From 738da982b87880770b1432099322a847816633af Mon Sep 17 00:00:00 2001
From: Nikolai <osterei33@gmx.de>
Date: Fri, 27 Apr 2018 10:04:14 +0200
Subject: [PATCH] Don't refit StandardScaler to test data
---
toolkit.py | 6 ++++--
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/toolkit.py b/toolkit.py
index 3df27c6..9159901 100755
--- a/toolkit.py
+++ b/toolkit.py
@@ -183,8 +183,10 @@ class KerasROOTClassification:
self._scaler = StandardScaler()
logger.info("Fitting StandardScaler to training data")
self._scaler.fit(self.x_train)
- logger.info("Fitting StandardScaler to test data")
- self._scaler.fit(self.x_test)
+ # i think this would refit to test data (and overwrite the parameters)
+ # probably we either want to fit only training data or training and test data together
+ # logger.info("Fitting StandardScaler to test data")
+ # self._scaler.fit(self.x_test)
joblib.dump(self._scaler, filename)
return self._scaler
--
GitLab