Data
Search for Best Configuration
M1 <- 7000001
M2 <- 8000000
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 0.0364 -0.0032 0.0042 -0.0022
## X2 0.0015 1.0000 -0.0004 -0.0001 0.0000 -0.0009
## X3 0.0364 -0.0004 1.0000 -0.0006 0.0062 -0.0003
## X4 -0.0032 -0.0001 -0.0006 1.0000 -0.0015 -0.0011
## X5 0.0042 0.0000 0.0062 -0.0015 1.0000 0.0001
## X6 -0.0022 -0.0009 -0.0003 -0.0011 0.0001 1.0000
names(Xsum) <- M1:M2
Xsum %>%
summary %>%
round(2)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 3.29 16.37 20.37 21.03 24.97 68.54
Xsum %>%
sd %>%
round(2)
## [1] 6.48
Xsum %>%
`<=`(5) %>%
which %>%
`[`(Xsum, .) %>%
round(2)
## 7001897 7007295 7016007 7018751 7028465 7036556 7040385 7046325 7052294 7063143
## 4.11 3.68 3.29 3.96 4.99 4.85 4.89 3.78 4.30 4.52
## 7066097 7097457 7100424 7122358 7124267 7155678 7156277 7159153 7175166 7185541
## 4.91 4.56 4.74 4.51 4.30 3.98 4.40 4.06 4.25 4.98
## 7195466 7216419 7217377 7220169 7226189 7241419 7247978 7248408 7250395 7250929
## 4.68 3.87 4.71 4.19 4.93 4.60 4.91 4.90 4.84 3.67
## 7257060 7264044 7265783 7275829 7281746 7281938 7295444 7309325 7319419 7343051
## 4.88 3.91 4.59 4.28 4.53 3.73 4.48 4.73 4.72 4.83
## 7361623 7362088 7363384 7377292 7380324 7383493 7398096 7403092 7406321 7419271
## 4.79 4.18 4.42 4.50 4.97 4.11 4.43 4.63 3.93 4.61
## 7426356 7426376 7448115 7448946 7449419 7475224 7480500 7484906 7499362 7501030
## 4.39 4.80 4.89 4.41 4.97 4.88 4.84 4.91 4.40 4.82
## 7505882 7524146 7528452 7531381 7539998 7546797 7553447 7565689 7574402 7579552
## 4.72 3.89 3.45 4.27 4.48 4.91 4.99 4.09 4.09 4.73
## 7586277 7588916 7593923 7598403 7601841 7609208 7610956 7615691 7628382 7629216
## 4.37 3.98 4.82 4.59 4.83 4.67 4.45 3.37 4.89 4.85
## 7629996 7630864 7632123 7636254 7636500 7659236 7676801 7682850 7683553 7694763
## 4.52 4.78 4.66 4.19 4.01 4.96 5.00 4.79 4.43 4.96
## 7698425 7712630 7712761 7728206 7732958 7736198 7737312 7739188 7741781 7754083
## 3.62 4.97 3.65 4.22 4.21 3.97 4.88 3.98 4.28 4.34
## 7765662 7778397 7786906 7797080 7798837 7800157 7801558 7823709 7831581 7838055
## 4.31 4.69 4.26 4.44 4.72 4.51 4.68 4.49 4.60 4.93
## 7843566 7854665 7856250 7856262 7857664 7863127 7869656 7898916 7899148 7918418
## 4.87 4.94 4.77 4.40 4.77 4.24 4.90 4.61 4.21 4.36
## 7918534 7932515 7935441 7940954 7950287 7956601 7958504 7958879 7963570 7973609
## 4.93 4.91 4.12 3.94 4.31 4.30 4.34 4.54 3.49 3.95
## 7976029 7983861 7989776
## 4.28 4.67 4.66
Xmin <- names(Xsum[which(Xsum == min(Xsum))])
Xmin
## [1] "7016007"
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] 1.07734302 0.16247639 0.00000000 0.04853833 0.99601651 1.01050945
##
## $Xsum
## [1] 3.294884
학번
class_roll$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 |
21 |
29 |
27 |
52 |
19 |
51 |
109 |
| Black |
16 |
29 |
28 |
56 |
19 |
47 |
113 |
X1min <- tbl1 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X1min
## X-squared
## 1.077343
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
## 0.04853833
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 |
37 |
26 |
24 |
32 |
28 |
36 |
37 |
34 |
| Black |
23 |
32 |
31 |
27 |
27 |
32 |
27 |
38 |
39 |
32 |
X5min <- tbl5 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X5min
## X-squared
## 0.9960165
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 |
66 |
51 |
23 |
168 |
| Black |
62 |
44 |
26 |
176 |
X6min <- tbl6 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X6min
## X-squared
## 1.010509
Sum of Chi_Squares
Xsum_min <- X1min + X2min + X3min + X4min + X5min + X6min
Xsum_min
## X-squared
## 3.294884