Data
Search for Best Configuration
M1 <- 2000001
M2 <- 3000000
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 0.0018 0.0370 -0.0024 0.0040 -0.0026
## X2 0.0018 1.0000 -0.0017 0.0005 0.0013 -0.0012
## X3 0.0370 -0.0017 1.0000 -0.0002 0.0046 -0.0017
## X4 -0.0024 0.0005 -0.0002 1.0000 -0.0032 -0.0017
## X5 0.0040 0.0013 0.0046 -0.0032 1.0000 -0.0002
## X6 -0.0026 -0.0012 -0.0017 -0.0017 -0.0002 1.0000
names(Xsum) <- M1:M2
Xsum %>%
summary %>%
round(2)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 3.20 16.37 20.36 21.03 24.96 81.95
Xsum %>%
sd %>%
round(2)
## [1] 6.48
Xsum %>%
`<=`(5) %>%
which %>%
`[`(Xsum, .) %>%
round(2)
## 2007385 2010019 2018140 2029947 2032987 2034427 2034654 2037798 2048523 2048589
## 4.56 4.37 4.59 4.99 4.86 4.41 4.74 4.74 3.22 3.23
## 2064016 2089514 2112278 2120324 2130097 2131879 2134999 2137627 2155732 2157468
## 4.86 4.68 4.55 4.12 4.71 4.43 4.91 4.85 3.84 4.61
## 2175587 2175893 2182941 2184316 2192613 2221709 2226365 2231106 2267711 2273209
## 4.94 4.83 4.90 4.72 4.10 4.59 4.07 4.18 3.97 4.43
## 2283356 2287104 2303940 2314723 2318954 2325332 2325627 2329325 2333767 2338593
## 4.58 4.04 4.76 3.76 5.00 4.48 3.85 4.64 4.70 4.16
## 2344586 2350396 2358594 2359572 2363473 2365802 2366943 2387429 2398722 2408037
## 4.92 4.64 4.67 3.90 4.99 4.82 4.74 4.06 4.60 3.97
## 2428478 2437840 2457807 2461629 2473855 2478202 2484458 2484810 2493645 2498667
## 4.75 3.59 4.64 3.94 4.75 4.66 3.82 4.43 4.28 4.79
## 2501829 2510777 2511151 2522696 2529744 2533909 2541129 2558244 2572873 2573656
## 4.75 4.71 4.59 4.72 4.70 3.88 4.61 4.42 3.20 4.02
## 2596829 2608182 2609660 2610544 2626559 2639214 2639931 2645345 2648376 2652219
## 4.91 4.42 4.85 4.82 4.67 4.55 3.60 4.80 4.94 4.84
## 2656432 2660194 2672270 2678320 2682465 2687714 2688697 2697187 2700475 2717666
## 4.78 4.68 3.69 4.52 4.60 4.69 4.61 4.77 4.66 4.61
## 2718138 2719199 2745293 2747589 2749748 2752844 2767654 2778712 2791372 2815296
## 5.00 3.91 4.73 4.55 4.44 4.60 3.91 4.89 4.60 4.98
## 2816410 2817519 2820680 2850767 2857819 2858775 2865359 2865820 2868185 2886002
## 3.42 4.12 4.35 3.46 3.72 4.88 4.93 4.53 4.36 4.00
## 2894202 2894259 2895425 2910850 2913078 2915848 2917250 2928599 2929759 2934676
## 4.86 4.83 4.88 4.62 4.68 4.48 4.17 4.35 3.90 4.23
## 2934998 2935516 2942404 2944211 2951829 2953794 2957268 2961019 2979331
## 4.52 4.29 4.74 4.62 4.63 4.87 4.63 4.85 4.28
Xmin <- names(Xsum[which(Xsum == min(Xsum))])
Xmin
## [1] "2572873"
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] 1.95408477 0.05849150 0.07386091 0.04853833 0.95977579 0.10869611
##
## $Xsum
## [1] 3.203447
학번
class_roll$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 |
18 |
30 |
23 |
54 |
19 |
52 |
112 |
| Black |
19 |
28 |
32 |
54 |
19 |
46 |
110 |
X1min <- tbl1 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X1min
## X-squared
## 1.954085
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 |
151 |
157 |
| Black |
148 |
160 |
X2min <- tbl2 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X2min
## X-squared
## 0.0584915
학적 상태
tbl3 <- class_roll$status %>%
table(class_roll$group, .)
tbl3 %>%
pander
X3min <- tbl3 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X3min
## X-squared
## 0.07386091
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
## 0.04853833
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 |
24 |
31 |
33 |
27 |
27 |
31 |
30 |
36 |
37 |
32 |
| Black |
23 |
31 |
35 |
26 |
24 |
33 |
25 |
38 |
39 |
34 |
X5min <- tbl5 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X5min
## X-squared
## 0.9597758
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 |
65 |
48 |
25 |
170 |
| Black |
63 |
47 |
24 |
174 |
X6min <- tbl6 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X6min
## X-squared
## 0.1086961
Sum of Chi_Squares
Xsum_min <- X1min + X2min + X3min + X4min + X5min + X6min
Xsum_min
## X-squared
## 3.203447