arthur/ml_exercises
1
0
Fork 0
mirror of https://github.com/ArthurDanjou/ml_exercises.git synced 2026-01-14 12:14:38 +01:00
Code Issues Packages Projects Releases Wiki Activity

add pandas output transform to scaler

Browse Source
This commit is contained in:
franzi
2024-03-07 14:22:56 +01:00
parent c4bbf2787c
commit 5bb8ec6fe7
1 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
notebooks/4_analyze_toydata.ipynb
View File

@@ -778,8 +778,8 @@
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"# scale the data\n", "# scale the data (but make sure it stays a pandas dataframe)\n",
"scaler = StandardScaler()\n", "scaler = StandardScaler().set_output(transform=\"pandas\")\n",
"# training data: fit & transform \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", "# (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", "X_train = scaler.fit_transform(X_train)\n",
@@ -836,7 +836,7 @@
"y = df_new[\"faulty\"]\n", "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", "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", "# 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_train = scaler.fit_transform(X_train)\n",
"X_test = scaler.transform(X_test)\n", "X_test = scaler.transform(X_test)\n",
"# train the model again with most of the default parameter setting\n", "# train the model again with most of the default parameter setting\n",