Getting started
set.seed(123)
(index_train <- base::sample.int(n = nrow(X),
size = floor(0.8*nrow(X)),
replace = FALSE))## [1] 31 15 19 14 3 10 18 22 11 5 20 29 23 30 9 28 8 27 7 32 26 17 4 1 24X_train <- X[index_train, ]
y_train <- y[index_train]
X_test <- X[-index_train, ]
y_test <- y[-index_train]
dim(X_train)## [1] 25 10## [1] 7 100 - lm regression
## [1] "regression"## [1] "Regressor"## [1] "lm"## Elapsed: 0.002 s## [1] 3.548852## $preds
## Mazda RX4 Wag Valiant Merc 450SE Merc 450SL
## 21.67584 19.80291 14.75149 15.70693
## Lincoln Continental Toyota Corona Pontiac Firebird
## 12.03666 28.20630 13.55241
##
## $lower
## Mazda RX4 Wag Valiant Merc 450SE Merc 450SL
## 10.675844 8.802908 3.751488 4.706932
## Lincoln Continental Toyota Corona Pontiac Firebird
## 1.036659 17.206298 2.552412
##
## $upper
## Mazda RX4 Wag Valiant Merc 450SE Merc 450SL
## 32.67584 30.80291 25.75149 26.70693
## Lincoln Continental Toyota Corona Pontiac Firebird
## 23.03666 39.20630 24.55241plot(c(y_train, res$preds), type='l',
main="",
ylab="",
ylim = c(min(c(res$upper, res$lower, y)),
max(c(res$upper, res$lower, y))))
lines(c(y_train, res$upper), col="gray60")
lines(c(y_train, res$lower), col="gray60")
lines(c(y_train, res$preds), col = "red")
lines(c(y_train, y_test), col = "blue")
## [1] 1t0 <- proc.time()[3]
obj$fit(X_train, y_train,
pi_method = "jackknifeplus")
cat("Elapsed: ", proc.time()[3] - t0, "s \n")## Elapsed: 0.041 sobj$set_level(95L)
res <- obj$predict(X = X_test)
plot(c(y_train, res$preds), type='l',
main="",
ylab="",
ylim = c(min(c(res$upper, res$lower, y)),
max(c(res$upper, res$lower, y))))
lines(c(y_train, res$upper), col="gray60")
lines(c(y_train, res$lower), col="gray60")
lines(c(y_train, res$preds), col = "red")
lines(c(y_train, y_test), col = "blue")
## [1] 11 - ranger regression
obj <- learningmachine::Regressor$new(method = "ranger", pi_method = "splitconformal")
obj$get_type()## [1] "regression"## [1] "Regressor"## Elapsed: 0.01 s## [1] 2.302783## Elapsed: 0.011 sobj$set_level(95)
res <- obj$predict(X = X_test)
plot(c(y_train, res$preds), type='l',
main="",
ylab="",
ylim = c(min(c(res$upper, res$lower, y)),
max(c(res$upper, res$lower, y))))
lines(c(y_train, res$upper), col="gray60")
lines(c(y_train, res$lower), col="gray60")
lines(c(y_train, res$preds), col = "red")
lines(c(y_train, y_test), col = "blue")
## [1] 1res <- obj$predict(X = X_test)
plot(c(y_train, res$preds), type='l',
main="",
ylab="",
ylim = c(min(c(res$upper, res$lower, y)),
max(c(res$upper, res$lower, y))))
lines(c(y_train, res$upper), col="gray60")
lines(c(y_train, res$lower), col="gray60")
lines(c(y_train, res$preds), col = "red")
lines(c(y_train, y_test), col = "blue")
## [1] 12 - KRR & ranger regression on
Boston
# Boston dataset (dataset has an ethical problem)
library(MASS)
data("Boston")
set.seed(13)
train_idx <- sample(nrow(Boston), 0.8 * nrow(Boston))
X_train <- as.matrix(Boston[train_idx, -ncol(Boston)])
X_test <- as.matrix(Boston[-train_idx, -ncol(Boston)])
y_train <- Boston$medv[train_idx]
y_test <- Boston$medv[-train_idx]KRR
## [1] "regression"## [1] "Regressor"## [1] "krr"t0 <- proc.time()[3]
obj$fit(X_train, y_train, reg_lambda = 0.1)
cat("Elapsed: ", proc.time()[3] - t0, "s \n")## Elapsed: 0.029 s## [1] 2.888748## $R_squared
## [1] 0.906853
##
## $R_squared_adj
## [1] 0.8930926
##
## $Residuals
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## -8.33671 -1.10461 -0.02411 0.12105 1.46980 9.29398
##
## $citests
## estimate lower upper p-value signif
## crim -0.0544164530 -0.075529516 -0.0333033896 1.509961e-06 ***
## zn -0.0046418101 -0.009605912 0.0003222914 6.652189e-02 .
## indus -0.0245357110 -0.051187606 0.0021161842 7.077114e-02 .
## chas 7.1730075477 6.375361838 7.9706532576 5.512518e-33 ***
## nox -9.4958030753 -12.095806303 -6.8957998474 8.811259e-11 ***
## rm 4.7080249286 3.939353604 5.4766962526 1.787394e-21 ***
## age -0.0439718628 -0.053082559 -0.0348611667 7.779486e-16 ***
## dis -1.4214523042 -1.573146091 -1.2697585171 2.257304e-34 ***
## rad 0.1810040336 0.155692359 0.2063157080 8.827967e-26 ***
## tax -0.0115644823 -0.013066430 -0.0100625342 5.303780e-28 ***
## ptratio -0.4819300831 -0.582754790 -0.3811053766 1.242164e-15 ***
## black -0.0002461991 -0.001967809 0.0014754112 7.772335e-01
## lstat -0.4091458985 -0.475209948 -0.3430818492 9.126116e-22 ***
##
## $signif_codes
## [1] "Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1"
##
## $effects
## ── Data Summary ────────────────────────
## Values
## Name effects
## Number of rows 102
## Number of columns 13
## _______________________
## Column type frequency:
## numeric 13
## ________________________
## Group variables None
##
## ── Variable type: numeric ──────────────────────────────────────────────────────
## skim_variable mean sd p0 p25 p50 p75
## 1 crim -0.0544 0.107 -0.416 -0.0696 -0.00478 0.00661
## 2 zn -0.00464 0.0253 -0.0524 -0.0200 -0.00301 0.00416
## 3 indus -0.0245 0.136 -0.308 -0.109 -0.0396 0.0220
## 4 chas 7.17 4.06 -17.7 5.97 7.12 9.16
## 5 nox -9.50 13.2 -78.3 -15.0 -7.32 -2.30
## 6 rm 4.71 3.91 -3.43 1.83 4.48 7.72
## 7 age -0.0440 0.0464 -0.138 -0.0778 -0.0506 -0.00674
## 8 dis -1.42 0.772 -3.43 -1.80 -1.32 -0.933
## 9 rad 0.181 0.129 -0.0944 0.0827 0.173 0.261
## 10 tax -0.0116 0.00765 -0.0388 -0.0148 -0.00963 -0.00718
## 11 ptratio -0.482 0.513 -2.13 -0.671 -0.441 -0.209
## 12 black -0.000246 0.00877 -0.0263 -0.00450 0.0000316 0.00344
## 13 lstat -0.409 0.336 -1.62 -0.474 -0.310 -0.189
## p100 hist
## 1 0.107 ▁▁▂▇▅
## 2 0.0728 ▃▇▇▂▁
## 3 0.499 ▂▇▂▁▁
## 4 14.8 ▁▁▁▇▅
## 5 15.5 ▁▁▁▇▃
## 6 12.4 ▃▇▇▇▅
## 7 0.0628 ▂▇▆▃▂
## 8 0.0716 ▂▂▇▇▃
## 9 0.492 ▂▇▇▃▂
## 10 0.00304 ▁▁▃▇▂
## 11 1.01 ▁▁▇▃▁
## 12 0.0391 ▁▇▇▁▁
## 13 0.0311 ▁▁▂▆▇## Elapsed: 0.793 s## $R_squared
## [1] 0.906853
##
## $R_squared_adj
## [1] 0.8930926
##
## $Residuals
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## -8.33671 -1.10461 -0.02411 0.12105 1.46980 9.29398
##
## $citests
## estimate lower upper p-value signif
## crim -0.0538049728 -0.07788039 -0.0339150922 3.330856e-165 ***
## zn -0.0046264575 -0.00930898 0.0002208004 2.129513e-162 ***
## indus -0.0250873356 -0.04983945 0.0013580905 3.367434e-162 ***
## chas 7.1874845264 6.31700628 7.8848224325 3.330856e-165 ***
## nox -9.4746636134 -12.26642878 -6.9077586130 3.330856e-165 ***
## rm 4.7102428290 3.86896609 5.5034002307 3.330856e-165 ***
## age -0.0440650425 -0.05296489 -0.0349701343 3.330856e-165 ***
## dis -1.4211028552 -1.56809609 -1.2833726839 3.330856e-165 ***
## rad 0.1812312885 0.15663376 0.2067723827 3.330856e-165 ***
## tax -0.0115489146 -0.01305204 -0.0100571311 3.330856e-165 ***
## ptratio -0.4789522388 -0.58263847 -0.3853958372 3.330856e-165 ***
## black -0.0002264778 -0.00187825 0.0015182254 9.583495e-16 ***
## lstat -0.4057946096 -0.47807035 -0.3461364993 3.330856e-165 ***
##
## $signif_codes
## [1] "Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1"
##
## $effects
## ── Data Summary ────────────────────────
## Values
## Name effects
## Number of rows 102
## Number of columns 13
## _______________________
## Column type frequency:
## numeric 13
## ________________________
## Group variables None
##
## ── Variable type: numeric ──────────────────────────────────────────────────────
## skim_variable mean sd p0 p25 p50 p75
## 1 crim -0.0544 0.107 -0.416 -0.0696 -0.00478 0.00661
## 2 zn -0.00464 0.0253 -0.0524 -0.0200 -0.00301 0.00416
## 3 indus -0.0245 0.136 -0.308 -0.109 -0.0396 0.0220
## 4 chas 7.17 4.06 -17.7 5.97 7.12 9.16
## 5 nox -9.50 13.2 -78.3 -15.0 -7.32 -2.30
## 6 rm 4.71 3.91 -3.43 1.83 4.48 7.72
## 7 age -0.0440 0.0464 -0.138 -0.0778 -0.0506 -0.00674
## 8 dis -1.42 0.772 -3.43 -1.80 -1.32 -0.933
## 9 rad 0.181 0.129 -0.0944 0.0827 0.173 0.261
## 10 tax -0.0116 0.00765 -0.0388 -0.0148 -0.00963 -0.00718
## 11 ptratio -0.482 0.513 -2.13 -0.671 -0.441 -0.209
## 12 black -0.000246 0.00877 -0.0263 -0.00450 0.0000316 0.00344
## 13 lstat -0.409 0.336 -1.62 -0.474 -0.310 -0.189
## p100 hist
## 1 0.107 ▁▁▂▇▅
## 2 0.0728 ▃▇▇▂▁
## 3 0.499 ▂▇▂▁▁
## 4 14.8 ▁▁▁▇▅
## 5 15.5 ▁▁▁▇▃
## 6 12.4 ▃▇▇▇▅
## 7 0.0628 ▂▇▆▃▂
## 8 0.0716 ▂▂▇▇▃
## 9 0.492 ▂▇▇▃▂
## 10 0.00304 ▁▁▃▇▂
## 11 1.01 ▁▁▇▃▁
## 12 0.0391 ▁▇▇▁▁
## 13 0.0311 ▁▁▂▆▇## Elapsed: 1.229 s## $R_squared
## [1] 0.906853
##
## $R_squared_adj
## [1] 0.8930926
##
## $Residuals
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## -8.33671 -1.10461 -0.02411 0.12105 1.46980 9.29398
##
## $citests
## estimate lower upper p-value signif
## crim -0.037922954 -0.07328928 -0.0139185368 1.268525e-83 ***
## zn -0.003245926 -0.01123917 0.0042341372 8.112018e-51 ***
## indus -0.009505317 -0.05165442 0.0376237962 3.771573e-16 ***
## chas 7.003792862 6.02912386 7.9131077572 1.268525e-83 ***
## nox -8.038548064 -12.47241636 -4.7336175973 1.268525e-83 ***
## rm 5.371557272 4.35587894 6.1934399509 1.268525e-83 ***
## age -0.050808359 -0.06384589 -0.0376572320 1.268525e-83 ***
## dis -1.371538135 -1.57056696 -1.1796657263 1.268525e-83 ***
## rad 0.185007799 0.15210036 0.2141058406 1.268525e-83 ***
## tax -0.011855390 -0.01433893 -0.0099523056 1.268525e-83 ***
## ptratio -0.561089487 -0.71011786 -0.4057723234 1.268525e-83 ***
## black -0.001429035 -0.00335513 0.0004864625 1.733542e-76 ***
## lstat -0.403259203 -0.50131121 -0.3087645375 1.268525e-83 ***
##
## $signif_codes
## [1] "Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1"
##
## $effects
## ── Data Summary ────────────────────────
## Values
## Name effects
## Number of rows 102
## Number of columns 13
## _______________________
## Column type frequency:
## numeric 13
## ________________________
## Group variables None
##
## ── Variable type: numeric ──────────────────────────────────────────────────────
## skim_variable mean sd p0 p25 p50 p75
## 1 crim -0.0544 0.107 -0.416 -0.0696 -0.00478 0.00661
## 2 zn -0.00464 0.0253 -0.0524 -0.0200 -0.00301 0.00416
## 3 indus -0.0245 0.136 -0.308 -0.109 -0.0396 0.0220
## 4 chas 7.17 4.06 -17.7 5.97 7.12 9.16
## 5 nox -9.50 13.2 -78.3 -15.0 -7.32 -2.30
## 6 rm 4.71 3.91 -3.43 1.83 4.48 7.72
## 7 age -0.0440 0.0464 -0.138 -0.0778 -0.0506 -0.00674
## 8 dis -1.42 0.772 -3.43 -1.80 -1.32 -0.933
## 9 rad 0.181 0.129 -0.0944 0.0827 0.173 0.261
## 10 tax -0.0116 0.00765 -0.0388 -0.0148 -0.00963 -0.00718
## 11 ptratio -0.482 0.513 -2.13 -0.671 -0.441 -0.209
## 12 black -0.000246 0.00877 -0.0263 -0.00450 0.0000316 0.00344
## 13 lstat -0.409 0.336 -1.62 -0.474 -0.310 -0.189
## p100 hist
## 1 0.107 ▁▁▂▇▅
## 2 0.0728 ▃▇▇▂▁
## 3 0.499 ▂▇▂▁▁
## 4 14.8 ▁▁▁▇▅
## 5 15.5 ▁▁▁▇▃
## 6 12.4 ▃▇▇▇▅
## 7 0.0628 ▂▇▆▃▂
## 8 0.0716 ▂▂▇▇▃
## 9 0.492 ▂▇▇▃▂
## 10 0.00304 ▁▁▃▇▂
## 11 1.01 ▁▁▇▃▁
## 12 0.0391 ▁▇▇▁▁
## 13 0.0311 ▁▁▂▆▇## Elapsed: 0.774 sranger
## [1] "regression"## [1] "Regressor"## Elapsed: 0.052 s## [1] 3.74535## $R_squared
## [1] 0.8434207
##
## $R_squared_adj
## [1] 0.8202897
##
## $Residuals
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## -8.8563 -1.5963 -0.1491 0.4260 1.9961 12.6714
##
## $Coverage_rate
## [1] 100
##
## $citests
## estimate lower upper p-value signif
## crim -49.6344261 -232.91685299 133.6480007 5.923034e-01
## zn 0.0784486 -0.06027044 0.2171676 2.645894e-01
## indus -18.8096072 -34.04595819 -3.5732562 1.604939e-02 *
## chas 0.0000000 NaN NaN NaN
## nox -467.8840363 -627.07556952 -308.6925031 6.664467e-08 ***
## rm 276.5215702 225.72209883 327.3210416 1.573542e-18 ***
## age -2.0367081 -2.86343009 -1.2099861 3.857020e-06 ***
## dis 22.5199587 -1.94139968 46.9813170 7.076063e-02 .
## rad 1.5745877 -0.25222578 3.4014011 9.036604e-02 .
## tax -0.6832444 -0.89986179 -0.4666270 9.564055e-09 ***
## ptratio -31.9041989 -38.38822071 -25.4201770 3.019931e-16 ***
## black -0.3827134 -0.63975500 -0.1256717 3.907316e-03 **
## lstat -44.9609199 -57.58730968 -32.3345300 2.116676e-10 ***
##
## $signif_codes
## [1] "Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1"
##
## $effects
## ── Data Summary ────────────────────────
## Values
## Name effects
## Number of rows 102
## Number of columns 13
## _______________________
## Column type frequency:
## numeric 13
## ________________________
## Group variables None
##
## ── Variable type: numeric ──────────────────────────────────────────────────────
## skim_variable mean sd p0 p25 p50 p75 p100
## 1 crim -49.6 933. -6399. -70.6 -10.7 53.3 2113.
## 2 zn 0.0784 0.706 -1.09 0 0 0 5.76
## 3 indus -18.8 77.6 -451. -7.13 2.68 7.68 49.6
## 4 chas 0 0 0 0 0 0 0
## 5 nox -468. 810. -3221. -897. -224. 53.8 769.
## 6 rm 277. 259. -17.7 73.5 191. 361. 855.
## 7 age -2.04 4.21 -34.1 -2.99 -1.10 0 7.16
## 8 dis 22.5 125. -167. -25.8 -3.58 4.74 644.
## 9 rad 1.57 9.30 -4.32 0 0 0.242 88.1
## 10 tax -0.683 1.10 -4.90 -0.606 -0.305 -0.121 0.333
## 11 ptratio -31.9 33.0 -150. -42.1 -21.2 -8.87 7.14
## 12 black -0.383 1.31 -4.96 -0.884 0 0.424 2.11
## 13 lstat -45.0 64.3 -332. -53.9 -24.2 -6.86 24.7
## hist
## 1 ▁▁▁▇▁
## 2 ▇▁▁▁▁
## 3 ▁▁▁▁▇
## 4 ▁▁▇▁▁
## 5 ▁▁▅▇▆
## 6 ▇▃▂▁▂
## 7 ▁▁▁▇▇
## 8 ▇▇▁▁▁
## 9 ▇▁▁▁▁
## 10 ▁▁▁▁▇
## 11 ▁▁▂▅▇
## 12 ▁▁▂▇▂
## 13 ▁▁▁▂▇## Elapsed: 0.455 s## Warning in wilcox.test.default(x, mu = mu_0): cannot compute exact p-value with
## zeroes## $R_squared
## [1] 0.8434207
##
## $R_squared_adj
## [1] 0.8202897
##
## $Residuals
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## -8.8563 -1.5963 -0.1491 0.4260 1.9961 12.6714
##
## $Coverage_rate
## [1] 100
##
## $citests
## estimate lower upper p-value signif
## crim -45.39300398 -252.35254750 105.6958272 1.682119e-56 ***
## zn 0.07113834 -0.04309201 0.2304618 3.967833e-137 ***
## indus -18.37780619 -34.75011937 -5.5584701 3.371100e-165 ***
## chas 0.00000000 0.00000000 0.0000000 NaN
## nox -464.07375760 -633.95015108 -310.1167462 3.330856e-165 ***
## rm 274.35623912 225.68252481 332.0295218 3.330856e-165 ***
## age -2.01815861 -2.94318020 -1.2850614 3.330856e-165 ***
## dis 21.29375149 0.03005176 48.1614331 5.506114e-163 ***
## rad 1.43034678 0.30692307 3.5901415 3.330856e-165 ***
## tax -0.68195179 -0.90608771 -0.4707029 3.330856e-165 ***
## ptratio -31.83678007 -39.05187548 -25.5074573 3.330856e-165 ***
## black -0.38032502 -0.61610598 -0.1410594 3.360994e-165 ***
## lstat -44.75647422 -58.07568071 -33.4538379 3.330856e-165 ***
##
## $signif_codes
## [1] "Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1"
##
## $effects
## ── Data Summary ────────────────────────
## Values
## Name effects
## Number of rows 102
## Number of columns 13
## _______________________
## Column type frequency:
## numeric 13
## ________________________
## Group variables None
##
## ── Variable type: numeric ──────────────────────────────────────────────────────
## skim_variable mean sd p0 p25 p50 p75 p100
## 1 crim -49.6 933. -6399. -70.6 -10.7 53.3 2113.
## 2 zn 0.0784 0.706 -1.09 0 0 0 5.76
## 3 indus -18.8 77.6 -451. -7.13 2.68 7.68 49.6
## 4 chas 0 0 0 0 0 0 0
## 5 nox -468. 810. -3221. -897. -224. 53.8 769.
## 6 rm 277. 259. -17.7 73.5 191. 361. 855.
## 7 age -2.04 4.21 -34.1 -2.99 -1.10 0 7.16
## 8 dis 22.5 125. -167. -25.8 -3.58 4.74 644.
## 9 rad 1.57 9.30 -4.32 0 0 0.242 88.1
## 10 tax -0.683 1.10 -4.90 -0.606 -0.305 -0.121 0.333
## 11 ptratio -31.9 33.0 -150. -42.1 -21.2 -8.87 7.14
## 12 black -0.383 1.31 -4.96 -0.884 0 0.424 2.11
## 13 lstat -45.0 64.3 -332. -53.9 -24.2 -6.86 24.7
## hist
## 1 ▁▁▁▇▁
## 2 ▇▁▁▁▁
## 3 ▁▁▁▁▇
## 4 ▁▁▇▁▁
## 5 ▁▁▅▇▆
## 6 ▇▃▂▁▂
## 7 ▁▁▁▇▇
## 8 ▇▇▁▁▁
## 9 ▇▁▁▁▁
## 10 ▁▁▁▁▇
## 11 ▁▁▂▅▇
## 12 ▁▁▂▇▂
## 13 ▁▁▁▂▇## Elapsed: 0.69 s## Warning in wilcox.test.default(x, mu = mu_0): cannot compute exact p-value with
## zeroes## $R_squared
## [1] 0.8434207
##
## $R_squared_adj
## [1] 0.8202897
##
## $Residuals
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## -8.8563 -1.5963 -0.1491 0.4260 1.9961 12.6714
##
## $Coverage_rate
## [1] 100
##
## $citests
## estimate lower upper p-value signif
## crim -5.7668376 -191.32459192 166.6670019 4.503969e-02 *
## zn 0.1435863 -0.04898389 0.4653465 1.780801e-75 ***
## indus -30.1885421 -60.17170897 -7.3625392 1.268525e-83 ***
## chas 0.0000000 0.00000000 0.0000000 NaN
## nox -475.8384341 -689.18361469 -238.1966040 1.268525e-83 ***
## rm 295.6431870 225.05343996 372.1962857 1.268525e-83 ***
## age -1.7449947 -3.43479688 -0.6898904 1.268525e-83 ***
## dis 20.2776295 -14.47594907 65.3191964 5.215786e-65 ***
## rad 2.4761206 0.27316780 7.7188457 1.331000e-83 ***
## tax -0.6569972 -1.03400273 -0.3784882 1.268525e-83 ***
## ptratio -34.7056749 -43.95146053 -26.6399388 1.268525e-83 ***
## black -0.6447480 -1.08425142 -0.2753894 1.268525e-83 ***
## lstat -48.7558107 -68.57485771 -32.8653183 1.268525e-83 ***
##
## $signif_codes
## [1] "Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1"
##
## $effects
## ── Data Summary ────────────────────────
## Values
## Name effects
## Number of rows 102
## Number of columns 13
## _______________________
## Column type frequency:
## numeric 13
## ________________________
## Group variables None
##
## ── Variable type: numeric ──────────────────────────────────────────────────────
## skim_variable mean sd p0 p25 p50 p75 p100
## 1 crim -49.6 933. -6399. -70.6 -10.7 53.3 2113.
## 2 zn 0.0784 0.706 -1.09 0 0 0 5.76
## 3 indus -18.8 77.6 -451. -7.13 2.68 7.68 49.6
## 4 chas 0 0 0 0 0 0 0
## 5 nox -468. 810. -3221. -897. -224. 53.8 769.
## 6 rm 277. 259. -17.7 73.5 191. 361. 855.
## 7 age -2.04 4.21 -34.1 -2.99 -1.10 0 7.16
## 8 dis 22.5 125. -167. -25.8 -3.58 4.74 644.
## 9 rad 1.57 9.30 -4.32 0 0 0.242 88.1
## 10 tax -0.683 1.10 -4.90 -0.606 -0.305 -0.121 0.333
## 11 ptratio -31.9 33.0 -150. -42.1 -21.2 -8.87 7.14
## 12 black -0.383 1.31 -4.96 -0.884 0 0.424 2.11
## 13 lstat -45.0 64.3 -332. -53.9 -24.2 -6.86 24.7
## hist
## 1 ▁▁▁▇▁
## 2 ▇▁▁▁▁
## 3 ▁▁▁▁▇
## 4 ▁▁▇▁▁
## 5 ▁▁▅▇▆
## 6 ▇▃▂▁▂
## 7 ▁▁▁▇▇
## 8 ▇▇▁▁▁
## 9 ▇▁▁▁▁
## 10 ▁▁▁▁▇
## 11 ▁▁▂▅▇
## 12 ▁▁▂▇▂
## 13 ▁▁▁▂▇## Elapsed: 0.487 s3 - KRR regression on mtcars
X <- as.matrix(mtcars[,-1])
y <- mtcars$mpg
set.seed(123)
(index_train <- base::sample.int(n = nrow(X),
size = floor(0.7*nrow(X)),
replace = FALSE))## [1] 31 15 19 14 3 10 18 22 11 5 20 29 23 30 9 28 8 27 7 32 26 17X_train <- X[index_train, ]
y_train <- y[index_train]
X_test <- X[-index_train, ]
y_test <- y[-index_train]
dim(X_train)## [1] 22 10## [1] 10 10## [1] "regression"## [1] "Regressor"t0 <- proc.time()[3]
obj$fit(X_train, y_train, reg_lambda = 0.1)
cat("Elapsed: ", proc.time()[3] - t0, "s \n")## Elapsed: 0.002 s## $preds
## [1] 22.151349 21.802194 12.541365 10.124759 13.408181 14.155816 7.421184
## [8] 16.879536 13.615153 12.749565
##
## $lower
## [1] 12.1513495 11.8021941 2.5413650 0.1247588 3.4081805 4.1558157
## [7] -2.5788160 6.8795365 3.6151533 2.7495651
##
## $upper
## [1] 32.15135 31.80219 22.54137 20.12476 23.40818 24.15582 17.42118 26.87954
## [9] 23.61515 22.74957t0 <- proc.time()[3]
obj$fit(X_train, y_train, reg_lambda = 0.1)
cat("Elapsed: ", proc.time()[3] - t0, "s \n")## Elapsed: 0.002 sobj$set_level(95)
obj$set_pi_method("splitconformal")
res <- obj$predict(X = X_test)
plot(c(y_train, res$preds), type='l',
main="",
ylab="",
ylim = c(min(c(res$upper, res$lower, y)),
max(c(res$upper, res$lower, y))))
lines(c(y_train, res$upper), col="gray60")
lines(c(y_train, res$lower), col="gray60")
lines(c(y_train, res$preds), col = "red")
lines(c(y_train, y_test), col = "blue")
## [1] 1t0 <- proc.time()[3]
obj$fit(X_train, y_train, reg_lambda = 0.1)
cat("Elapsed: ", proc.time()[3] - t0, "s \n")## Elapsed: 0.002 sres <- obj$predict(X = X_test)
plot(c(y_train, res$preds), type='l',
main="",
ylab="",
ylim = c(min(c(res$upper, res$lower, y)),
max(c(res$upper, res$lower, y))))
lines(c(y_train, res$upper), col="gray60")
lines(c(y_train, res$lower), col="gray60")
lines(c(y_train, res$preds), col = "red")
lines(c(y_train, y_test), col = "blue")
## [1] 1## $R_squared
## [1] -0.8614864
##
## $R_squared_adj
## [1] 17.75338
##
## $Residuals
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## -1.1513 0.5083 3.0680 3.4751 5.9929 8.8586
##
## $Coverage_rate
## [1] 100
##
## $citests
## estimate lower upper p-value signif
## cyl -23.98943109 -46.4975109 -1.4813513 3.918219e-02 *
## disp -0.61133395 -0.9655770 -0.2570909 3.597927e-03 **
## hp -0.07828878 -0.3785573 0.2219797 5.698268e-01
## drat 310.94399534 160.4146969 461.4732937 1.163859e-03 **
## wt -197.39979731 -240.1776661 -154.6219286 2.500030e-06 ***
## qsec -19.50660485 -54.1139966 15.1007869 2.342132e-01
## vs 69.84795566 -85.8899529 225.5858643 3.368080e-01
## am 137.97019623 -0.2148915 276.1552839 5.028830e-02 .
## gear 191.57905165 134.3446800 248.8134233 3.424783e-05 ***
## carb 3.39227959 -22.2875140 29.0720732 7.718555e-01
##
## $signif_codes
## [1] "Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1"
##
## $effects
## ── Data Summary ────────────────────────
## Values
## Name effects
## Number of rows 10
## Number of columns 10
## _______________________
## Column type frequency:
## numeric 10
## ________________________
## Group variables None
##
## ── Variable type: numeric ──────────────────────────────────────────────────────
## skim_variable mean sd p0 p25 p50 p75 p100
## 1 cyl -24.0 31.5 -64.0 -40.9 -34.1 -0.849 37.6
## 2 disp -0.611 0.495 -1.66 -0.934 -0.429 -0.307 -0.0817
## 3 hp -0.0783 0.420 -1.00 -0.218 -0.0402 0.235 0.359
## 4 drat 311. 210. -159. 195. 369. 464. 534.
## 5 wt -197. 59.8 -280. -252. -196. -144. -124.
## 6 qsec -19.5 48.4 -73.4 -60.0 -29.3 12.8 60.3
## 7 vs 69.8 218. -218. -104. 86.1 103. 421.
## 8 am 138. 193. -161. 99.8 162. 201. 516.
## 9 gear 192. 80.0 74.7 142. 178. 224. 367.
## 10 carb 3.39 35.9 -56.3 -6.54 3.71 36.0 41.3
## hist
## 1 ▃▇▂▃▂
## 2 ▂▂▂▆▇
## 3 ▂▁▆▃▇
## 4 ▂▁▆▃▇
## 5 ▇▁▇▂▇
## 6 ▇▇▂▂▅
## 7 ▆▂▇▁▃
## 8 ▂▁▇▁▁
## 9 ▂▇▃▂▂
## 10 ▃▁▆▂▇## Elapsed: 0.098 s## $R_squared
## [1] -0.8614864
##
## $R_squared_adj
## [1] 17.75338
##
## $Residuals
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## -1.1513 0.5083 3.0680 3.4751 5.9929 8.8586
##
## $Coverage_rate
## [1] 100
##
## $citests
## estimate lower upper p-value signif
## cyl -24.90623398 -40.2794196 -5.6202611 3.536958e-165 ***
## disp -0.60214954 -0.9189034 -0.3419554 3.330824e-165 ***
## hp -0.06820063 -0.3342753 0.1339877 1.174915e-64 ***
## drat 314.63303511 178.9216937 418.0172986 3.330824e-165 ***
## wt -197.32353350 -232.9121566 -163.3831785 3.330824e-165 ***
## qsec -19.52528169 -44.6875092 9.0752923 1.159421e-146 ***
## vs 71.87587019 -47.6861837 190.9669405 1.623953e-133 ***
## am 139.18488710 28.8373119 248.4883434 4.072915e-165 ***
## gear 190.53694931 146.5700802 240.0194316 3.330824e-165 ***
## carb 3.53972676 -17.6098472 22.3805033 3.220691e-21 ***
##
## $signif_codes
## [1] "Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1"
##
## $effects
## ── Data Summary ────────────────────────
## Values
## Name effects
## Number of rows 10
## Number of columns 10
## _______________________
## Column type frequency:
## numeric 10
## ________________________
## Group variables None
##
## ── Variable type: numeric ──────────────────────────────────────────────────────
## skim_variable mean sd p0 p25 p50 p75 p100
## 1 cyl -24.0 31.5 -64.0 -40.9 -34.1 -0.849 37.6
## 2 disp -0.611 0.495 -1.66 -0.934 -0.429 -0.307 -0.0817
## 3 hp -0.0783 0.420 -1.00 -0.218 -0.0402 0.235 0.359
## 4 drat 311. 210. -159. 195. 369. 464. 534.
## 5 wt -197. 59.8 -280. -252. -196. -144. -124.
## 6 qsec -19.5 48.4 -73.4 -60.0 -29.3 12.8 60.3
## 7 vs 69.8 218. -218. -104. 86.1 103. 421.
## 8 am 138. 193. -161. 99.8 162. 201. 516.
## 9 gear 192. 80.0 74.7 142. 178. 224. 367.
## 10 carb 3.39 35.9 -56.3 -6.54 3.71 36.0 41.3
## hist
## 1 ▃▇▂▃▂
## 2 ▂▂▂▆▇
## 3 ▂▁▆▃▇
## 4 ▂▁▆▃▇
## 5 ▇▁▇▂▇
## 6 ▇▇▂▂▅
## 7 ▆▂▇▁▃
## 8 ▂▁▇▁▁
## 9 ▂▇▃▂▂
## 10 ▃▁▆▂▇## Elapsed: 0.223 s## $R_squared
## [1] -0.8614864
##
## $R_squared_adj
## [1] 17.75338
##
## $Residuals
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## -1.1513 0.5083 3.0680 3.4751 5.9929 8.8586
##
## $Coverage_rate
## [1] 100
##
## $citests
## estimate lower upper p-value signif
## cyl -30.3071287 -49.9396464 -8.4953754 1.274399e-83 ***
## disp -0.5711107 -0.9053391 -0.2698173 1.248685e-83 ***
## hp -0.1447852 -0.6649476 0.2193783 1.927937e-42 ***
## drat 235.3168021 22.7135545 438.1655998 2.124126e-83 ***
## wt -212.1232593 -259.4448623 -164.8016563 1.252428e-83 ***
## qsec -4.0186808 -46.0259583 39.5943470 4.746701e-04 ***
## vs 83.9673011 -61.9645779 278.4586560 5.121587e-65 ***
## am 96.8375738 -40.2796351 191.6570772 6.634928e-76 ***
## gear 167.6983530 105.2072207 220.0858429 1.255511e-83 ***
## carb -7.0945741 -33.9051378 13.4955287 2.013463e-30 ***
##
## $signif_codes
## [1] "Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1"
##
## $effects
## ── Data Summary ────────────────────────
## Values
## Name effects
## Number of rows 10
## Number of columns 10
## _______________________
## Column type frequency:
## numeric 10
## ________________________
## Group variables None
##
## ── Variable type: numeric ──────────────────────────────────────────────────────
## skim_variable mean sd p0 p25 p50 p75 p100
## 1 cyl -24.0 31.5 -64.0 -40.9 -34.1 -0.849 37.6
## 2 disp -0.611 0.495 -1.66 -0.934 -0.429 -0.307 -0.0817
## 3 hp -0.0783 0.420 -1.00 -0.218 -0.0402 0.235 0.359
## 4 drat 311. 210. -159. 195. 369. 464. 534.
## 5 wt -197. 59.8 -280. -252. -196. -144. -124.
## 6 qsec -19.5 48.4 -73.4 -60.0 -29.3 12.8 60.3
## 7 vs 69.8 218. -218. -104. 86.1 103. 421.
## 8 am 138. 193. -161. 99.8 162. 201. 516.
## 9 gear 192. 80.0 74.7 142. 178. 224. 367.
## 10 carb 3.39 35.9 -56.3 -6.54 3.71 36.0 41.3
## hist
## 1 ▃▇▂▃▂
## 2 ▂▂▂▆▇
## 3 ▂▁▆▃▇
## 4 ▂▁▆▃▇
## 5 ▇▁▇▂▇
## 6 ▇▇▂▂▅
## 7 ▆▂▇▁▃
## 8 ▂▁▇▁▁
## 9 ▂▇▃▂▂
## 10 ▃▁▆▂▇## Elapsed: 0.1 sobj$set_pi_method("kdejackknifeplus")
t0 <- proc.time()[3]
obj$fit(X_train, y_train, reg_lambda = 0.1)## | | | 0% | |=== | 5% | |======= | 10% | |========== | 14% | |============= | 19% | |================= | 24% | |==================== | 29% | |======================= | 33% | |=========================== | 38% | |============================== | 43% | |================================= | 48% | |===================================== | 52% | |======================================== | 57% | |=========================================== | 62% | |=============================================== | 67% | |================================================== | 71% | |===================================================== | 76% | |========================================================= | 81% | |============================================================ | 86% | |=============================================================== | 90% | |=================================================================== | 95% | |======================================================================| 100%## Elapsed: 0.012 sres <- obj$predict(X = X_test)
plot(c(y_train, res$preds), type='l',
main="",
ylab="",
ylim = c(min(c(res$upper, res$lower, y)),
max(c(res$upper, res$lower, y))))
lines(c(y_train, res$upper), col="gray60")
lines(c(y_train, res$lower), col="gray60")
lines(c(y_train, res$preds), col = "red")
lines(c(y_train, y_test), col = "blue")
## [1] 1## $R_squared
## [1] -3.416998
##
## $R_squared_adj
## [1] 40.75299
##
## $Residuals
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 3.516 4.540 6.386 6.917 8.633 12.992
##
## $Coverage_rate
## [1] 100
##
## $citests
## estimate lower upper p-value signif
## cyl -36.7817740 -50.6623622 -22.9011858 2.038888e-04 ***
## disp -0.2133047 -0.6537255 0.2271161 3.017009e-01
## hp -0.2920633 -0.8288709 0.2447443 2.495994e-01
## drat 259.9789584 141.9967301 377.9611867 7.545111e-04 ***
## wt -125.6032827 -159.9084338 -91.2981317 1.675653e-05 ***
## qsec 6.1547882 -22.2053730 34.5149494 6.352182e-01
## vs 35.1176737 -92.7670167 163.0023641 5.498770e-01
## am 85.8109695 -32.8651723 204.4871113 1.363325e-01
## gear 264.4099446 185.2573493 343.5625399 3.479849e-05 ***
## carb -24.1859057 -56.7206453 8.3488338 1.269314e-01
##
## $signif_codes
## [1] "Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1"
##
## $effects
## ── Data Summary ────────────────────────
## Values
## Name effects
## Number of rows 10
## Number of columns 10
## _______________________
## Column type frequency:
## numeric 10
## ________________________
## Group variables None
##
## ── Variable type: numeric ──────────────────────────────────────────────────────
## skim_variable mean sd p0 p25 p50 p75 p100
## 1 cyl -36.8 19.4 -52.8 -48.3 -40.9 -37.7 13.0
## 2 disp -0.213 0.616 -1.19 -0.561 -0.212 -0.146 0.781
## 3 hp -0.292 0.750 -1.73 -0.461 0.00750 0.135 0.531
## 4 drat 260. 165. -74.7 161. 265. 381. 485.
## 5 wt -126. 48.0 -202. -152. -125. -105. -30.9
## 6 qsec 6.15 39.6 -55.5 -20.7 -1.84 33.6 64.2
## 7 vs 35.1 179. -232. -108. 68.7 95.1 292.
## 8 am 85.8 166. -205. 94.4 122. 144. 346.
## 9 gear 264. 111. 122. 206. 242. 301. 529.
## 10 carb -24.2 45.5 -73.7 -54.9 -47.2 22.6 39.5
## hist
## 1 ▇▅▂▁▂
## 2 ▂▃▇▁▃
## 3 ▃▁▂▇▆
## 4 ▂▃▁▇▆
## 5 ▃▂▇▂▂
## 6 ▂▇▅▅▅
## 7 ▇▁▇▅▅
## 8 ▃▁▇▆▂
## 9 ▇▇▇▁▂
## 10 ▇▇▁▂▇## Elapsed: 0.146 s## $R_squared
## [1] -3.416998
##
## $R_squared_adj
## [1] 40.75299
##
## $Residuals
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 3.516 4.540 6.386 6.917 8.633 12.992
##
## $Coverage_rate
## [1] 100
##
## $citests
## estimate lower upper p-value signif
## cyl -37.7454484 -45.5951036 -25.4424864 3.330824e-165 ***
## disp -0.2106604 -0.5751210 0.1509308 3.774075e-133 ***
## hp -0.2879116 -0.7162016 0.1127945 9.161570e-149 ***
## drat 260.2656421 157.3020284 349.2281183 3.330824e-165 ***
## wt -126.0333424 -152.2494144 -97.9210297 3.330824e-165 ***
## qsec 6.5179006 -16.0686231 30.1460294 2.976614e-52 ***
## vs 38.6340339 -67.2977058 131.2472107 2.898223e-78 ***
## am 87.8700197 -8.0927507 171.5314902 7.071000e-160 ***
## gear 263.7730423 206.7863856 330.1303853 3.330824e-165 ***
## carb -24.3011733 -49.1225434 2.5087847 7.537326e-162 ***
##
## $signif_codes
## [1] "Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1"
##
## $effects
## ── Data Summary ────────────────────────
## Values
## Name effects
## Number of rows 10
## Number of columns 10
## _______________________
## Column type frequency:
## numeric 10
## ________________________
## Group variables None
##
## ── Variable type: numeric ──────────────────────────────────────────────────────
## skim_variable mean sd p0 p25 p50 p75 p100
## 1 cyl -36.8 19.4 -52.8 -48.3 -40.9 -37.7 13.0
## 2 disp -0.213 0.616 -1.19 -0.561 -0.212 -0.146 0.781
## 3 hp -0.292 0.750 -1.73 -0.461 0.00750 0.135 0.531
## 4 drat 260. 165. -74.7 161. 265. 381. 485.
## 5 wt -126. 48.0 -202. -152. -125. -105. -30.9
## 6 qsec 6.15 39.6 -55.5 -20.7 -1.84 33.6 64.2
## 7 vs 35.1 179. -232. -108. 68.7 95.1 292.
## 8 am 85.8 166. -205. 94.4 122. 144. 346.
## 9 gear 264. 111. 122. 206. 242. 301. 529.
## 10 carb -24.2 45.5 -73.7 -54.9 -47.2 22.6 39.5
## hist
## 1 ▇▅▂▁▂
## 2 ▂▃▇▁▃
## 3 ▃▁▂▇▆
## 4 ▂▃▁▇▆
## 5 ▃▂▇▂▂
## 6 ▂▇▅▅▅
## 7 ▇▁▇▅▅
## 8 ▃▁▇▆▂
## 9 ▇▇▇▁▂
## 10 ▇▇▁▂▇## Elapsed: 0.271 s## $R_squared
## [1] -3.416998
##
## $R_squared_adj
## [1] 40.75299
##
## $Residuals
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 3.516 4.540 6.386 6.917 8.633 12.992
##
## $Coverage_rate
## [1] 100
##
## $citests
## estimate lower upper p-value signif
## cyl -39.6925349 -46.8125094 -31.4799014 1.250193e-83 ***
## disp -0.2225326 -0.8085783 0.3715319 2.958215e-47 ***
## hp -0.1914698 -0.8268261 0.3270041 1.743778e-31 ***
## drat 241.6087630 67.3659664 403.8505741 1.354810e-83 ***
## wt -125.2136758 -160.8136793 -75.5920029 1.249915e-83 ***
## qsec 5.3742789 -34.4860716 45.2346295 3.512780e-08 ***
## vs 57.7189131 -67.2086900 197.2153460 2.032329e-56 ***
## am 65.7388561 -67.8044887 153.3095833 2.324709e-56 ***
## gear 224.5553844 167.1960533 274.9425132 1.248716e-83 ***
## carb -40.1390242 -64.1761115 -4.3770155 1.820336e-83 ***
##
## $signif_codes
## [1] "Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1"
##
## $effects
## ── Data Summary ────────────────────────
## Values
## Name effects
## Number of rows 10
## Number of columns 10
## _______________________
## Column type frequency:
## numeric 10
## ________________________
## Group variables None
##
## ── Variable type: numeric ──────────────────────────────────────────────────────
## skim_variable mean sd p0 p25 p50 p75 p100
## 1 cyl -36.8 19.4 -52.8 -48.3 -40.9 -37.7 13.0
## 2 disp -0.213 0.616 -1.19 -0.561 -0.212 -0.146 0.781
## 3 hp -0.292 0.750 -1.73 -0.461 0.00750 0.135 0.531
## 4 drat 260. 165. -74.7 161. 265. 381. 485.
## 5 wt -126. 48.0 -202. -152. -125. -105. -30.9
## 6 qsec 6.15 39.6 -55.5 -20.7 -1.84 33.6 64.2
## 7 vs 35.1 179. -232. -108. 68.7 95.1 292.
## 8 am 85.8 166. -205. 94.4 122. 144. 346.
## 9 gear 264. 111. 122. 206. 242. 301. 529.
## 10 carb -24.2 45.5 -73.7 -54.9 -47.2 22.6 39.5
## hist
## 1 ▇▅▂▁▂
## 2 ▂▃▇▁▃
## 3 ▃▁▂▇▆
## 4 ▂▃▁▇▆
## 5 ▃▂▇▂▂
## 6 ▂▇▅▅▅
## 7 ▇▁▇▅▅
## 8 ▃▁▇▆▂
## 9 ▇▇▇▁▂
## 10 ▇▇▁▂▇## Elapsed: 0.148 sxgboost
obj <- learningmachine::Regressor$new(method = "xgboost", pi_method = "splitconformal")
obj$get_type()## [1] "regression"## [1] "Regressor"t0 <- proc.time()[3]
obj$fit(X_train, y_train, nrounds=10, verbose=FALSE)
cat("Elapsed: ", proc.time()[3] - t0, "s \n")## Elapsed: 0.014 s## $preds
## [1] 18.13500 18.13500 17.13105 17.13105 14.64118 14.64118 14.03685 21.29947
## [9] 15.33300 14.03685
##
## $lower
## [1] 12.135002 12.135002 11.131052 11.131052 8.641179 8.641179 8.036854
## [8] 15.299475 9.333004 8.036854
##
## $upper
## [1] 24.13500 24.13500 23.13105 23.13105 20.64118 20.64118 20.03685 27.29947
## [9] 21.33300 20.03685## $R_squared
## [1] 0.2881145
##
## $R_squared_adj
## [1] 7.406969
##
## $Residuals
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## -3.6369 0.3926 2.2088 1.5079 2.8650 5.1631
##
## $Coverage_rate
## [1] 100
##
## $citests
## estimate lower upper p-value signif
## cyl 0.0000000 NaN NaN NaN
## disp -0.1859971 -0.6067516 0.2347575 0.3434364
## hp 0.0000000 NaN NaN NaN
## drat 28.9866074 -18.4823056 76.4555203 0.2004909
## wt 0.0000000 NaN NaN NaN
## qsec -1.7295559 -5.6420830 2.1829713 0.3434364
## vs 0.0000000 NaN NaN NaN
## am 0.0000000 NaN NaN NaN
## gear 0.0000000 NaN NaN NaN
## carb 0.0000000 NaN NaN NaN
##
## $signif_codes
## [1] "Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1"
##
## $effects
## ── Data Summary ────────────────────────
## Values
## Name effects
## Number of rows 10
## Number of columns 10
## _______________________
## Column type frequency:
## numeric 10
## ________________________
## Group variables None
##
## ── Variable type: numeric ──────────────────────────────────────────────────────
## skim_variable mean sd p0 p25 p50 p75 p100 hist
## 1 cyl 0 0 0 0 0 0 0 ▁▁▇▁▁
## 2 disp -0.186 0.588 -1.86 0 0 0 0 ▁▁▁▁▇
## 3 hp 0 0 0 0 0 0 0 ▁▁▇▁▁
## 4 drat 29.0 66.4 0 0 0 0 200. ▇▁▁▁▁
## 5 wt 0 0 0 0 0 0 0 ▁▁▇▁▁
## 6 qsec -1.73 5.47 -17.3 0 0 0 0 ▁▁▁▁▇
## 7 vs 0 0 0 0 0 0 0 ▁▁▇▁▁
## 8 am 0 0 0 0 0 0 0 ▁▁▇▁▁
## 9 gear 0 0 0 0 0 0 0 ▁▁▇▁▁
## 10 carb 0 0 0 0 0 0 0 ▁▁▇▁▁## Elapsed: 0.181 s## Warning in wilcox.test.default(x, mu = mu_0): cannot compute exact p-value with
## zeroes
## Warning in wilcox.test.default(x, mu = mu_0): cannot compute exact p-value with
## zeroes
## Warning in wilcox.test.default(x, mu = mu_0): cannot compute exact p-value with
## zeroes
## Warning in wilcox.test.default(x, mu = mu_0): cannot compute exact p-value with
## zeroes
## Warning in wilcox.test.default(x, mu = mu_0): cannot compute exact p-value with
## zeroes
## Warning in wilcox.test.default(x, mu = mu_0): cannot compute exact p-value with
## zeroes
## Warning in wilcox.test.default(x, mu = mu_0): cannot compute exact p-value with
## zeroes## $R_squared
## [1] 0.2881145
##
## $R_squared_adj
## [1] 7.406969
##
## $Residuals
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## -3.6369 0.3926 2.2088 1.5079 2.8650 5.1631
##
## $Coverage_rate
## [1] 100
##
## $citests
## estimate lower upper p-value signif
## cyl 0.0000000 0.0000000 0.00000 NaN
## disp -0.1859971 -0.5579912 0.00000 8.962365e-118 ***
## hp 0.0000000 0.0000000 0.00000 NaN
## drat 28.9866074 0.0000000 77.95299 5.856765e-149 ***
## wt 0.0000000 0.0000000 0.00000 NaN
## qsec -1.7295559 -5.1886676 0.00000 9.526227e-117 ***
## vs 0.0000000 0.0000000 0.00000 NaN
## am 0.0000000 0.0000000 0.00000 NaN
## gear 0.0000000 0.0000000 0.00000 NaN
## carb 0.0000000 0.0000000 0.00000 NaN
##
## $signif_codes
## [1] "Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1"
##
## $effects
## ── Data Summary ────────────────────────
## Values
## Name effects
## Number of rows 10
## Number of columns 10
## _______________________
## Column type frequency:
## numeric 10
## ________________________
## Group variables None
##
## ── Variable type: numeric ──────────────────────────────────────────────────────
## skim_variable mean sd p0 p25 p50 p75 p100 hist
## 1 cyl 0 0 0 0 0 0 0 ▁▁▇▁▁
## 2 disp -0.186 0.588 -1.86 0 0 0 0 ▁▁▁▁▇
## 3 hp 0 0 0 0 0 0 0 ▁▁▇▁▁
## 4 drat 29.0 66.4 0 0 0 0 200. ▇▁▁▁▁
## 5 wt 0 0 0 0 0 0 0 ▁▁▇▁▁
## 6 qsec -1.73 5.47 -17.3 0 0 0 0 ▁▁▁▁▇
## 7 vs 0 0 0 0 0 0 0 ▁▁▇▁▁
## 8 am 0 0 0 0 0 0 0 ▁▁▇▁▁
## 9 gear 0 0 0 0 0 0 0 ▁▁▇▁▁
## 10 carb 0 0 0 0 0 0 0 ▁▁▇▁▁## Elapsed: 0.303 s## Warning in wilcox.test.default(x, mu = mu_0): cannot compute exact p-value with
## zeroes
## Warning in wilcox.test.default(x, mu = mu_0): cannot compute exact p-value with
## zeroes
## Warning in wilcox.test.default(x, mu = mu_0): cannot compute exact p-value with
## zeroes
## Warning in wilcox.test.default(x, mu = mu_0): cannot compute exact p-value with
## zeroes
## Warning in wilcox.test.default(x, mu = mu_0): cannot compute exact p-value with
## zeroes
## Warning in wilcox.test.default(x, mu = mu_0): cannot compute exact p-value with
## zeroes
## Warning in wilcox.test.default(x, mu = mu_0): cannot compute exact p-value with
## zeroes
## Warning in wilcox.test.default(x, mu = mu_0): cannot compute exact p-value with
## zeroes## $R_squared
## [1] 0.2881145
##
## $R_squared_adj
## [1] 7.406969
##
## $Residuals
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## -3.6369 0.3926 2.2088 1.5079 2.8650 5.1631
##
## $Coverage_rate
## [1] 100
##
## $citests
## estimate lower upper p-value signif
## cyl 0.0000000 0.000000 0.0000 NaN
## disp -0.3719941 -1.115982 0.0000 3.09525e-59 ***
## hp 0.0000000 0.000000 0.0000 NaN
## drat 39.9595601 0.000000 119.8787 2.16282e-59 ***
## wt 0.0000000 0.000000 0.0000 NaN
## qsec 0.0000000 0.000000 0.0000 NaN
## vs 0.0000000 0.000000 0.0000 NaN
## am 0.0000000 0.000000 0.0000 NaN
## gear 0.0000000 0.000000 0.0000 NaN
## carb 0.0000000 0.000000 0.0000 NaN
##
## $signif_codes
## [1] "Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1"
##
## $effects
## ── Data Summary ────────────────────────
## Values
## Name effects
## Number of rows 10
## Number of columns 10
## _______________________
## Column type frequency:
## numeric 10
## ________________________
## Group variables None
##
## ── Variable type: numeric ──────────────────────────────────────────────────────
## skim_variable mean sd p0 p25 p50 p75 p100 hist
## 1 cyl 0 0 0 0 0 0 0 ▁▁▇▁▁
## 2 disp -0.186 0.588 -1.86 0 0 0 0 ▁▁▁▁▇
## 3 hp 0 0 0 0 0 0 0 ▁▁▇▁▁
## 4 drat 29.0 66.4 0 0 0 0 200. ▇▁▁▁▁
## 5 wt 0 0 0 0 0 0 0 ▁▁▇▁▁
## 6 qsec -1.73 5.47 -17.3 0 0 0 0 ▁▁▁▁▇
## 7 vs 0 0 0 0 0 0 0 ▁▁▇▁▁
## 8 am 0 0 0 0 0 0 0 ▁▁▇▁▁
## 9 gear 0 0 0 0 0 0 0 ▁▁▇▁▁
## 10 carb 0 0 0 0 0 0 0 ▁▁▇▁▁## Elapsed: 0.181 st0 <- proc.time()[3]
obj$fit(X_train, y_train, nrounds=10, verbose=FALSE)
cat("Elapsed: ", proc.time()[3] - t0, "s \n")## Elapsed: 0.007 sobj$set_level(95)
res <- obj$predict(X = X_test)
plot(c(y_train, res$preds), type='l',
main="",
ylab="",
ylim = c(min(c(res$upper, res$lower, y)),
max(c(res$upper, res$lower, y))))
lines(c(y_train, res$upper), col="gray60")
lines(c(y_train, res$lower), col="gray60")
lines(c(y_train, res$preds), col = "red")
lines(c(y_train, y_test), col = "blue")
## [1] 1obj$set_pi_method("kdesplitconformal")
t0 <- proc.time()[3]
obj$fit(X_train, y_train, nrounds=10, verbose=FALSE)
cat("Elapsed: ", proc.time()[3] - t0, "s \n")## Elapsed: 0.008 sobj$set_level(95)
res <- obj$predict(X = X_test)
plot(c(y_train, res$preds), type='l',
main="",
ylab="",
ylim = c(min(c(res$upper, res$lower, y)),
max(c(res$upper, res$lower, y))))
lines(c(y_train, res$upper), col="gray60")
lines(c(y_train, res$lower), col="gray60")
lines(c(y_train, res$preds), col = "red")
lines(c(y_train, y_test), col = "blue")
## [1] 1obj$set_pi_method("bootjackknifeplus")
t0 <- proc.time()[3]
obj$fit(X_train, y_train, nrounds=10, verbose=FALSE)
cat("Elapsed: ", proc.time()[3] - t0, "s \n")## Elapsed: 0 sobj$set_level(95)
res <- obj$predict(X = X_test)
plot(c(y_train, res$preds), type='l',
main="",
ylab="",
ylim = c(min(c(res$upper, res$lower, y)),
max(c(res$upper, res$lower, y))))
lines(c(y_train, res$upper), col="gray60")
lines(c(y_train, res$lower), col="gray60")
lines(c(y_train, res$preds), col = "red")
lines(c(y_train, y_test), col = "blue")
## [1] 14 - RVFL regression
obj <- learningmachine::Regressor$new(method = "rvfl",
nb_hidden = 50L,
pi_method = "splitconformal")
obj$get_type()## [1] "regression"## [1] "Regressor"t0 <- proc.time()[3]
obj$fit(X_train, y_train, reg_lambda = 0.01)
cat("Elapsed: ", proc.time()[3] - t0, "s \n")## Elapsed: 0.004 s## $preds
## Mazda RX4 Mazda RX4 Wag Hornet 4 Drive Valiant
## 21.350888 19.789387 13.106761 9.695310
## Merc 450SE Merc 450SL Lincoln Continental Toyota Corona
## 11.131161 12.568682 2.044672 19.289805
## Camaro Z28 Pontiac Firebird
## 14.847878 12.282272
##
## $lower
## Mazda RX4 Mazda RX4 Wag Hornet 4 Drive Valiant
## 12.3508879 10.7893873 4.1067608 0.6953102
## Merc 450SE Merc 450SL Lincoln Continental Toyota Corona
## 2.1311611 3.5686817 -6.9553279 10.2898053
## Camaro Z28 Pontiac Firebird
## 5.8478777 3.2822719
##
## $upper
## Mazda RX4 Mazda RX4 Wag Hornet 4 Drive Valiant
## 30.35089 28.78939 22.10676 18.69531
## Merc 450SE Merc 450SL Lincoln Continental Toyota Corona
## 20.13116 21.56868 11.04467 28.28981
## Camaro Z28 Pontiac Firebird
## 23.84788 21.28227## $R_squared
## [1] -1.505856
##
## $R_squared_adj
## [1] 23.55271
##
## $Residuals
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## -1.548 1.461 5.000 4.349 7.949 8.405
##
## $Coverage_rate
## [1] 100
##
## $citests
## estimate lower upper p-value signif
## cyl 137.649985 39.777048 235.5229227 1.115728e-02 *
## disp -2.406399 -4.650678 -0.1621204 3.825959e-02 *
## hp -0.527573 -1.402043 0.3468975 2.054686e-01
## drat 707.372951 246.095138 1168.6507638 7.059500e-03 **
## wt -500.429007 -565.047979 -435.8100352 2.910469e-08 ***
## qsec -89.930939 -124.899691 -54.9621860 2.537870e-04 ***
## vs 234.198406 -127.886990 596.2838006 1.774484e-01
## am -235.789718 -512.422513 40.8430776 8.592503e-02 .
## gear 52.646721 -6.640614 111.9340567 7.547657e-02 .
## carb -17.100561 -87.819649 53.6185270 5.976705e-01
##
## $signif_codes
## [1] "Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1"
##
## $effects
## ── Data Summary ────────────────────────
## Values
## Name effects
## Number of rows 10
## Number of columns 10
## _______________________
## Column type frequency:
## numeric 10
## ________________________
## Group variables None
##
## ── Variable type: numeric ──────────────────────────────────────────────────────
## skim_variable mean sd p0 p25 p50 p75 p100
## 1 cyl 138. 137. -8.40 75.8 91.1 98.6 394.
## 2 disp -2.41 3.14 -8.46 -1.32 -1.08 -0.775 -0.300
## 3 hp -0.528 1.22 -3.40 -0.695 -0.188 0.0137 0.893
## 4 drat 707. 645. 55.7 388. 482. 563. 1939.
## 5 wt -500. 90.3 -698. -538. -500. -458. -377.
## 6 qsec -89.9 48.9 -145. -128. -102. -64.0 2.67
## 7 vs 234. 506. -121. -13.2 36.8 53.2 1269.
## 8 am -236. 387. -653. -450. -397. -168. 519.
## 9 gear 52.6 82.9 -107. -4.69 66.2 112. 170.
## 10 carb -17.1 98.9 -117. -64.6 -60.6 -17.5 171.
## hist
## 1 ▂▇▁▁▂
## 2 ▂▁▁▁▇
## 3 ▁▁▁▇▂
## 4 ▅▇▁▁▃
## 5 ▂▁▆▇▃
## 6 ▇▆▁▂▃
## 7 ▇▁▁▁▂
## 8 ▆▇▂▁▃
## 9 ▂▅▅▅▇
## 10 ▇▂▁▁▂## Elapsed: 0.123 s## $R_squared
## [1] -1.505856
##
## $R_squared_adj
## [1] 23.55271
##
## $Residuals
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## -1.548 1.461 5.000 4.349 7.949 8.405
##
## $Coverage_rate
## [1] 100
##
## $citests
## estimate lower upper p-value signif
## cyl 137.0111423 69.296022 213.05499150 3.330824e-165 ***
## disp -2.4063335 -4.151551 -0.85145010 3.330755e-165 ***
## hp -0.4894821 -1.206580 0.06393166 1.559621e-159 ***
## drat 704.2409575 379.648789 1088.69475280 3.330824e-165 ***
## wt -499.6464041 -553.621396 -453.75958810 3.330824e-165 ***
## qsec -89.9155324 -116.434421 -60.70468612 3.330824e-165 ***
## vs 235.1520119 -14.444923 528.12353553 2.876117e-162 ***
## am -241.1699530 -437.064336 -4.24144263 3.530328e-163 ***
## gear 52.2145847 5.676782 96.67674463 1.907992e-164 ***
## carb -17.7070158 -67.018662 43.26358463 1.396168e-56 ***
##
## $signif_codes
## [1] "Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1"
##
## $effects
## ── Data Summary ────────────────────────
## Values
## Name effects
## Number of rows 10
## Number of columns 10
## _______________________
## Column type frequency:
## numeric 10
## ________________________
## Group variables None
##
## ── Variable type: numeric ──────────────────────────────────────────────────────
## skim_variable mean sd p0 p25 p50 p75 p100
## 1 cyl 138. 137. -8.40 75.8 91.1 98.6 394.
## 2 disp -2.41 3.14 -8.46 -1.32 -1.08 -0.775 -0.300
## 3 hp -0.528 1.22 -3.40 -0.695 -0.188 0.0137 0.893
## 4 drat 707. 645. 55.7 388. 482. 563. 1939.
## 5 wt -500. 90.3 -698. -538. -500. -458. -377.
## 6 qsec -89.9 48.9 -145. -128. -102. -64.0 2.67
## 7 vs 234. 506. -121. -13.2 36.8 53.2 1269.
## 8 am -236. 387. -653. -450. -397. -168. 519.
## 9 gear 52.6 82.9 -107. -4.69 66.2 112. 170.
## 10 carb -17.1 98.9 -117. -64.6 -60.6 -17.5 171.
## hist
## 1 ▂▇▁▁▂
## 2 ▂▁▁▁▇
## 3 ▁▁▁▇▂
## 4 ▅▇▁▁▃
## 5 ▂▁▆▇▃
## 6 ▇▆▁▂▃
## 7 ▇▁▁▁▂
## 8 ▆▇▂▁▃
## 9 ▂▅▅▅▇
## 10 ▇▂▁▁▂## Elapsed: 0.235 s## $R_squared
## [1] -1.505856
##
## $R_squared_adj
## [1] 23.55271
##
## $Residuals
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## -1.548 1.461 5.000 4.349 7.949 8.405
##
## $Coverage_rate
## [1] 100
##
## $citests
## estimate lower upper p-value signif
## cyl 150.3445262 88.261264 269.41286765 1.248649e-83 ***
## disp -2.4328464 -5.421507 -0.81931062 1.249850e-83 ***
## hp -0.4640731 -1.082605 -0.06685299 1.794965e-83 ***
## drat 662.0105731 262.533030 1325.90195856 1.252851e-83 ***
## wt -474.1652942 -517.745280 -421.84616624 1.255113e-83 ***
## qsec -87.0403486 -131.680654 -38.41153592 1.246480e-83 ***
## vs 250.8622825 -48.266736 766.57411839 4.761711e-64 ***
## am -253.3430623 -539.300395 152.68582253 3.046252e-73 ***
## gear 67.8915285 20.918430 106.80377874 1.252445e-83 ***
## carb -15.7962310 -70.922940 80.05178042 7.220253e-13 ***
##
## $signif_codes
## [1] "Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1"
##
## $effects
## ── Data Summary ────────────────────────
## Values
## Name effects
## Number of rows 10
## Number of columns 10
## _______________________
## Column type frequency:
## numeric 10
## ________________________
## Group variables None
##
## ── Variable type: numeric ──────────────────────────────────────────────────────
## skim_variable mean sd p0 p25 p50 p75 p100
## 1 cyl 138. 137. -8.40 75.8 91.1 98.6 394.
## 2 disp -2.41 3.14 -8.46 -1.32 -1.08 -0.775 -0.300
## 3 hp -0.528 1.22 -3.40 -0.695 -0.188 0.0137 0.893
## 4 drat 707. 645. 55.7 388. 482. 563. 1939.
## 5 wt -500. 90.3 -698. -538. -500. -458. -377.
## 6 qsec -89.9 48.9 -145. -128. -102. -64.0 2.67
## 7 vs 234. 506. -121. -13.2 36.8 53.2 1269.
## 8 am -236. 387. -653. -450. -397. -168. 519.
## 9 gear 52.6 82.9 -107. -4.69 66.2 112. 170.
## 10 carb -17.1 98.9 -117. -64.6 -60.6 -17.5 171.
## hist
## 1 ▂▇▁▁▂
## 2 ▂▁▁▁▇
## 3 ▁▁▁▇▂
## 4 ▅▇▁▁▃
## 5 ▂▁▆▇▃
## 6 ▇▆▁▂▃
## 7 ▇▁▁▁▂
## 8 ▆▇▂▁▃
## 9 ▂▅▅▅▇
## 10 ▇▂▁▁▂## Elapsed: 0.113 s## Elapsed: 0.003 sobj$set_level(95)
res <- obj$predict(X = X_test)
plot(c(y_train, res$preds), type='l',
main="",
ylab="",
ylim = c(min(c(res$upper, res$lower, y)),
max(c(res$upper, res$lower, y))))
lines(c(y_train, res$upper), col="gray60")
lines(c(y_train, res$lower), col="gray60")
lines(c(y_train, res$preds), col = "red")
lines(c(y_train, y_test), col = "blue")
abline(v = length(y_train), lty=2, col="black")
## [1] 1update RVFL model
newx <- X_test[1, ]
newy <- y_test[1]
new_X_test <- X_test[-1, ]
new_y_test <- y_test[-1]
t0 <- proc.time()[3]
obj$update(newx, newy)
cat("Elapsed: ", proc.time()[3] - t0, "s \n")## Elapsed: 0.003 s## Min. 1st Qu. Median Mean 3rd Qu. Max.
## -0.68212 -0.26567 -0.05157 0.00700 0.21046 2.19222## Min. 1st Qu. Median Mean 3rd Qu. Max.
## -0.030666 -0.002610 0.004189 0.002917 0.011386 0.025243
## $R_squared
## [1] -1.809339
##
## $R_squared_adj
## [1] 12.23735
##
## $Residuals
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## -1.168 2.513 5.541 5.058 8.185 8.703
##
## $Coverage_rate
## [1] 100
##
## $citests
## estimate lower upper p-value signif
## cyl 111.6701473 17.076928 206.2633669 2.615518e-02 *
## disp -1.7983224 -3.876380 0.2797349 8.106884e-02 .
## hp -0.4167545 -1.501658 0.6681495 4.015523e-01
## drat 569.9102780 148.862037 990.9585186 1.420088e-02 *
## wt -504.1496696 -583.757006 -424.5423330 4.741273e-07 ***
## qsec -107.9102921 -138.571336 -77.2492482 3.936777e-05 ***
## vs 145.0280002 -173.164419 463.2204193 3.239468e-01
## am -319.6910568 -566.618653 -72.7634604 1.745263e-02 *
## gear 57.7630332 -18.934712 134.4607782 1.206459e-01
## carb -42.9572292 -108.690903 22.7764447 1.702409e-01
##
## $signif_codes
## [1] "Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1"
##
## $effects
## ── Data Summary ────────────────────────
## Values
## Name effects
## Number of rows 9
## Number of columns 10
## _______________________
## Column type frequency:
## numeric 10
## ________________________
## Group variables None
##
## ── Variable type: numeric ──────────────────────────────────────────────────────
## skim_variable mean sd p0 p25 p50 p75 p100
## 1 cyl 112. 123. -13.5 64.5 93.6 93.9 426.
## 2 disp -1.80 2.70 -8.94 -1.41 -0.805 -0.689 -0.361
## 3 hp -0.417 1.41 -3.54 -0.679 -0.0942 -0.0556 1.19
## 4 drat 570. 548. 36.8 371. 439. 501. 1972.
## 5 wt -504. 104. -742. -523. -497. -461. -382.
## 6 qsec -108. 39.9 -152. -143. -115. -93.0 -35.9
## 7 vs 145. 414. -116. -23.9 51.1 81.2 1231.
## 8 am -320. 321. -575. -479. -395. -368. 465.
## 9 gear 57.8 99.8 -113. 1.22 35.2 130. 196.
## 10 carb -43.0 85.5 -129. -79.6 -77.9 -22.5 165.
## hist
## 1 ▅▇▁▁▂
## 2 ▁▁▁▁▇
## 3 ▂▁▂▇▃
## 4 ▅▇▁▁▂
## 5 ▂▁▂▇▃
## 6 ▇▅▅▂▂
## 7 ▇▁▁▁▁
## 8 ▇▁▁▁▁
## 9 ▃▇▇▇▇
## 10 ▇▅▁▁▂## Elapsed: 0.127 sstart <- proc.time()[3]
obj$summary(new_X_test, y=new_y_test, show_progress=FALSE, type_ci="bootstrap")## $R_squared
## [1] -1.809339
##
## $R_squared_adj
## [1] 12.23735
##
## $Residuals
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## -1.168 2.513 5.541 5.058 8.185 8.703
##
## $Coverage_rate
## [1] 100
##
## $citests
## estimate lower upper p-value signif
## cyl 112.3919404 55.200080 198.90428 3.330730e-165 ***
## disp -1.7848239 -3.647352 -0.74150 3.330730e-165 ***
## hp -0.3674135 -1.299011 0.34313 3.063436e-110 ***
## drat 565.9832345 325.398523 950.32059 3.330730e-165 ***
## wt -504.3143079 -572.073593 -451.85782 3.330730e-165 ***
## qsec -107.9791731 -129.437921 -82.20922 3.330730e-165 ***
## vs 144.4399640 -32.248151 427.63924 2.565958e-145 ***
## am -324.5343769 -475.286679 -100.58739 3.688681e-165 ***
## gear 57.8310159 -1.595434 116.61761 2.545767e-162 ***
## carb -42.8382811 -84.631850 12.61998 4.603546e-153 ***
##
## $signif_codes
## [1] "Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1"
##
## $effects
## ── Data Summary ────────────────────────
## Values
## Name effects
## Number of rows 9
## Number of columns 10
## _______________________
## Column type frequency:
## numeric 10
## ________________________
## Group variables None
##
## ── Variable type: numeric ──────────────────────────────────────────────────────
## skim_variable mean sd p0 p25 p50 p75 p100
## 1 cyl 112. 123. -13.5 64.5 93.6 93.9 426.
## 2 disp -1.80 2.70 -8.94 -1.41 -0.805 -0.689 -0.361
## 3 hp -0.417 1.41 -3.54 -0.679 -0.0942 -0.0556 1.19
## 4 drat 570. 548. 36.8 371. 439. 501. 1972.
## 5 wt -504. 104. -742. -523. -497. -461. -382.
## 6 qsec -108. 39.9 -152. -143. -115. -93.0 -35.9
## 7 vs 145. 414. -116. -23.9 51.1 81.2 1231.
## 8 am -320. 321. -575. -479. -395. -368. 465.
## 9 gear 57.8 99.8 -113. 1.22 35.2 130. 196.
## 10 carb -43.0 85.5 -129. -79.6 -77.9 -22.5 165.
## hist
## 1 ▅▇▁▁▂
## 2 ▁▁▁▁▇
## 3 ▂▁▂▇▃
## 4 ▅▇▁▁▂
## 5 ▂▁▂▇▃
## 6 ▇▅▅▂▂
## 7 ▇▁▁▁▁
## 8 ▇▁▁▁▁
## 9 ▃▇▇▇▇
## 10 ▇▅▁▁▂## Elapsed: 0.234 sstart <- proc.time()[3]
obj$summary(new_X_test, y=new_y_test, show_progress=FALSE, type_ci="conformal")## $R_squared
## [1] -1.809339
##
## $R_squared_adj
## [1] 12.23735
##
## $Residuals
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## -1.168 2.513 5.541 5.058 8.185 8.703
##
## $Coverage_rate
## [1] 100
##
## $citests
## estimate lower upper p-value signif
## cyl 140.206405 31.603822 293.1593917 1.250495e-83 ***
## disp -2.350759 -5.684574 -0.5579624 1.246806e-83 ***
## hp -1.063336 -2.384855 -0.2331024 1.246643e-83 ***
## drat 664.475986 223.820350 1304.6007257 1.251103e-83 ***
## wt -497.028711 -612.525811 -408.8952369 1.252549e-83 ***
## qsec -102.835585 -141.642304 -62.5335162 1.250340e-83 ***
## vs 301.065907 64.994420 770.3673395 1.170730e-83 ***
## am -223.403879 -467.258502 171.5791962 8.896529e-68 ***
## gear 107.408867 52.086950 163.9796862 1.250275e-83 ***
## carb -40.474522 -108.737967 67.5130388 4.138039e-49 ***
##
## $signif_codes
## [1] "Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1"
##
## $effects
## ── Data Summary ────────────────────────
## Values
## Name effects
## Number of rows 9
## Number of columns 10
## _______________________
## Column type frequency:
## numeric 10
## ________________________
## Group variables None
##
## ── Variable type: numeric ──────────────────────────────────────────────────────
## skim_variable mean sd p0 p25 p50 p75 p100
## 1 cyl 112. 123. -13.5 64.5 93.6 93.9 426.
## 2 disp -1.80 2.70 -8.94 -1.41 -0.805 -0.689 -0.361
## 3 hp -0.417 1.41 -3.54 -0.679 -0.0942 -0.0556 1.19
## 4 drat 570. 548. 36.8 371. 439. 501. 1972.
## 5 wt -504. 104. -742. -523. -497. -461. -382.
## 6 qsec -108. 39.9 -152. -143. -115. -93.0 -35.9
## 7 vs 145. 414. -116. -23.9 51.1 81.2 1231.
## 8 am -320. 321. -575. -479. -395. -368. 465.
## 9 gear 57.8 99.8 -113. 1.22 35.2 130. 196.
## 10 carb -43.0 85.5 -129. -79.6 -77.9 -22.5 165.
## hist
## 1 ▅▇▁▁▂
## 2 ▁▁▁▁▇
## 3 ▂▁▂▇▃
## 4 ▅▇▁▁▂
## 5 ▂▁▂▇▃
## 6 ▇▅▅▂▂
## 7 ▇▁▁▁▁
## 8 ▇▁▁▁▁
## 9 ▃▇▇▇▇
## 10 ▇▅▁▁▂## Elapsed: 0.11 sres <- obj$predict(X = new_X_test)
new_y_train <- c(y_train, newy)
plot(c(new_y_train, res$preds), type='l',
main="",
ylab="",
ylim = c(min(c(res$upper, res$lower, y)),
max(c(res$upper, res$lower, y))))
lines(c(new_y_train, res$upper), col="gray60")
lines(c(new_y_train, res$lower), col="gray60")
lines(c(new_y_train, res$preds), col = "red")
lines(c(new_y_train, new_y_test), col = "blue")
abline(v = length(y_train), lty=2, col="black")
## [1] 1update RVFL model (Pt.2)
newx <- X_test[2, ]
newy <- y_test[2]
new_X_test <- X_test[-c(1, 2), ]
new_y_test <- y_test[-c(1, 2)]## Elapsed: 0.002 s## $R_squared
## [1] -3.356623
##
## $R_squared_adj
## [1] 11.16545
##
## $Residuals
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## -1.950 5.030 6.374 6.369 8.774 11.528
##
## $Coverage_rate
## [1] 75
##
## $citests
## estimate lower upper p-value signif
## cyl 40.8981137 6.878148 74.9180798 2.494779e-02 *
## disp -0.7335494 -1.206939 -0.2601595 8.026181e-03 **
## hp -0.8233606 -2.198927 0.5522055 1.998737e-01
## drat 549.7206897 416.053783 683.3875968 2.570765e-05 ***
## wt -469.9351032 -535.877454 -403.9927527 6.344763e-07 ***
## qsec -116.6183871 -156.767393 -76.4693814 2.380078e-04 ***
## vs -194.4213942 -288.046178 -100.7966103 1.732503e-03 **
## am -395.7216847 -562.762331 -228.6810387 8.143911e-04 ***
## gear 53.0732573 -59.833653 165.9801679 3.030574e-01
## carb -25.9448064 -63.759959 11.8703467 1.487567e-01
##
## $signif_codes
## [1] "Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1"
##
## $effects
## ── Data Summary ────────────────────────
## Values
## Name effects
## Number of rows 8
## Number of columns 10
## _______________________
## Column type frequency:
## numeric 10
## ________________________
## Group variables None
##
## ── Variable type: numeric ──────────────────────────────────────────────────────
## skim_variable mean sd p0 p25 p50 p75 p100
## 1 cyl 40.9 40.7 -40.5 23.9 56.3 69.9 77.8
## 2 disp -0.734 0.566 -1.64 -1.03 -0.571 -0.372 -0.139
## 3 hp -0.823 1.65 -3.99 -1.18 -0.974 -0.196 1.25
## 4 drat 550. 160. 170. 549. 606. 642. 643.
## 5 wt -470. 78.9 -543. -537. -489. -437. -336.
## 6 qsec -117. 48.0 -179. -143. -131. -99.1 -29.9
## 7 vs -194. 112. -377. -283. -162. -120. -46.3
## 8 am -396. 200. -719. -481. -357. -319. -67.7
## 9 gear 53.1 135. -143. -23.9 16.5 172. 231.
## 10 carb -25.9 45.2 -101. -48.8 -23.8 -9.36 45.7
## hist
## 1 ▂▂▂▁▇
## 2 ▅▁▂▇▅
## 3 ▂▁▇▂▃
## 4 ▁▁▁▁▇
## 5 ▇▅▂▁▅
## 6 ▂▇▂▂▂
## 7 ▂▅▂▇▂
## 8 ▃▁▇▂▂
## 9 ▂▅▅▁▇
## 10 ▂▅▇▁▅## Elapsed: 0.1 st0 <- proc.time()[3]
obj$summary(new_X_test, y=new_y_test, show_progress=FALSE, type_ci="bootstrap")## $R_squared
## [1] -3.356623
##
## $R_squared_adj
## [1] 11.16545
##
## $Residuals
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## -1.950 5.030 6.374 6.369 8.774 11.528
##
## $Coverage_rate
## [1] 75
##
## $citests
## estimate lower upper p-value signif
## cyl 41.4258367 12.588077 65.2679002 4.350539e-165 ***
## disp -0.7222008 -1.115485 -0.4125830 3.330513e-165 ***
## hp -0.8065083 -1.909190 0.1497299 1.786493e-158 ***
## drat 558.7650921 437.296154 627.3085008 3.330513e-165 ***
## wt -472.0764594 -515.956910 -418.1652602 3.330513e-165 ***
## qsec -118.3772945 -145.482273 -83.8895245 3.330513e-165 ***
## vs -193.6445785 -265.087370 -124.5273605 3.329761e-165 ***
## am -388.8129686 -519.250653 -272.5465744 3.330513e-165 ***
## gear 51.8672891 -32.695264 137.3143094 4.222165e-136 ***
## carb -25.7347296 -54.019221 2.3478991 1.826091e-161 ***
##
## $signif_codes
## [1] "Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1"
##
## $effects
## ── Data Summary ────────────────────────
## Values
## Name effects
## Number of rows 8
## Number of columns 10
## _______________________
## Column type frequency:
## numeric 10
## ________________________
## Group variables None
##
## ── Variable type: numeric ──────────────────────────────────────────────────────
## skim_variable mean sd p0 p25 p50 p75 p100
## 1 cyl 40.9 40.7 -40.5 23.9 56.3 69.9 77.8
## 2 disp -0.734 0.566 -1.64 -1.03 -0.571 -0.372 -0.139
## 3 hp -0.823 1.65 -3.99 -1.18 -0.974 -0.196 1.25
## 4 drat 550. 160. 170. 549. 606. 642. 643.
## 5 wt -470. 78.9 -543. -537. -489. -437. -336.
## 6 qsec -117. 48.0 -179. -143. -131. -99.1 -29.9
## 7 vs -194. 112. -377. -283. -162. -120. -46.3
## 8 am -396. 200. -719. -481. -357. -319. -67.7
## 9 gear 53.1 135. -143. -23.9 16.5 172. 231.
## 10 carb -25.9 45.2 -101. -48.8 -23.8 -9.36 45.7
## hist
## 1 ▂▂▂▁▇
## 2 ▅▁▂▇▅
## 3 ▂▁▇▂▃
## 4 ▁▁▁▁▇
## 5 ▇▅▂▁▅
## 6 ▂▇▂▂▂
## 7 ▂▅▂▇▂
## 8 ▃▁▇▂▂
## 9 ▂▅▅▁▇
## 10 ▂▅▇▁▅## Elapsed: 0.228 st0 <- proc.time()[3]
obj$summary(new_X_test, y=new_y_test, show_progress=FALSE, type_ci="conformal")## $R_squared
## [1] -3.356623
##
## $R_squared_adj
## [1] 11.16545
##
## $Residuals
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## -1.950 5.030 6.374 6.369 8.774 11.528
##
## $Coverage_rate
## [1] 75
##
## $citests
## estimate lower upper p-value signif
## cyl 58.2449258 39.674124 73.4093157 1.110860e-83 ***
## disp -0.7298717 -1.364532 -0.2545631 1.136036e-83 ***
## hp -0.3864945 -1.054373 0.6831616 3.352809e-48 ***
## drat 597.4424346 554.087929 640.7969406 1.131334e-83 ***
## wt -506.1389175 -537.214571 -475.0632642 1.118220e-83 ***
## qsec -132.3622867 -143.160353 -118.9186944 1.094728e-83 ***
## vs -222.6300825 -283.532484 -160.6471851 1.142960e-83 ***
## am -360.1349715 -411.143585 -309.3340192 1.145999e-83 ***
## gear 3.3479327 -77.909561 114.9982065 4.143707e-04 ***
## carb -17.1193947 -34.343046 8.3335623 1.780062e-74 ***
##
## $signif_codes
## [1] "Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1"
##
## $effects
## ── Data Summary ────────────────────────
## Values
## Name effects
## Number of rows 8
## Number of columns 10
## _______________________
## Column type frequency:
## numeric 10
## ________________________
## Group variables None
##
## ── Variable type: numeric ──────────────────────────────────────────────────────
## skim_variable mean sd p0 p25 p50 p75 p100
## 1 cyl 40.9 40.7 -40.5 23.9 56.3 69.9 77.8
## 2 disp -0.734 0.566 -1.64 -1.03 -0.571 -0.372 -0.139
## 3 hp -0.823 1.65 -3.99 -1.18 -0.974 -0.196 1.25
## 4 drat 550. 160. 170. 549. 606. 642. 643.
## 5 wt -470. 78.9 -543. -537. -489. -437. -336.
## 6 qsec -117. 48.0 -179. -143. -131. -99.1 -29.9
## 7 vs -194. 112. -377. -283. -162. -120. -46.3
## 8 am -396. 200. -719. -481. -357. -319. -67.7
## 9 gear 53.1 135. -143. -23.9 16.5 172. 231.
## 10 carb -25.9 45.2 -101. -48.8 -23.8 -9.36 45.7
## hist
## 1 ▂▂▂▁▇
## 2 ▅▁▂▇▅
## 3 ▂▁▇▂▃
## 4 ▁▁▁▁▇
## 5 ▇▅▂▁▅
## 6 ▂▇▂▂▂
## 7 ▂▅▂▇▂
## 8 ▃▁▇▂▂
## 9 ▂▅▅▁▇
## 10 ▂▅▇▁▅## Elapsed: 0.112 sres <- obj$predict(X = new_X_test)
new_y_train <- c(y_train, y_test[c(1, 2)])
plot(c(new_y_train, res$preds), type='l',
main="",
ylab="",
ylim = c(min(c(res$upper, res$lower, y)),
max(c(res$upper, res$lower, y))))
lines(c(new_y_train, res$upper), col="gray60")
lines(c(new_y_train, res$lower), col="gray60")
lines(c(new_y_train, res$preds), col = "red")
lines(c(new_y_train, new_y_test), col = "blue")
abline(v = length(y_train), lty=2, col="black")
## [1] 0.75