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 0.0021 0.0378 -0.0029 0.0043 -0.0022
## X2 0.0021 1.0000 -0.0019 0.0000 0.0009 0.0001
## X3 0.0378 -0.0019 1.0000 0.0000 0.0032 -0.0014
## X4 -0.0029 0.0000 0.0000 1.0000 -0.0014 -0.0017
## X5 0.0043 0.0009 0.0032 -0.0014 1.0000 0.0018
## X6 -0.0022 0.0001 -0.0014 -0.0017 0.0018 1.0000
names(Xsum) <- M1:M2
Xsum %>%
summary %>%
round(2)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 2.70 16.37 20.37 21.03 24.97 66.45
Xsum %>%
sd %>%
round(2)
## [1] 6.49
Xsum %>%
`<=`(5) %>%
which %>%
`[`(Xsum, .) %>%
round(2)
## 5002489 5007327 5032170 5050920 5057826 5073995 5075061 5083869 5087448 5094229
## 4.93 3.72 4.91 4.77 4.87 4.89 3.84 4.66 4.55 3.92
## 5102577 5106150 5107983 5116635 5130560 5134043 5154159 5163828 5165025 5171952
## 4.69 4.76 4.51 4.58 3.22 4.96 4.31 4.89 3.40 4.07
## 5199626 5211423 5212939 5214592 5215367 5227596 5227878 5230181 5230935 5237583
## 4.87 4.81 4.75 4.10 4.34 4.85 4.95 3.56 3.04 3.78
## 5238853 5250998 5258341 5262385 5263830 5267350 5275695 5276022 5278595 5283114
## 4.13 3.55 4.66 3.94 4.27 4.79 4.69 4.51 4.59 3.97
## 5283278 5292338 5301015 5310579 5321465 5324201 5327310 5336016 5364563 5370443
## 4.88 4.87 4.72 3.59 4.81 4.58 3.01 3.62 4.82 4.52
## 5380640 5396542 5399595 5413277 5414867 5437989 5448304 5452222 5458288 5459491
## 4.56 4.96 4.93 4.77 4.23 4.94 4.80 4.71 4.98 4.22
## 5478131 5486974 5490165 5491754 5512539 5527093 5535510 5545635 5552963 5579348
## 3.93 4.67 4.64 4.83 4.31 4.62 4.83 3.98 4.52 4.50
## 5581245 5587191 5589199 5606128 5609550 5611650 5617906 5642196 5647148 5648486
## 4.91 4.75 2.70 4.23 4.61 4.37 4.25 4.57 4.99 4.21
## 5648885 5660207 5660968 5670675 5671336 5675929 5677919 5681890 5688935 5692120
## 4.96 4.46 4.56 4.98 4.91 4.56 4.44 4.57 3.96 4.70
## 5694538 5703418 5714387 5717598 5735642 5736719 5739325 5739463 5748250 5759481
## 4.65 4.24 3.51 4.12 3.65 4.59 4.86 4.07 4.64 4.15
## 5770232 5797695 5798600 5808406 5812932 5833813 5839213 5845994 5847327 5855811
## 4.85 4.55 4.20 4.51 4.89 4.81 3.80 4.59 4.34 3.83
## 5864610 5868492 5869349 5871368 5874288 5877964 5878493 5903978 5918295 5919458
## 4.78 3.67 4.91 4.66 3.92 3.32 4.93 4.89 4.07 4.61
## 5962121 5980763 5985885 5993284
## 4.61 3.06 3.92 2.97
Xmin <- names(Xsum[which(Xsum == min(Xsum))])
Xmin
## [1] "5589199"
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] 1.2860187 0.1624764 0.0000000 0.0000000 0.9764732 0.2719614
##
## $Xsum
## [1] 2.69693
학번
class_roll$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 |
20 |
29 |
26 |
50 |
20 |
51 |
112 |
| Black |
17 |
29 |
29 |
58 |
18 |
47 |
110 |
X1min <- tbl1 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X1min
## X-squared
## 1.286019
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 |
147 |
161 |
| Black |
152 |
156 |
X2min <- tbl2 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X2min
## X-squared
## 0.1624764
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
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 |
30 |
34 |
26 |
27 |
35 |
27 |
36 |
38 |
32 |
| Black |
24 |
32 |
34 |
27 |
24 |
29 |
28 |
38 |
38 |
34 |
X5min <- tbl5 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X5min
## X-squared
## 0.9764732
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 |
47 |
26 |
170 |
| Black |
63 |
48 |
23 |
174 |
X6min <- tbl6 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X6min
## X-squared
## 0.2719614
Sum of Chi_Squares
Xsum_min <- X1min + X2min + X3min + X4min + X5min + X6min
Xsum_min
## X-squared
## 2.69693