframe和Series都有自己的index，.values才能取到真正的值并赋给下一个变量
y_true_test['time'] = file.values
y_true_test = y_true_test.set_index('time')
y_true_test.index = pd.to_datetime(y_true_test.index)
calc_RMSE(predicted_data=unnorm_data,
y_test_true=y_true_test,
begin_date=begin_date,
end_date=end_date)
def main():
config_path = 'config/config.json'
with open(config_path, 'r') as f:
configs = json.load(f)
logging.info("Loaded {}".format(config_path))
logging.info("\n{}\n".format(configs))
data_path = configs['data']['filename']
data_dir = os.path.dirname(data_path)
dtypes = configs['data'].get('dtypes', None)
windowed_normalization = configs['data']['normalise']
data = DataLoader(data_path,
configs['data']['train_test_split'],
configs['data']['columns'],
scaler_path=os.path.join(data_dir, "scaler"),
windowed_normalization=windowed_normalization,
dtypes=dtypes)
model = Model()
if configs['model'].get('load_model'):
model_path = os.path.join(configs['model']['load_model'])
logging.info("Loading {}".format(model_path))
model.load_model(model_path, configs)
plot_dir = os.path.join(os.path.dirname(model_path), "plots")
os.makedirs(plot_dir, exist_ok=True)
else:
plot_dir = os.path.join(configs['model']['save_dir'], "plots")
os.makedirs(plot_dir, exist_ok=True)
model.build_model(configs)
x, y = data.get_train_data(
seq_len=configs['data']['sequence_length'],
windowed_normalization=windowed_normalization)
'''
# in-memory training
model.train(
x,
y,
epochs = configs['training']['epochs'],
batch_size = configs['training']['batch_size'],
save_dir = configs['model']['save_dir']
)
'''
# out-of-memory generative training
steps_per_epoch = math.ceil(
(data.len_train - configs['data']['sequence_length']) /
configs['training']['batch_size'])
model.train_generator(data_gen=data.generate_train_batch(
seq_len=configs['data']['sequence_length'],
batch_size=configs['training']['batch_size'],
windowed_normalization=windowed_normalization),
epochs=configs['training']['epochs'],
batch_size=configs['training']['batch_size'],
steps_per_epoch=steps_per_epoch,
save_dir=configs['model']['save_dir'])
x_test, y_test = data.get_test_data(
seq_len=configs['data']['sequence_length'],
windowed_normalization=windowed_normalization)
predictions_multiple = model.predict_sequences_multiple(
x_test, configs['data']['sequence_length'],
configs['data']['sequence_length'])
plot_results_multiple(predictions_multiple,
y_test,
configs['data']['sequence_length'],
out_path=os.path.join(plot_dir, "multiple.png"))
def lstm(sTicker, postn, sFile, file_to_save):
configs = json.load(open('config.json', 'r'))
# print("hello")
# "How can I safely create a nested directory in Python?"
# stackoverflow.com/questions/273192/how-can-i-safely-create-a-nested-directory-in-python
if not os.path.exists(configs['model']['save_dir']):
os.makedirs(configs['model']['save_dir'])
data = DataLoader(os.path.join(os.getcwd(), file_to_save),
configs['data']['train_test_split'],
configs['data']['columns'])
try:
model = Model()
model.build_model(configs)
x, y = data.get_train_data(
seq_len=configs['data']['sequence_length'],
normalise=configs['data']['normalise'])
# out-of memory generative training
steps_per_epoch = math.ceil(
(data.len_train - configs['data']['sequence_length']) /
configs['training']['batch_size'])
model.train_generator(data_gen=data.generate_train_batch(
seq_len=configs['data']['sequence_length'],
batch_size=configs['training']['batch_size'],
normalise=configs['data']['normalise']),
epochs=configs['training']['epochs'],
batch_size=configs['training']['batch_size'],
steps_per_epoch=steps_per_epoch,
save_dir=configs['model']['save_dir'],
file_name=sTicker)
x_test, y_test = data.get_test_data(
seq_len=configs['data']['sequence_length'],
normalise=configs['data']['normalise'])
predictions = model.predict_sequences_multiple(
x_test, configs['data']['sequence_length'],
configs['data']['sequence_length'])
# predictions = model.predict_sequence_full(x_test, configs['data']['sequence_length'])
# predictions = model.predict_point_by_point(x_test)
prediction_data = predictions[-1:]
prediction_data = prediction_data[0]
normalizer = data.data_test[-50, [0]]
# print(normalizer)
finaloutput = []
# print(prediction_data)
for i in range(len(prediction_data)):
finaloutput.append((prediction_data[i] + 1) * normalizer[0])
# print(finaloutput)
numpyFinal = np.array(finaloutput)
save_future(sTicker, numpyFinal)
plot_results_triple(sFile, finaloutput, file_to_save, sTicker,
predictions, y_test,
configs['data']['sequence_length'])
# plot_results_multiple(sTicker, predictions, y_test, configs['data']['sequence_length'])
# plot_results(sTicker, predictions, y_test)
totalDiff = [0] * len(predictions[0])
for x in range(0, 49):
y = y_test[(len(y_test) - 49) +
x] - predictions[len(predictions) - 1][x]
if y < 0.0:
y *= -1
totalDiff[x] = y
stdDev = float(np.std(totalDiff, 0))
nPred = predictions[len(predictions) - 1]
closeVal1 = pd.read_csv('stock_market_data.csv')
closeVal2 = closeVal1['Close']
closeVal3 = closeVal2[len(closeVal2) - 1]
avgPerc = 0
for deviate in nPred:
avgPerc += float(deviate)
divisor = len(nPred)
nMod1 = avgPerc / divisor
latPerc = nPred[len(nPred) - 1] - nPred[len(nPred) - 2]
nMod2 = nMod1 + 1
nMod3 = latPerc + 1
dPred1 = closeVal3 * nMod2
dPred2 = closeVal3 * nMod3
sFile['price_latest'][postn] = "{0:.2f}".format(closeVal3)
sFile['percent_change_avg'][postn] = "{0:.6f}".format(nMod1)
sFile['percent_change_latest'][postn] = "{0:.6f}".format(latPerc)
sFile['prediction_by_avg'][postn] = "{0:.2f}".format(dPred1)
sFile['prediction_by_latest'][postn] = "{0:.2f}".format(dPred2)
sFile['standard_deviation'][postn] = "{0:.6f}".format(stdDev)
except:
sFile['price_latest'][postn] = "n/a"
sFile['percent_change_avg'][postn] = "n/a"
sFile['percent_change_latest'][postn] = "n/a"
sFile['prediction_by_avg'][postn] = "n/a"
sFile['prediction_by_latest'][postn] = "n/a"
sFile['standard_deviation'][postn] = "n/a"
updatedFile = pd.DataFrame({
'stock_ticker':
sFile['stock_ticker'],
'percent_change_avg':
sFile['percent_change_avg'],
'percent_change_latest':
sFile['percent_change_latest'],
'prediction_by_avg':
sFile['prediction_by_avg'],
'prediction_by_latest':
sFile['prediction_by_latest'],
'price_latest':
sFile['price_latest'],
'standard_deviation':
sFile['standard_deviation']
})
updatedFile.to_csv("stock_performance.csv", index=False, header=True)
