Data
Search for Best Configuration
M1 <- 4000001
M2 <- 5000000
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 -0.0026 0.0206 0.0040 -0.0029 -0.0052
## X2 -0.0026 1.0000 -0.0030 0.0002 -0.0015 -0.0006
## X3 0.0206 -0.0030 1.0000 0.0016 -0.0031 -0.0043
## X4 0.0040 0.0002 0.0016 1.0000 -0.0047 0.0025
## X5 -0.0029 -0.0015 -0.0031 -0.0047 1.0000 -0.0017
## X6 -0.0052 -0.0006 -0.0043 0.0025 -0.0017 1.0000
names(Xsum) <- M1:M2
Xsum %>%
summary %>%
round(2)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 2.53 16.43 20.42 21.04 24.97 65.25
Xsum %>%
sd %>%
round(2)
## [1] 6.41
Xsum %>%
`<=`(5) %>%
which %>%
`[`(Xsum, .) %>%
round(2)
## 4022557 4031065 4033502 4051312 4060771 4062173 4064450 4067539 4068983 4070519
## 4.90 4.94 4.72 4.78 4.98 4.63 4.31 5.00 4.64 4.67
## 4077278 4085313 4090873 4102216 4137390 4140143 4145247 4146062 4146682 4152711
## 2.53 4.98 4.05 4.02 4.06 4.80 4.90 4.26 4.89 4.40
## 4152986 4175507 4176090 4179234 4181032 4182605 4189115 4192542 4194030 4199065
## 4.85 4.89 4.82 5.00 4.99 4.59 4.86 4.88 4.41 4.05
## 4213396 4215595 4247406 4261088 4261456 4270605 4283564 4295023 4303224 4312351
## 4.66 4.79 4.92 4.77 4.92 4.79 4.70 4.95 4.16 4.40
## 4314520 4317743 4321829 4322333 4333479 4348165 4361801 4366095 4368622 4371381
## 4.90 4.79 4.51 4.61 4.30 4.71 4.84 4.32 4.12 4.83
## 4373168 4376269 4384527 4390387 4398367 4399892 4401184 4415681 4422618 4424727
## 4.72 4.12 4.94 4.26 4.12 4.87 4.44 4.37 4.43 2.96
## 4426700 4431301 4439186 4446051 4450457 4453161 4460962 4469941 4478388 4497932
## 4.22 4.93 4.83 4.99 4.47 4.95 4.46 4.66 4.85 4.27
## 4500871 4506135 4523558 4523619 4537522 4541156 4567278 4583856 4615950 4620012
## 4.96 4.83 4.96 4.91 4.64 4.82 4.88 4.64 4.59 4.29
## 4639404 4639820 4658417 4667735 4668603 4676488 4678155 4690792 4702890 4708049
## 4.73 4.96 4.99 4.45 4.94 4.13 4.65 4.81 4.64 4.33
## 4710642 4719973 4721228 4729463 4749807 4778328 4790219 4798979 4804771 4816048
## 4.99 4.05 3.59 4.53 4.94 4.97 3.70 4.93 4.71 4.28
## 4821575 4830443 4833697 4840946 4847140 4849815 4854582 4857650 4858283 4872952
## 4.73 4.43 4.85 4.84 4.82 4.17 4.20 4.96 4.70 4.58
## 4873267 4902398 4906104 4914804 4927967 4929902 4933172 4933174 4937566 4941094
## 3.52 4.32 4.55 4.81 4.13 4.61 4.83 4.91 4.66 4.13
## 4987745 4996869
## 4.86 4.91
Xmin <- names(Xsum[which(Xsum == min(Xsum))])
Xmin
## [1] "4077278"
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] 1.034935859 0.008232683 0.000000000 0.141897810 1.147407411 0.198455775
##
## $Xsum
## [1] 2.53093
학번
class_roll$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 |
17 |
36 |
32 |
35 |
17 |
68 |
38 |
| Black |
15 |
32 |
32 |
39 |
18 |
64 |
43 |
X1min <- tbl1 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X1min
## X-squared
## 1.034936
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 |
119 |
124 |
| Black |
120 |
123 |
X2min <- tbl2 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X2min
## X-squared
## 0.008232683
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 |
21 |
22 |
24 |
24 |
28 |
23 |
22 |
28 |
25 |
26 |
| Black |
20 |
21 |
21 |
29 |
31 |
21 |
20 |
30 |
24 |
26 |
X5min <- tbl5 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X5min
## X-squared
## 1.147407
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 |
47 |
40 |
15 |
141 |
| Black |
45 |
43 |
16 |
139 |
X6min <- tbl6 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X6min
## X-squared
## 0.1984558
Sum of Chi_Squares
Xsum_min <- X1min + X2min + X3min + X4min + X5min + X6min
Xsum_min
## X-squared
## 2.53093