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 0.0015 0.0358 -0.0021 0.0034 -0.0032
## X2 0.0015 1.0000 -0.0005 -0.0002 0.0013 -0.0015
## X3 0.0358 -0.0005 1.0000 -0.0007 0.0060 0.0004
## X4 -0.0021 -0.0002 -0.0007 1.0000 -0.0016 -0.0027
## X5 0.0034 0.0013 0.0060 -0.0016 1.0000 0.0005
## X6 -0.0032 -0.0015 0.0004 -0.0027 0.0005 1.0000
names(Xsum) <- M1:M2
Xsum %>%
summary %>%
round(2)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 2.75 16.37 20.35 21.02 24.96 73.47
Xsum %>%
sd %>%
round(2)
## [1] 6.48
Xsum %>%
`<=`(5) %>%
which %>%
`[`(Xsum, .) %>%
round(2)
## 4018499 4034338 4037125 4055381 4058905 4059328 4061129 4067309 4094797 4118540
## 4.15 4.27 4.65 4.56 4.56 4.78 3.81 4.41 4.64 4.68
## 4120734 4123753 4140799 4142316 4147439 4154356 4155151 4155576 4157276 4171179
## 4.17 4.26 4.77 4.96 4.62 4.67 4.78 4.13 4.68 4.89
## 4179741 4181367 4195506 4197270 4209891 4231607 4241357 4270705 4272530 4281439
## 3.76 4.66 4.81 4.40 4.88 4.84 4.74 5.00 4.52 4.96
## 4296505 4298835 4298950 4311409 4320478 4322908 4328182 4329849 4356093 4394139
## 4.56 4.60 4.22 4.72 4.30 4.62 4.54 4.24 4.84 4.80
## 4412209 4431185 4433304 4442647 4444451 4446717 4454780 4460208 4488852 4489900
## 4.67 4.10 4.96 4.97 4.61 4.17 2.75 4.52 4.67 4.96
## 4496431 4504497 4508289 4517167 4527151 4532579 4541949 4543753 4560837 4561852
## 4.89 4.60 3.66 4.75 4.64 4.03 4.20 4.52 4.73 4.59
## 4564999 4570374 4585807 4594013 4594553 4596628 4602708 4608858 4647992 4653701
## 4.82 4.83 4.56 4.62 4.61 4.82 4.21 4.83 4.08 4.89
## 4661126 4694564 4705552 4706622 4714892 4727053 4732441 4735991 4747739 4752614
## 4.85 4.99 3.85 4.35 4.40 4.36 4.45 4.94 4.37 4.79
## 4762474 4769661 4770735 4777286 4778699 4779458 4784860 4786335 4825582 4826093
## 4.97 4.95 4.80 4.94 4.67 4.11 4.17 4.77 4.73 3.80
## 4847256 4849866 4851395 4881358 4892565 4893374 4893451 4900962 4906951 4918638
## 4.55 3.91 4.69 4.06 4.13 4.12 4.71 4.34 4.71 4.80
## 4925010 4926287 4926453 4930439 4943169 4945510 4961083 4962241 4969147 4976671
## 4.58 4.04 4.88 4.52 3.92 4.64 4.77 4.80 4.99 4.52
## 4982207 4982821 4996367
## 4.22 4.78 4.46
Xmin <- names(Xsum[which(Xsum == min(Xsum))])
Xmin
## [1] "4454780"
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] 0.8299960 0.0584915 0.2954436 0.1941533 0.8463114 0.5219614
##
## $Xsum
## [1] 2.746357
학번
class_roll$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 |
19 |
26 |
27 |
54 |
20 |
50 |
112 |
| Black |
18 |
32 |
28 |
54 |
18 |
48 |
110 |
X1min <- tbl1 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X1min
## X-squared
## 0.829996
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 |
148 |
160 |
| Black |
151 |
157 |
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
## 0.2954436
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
## 0.1941533
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 |
30 |
34 |
28 |
25 |
33 |
25 |
38 |
38 |
33 |
| Black |
23 |
32 |
34 |
25 |
26 |
31 |
30 |
36 |
38 |
33 |
X5min <- tbl5 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X5min
## X-squared
## 0.8463114
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 |
67 |
48 |
23 |
170 |
| Black |
61 |
47 |
26 |
174 |
X6min <- tbl6 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X6min
## X-squared
## 0.5219614
Sum of Chi_Squares
Xsum_min <- X1min + X2min + X3min + X4min + X5min + X6min
Xsum_min
## X-squared
## 2.746357