'''
PART 1:多個x時間變數用於預測y的時間
但是y不作為x的一份子
'''
# 創造資料
from numpy import array
from numpy import hstack
from keras.models import Sequential
from keras.layers import LSTM
from keras.layers import Dense
# define input sequence
in_seq1 = array([10, 20, 30, 40, 50, 60, 70, 80, 90])
in_seq2 = array([15, 25, 35, 45, 55, 65, 75, 85, 95])
out_seq = array([in_seq1[i]+in_seq2[i] for i in range(len(in_seq1))])
# convert to [rows, columns] structure
in_seq1 = in_seq1.reshape((len(in_seq1), 1))
in_seq2 = in_seq2.reshape((len(in_seq2), 1))
out_seq = out_seq.reshape((len(out_seq), 1))
# horizontally stack columns
dataset = hstack((in_seq1, in_seq2, out_seq))
print(dataset)

'''
[[ 10  15  25]
 [ 20  25  45]
 [ 30  35  65]
 [ 40  45  85]
 [ 50  55 105]
 [ 60  65 125]
 [ 70  75 145]
 [ 80  85 165]
 [ 90  95 185]]

現在定為時間步長為3
舉個例子，就是用
10 15
20 25
30 35
預測65
'''

# split a multivariate sequence into samples
def split_sequences(sequences, n_steps):
	X, y = list(), list()
	for i in range(len(sequences)):
		end_ix = i + n_steps
		if end_ix > len(sequences):
			break
		seq_x, seq_y = sequences[i:end_ix, :-1], sequences[end_ix-1, -1]   # 和單變數最大的不同在這裡
		X.append(seq_x)
		y.append(seq_y)
	return array(X), array(y)
 
n_steps = 3
X,y = split_sequences(dataset,n_steps)
print(X.shape,y.shape)
for i in range(len(X)):
    print(X[i],y[i])

n_features = X.shape[2]
'''
[[10 15]
 [20 25]
 [30 35]] 65
[[20 25]
 [30 35]
 [40 45]] 85
[[30 35]
 [40 45]
 [50 55]] 105
[[40 45]
 [50 55]
 [60 65]] 125
[[50 55]
 [60 65]
 [70 75]] 145
[[60 65]
 [70 75]
 [80 85]] 165
[[70 75]
 [80 85]
 [90 95]] 185
'''

model = Sequential()
model.add(LSTM(50,activation='relu',input_shape=(n_steps,n_features)))
model.add(Dense(1))
model.compile(optimizer='adam',loss='mse')
model.fit(X,y,epochs=200,verbose=0)

#預測模型
x_input = array([[80, 85], [90, 95], [100, 105]])
x_input = x_input.reshape((1, n_steps, n_features))  # 轉換成樣本量+步長+特徵的格式
yhat = model.predict(x_input, verbose=0)
print(yhat)                                          # 209.00851


'''
PART 2:多個x時間變數預測多個X時間變數的下一步
      即平行預測
'''

from numpy import array
from numpy import hstack
 
# split a multivariate sequence into samples
def split_sequences(sequences, n_steps):
	X, y = list(), list()
	for i in range(len(sequences)):
		end_ix = i + n_steps
		if end_ix > len(sequences)-1:
			break
        # 最關鍵的不一樣在這一步
		seq_x, seq_y = sequences[i:end_ix, :], sequences[end_ix, :]
		X.append(seq_x)
		y.append(seq_y)
	return array(X), array(y)
 

in_seq1 = array([10, 20, 30, 40, 50, 60, 70, 80, 90])
in_seq2 = array([15, 25, 35, 45, 55, 65, 75, 85, 95])
out_seq = array([in_seq1[i]+in_seq2[i] for i in range(len(in_seq1))])
in_seq1 = in_seq1.reshape((len(in_seq1), 1))
in_seq2 = in_seq2.reshape((len(in_seq2), 1))
out_seq = out_seq.reshape((len(out_seq), 1))
dataset = hstack((in_seq1, in_seq2, out_seq))
# choose a number of time steps
n_steps = 3
# convert into input/output
X, y = split_sequences(dataset, n_steps)
print(X.shape, y.shape)
# summarize the data
for i in range(len(X)):
	print(X[i], y[i])

'''
[[10 15 25]
 [20 25 45]
 [30 35 65]] [40 45 85]
[[20 25 45]
 [30 35 65]
 [40 45 85]] [ 50  55 105]
[[ 30  35  65]
 [ 40  45  85]
 [ 50  55 105]] [ 60  65 125]
[[ 40  45  85]
 [ 50  55 105]
 [ 60  65 125]] [ 70  75 145]
[[ 50  55 105]
 [ 60  65 125]
 [ 70  75 145]] [ 80  85 165]
[[ 60  65 125]
 [ 70  75 145]
 [ 80  85 165]] [ 90  95 185]
'''
n_features = X.shape[2]
# define stack model
model = Sequential()
model.add(LSTM(100, activation='relu', return_sequences=True, input_shape=(n_steps, n_features)))
model.add(LSTM(100, activation='relu'))
# 和多對一不同點在於，這裡多對多的Dense的神經元=features數目
model.add(Dense(n_features))
model.compile(optimizer='adam', loss='mse')
# fit model
model.fit(X, y, epochs=400, verbose=0)
# demonstrate prediction
x_input = array([[70,75,145], [80,85,165], [90,95,185]])
x_input = x_input.reshape((1, n_steps, n_features))
yhat = model.predict(x_input, verbose=0)
print(yhat)                        # [[100.58976  107.512665 207.87833 ]]