I have dataframe as following for time series where SETTLEMENTDATE
is index. I want to take first row, i.e 2018-11-01 14:30:00
and values of T_1
, T_2
, T_3
, T_4
, T_5
, T_6
as a sequence and predict sequence of DE_1
, DE_2
, DE_3
, DE_4
.
I am using keras for Sequence to sequence time series using LSTM. I tried to take T_1
to T_6
as input dataframe 'X'
and DE_1
to DE_4
as output dataframe 'y'
. I reshaped it using X = np.array(X)
y = np.array(y)
and then X = X.reshape(4,6,1)
and y = y.reshape(4,4,1)
to feed to batch_input_shape()
but it does not work.
How to get data in proper shape to feed to LSTM layer?
T_1 T_2 T_3 T_4 T_5 T_6 DE_1 DE_2 DE_3 DE_4
SETTLEMENTDATE
2018-11-01 14:30:00 1645.82 1623.23 1619.09 1581.94 1538.20 1543.48 1624.23 1722.85 1773.77 1807.04
2018-11-01 15:00:00 1628.60 1645.82 1623.23 1619.09 1581.94 1538.20 1722.85 1773.77 1807.04 1873.53
2018-11-01 15:30:00 1624.23 1628.60 1645.82 1623.23 1619.09 1581.94 1773.77 1807.04 1873.53 1889.06
2018-11-01 16:00:00 1722.85 1624.23 1628.60 1645.82 1623.23 1619.09 1807.04 1873.53 1889.06 1924.57