time series foreacsting using lstm

Question

      date        a  b  c  d  e  
      10-01-2020  1  2  3  4  5
df =  11-01-2020  8  5  6  3  7
      12-01-2020  6  4  11 9  8
      13-01-2020  8  7  12 8  7



train_df,test_df = df[1:3], df[3:] 

train = train_df
    scalers={}
    for i in train_df.columns:
    scaler = MinMaxScaler(feature_range=(-1,1))
    s_s = scaler.fit_transform(train[i].values.reshape(-1,1))
    s_s=np.reshape(s_s,len(s_s))
    scalers['scaler_'+ i] = scaler
    train[i]=s_s
test = test_df
for i in train_df.columns:
    scaler = scalers['scaler_'+i]
    s_s = scaler.transform(test[i].values.reshape(-1,1))
    s_s=np.reshape(s_s,len(s_s))
    scalers['scaler_'+i] = scaler
    test[i]=s_s

i am using stacked Lstm to predict the value of next column for each column but i am getting a value error.Value Error: could not convert string to float: '12-01-2020'should i remove the date column or bypass??? or should i use different time series modeling for this problem?

Answer 1

You cannot convert date to float as there is a hyphen in the date string.