This is an automated email from the ASF dual-hosted git repository.
mboehm7 pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/systemds.git
The following commit(s) were added to refs/heads/main by this push:
new 70c7657c38 [MINOR] Additional test script for learned sampling
70c7657c38 is described below
commit 70c7657c38b5f2c611a7506463308a78804bbee0
Author: Matthias Boehm <mboe...@gmail.com>
AuthorDate: Thu May 1 15:51:03 2025 +0200
[MINOR] Additional test script for learned sampling
This script clusters data points by their gradients (with sample size
centroids) and then samples one point cluster. On the adult dataset
the results were non-conclusive compared to random sampling.
---
.../learnedSampling/5_ClusteredSampling.dml | 64 ++++++++++++++++++++++
1 file changed, 64 insertions(+)
diff --git a/scripts/staging/learnedSampling/5_ClusteredSampling.dml
b/scripts/staging/learnedSampling/5_ClusteredSampling.dml
new file mode 100644
index 0000000000..91337796ed
--- /dev/null
+++ b/scripts/staging/learnedSampling/5_ClusteredSampling.dml
@@ -0,0 +1,64 @@
+#-------------------------------------------------------------
+#
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements. See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership. The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License. You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing,
+# software distributed under the License is distributed on an
+# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+# KIND, either express or implied. See the License for the
+# specific language governing permissions and limitations
+# under the License.
+#
+#-------------------------------------------------------------
+
+# clustered gradients (no better than random sampling)
+# Accuracy (%): 88.39168202158463
+# Accuracy (%): 83.76164636019249
+# Accuracy (%): 96.04281828551373
+# Accuracy (%): 78.03829220845705
+# Accuracy (%): 100.0
+# Accuracy (%): 66.66325381386301
+
+# clustered data (no better than random sampling)
+# Accuracy (%): 86.95270685268054
+# Accuracy (%): 83.3316269069315
+# Accuracy (%): 96.472755988418
+# Accuracy (%): 73.82000614313505
+# Accuracy (%): 100.0
+# Accuracy (%): 69.74505989556671
+
+X = read("data/Adult_X.csv")
+y = read("data/Adult_y.csv")
+B = read("data/Adult_W.csv")
+
+[Xtrain,Xtest,ytrain,ytest] = split(X=X,Y=y,f=0.7,cont=FALSE,seed=7)
+
+sf = matrix("0.1 0.01 0.001", rows=3, cols=1)
+for(i in 1:nrow(sf)) {
+ sfi = as.scalar(sf[i]);
+
+ w = B[1:ncol(X), ];
+ icpt = as.scalar(B[nrow(B),])
+ Xgrad = sigmoid(Xtrain %*% w + icpt)-(ytrain == 1)
+ [C,Y]=kmeans(X=Xgrad, k=sfi*nrow(Xtrain), seed=7)
+
+ Yone = table(seq(1,nrow(Xtrain)),Y)
+ I = rowIndexMax(Yone); #pick first in every cluster
+ P = table(seq(1,nrow(I)), I, nrow(I), nrow(Xtrain))
+ P = removeEmpty(target=P, margin="rows");
+ Xtrain2 = P %*% Xtrain
+ ytrain2 = P %*% ytrain
+ B = multiLogReg(X=Xtrain2, Y=ytrain2, maxii=50, icpt=2, reg=0.001,
verbose=FALSE);
+
+ [M,yhat,acc] = multiLogRegPredict(X=Xtrain2, B=B, Y=ytrain2, verbose=TRUE);
+ [M,yhat,acc] = multiLogRegPredict(X=Xtest, B=B, Y=ytest, verbose=TRUE);
+}
+
