Open GaryCooper23 opened 1 year ago
Currently I am trying to load the data separately:
# load custom price data
data_close = pd.read_csv('data/EURUSD_M1_202208_CLOSE.csv', encoding= 'unicode_escape')
prices = data_close
data_indicator = pd.read_csv('data/EURUSD_M1_202208_INDICATOR.csv', encoding= 'unicode_escape')
inputs = data_indicator
Dear Dylon, many thanks for providing us your skeleton!
Unfortunately I have problems to feed this with real stock market data. I am currently trying from a csv file. In doing so, I get various errors from pandas and also from tensorflow:
-> base.py", line 3800, in get_loc return self._engine.get_loc(casted_key)
-> WARNING:tensorflow:Model was constructed with shape (None, 4) for input KerasTensor(type_spec=TensorSpec(shape=(None, 4), dtype=tf.float32, name='dense_input'), name='dense_input', description="created by layer 'dense_input'"), but it was called on an input with incompatible shape (None,).
What was your idea behind the values "prices" and "inputs"? As values I try to take the close price of 1 minute candles. As inputs I decided to use a trend indicator, which gives a positive or negative value. These data I have currently calculated and entered manually in the CSV file.
Are there any special guidelines that the price of the stock must have?
I have here several CSV files that I would like to use. EURUSD_M1_202208.csv YM_M1_202208.csv