|
|
@@ -31,7 +31,7 @@ def data_column_cleaning(data, logger, clean_value=[-99.0, -99]):
|
|
|
for val in clean_value:
|
|
|
data1 = data1.replace(val, np.nan)
|
|
|
# nan 列超过80% 删除
|
|
|
- data1 = data1.dropna(axis=1, thresh=len(data) * 0.8)
|
|
|
+ data1 = data1.dropna(axis=1, thresh=len(data) * 0.5)
|
|
|
# 删除取值全部相同的列
|
|
|
data1 = data1.loc[:, (data1 != data1.iloc[0]).any()]
|
|
|
data = data[data1.columns.tolist()]
|
David