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

ensure columns are only dropped in training

Browse Source
This commit is contained in:
robcaulk 2022-09-09 20:37:21 +02:00
parent cdc72bf8ca
commit 05581db4e3
1 changed files with 4 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
freqtrade/freqai/data_kitchen.py
View File

@ -209,14 +209,13 @@ class FreqaiDataKitchen:
filtered_df = unfiltered_df.filter(training_feature_list, axis=1) filtered_df = unfiltered_df.filter(training_feature_list, axis=1)
filtered_df = filtered_df.replace([np.inf, -np.inf], np.nan) filtered_df = filtered_df.replace([np.inf, -np.inf], np.nan)
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.")
drop_index = pd.isnull(filtered_df).any(1) # get the rows that have NaNs, drop_index = pd.isnull(filtered_df).any(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.
if (training_filter): if (training_filter):
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