nateemma
commented
1 year ago Hi,
sorry, just saw your email.
This error means that you are passing in a DataFrame that has not been normalized - the default 'date' column is text.
Also, that is an old version that I should have removed. The newer version is NNPredict.py As an aside, there is a family of related strategies called NNPredict_*.py, and NNPredict.py is the base class (and uses an LSTM model as default).
Hope that helps,
Cheers,
Phil
On Wed, Jan 25, 2023 at 7:14 AM Luiz Paulo Nievola @.***> wrote:
model not found (/freqtrade/user_data/treinoscheckpoint.h5)... data:[0:24608] train:[4921:24597] train_result:[4933:24609] test:[0:4918] test_result:[12:4930] 2023-01-25 15:09:04,217 - freqtrade - ERROR - Fatal exception! Traceback (most recent call last): File "/freqtrade/freqtrade/main.py", line 42, in main return_code = args'func' http://args File "/freqtrade/freqtrade/commands/optimize_commands.py", line 58, in start_backtesting backtesting.start() File "/freqtrade/freqtrade/optimize/backtesting.py", line 1335, in start min_date, max_date = self.backtest_one_strategy(strat, data, timerange) File "/freqtrade/freqtrade/optimize/backtesting.py", line 1236, in backtest_one_strategy preprocessed = self.strategy.advise_all_indicators(data) File "/freqtrade/freqtrade/strategy/interface.py", line 1203, in advise_all_indicators return {pair: self.advise_indicators(pair_data.copy(), {'pair': pair}).copy() File "/freqtrade/freqtrade/strategy/interface.py", line 1203, in return {pair: self.advise_indicators(pair_data.copy(), {'pair': pair}).copy() File "/freqtrade/freqtrade/strategy/interface.py", line 1221, in advise_indicators return self.populate_indicators(dataframe, metadata) File "/freqtrade/user_data/strategies/Predict_LSTM.py", line 289, in populate_indicators dataframe = self.train_model(dataframe, self.curr_pair) File "/freqtrade/user_data/strategies/Predict_LSTM.py", line 461, in train_model df_tensor = self.dataframeUtils.df_to_tensor(df_norm, self.seq_len) File "/freqtrade/user_data/strategies/DataframeUtils.py", line 492, in df_to_tensor tensor_arr[row][seq] = data[src_row] TypeError: float() argument must be a string or a real number, not 'Timestamp' ERROR: 1
— Reply to this email directly, view it on GitHub https://github.com/nateemma/strategies/issues/7, or unsubscribe https://github.com/notifications/unsubscribe-auth/ABD4X577NH54VM3ZK7NF2YDWUE7NJANCNFSM6AAAAAAUGOCYQY . You are receiving this because you are subscribed to this thread.Message ID: @.***>
maledicente
model not found (/freqtrade/user_data/treinoscheckpoint.h5)... data:[0:24608] train:[4921:24597] train_result:[4933:24609] test:[0:4918] test_result:[12:4930] 2023-01-25 15:09:04,217 - freqtrade - ERROR - Fatal exception! Traceback (most recent call last): File "/freqtrade/freqtrade/main.py", line 42, in main return_code = args'func' File "/freqtrade/freqtrade/commands/optimize_commands.py", line 58, in start_backtesting backtesting.start() File "/freqtrade/freqtrade/optimize/backtesting.py", line 1335, in start min_date, max_date = self.backtest_one_strategy(strat, data, timerange) File "/freqtrade/freqtrade/optimize/backtesting.py", line 1236, in backtest_one_strategy preprocessed = self.strategy.advise_all_indicators(data) File "/freqtrade/freqtrade/strategy/interface.py", line 1203, in advise_all_indicators return {pair: self.advise_indicators(pair_data.copy(), {'pair': pair}).copy() File "/freqtrade/freqtrade/strategy/interface.py", line 1203, in
return {pair: self.advise_indicators(pair_data.copy(), {'pair': pair}).copy()
File "/freqtrade/freqtrade/strategy/interface.py", line 1221, in advise_indicators
return self.populate_indicators(dataframe, metadata)
File "/freqtrade/user_data/strategies/Predict_LSTM.py", line 289, in populate_indicators
dataframe = self.train_model(dataframe, self.curr_pair)
File "/freqtrade/user_data/strategies/Predict_LSTM.py", line 461, in train_model
df_tensor = self.dataframeUtils.df_to_tensor(df_norm, self.seq_len)
File "/freqtrade/user_data/strategies/DataframeUtils.py", line 492, in df_to_tensor
tensor_arr[row][seq] = data[src_row]
TypeError: float() argument must be a string or a real number, not 'Timestamp'
ERROR: 1