From 9a45dc8bcbcca10c6bac7a31564b4bad16bb6787 Mon Sep 17 00:00:00 2001
From: Andri Joos <andri@joos.io>
Date: Tue, 12 Nov 2024 21:53:41 +0100
Subject: [PATCH] fix dropping columns when removing unimportant predictors
---
app/preprocessing/transform_dataset.py | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/app/preprocessing/transform_dataset.py b/app/preprocessing/transform_dataset.py
index 5711f94..914be5a 100644
--- a/app/preprocessing/transform_dataset.py
+++ b/app/preprocessing/transform_dataset.py
@@ -194,7 +194,7 @@ def _remove_unimportant_predictors(train_files: List[Path], all_files: List[Path
df = pd.read_parquet(file)
columns_to_drop = [col for col in df.columns if col not in columns_to_keep]
- df.drop(columns=columns_to_drop)
+ df = df.drop(columns=columns_to_drop)
df.to_parquet(out_dir / file.name)
--
GitLab