Data
Search for Best Configuration
M1 <- 3000001
M2 <- 4000000
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 -0.0043 0.0219 0.0042 -0.0038 -0.0028
## X2 -0.0043 1.0000 -0.0020 0.0000 -0.0016 -0.0010
## X3 0.0219 -0.0020 1.0000 0.0021 -0.0022 -0.0047
## X4 0.0042 0.0000 0.0021 1.0000 -0.0038 0.0011
## X5 -0.0038 -0.0016 -0.0022 -0.0038 1.0000 -0.0019
## X6 -0.0028 -0.0010 -0.0047 0.0011 -0.0019 1.0000
names(Xsum) <- M1:M2
Xsum %>%
summary %>%
round(2)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 2.04 16.44 20.40 21.04 24.96 67.49
Xsum %>%
sd %>%
round(2)
## [1] 6.42
Xsum %>%
`<=`(5) %>%
which %>%
`[`(Xsum, .) %>%
round(2)
## 3001529 3006931 3023635 3029548 3032626 3053411 3058281 3058469 3068636 3068890
## 3.12 4.43 4.49 3.78 5.00 4.95 4.71 3.45 4.88 4.48
## 3074553 3094409 3107543 3116780 3119729 3144402 3155913 3156100 3166288 3175246
## 3.89 4.52 4.21 4.50 4.88 3.36 4.40 4.93 4.65 4.99
## 3186466 3189686 3191188 3198954 3201735 3212532 3224636 3224952 3233885 3260876
## 4.01 4.99 4.60 4.96 4.50 4.49 4.40 4.99 4.41 4.96
## 3269587 3272527 3274098 3287540 3307304 3309679 3313741 3320842 3347610 3364242
## 4.97 4.92 2.85 4.20 4.99 4.33 4.96 4.04 4.48 4.76
## 3371025 3377687 3387275 3387739 3388200 3404747 3411318 3413447 3414552 3432983
## 4.52 4.87 4.70 3.98 4.60 4.94 4.16 4.92 3.42 3.80
## 3472872 3491107 3497339 3510038 3517220 3518843 3527648 3528203 3548758 3557172
## 3.63 4.45 4.48 4.49 4.89 5.00 4.23 4.90 4.42 4.71
## 3559076 3577912 3597970 3609069 3609183 3609292 3629335 3631310 3633979 3643534
## 4.30 2.96 4.70 4.82 4.68 5.00 4.29 3.22 4.54 4.91
## 3646753 3654218 3656673 3659497 3669487 3687616 3687798 3691266 3697259 3715954
## 4.97 4.34 3.81 4.50 3.38 4.66 4.62 4.71 3.66 4.82
## 3724684 3730660 3750954 3752240 3765463 3766329 3767471 3781170 3792218 3802909
## 2.04 2.96 4.35 4.16 4.18 4.47 4.67 3.58 4.85 4.72
## 3810664 3821430 3828152 3834899 3840675 3844096 3857828 3858320 3871710 3875722
## 4.34 4.86 4.93 4.48 4.99 4.82 4.75 4.57 5.00 3.92
## 3882185 3886216 3896101 3900040 3906774 3926931 3944272 3955824 3968062 3979209
## 4.32 4.60 4.49 4.97 3.81 4.30 4.08 4.40 4.47 4.98
## 3980055 3987806
## 4.91 4.80
Xmin <- names(Xsum[which(Xsum == min(Xsum))])
Xmin
## [1] "3724684"
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] 0.8712759 0.2058171 0.0000000 0.1418978 0.7164201 0.1020702
##
## $Xsum
## [1] 2.037481
학번
class_roll$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 |
16 |
34 |
31 |
36 |
18 |
64 |
44 |
| Black |
16 |
34 |
33 |
38 |
17 |
68 |
37 |
X1min <- tbl1 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X1min
## X-squared
## 0.8712759
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 |
122 |
121 |
| Black |
117 |
126 |
X2min <- tbl2 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X2min
## X-squared
## 0.2058171
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 |
23 |
21 |
26 |
31 |
21 |
21 |
29 |
25 |
26 |
| Black |
21 |
20 |
24 |
27 |
28 |
23 |
21 |
29 |
24 |
26 |
X5min <- tbl5 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X5min
## X-squared
## 0.7164201
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 |
45 |
42 |
15 |
141 |
| Black |
47 |
41 |
16 |
139 |
X6min <- tbl6 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X6min
## X-squared
## 0.1020702
Sum of Chi_Squares
Xsum_min <- X1min + X2min + X3min + X4min + X5min + X6min
Xsum_min
## X-squared
## 2.037481