From 5bb8ec6fe7fbc5ccb11ed23a870d5eec8759f00d Mon Sep 17 00:00:00 2001 From: franzi Date: Thu, 7 Mar 2024 14:22:56 +0100 Subject: [PATCH] add pandas output transform to scaler --- notebooks/4_analyze_toydata.ipynb | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/notebooks/4_analyze_toydata.ipynb b/notebooks/4_analyze_toydata.ipynb index 342d57b..4bfe564 100644 --- a/notebooks/4_analyze_toydata.ipynb +++ b/notebooks/4_analyze_toydata.ipynb @@ -778,8 +778,8 @@ "metadata": {}, "outputs": [], "source": [ - "# scale the data\n", - "scaler = StandardScaler()\n", + "# scale the data (but make sure it stays a pandas dataframe)\n", + "scaler = StandardScaler().set_output(transform=\"pandas\")\n", "# training data: fit & transform \n", "# (fit: compute mean and std of each feature; transform: subtract mean from each feature and divide by std)\n", "X_train = scaler.fit_transform(X_train)\n", @@ -836,7 +836,7 @@ "y = df_new[\"faulty\"]\n", "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33, random_state=15)\n", "# and don't forget to scale the data again!\n", - "scaler = StandardScaler()\n", + "scaler = StandardScaler().set_output(transform=\"pandas\")\n", "X_train = scaler.fit_transform(X_train)\n", "X_test = scaler.transform(X_test)\n", "# train the model again with most of the default parameter setting\n",