Data
Search for Best Configuration
M1 <- 9000001
M2 <- 10000000
Xsum <- numeric(0)
Xsum <- sapply(M1:M2, red_and_black)
# 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)
names(Xsum) <- M1:M2
Xsum %>%
summary %>%
round(2)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 2.92 16.35 20.36 21.03 24.99 74.30
Xsum %>%
sd %>%
round(2)
## [1] 6.52
Xsum %>%
`<=`(5) %>%
which %>%
`[`(Xsum, .) %>%
round(2)
## 9000655 9005380 9006413 9007008 9023236 9024813 9025651 9046884 9048751 9052478
## 4.67 4.76 4.89 4.96 4.76 4.52 4.79 4.09 4.86 4.58
## 9067268 9077125 9082545 9096724 9106351 9109197 9113897 9133211 9138200 9139402
## 4.75 3.89 3.29 4.63 4.91 3.61 4.65 4.57 4.67 4.97
## 9145526 9145537 9153519 9159713 9163338 9168587 9172581 9174766 9175126 9175588
## 3.81 4.86 4.53 4.74 4.85 4.00 4.70 4.75 4.33 3.67
## 9180926 9186095 9187195 9203805 9215502 9232488 9233750 9234351 9235645 9258036
## 4.55 4.63 4.81 4.88 4.57 4.80 4.35 4.53 4.08 3.89
## 9267524 9279015 9280891 9282712 9283725 9298195 9298373 9315322 9320980 9322053
## 3.88 4.97 4.10 4.46 4.98 4.92 4.91 4.67 4.61 4.16
## 9323244 9328104 9331840 9339784 9348595 9349540 9360103 9367870 9372794 9375028
## 4.67 4.91 4.57 4.94 4.27 4.92 4.87 4.35 4.64 4.26
## 9381348 9398121 9405478 9412591 9414824 9420116 9437659 9445399 9449916 9465124
## 3.11 4.39 3.35 4.61 4.59 3.85 4.94 4.71 4.61 4.63
## 9467957 9476685 9482404 9485857 9489796 9496736 9502425 9503383 9509233 9512323
## 4.80 4.37 4.46 3.68 4.64 4.15 4.97 4.61 4.08 4.79
## 9537232 9542364 9571285 9575128 9578095 9579341 9580247 9585287 9595148 9598678
## 4.92 4.58 4.89 4.37 4.25 4.92 4.88 4.06 4.86 4.54
## 9599074 9602323 9615798 9621742 9657837 9661777 9672570 9680927 9681176 9686378
## 4.83 4.92 4.52 4.58 3.75 4.30 4.71 4.86 4.46 4.79
## 9688393 9690718 9695177 9696799 9712179 9712463 9716727 9736209 9742490 9746067
## 4.68 4.33 4.86 4.82 4.77 4.75 4.98 4.39 3.47 4.62
## 9759831 9760421 9767509 9778853 9781587 9796550 9799215 9815588 9819029 9842822
## 3.99 4.04 4.17 4.42 3.34 4.79 4.15 4.18 4.62 4.87
## 9844354 9847974 9852998 9856124 9863356 9864680 9905419 9908488 9917862 9923718
## 2.92 4.96 3.60 3.50 4.47 4.50 4.04 4.48 4.77 4.19
## 9925975 9926941 9932192 9935357 9936429 9944531 9945596 9948431 9961689 9965940
## 4.91 4.33 4.34 4.84 4.66 4.85 4.97 4.30 4.66 4.43
## 9967120 9970155 9973061 9976894 9990275 9999361 9999527
## 4.61 3.84 3.63 4.19 4.31 4.29 4.85
Xmin <- names(Xsum[which(Xsum == min(Xsum))])
Xmin
## [1] "9844354"
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(Xmin)
## [1] 2.915651
학번
class_roll$id_2 <-
class_roll$id %>%
ifelse(. <= 2016, "2016", .)
tbl1 <- class_roll %$%
table(.$group, .$id_2 %>% substr(1, 4)) %>%
`colnames<-`(c("2016 이전", 2017:2022))
tbl1 %>%
pander
| Red |
20 |
36 |
60 |
75 |
50 |
137 |
25 |
| Black |
21 |
35 |
61 |
79 |
51 |
132 |
25 |
X1min <- tbl1 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X1min
## X-squared
## 0.2522343
학번 홀짝
tbl2 <- class_roll$id %>%
as.numeric %>%
`%%`(2) %>%
factor(levels = c(1, 0), labels = c("홀", "짝")) %>%
table(class_roll$group, .)
tbl2 %>%
pander
| Red |
207 |
196 |
| Black |
213 |
191 |
X2min <- tbl2 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X2min
## X-squared
## 0.1490748
학적 상태
tbl3 <- class_roll$status %>%
table(class_roll$group, .)
tbl3 %>%
pander
X3min <- tbl3 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X3min
## X-squared
## 0.02730536
e-mail 서비스업체
tbl4 <- class_roll$email %>%
strsplit("@", fixed = TRUE) %>%
sapply("[", 2) %>%
`==`("naver.com") %>%
ifelse("네이버", "기타서비스") %>%
factor(levels = c("네이버", "기타서비스")) %>%
table(class_roll$group, .)
tbl4 %>%
pander
X4min <- tbl4 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X4min
## X-squared
## 0.005753858
전화번호의 분포
cut_label <- paste(paste0(0:9, "000"), paste0(0:9, "999"),
sep = "~")
tbl5 <- class_roll$cell_no %>%
substr(start = 8, stop = 11) %>%
sapply(as.numeric) %>%
cut(labels = cut_label,
breaks = seq(0, 10000, by = 1000)) %>%
table(class_roll$group, .)
tbl5 %>%
pander
| Red |
41 |
30 |
34 |
45 |
31 |
49 |
40 |
38 |
39 |
55 |
| Black |
40 |
35 |
34 |
40 |
33 |
49 |
44 |
39 |
43 |
47 |
X5min <- tbl5 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X5min
## X-squared
## 1.774663
성씨 분포
f_name <- class_roll$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 |
73 |
57 |
29 |
244 |
| Black |
75 |
64 |
31 |
234 |
X6min <- tbl6 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X6min
## X-squared
## 0.7066193
Sum of Chi_Squares
Xsum_min <- X1min + X2min + X3min + X4min + X5min + X6min
Xsum_min
## X-squared
## 2.915651