gavindiaz/NexQuant
1
0
Fork 0
mirror of https://github.com/NicolasBohn/NexQuant.git synced 2026-08-03 02:17:43 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix two template (#376)

Browse Source
This commit is contained in:
WinstonLiyt
2024-09-28 06:12:06 +08:00
committed by GitHub
parent 5787a546b5
commit 7642adc703
2 changed files with 1 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files
rdagent/scenarios/kaggle/experiment/digit-recognizer_template/fea_share_preprocess.py
+1 -6
View File
@@ -57,7 +57,7 @@ def clean_and_impute_data(X_train, X_valid, X_test):
then imputes missing values using the mean strategy.
Also removes duplicate columns.
"""
# Replace inf and -inf with NaN
# Replace inf and -inf with NaNa
X_train.replace([np.inf, -np.inf], np.nan, inplace=True)
X_valid.replace([np.inf, -np.inf], np.nan, inplace=True)
X_test.replace([np.inf, -np.inf], np.nan, inplace=True)
@@ -68,9 +68,4 @@ def clean_and_impute_data(X_train, X_valid, X_test):
X_valid = pd.DataFrame(imputer.transform(X_valid), columns=X_valid.columns)
X_test = pd.DataFrame(imputer.transform(X_test), columns=X_test.columns)
# Remove duplicate columns
X_train = X_train.loc[:, ~X_train.columns.duplicated()]
X_valid = X_valid.loc[:, ~X_valid.columns.duplicated()]
X_test = X_test.loc[:, ~X_test.columns.duplicated()]
return X_train, X_valid, X_test
rdagent/scenarios/kaggle/experiment/playground-series-s4e8_template/train.py
-5
View File
@@ -53,11 +53,6 @@ X_test = pd.concat(X_test_l, axis=1, keys=[f"feature_{i}" for i in range(len(X_t
print(X_train.shape, X_valid.shape, X_test.shape)
# Handle inf and -inf values
X_train.replace([np.inf, -np.inf], np.nan, inplace=True)
X_valid.replace([np.inf, -np.inf], np.nan, inplace=True)
X_test.replace([np.inf, -np.inf], np.nan, inplace=True)
from sklearn.impute import SimpleImputer
imputer = SimpleImputer(strategy="mean")