Data
Search for Best Configuration
M1 <- 5000001
M2 <- 6000000
Xsum <- numeric(0)
Values_mat <- numeric(0)
for(k in M1:M2){
set.seed(k)
N <- nrow(class_roll)
class_roll$group <-
sample(1:N) %%
2 %>%
factor(levels = c(0, 1), labels = c("Red", "Black"))
Xsum <- c(Xsum, red_and_black(class_roll)$Xsum)
Values_mat <- rbind(Values_mat, red_and_black(class_roll)$Values)
}
colnames(Values_mat) <- paste0("X", 1:6)
# Values_mat
# pairs(Values_mat)
cor(Values_mat) %>%
round(4)
## X1 X2 X3 X4 X5 X6
## X1 1.0000 -0.0032 0.0224 0.0059 -0.0022 -0.0051
## X2 -0.0032 1.0000 -0.0015 0.0003 -0.0019 0.0009
## X3 0.0224 -0.0015 1.0000 0.0023 -0.0010 -0.0025
## X4 0.0059 0.0003 0.0023 1.0000 -0.0053 0.0001
## X5 -0.0022 -0.0019 -0.0010 -0.0053 1.0000 -0.0031
## X6 -0.0051 0.0009 -0.0025 0.0001 -0.0031 1.0000
names(Xsum) <- M1:M2
Xsum %>%
summary %>%
round(2)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 2.71 16.43 20.41 21.05 24.98 67.07
Xsum %>%
sd %>%
round(2)
## [1] 6.42
Xsum %>%
`<=`(5) %>%
which %>%
`[`(Xsum, .) %>%
round(2)
## 5011576 5037273 5063115 5064038 5074816 5077650 5083730 5087856 5100280 5122628
## 4.42 4.30 4.87 4.33 4.71 4.95 2.79 4.92 4.00 4.44
## 5124221 5139086 5152454 5156974 5176753 5186737 5189986 5202359 5230726 5236986
## 3.21 4.97 4.91 4.50 4.26 4.85 4.92 4.68 4.11 4.61
## 5274098 5274327 5274858 5283657 5290823 5303067 5308945 5310984 5311647 5314410
## 4.46 4.84 4.66 4.01 4.90 4.25 4.23 4.47 4.87 4.77
## 5365530 5367387 5369331 5383984 5396115 5406897 5408008 5414223 5416011 5417095
## 4.90 4.55 4.41 4.79 3.89 4.39 5.00 4.47 4.27 4.66
## 5451476 5469939 5484694 5491760 5492691 5496751 5508032 5527298 5532763 5534199
## 4.58 4.43 4.77 2.71 3.17 4.29 4.63 4.87 4.76 3.99
## 5534893 5536556 5544441 5545237 5549723 5550746 5560027 5570141 5572691 5598840
## 4.75 4.96 4.17 4.45 4.75 4.97 4.87 4.70 4.90 4.54
## 5602314 5607299 5628476 5631010 5645961 5666044 5669711 5675696 5676639 5689882
## 4.82 4.89 4.80 4.06 4.91 4.66 4.86 4.70 2.93 3.78
## 5740020 5743567 5757873 5763610 5765313 5765898 5766471 5768338 5770145 5784696
## 4.68 4.94 4.03 4.45 4.82 4.15 3.69 4.78 3.76 4.53
## 5791963 5807404 5814089 5818845 5833509 5835605 5844144 5871202 5876049 5877785
## 4.50 4.67 4.32 4.96 3.96 3.21 4.77 3.38 4.93 2.88
## 5878270 5889026 5894836 5911615 5918296 5920598 5923304 5932507 5943597 5945238
## 3.01 4.37 4.42 3.59 4.89 4.93 4.95 4.49 4.24 4.95
## 5955197 5959282 5961361 5972648 5977559 5981053 5985968 5986086
## 4.54 3.98 4.68 4.80 4.78 4.83 3.81 4.78
Xmin <- names(Xsum[which(Xsum == min(Xsum))])
Xmin
## [1] "5491760"
Plot
hist(Xsum, prob = TRUE, nclass = 30, xlim = c(0, 50), ylim = c(0, 0.065))
x <- seq(0, 50, by = 0.1)
lines(x, dchisq(x, df = 21), col = "red")
legend("topright", inset = 0.05, legend = c("Xsum", "Chi-square(21)"), col = c("black", "red"), lty = 1)
plot(density(Xsum), xlim = c(0, 50), main = "Density Estimation of Xsum")
lines(x, dchisq(x, df = 21), col = "red")
legend("topright", inset = 0.05, legend = c("Xsum", "Chi-square(21)"), col = c("black", "red"), lty = 1)
Randomization
set.seed(Xmin)
N <- nrow(class_roll)
class_roll$group <-
sample(1:N) %%
2 %>%
factor(levels = c(0, 1), labels = c("Red", "Black"))
red_and_black(class_roll)
## $Values
## [1] 1.75711392 0.07409415 0.00000000 0.14189781 0.29392569 0.44317627
##
## $Xsum
## [1] 2.710208
학번
class_roll$id_2 <-
class_roll$id %>%
ifelse(. <= 2015, "2015", .)
tbl1 <- class_roll %$%
table(.$group, .$id_2 %>% substr(1, 4)) %>%
`colnames<-`(c("2015 이전", 2016:2021))
tbl1 %>%
pander
| Red |
17 |
35 |
30 |
33 |
17 |
68 |
43 |
| Black |
15 |
33 |
34 |
41 |
18 |
64 |
38 |
X1min <- tbl1 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X1min
## X-squared
## 1.757114
학번 홀짝
tbl2 <- class_roll$id %>%
as.numeric %>%
`%%`(2) %>%
factor(levels = c(1, 0), labels = c("홀", "짝")) %>%
table(class_roll$group, .)
tbl2 %>%
pander
| Red |
121 |
122 |
| Black |
118 |
125 |
X2min <- tbl2 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X2min
## X-squared
## 0.07409415
학적 상태
tbl3 <- class_roll$status %>%
table(class_roll$group, .)
tbl3 %>%
pander
X3min <- tbl3 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X3min
## X-squared
## 0
e-mail 서비스업체
tbl4 <- class_roll$email %>%
strsplit("@", fixed = TRUE) %>%
sapply("[", 2) %>%
`==`("naver.com") %>%
ifelse("네이버", "기타서비스") %>%
factor(levels = c("네이버", "기타서비스")) %>%
table(class_roll$group, .)
tbl4 %>%
pander
X4min <- tbl4 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X4min
## X-squared
## 0.1418978
전화번호의 분포
cut_label <- paste(paste0(0:9, "000"), paste0(0:9, "999"),
sep = "~")
tbl5 <- class_roll$cell_no %>%
substr(start = 8, stop = 11) %>%
sapply(as.numeric) %>%
cut(labels = cut_label,
breaks = seq(0, 10000, by = 1000)) %>%
table(class_roll$group, .)
tbl5 %>%
pander
| Red |
20 |
22 |
22 |
27 |
30 |
23 |
21 |
29 |
24 |
25 |
| Black |
21 |
21 |
23 |
26 |
29 |
21 |
21 |
29 |
25 |
27 |
X5min <- tbl5 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X5min
## X-squared
## 0.2939257
성씨 분포
f_name <- class_roll$name %>%
substring(first = 1, last = 1)
tbl6 <- f_name %>%
`%in%`(c("김", "이", "박")) %>%
ifelse(f_name, "기타") %>%
factor(levels = c("김", "이", "박", "기타")) %>%
table(class_roll$group, .)
tbl6 %>%
pander
| Red |
48 |
43 |
15 |
137 |
| Black |
44 |
40 |
16 |
143 |
X6min <- tbl6 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X6min
## X-squared
## 0.4431763
Sum of Chi_Squares
Xsum_min <- X1min + X2min + X3min + X4min + X5min + X6min
Xsum_min
## X-squared
## 2.710208