adelorenzo/stable
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Fix constant PCA

Browse Source
This commit is contained in:
th0rntwig 2022-10-15 23:30:12 +02:00
parent 62ca822597
commit 20fc521771
1 changed files with 12 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
freqtrade/freqai/data_kitchen.py
View File

@ -206,11 +206,15 @@ class FreqaiDataKitchen:
drop_index = pd.isnull(filtered_df).any(axis=1) # get the rows that have NaNs, drop_index = pd.isnull(filtered_df).any(axis=1) # get the rows that have NaNs,
drop_index = drop_index.replace(True, 1).replace(False, 0) # pep8 requirement. drop_index = drop_index.replace(True, 1).replace(False, 0) # pep8 requirement.
ft_params = self.freqai_config["feature_parameters"]
if (training_filter): if (training_filter):
const_cols = list((filtered_df.nunique() == 1).loc[lambda x: x].index) if not ft_params.get(
if const_cols: "principal_component_analysis", False
filtered_df = filtered_df.filter(filtered_df.columns.difference(const_cols)) ):
logger.warning(f"Removed features {const_cols} with constant values.") const_cols = list((filtered_df.nunique() == 1).loc[lambda x: x].index)
if const_cols:
filtered_df = filtered_df.filter(filtered_df.columns.difference(const_cols))
logger.warning(f"Removed features {const_cols} with constant values.")
# we don't care about total row number (total no. datapoints) in training, we only care # we don't care about total row number (total no. datapoints) in training, we only care
# about removing any row with NaNs # about removing any row with NaNs
# if labels has multiple columns (user wants to train multiple modelEs), we detect here # if labels has multiple columns (user wants to train multiple modelEs), we detect here
@ -241,7 +245,10 @@ class FreqaiDataKitchen:
self.data["filter_drop_index_training"] = drop_index self.data["filter_drop_index_training"] = drop_index
else: else:
filtered_df = self.check_pred_labels(filtered_df) if not ft_params.get(
"principal_component_analysis", False
):
filtered_df = self.check_pred_labels(filtered_df)
# we are backtesting so we need to preserve row number to send back to strategy, # we are backtesting so we need to preserve row number to send back to strategy,
# so now we use do_predict to avoid any prediction based on a NaN # so now we use do_predict to avoid any prediction based on a NaN
drop_index = pd.isnull(filtered_df).any(axis=1) drop_index = pd.isnull(filtered_df).any(axis=1)