Data
Search for Best Configuration
M1 <- 6000001
M2 <- 7000000
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 0.0217 0.0056 -0.0030 -0.0051
## X2 -0.0026 1.0000 -0.0019 -0.0014 -0.0033 -0.0014
## X3 0.0217 -0.0019 1.0000 0.0033 -0.0011 -0.0050
## X4 0.0056 -0.0014 0.0033 1.0000 -0.0043 0.0028
## X5 -0.0030 -0.0033 -0.0011 -0.0043 1.0000 -0.0014
## X6 -0.0051 -0.0014 -0.0050 0.0028 -0.0014 1.0000
names(Xsum) <- M1:M2
Xsum %>%
summary %>%
round(2)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 2.93 16.44 20.41 21.05 24.97 66.37
Xsum %>%
sd %>%
round(2)
## [1] 6.42
Xsum %>%
`<=`(5) %>%
which %>%
`[`(Xsum, .) %>%
round(2)
## 6008112 6027299 6029938 6042403 6045613 6049872 6060975 6066424 6098694 6111095
## 4.96 4.56 4.18 4.32 4.97 4.38 4.78 4.76 4.14 4.74
## 6111184 6118158 6128676 6130218 6143576 6149493 6151277 6162530 6185861 6191550
## 4.33 4.37 4.92 4.25 4.33 4.56 4.83 4.68 4.93 3.57
## 6199486 6200302 6209055 6212713 6215903 6222274 6225154 6229436 6229962 6231204
## 4.90 4.54 4.60 4.89 4.38 4.88 4.93 4.10 4.85 4.60
## 6239179 6263533 6274156 6279237 6282216 6282433 6289948 6294445 6294839 6299575
## 2.93 4.24 4.99 4.74 4.85 4.85 4.49 4.37 4.64 4.89
## 6306463 6328658 6351364 6356430 6358756 6374481 6376474 6381729 6383113 6384188
## 4.63 4.12 3.52 4.05 4.95 4.61 4.68 4.77 4.33 4.64
## 6420600 6441399 6443911 6446289 6452437 6466494 6482325 6490567 6494920 6532006
## 4.28 3.87 4.85 4.64 4.28 4.54 4.39 4.12 4.41 4.94
## 6534864 6539118 6545377 6549824 6559872 6576975 6587969 6590034 6612311 6615491
## 3.65 4.88 4.97 4.34 4.88 4.16 4.65 4.97 4.56 4.59
## 6634517 6647249 6652304 6654874 6668397 6670256 6671797 6685919 6697145 6711523
## 4.75 4.12 4.88 4.77 4.74 4.82 4.36 4.72 3.91 4.53
## 6715739 6716860 6730511 6738530 6749507 6754318 6780617 6781121 6782379 6785090
## 4.85 4.81 4.52 4.80 4.44 3.64 4.20 4.60 4.57 4.51
## 6820874 6836001 6850170 6852616 6856709 6861729 6872487 6879846 6880056 6909372
## 4.23 4.59 4.91 4.60 3.85 4.79 4.99 4.43 4.80 3.94
## 6912784 6933691 6938117 6967747 6969872 6971786 6975653 6988735 6991328 6992586
## 4.56 4.74 4.95 4.78 4.72 4.92 4.46 4.79 4.50 4.73
Xmin <- names(Xsum[which(Xsum == min(Xsum))])
Xmin
## [1] "6239179"
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] 0.099740637 0.008232683 0.508368201 0.015766423 1.906818411 0.390605741
##
## $Xsum
## [1] 2.929532
학번
class_roll$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 |
33 |
32 |
37 |
18 |
66 |
41 |
| Black |
16 |
35 |
32 |
37 |
17 |
66 |
40 |
X1min <- tbl1 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X1min
## X-squared
## 0.09974064
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
## 0.5083682
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 |
21 |
23 |
24 |
29 |
29 |
19 |
21 |
28 |
24 |
25 |
| Black |
20 |
20 |
21 |
24 |
30 |
25 |
21 |
30 |
25 |
27 |
X5min <- tbl5 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X5min
## X-squared
## 1.906818
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 |
46 |
39 |
16 |
142 |
| Black |
46 |
44 |
15 |
138 |
X6min <- tbl6 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X6min
## X-squared
## 0.3906057
Sum of Chi_Squares
Xsum_min <- X1min + X2min + X3min + X4min + X5min + X6min
Xsum_min
## X-squared
## 2.929532