Data
Search for Best Configuration
M1 <- 9000001
M2 <- 10000000
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 -0.0031 0.0216 0.0055 -0.0032 -0.0040
## X2 -0.0031 1.0000 -0.0016 -0.0020 -0.0018 -0.0014
## X3 0.0216 -0.0016 1.0000 0.0032 -0.0023 -0.0038
## X4 0.0055 -0.0020 0.0032 1.0000 -0.0038 0.0024
## X5 -0.0032 -0.0018 -0.0023 -0.0038 1.0000 -0.0033
## X6 -0.0040 -0.0014 -0.0038 0.0024 -0.0033 1.0000
names(Xsum) <- M1:M2
Xsum %>%
summary %>%
round(2)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 3.33 16.45 20.41 21.05 24.97 66.24
Xsum %>%
sd %>%
round(2)
## [1] 6.42
Xsum %>%
`<=`(5) %>%
which %>%
`[`(Xsum, .) %>%
round(2)
## 9014747 9025498 9026846 9027585 9030344 9039552 9042099 9047817 9049182 9050962
## 4.52 4.90 4.12 4.93 4.59 4.99 4.72 4.44 4.41 4.87
## 9063774 9066492 9067290 9067416 9086979 9104711 9105510 9111870 9115100 9115874
## 4.93 4.69 4.92 4.57 4.58 4.11 3.74 4.69 4.61 4.23
## 9128242 9135034 9135341 9140445 9141799 9152627 9174459 9196695 9200887 9209791
## 4.44 4.98 4.55 4.56 4.38 3.33 4.99 3.58 4.65 4.88
## 9218795 9231575 9246452 9247414 9263165 9264226 9265007 9269737 9276181 9288037
## 4.08 4.29 4.78 4.61 4.28 4.72 4.79 4.18 4.88 4.89
## 9296134 9298497 9304464 9317634 9319980 9333840 9343067 9349852 9351219 9355608
## 4.72 4.97 4.78 4.96 4.89 4.93 4.66 4.28 3.64 4.71
## 9387442 9428800 9438268 9452690 9463212 9479540 9490675 9492427 9498169 9502562
## 4.64 3.84 4.32 4.98 4.10 4.90 4.12 4.65 4.92 4.91
## 9508861 9511900 9522935 9531496 9533062 9534750 9545731 9550374 9563497 9565888
## 4.00 4.88 4.65 3.76 4.43 4.60 3.74 4.40 4.77 4.60
## 9570240 9570777 9588013 9588079 9591059 9593923 9596398 9599690 9604409 9607065
## 4.93 4.05 3.73 4.66 4.93 4.07 4.09 4.83 4.93 4.88
## 9611116 9614562 9629204 9635510 9641187 9658848 9666385 9671010 9673681 9682778
## 4.96 4.95 4.84 4.87 4.60 4.73 4.84 4.95 4.79 4.76
## 9689874 9699870 9700299 9718002 9719772 9730313 9731076 9732787 9738273 9771604
## 4.48 4.88 4.69 4.77 4.70 3.94 4.91 4.57 4.23 4.90
## 9774032 9780628 9785692 9788621 9818004 9831831 9832587 9838787 9846848 9851887
## 4.71 4.22 4.85 4.04 3.78 4.66 4.81 4.99 4.86 4.81
## 9854791 9867180 9869644 9875693 9887384 9889104 9911394 9914761 9923095 9931793
## 4.82 4.73 4.83 4.98 4.62 4.66 4.44 4.65 4.61 4.68
## 9935182 9966390 9973555 9986368
## 4.54 4.88 4.91 4.83
Xmin <- names(Xsum[which(Xsum == min(Xsum))])
Xmin
## [1] "9152627"
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] 1.30218171 0.07409415 0.50836820 0.01576642 1.19297371 0.23250502
##
## $Xsum
## [1] 3.325889
학번
class_roll$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 |
15 |
35 |
32 |
37 |
18 |
62 |
44 |
| Black |
17 |
33 |
32 |
37 |
17 |
70 |
37 |
X1min <- tbl1 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X1min
## X-squared
## 1.302182
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
## 0.5083682
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
## 0.01576642
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 |
23 |
20 |
23 |
26 |
31 |
21 |
21 |
28 |
24 |
26 |
| Black |
18 |
23 |
22 |
27 |
28 |
23 |
21 |
30 |
25 |
26 |
X5min <- tbl5 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X5min
## X-squared
## 1.192974
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 |
41 |
15 |
139 |
| Black |
44 |
42 |
16 |
141 |
X6min <- tbl6 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X6min
## X-squared
## 0.232505
Sum of Chi_Squares
Xsum_min <- X1min + X2min + X3min + X4min + X5min + X6min
Xsum_min
## X-squared
## 3.325889