From a137f76e7730ff907f68119aa5b7977f9e4f0552 Mon Sep 17 00:00:00 2001
From: icfaust <icfaust@gmail.com>
Date: Fri, 10 Jul 2026 03:23:30 -0700
Subject: [PATCH 1/2] add preprocessing benchmarking

---
 configs/regular/preprocessing.json | 41 ++++++++++++++++++++++++++++++
 1 file changed, 41 insertions(+)
 create mode 100644 configs/regular/preprocessing.json

diff --git a/configs/regular/preprocessing.json b/configs/regular/preprocessing.json
new file mode 100644
index 00000000..d0a8c1d7
--- /dev/null
+++ b/configs/regular/preprocessing.json
@@ -0,0 +1,41 @@
+{
+    "INCLUDE": ["../common/sklearn.json"],
+    "PARAMETERS_SETS": {
+        "preprocessing parameters": {
+            "algorithm": {
+                "estimator": "MaxAbsScaler",
+                "estimator_methods": { "training": "fit", "inference": "transform" }
+            }
+        },
+        "preprocessing datasets": [
+            {
+                "data": {
+                    "source": "make_regression",
+                    "generation_kwargs": [
+                        { "n_samples": 100000, "n_features": 5000, "noise": 1.0 },
+                        { "n_samples": 1000000, "n_features": 500, "noise": 1.0 },
+                        { "n_samples": 10000000, "n_features": 50, "noise": 1.0 }
+                    ],
+                    "split_kwargs": { "train_size": 0.5, "test_size": 0.5 },
+                    "dtype": ["float32", "float64"]
+                }
+            },
+            {
+                "data": {
+                    "dataset": ["sift", "gist", "svhn"],
+                    "split_kwargs": { "train_size": 0.5, "test_size": 0.5 },
+                    "dtype": ["float32", "float64"]
+                }
+            }
+        ]
+    },
+    "TEMPLATES": {
+        "sklearn preprocessing": {
+            "SETS": [
+                "sklearn-ex[cpu,gpu] implementations",
+                "preprocessing parameters",
+                "preprocessing datasets"
+            ]
+        }
+    }
+}

From b42d6459a644afa372aeda28b3c219d110035a8e Mon Sep 17 00:00:00 2001
From: Ian Faust <icfaust@gmail.com>
Date: Fri, 10 Jul 2026 12:50:01 +0200
Subject: [PATCH 2/2] Update preprocessing.json

---
 configs/regular/preprocessing.json | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/configs/regular/preprocessing.json b/configs/regular/preprocessing.json
index d0a8c1d7..c81fcc6b 100644
--- a/configs/regular/preprocessing.json
+++ b/configs/regular/preprocessing.json
@@ -31,11 +31,7 @@
     },
     "TEMPLATES": {
         "sklearn preprocessing": {
-            "SETS": [
-                "sklearn-ex[cpu,gpu] implementations",
-                "preprocessing parameters",
-                "preprocessing datasets"
-            ]
+            "SETS": ["sklearn-ex[cpu,gpu] implementations", "preprocessing parameters", "preprocessing datasets"]
         }
     }
 }