1_prepare_data.py

def PrepareData(days):
  df = init_df.copy()
  df['future'] = df['close'].shift(-days)
  last_sequence = np.array(df[['close']].tail(days))
  df.dropna(inplace=True)
  sequence_data = []
  sequences = deque(maxlen=N_STEPS)

  for entry, target in zip(df[['close'] + ['date']].values, df['future'].values):
      sequences.append(entry)
      if len(sequences) == N_STEPS:
          sequence_data.append([np.array(sequences), target])

  last_sequence = list([s[:len(['close'])] for s in sequences]) + list(last_sequence)
  last_sequence = np.array(last_sequence).astype(np.float32)

  # construct the X's and Y's
  X, Y = [], []
  for seq, target in sequence_data:
      X.append(seq)
      Y.append(target)

  # convert to numpy arrays
  X = np.array(X)
  Y = np.array(Y)

  return df, last_sequence, X, Y