From 38d8f0a401190083bfe6306c531b8b902f99bf84 Mon Sep 17 00:00:00 2001
From: Pierre-Edouard Portier <p6e7p7@freeshell.org>
Date: Sun, 29 Jan 2023 17:52:53 +0100
Subject: [PATCH] Experiments. Where is the error in nakr?

---
 ...em_approximation_housing_experiment_code.R | 20 +++++++-------
 pad.R                                         | 26 +++++++++++++++++++
 2 files changed, 36 insertions(+), 10 deletions(-)

diff --git a/19_b_nystroem_approximation_housing_experiment_code.R b/19_b_nystroem_approximation_housing_experiment_code.R
index 2c7986c..3c6d285 100644
--- a/19_b_nystroem_approximation_housing_experiment_code.R
+++ b/19_b_nystroem_approximation_housing_experiment_code.R
@@ -99,13 +99,13 @@ X.entr <- hous.dat.nakr$entr$X
 Y.entr <- hous.dat.nakr$entr$Y
 X.test <- hous.dat.nakr$test$X
 Y.test <- hous.dat.nakr$test$Y
-hous.dat.ca <- datasetHousing.mca()
-hous.cam <- mca(hous.dat.ca)
-nb.landmarks <- round(sqrt(nrow(X.entr)))
-landmarks <- landmarks.by.ca.clst(hous.cam, X.entr, nb.landmarks)
-nakrm <- kfold.nakr(X.entr, Y.entr, landmarks=landmarks)
-nakrm.yh <- predict(nakrm, X.test)
-nakrm.mae <- mean(abs(nakrm.yh - Y.test))
-# nakrm.yh.train <- predict(nakrm, X.entr)
-# rev(order(abs(nakrm.yh.train - Y.entr)))[1:20]
-# hist(Y.entr[rev(order(abs(nakrm.yh.train - Y.entr)))[1:200]])
\ No newline at end of file
+#  hous.dat.ca <- datasetHousing.mca()
+#  hous.cam <- mca(hous.dat.ca)
+#  nb.landmarks <- round(sqrt(nrow(X.entr)))
+#  landmarks <- landmarks.by.ca.clst(hous.cam, X.entr, nb.landmarks)
+#  nakrm <- kfold.nakr(X.entr, Y.entr, landmarks=landmarks)
+#  nakrm.yh <- predict(nakrm, X.test)
+#  nakrm.mae <- mean(abs(nakrm.yh - Y.test))
+#  nakrm.yh.train <- predict(nakrm, X.entr)
+#  rev(order(abs(nakrm.yh.train - Y.entr)))[1:20]
+#  hist(Y.entr[rev(order(abs(nakrm.yh.train - Y.entr)))[1:200]])
\ No newline at end of file
diff --git a/pad.R b/pad.R
index 8703faa..bb7f7c9 100644
--- a/pad.R
+++ b/pad.R
@@ -27,3 +27,29 @@
 #      adj = 0, cex = 0.6)
 # points(0, 0, pch = 3)
 # ```
+
+#  source("19_b_nystroem_approximation_housing_experiment_code.R")
+#  rdat <- hous.dat.nakr$dat[sample(nrow(hous.dat.nakr$dat), size=2000, replace=FALSE),]
+#  X <- rdat[,!(colnames(rdat) %in% c('median_house_value'))]
+#  Y <- rdat[,c('median_house_value')]
+#  names(Y) <- rownames(X)
+#  rsplt <- splitdata(list(X = X, Y = Y), 0.8)
+#  X.entr <- rsplt$entr$X
+#  Y.entr <- rsplt$entr$Y
+#  X.test <- rsplt$test$X
+#  Y.test <- rsplt$test$Y
+#  source("18_kernel_ridge_regression_code.R")
+#  krm <- krr(X.entr, Y.entr)
+#  krm.yh <- predict(krm, X.test)
+#  krm.mae <- mean(abs(krm.yh - Y.test)) # 35445.1
+#  source("15_loocv_code.R")
+#  rm <- ridge(X.entr, Y.entr)
+#  rm.yh <- predict(rm, X.test)
+#  rm.mae <- mean(abs(rm.yh - Y.test)) # 45786.62
+#  library(randomForest)
+#  rfm <- randomForest(X.entr, Y.entr)
+#  rfm.yh <- predict(rfm, X.test)
+#  rfm.mae <- mean(abs(rfm.yh - Y.test)) # 34229.02
+#  nakrm <- kfold.nakr(X.entr, Y.entr, nb.landmarks=500)
+#  nakrm.yh <- predict(nakrm, X.test)
+#  nakrm.mae <- mean(abs(nakrm.yh - Y.test)) # 65454.18
\ No newline at end of file