plt.plot(list(range(num_train)), train_x, color='b', label='training data')
plt.plot(list(range(num_train + len(valid), num_train + len(valid) + len(test))), test, color='y', label='predicted')
plt.plot(list(range(num_train, num_train + len(valid))), valid, color='g', label='test data')
plt.plot(list(range(num_train + len(valid), num_train + len(valid) + len(predictions))), predictions, color='r', label='predicted')
plt.legend()
#if filename is not None:
# plt.savefig(filename)
#else:
plt.show()
if __name__ == '__main__':
seq_size = 20
##Performing all the data operations
predictor = SeriesPredictor(input_dim = 1, seq_size = seq_size, hidden_dim = 100)
data = data_loader.load_series('datanew.csv')
train_data, valid_data, test_data = data_loader.split_data(data)
'''
print("How Train data looks like")
for i in range(10):
print(train_data[i])
'''
##Here we are making the data s.t the output at every time step is the value for the next time-step
train_x, train_y = [], []
for i in range(len(train_data) - seq_size - 1):
##Expand_dims is used since we have to feed the network with an input that has first dimension as batch_size, second dimension as seq_length and third
##dimension as input_dim
##The first dimension is fulfilled by appending many lists to train_x, third dimension is fulfilled by using expand_dims
label='predicted')
plt.plot(list(range(num_train, num_train + len(actual))),
actual,
color='g',
label='test data')
plt.legend() # 图例
if filename is not None:
plt.savefig(filename)
else:
plt.show()
if __name__ == '__main__':
seq_size = 5
predictor = SeriesPredictor(input_dim=1, seq_size=seq_size, hidden_dim=100)
data = data_loader.load_series('international-airline-passengers.csv')
train_data, actual_vals = data_loader.split_data(data)
train_x, train_y = [], []
# for i in range(len(train_data) - seq_size - 1): # num - window_size + 1
for i in range(len(train_data) - seq_size):
train_x.append(
np.expand_dims(
train_data[i:i + seq_size],
axis=1).tolist()) # shape=(batch, seq_size, input_dim)
train_y.append(train_data[i + 1:i + seq_size + 1])
test_x, test_y = [], []
# for i in range(len(actual_vals) - seq_size - 1):
for i in range(len(actual_vals) - seq_size):
# temp = np.expand_dims(actual_vals[i:i + seq_size], axis=1) # shape=(5, 1)
plt.figure()
num_train = len(train_x)
plt.plot(list(range(num_train)), train_x, color='b', label='training data')
plt.plot(list(range(num_train, num_train + len(predictions))), predictions, color='r', label='predicted')
plt.plot(list(range(num_train, num_train + len(actual))), actual, color='g', label='test data')
plt.legend()
if filename is not None:
plt.savefig(filename)
else:
plt.show()
if __name__ == '__main__':
seq_size = 5
predictor = SeriesPredictor(input_dim=1, seq_size=seq_size, hidden_dim=5)
data = data_loader.load_series('international-airline-passengers.csv')
train_data, actual_vals = data_loader.split_data(data)
train_x, train_y = [], []
for i in range(len(train_data) - seq_size - 1):
train_x.append(np.expand_dims(train_data[i:i+seq_size], axis=1).tolist())
train_y.append(train_data[i+1:i+seq_size+1])
test_x, test_y = [], []
for i in range(len(actual_vals) - seq_size - 1):
test_x.append(np.expand_dims(actual_vals[i:i+seq_size], axis=1).tolist())
test_y.append(actual_vals[i+1:i+seq_size+1])
predictor.train(train_x, train_y, test_x, test_y)
with tf.Session() as sess:
color='r',
label='predicted')
plt.plot(list(range(num_train, num_train + len(actual))),
actual,
color='g',
label='test data')
plt.legend()
plt.show()
if __name__ == '__main__':
mode = 2 #0训练 1继续训练 2看结果
seq_size = 60
predictor = SeriesPredictor(input_dim=5, seq_size=seq_size, hidden_dim=50)
data = data_loader.load_series('data_test.txt')
train_data, actual_vals, sample = data_loader.split_data(data, seq_size)
# print(train_data)
# print(np.shape(train_data))
train_x, train_y = [], []
for i in range(len(train_data) - seq_size - 1):
train_x.append(train_data[i:i + seq_size])
train_y.append(train_data[i + seq_size + 1])
# print(np.shape(train_x),np.shape(train_y))
# print(train_y)
# print(np.shape(train_y))
test_x, test_y = [], []
for i in range(len(actual_vals) - seq_size - 1):
test_x.append(actual_vals[i:i + seq_size])
test_y.append(actual_vals[i + seq_size + 1])
# Idk why its changing file_increment_num in gz_unzip, it shouldnt, and even though i put a placeholder it still does
channel_converted_value, channel_last_timestamp = create_lists_ccv_clt(
file_increment_num, 27)
channel_last_datetime = unix_timestamp_to_datetime(channel_last_timestamp)
"""
f = open('clt_ccv.csv', 'w')
for x,y in zip(channel_last_timestamp,channel_converted_value):
f.write(str(x) + "," + str(y) +'\n')
f.close()
"""
seq_size = 5
predictor = SeriesPredictor(input_dim=1, seq_size=seq_size, hidden_dim=100)
data = data_loader.load_series('2_ccv_clt.csv')
train_data, actual_vals = data_loader.split_data(data)
reconditioned_data = data_loader.recondition_data(data)
train_data_reconditioned, actual_vals_reconditioned = data_loader.split_data(
reconditioned_data)
train_data, actual_vals = data_loader.split_data(data)
train_x, train_y = [], []
for i in range(len(train_data) - seq_size - 1):
train_x.append(
np.expand_dims(train_data[i:i + seq_size], axis=1).tolist())
train_y.append(train_data[i + 1:i + seq_size + 1])
test_x, test_y = [], []
for i in range(len(actual_vals) - seq_size - 1):