Data
Search for Best Configuration
M1 <- 8000001
M2 <- 9000000
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 0.0017 0.0371 -0.0015 0.0058 0.0000
## X2 0.0017 1.0000 0.0015 0.0010 0.0009 -0.0007
## X3 0.0371 0.0015 1.0000 0.0015 0.0040 -0.0014
## X4 -0.0015 0.0010 0.0015 1.0000 -0.0008 -0.0015
## X5 0.0058 0.0009 0.0040 -0.0008 1.0000 0.0029
## X6 0.0000 -0.0007 -0.0014 -0.0015 0.0029 1.0000
names(Xsum) <- M1:M2
Xsum %>%
summary %>%
round(2)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 3.11 16.36 20.37 21.03 24.98 67.20
Xsum %>%
sd %>%
round(2)
## [1] 6.49
Xsum %>%
`<=`(5) %>%
which %>%
`[`(Xsum, .) %>%
round(2)
## 8004008 8005274 8015739 8018442 8025560 8032634 8036007 8040952 8044219 8046181
## 4.42 3.87 4.34 4.66 4.70 3.80 4.95 4.83 4.43 4.71
## 8050012 8051126 8052702 8059434 8060891 8061366 8071930 8075772 8077719 8078025
## 4.95 4.77 3.15 4.92 4.26 4.87 4.87 4.83 4.99 4.63
## 8083613 8094831 8103098 8106074 8113128 8123981 8148906 8151868 8152335 8152857
## 4.27 4.94 4.84 4.26 3.97 3.61 4.75 3.62 3.66 3.71
## 8154804 8160640 8180711 8183249 8183729 8187615 8189733 8191104 8201026 8203478
## 4.99 4.81 3.81 4.82 4.80 3.58 4.96 3.99 4.64 4.42
## 8206564 8221110 8222064 8222967 8224180 8231010 8244814 8246536 8248375 8249087
## 4.99 4.75 3.91 4.35 4.94 4.89 4.93 4.74 4.00 4.45
## 8252031 8262534 8265545 8269419 8291946 8306792 8329650 8329979 8337682 8349409
## 3.16 4.39 4.44 4.55 4.60 4.64 4.89 4.27 4.43 4.28
## 8356527 8356974 8383299 8387344 8414548 8416057 8435124 8440477 8442402 8463160
## 5.00 4.77 4.62 4.67 4.11 4.75 4.82 4.41 5.00 4.62
## 8477363 8480807 8490587 8500553 8514820 8527678 8529685 8552302 8554633 8561343
## 4.93 4.96 4.85 4.37 4.96 4.22 3.82 4.53 4.82 4.76
## 8576113 8576290 8586783 8588273 8588462 8591013 8600878 8613133 8633887 8636365
## 4.30 4.77 4.16 4.27 4.32 4.54 4.94 4.39 4.92 4.46
## 8650108 8650277 8652887 8666345 8669889 8671129 8675026 8684555 8711208 8712388
## 4.30 4.97 3.89 4.75 4.79 4.75 4.96 4.82 4.75 3.11
## 8712546 8724436 8729699 8759746 8779231 8785502 8799365 8810906 8823626 8836854
## 4.72 4.82 5.00 4.77 4.77 4.75 4.63 4.25 4.55 3.98
## 8840019 8855983 8857740 8872535 8875222 8877639 8881643 8887534 8891569 8894687
## 4.20 4.61 4.59 4.67 4.93 4.97 4.79 4.13 3.23 4.51
## 8896335 8903272 8913679 8917881 8918268 8920057 8944093 8947430 8949925 8952088
## 4.50 4.66 4.58 3.61 4.77 4.14 4.49 4.81 4.74 4.79
## 8963513 8966680 8969854 8974343 8989264
## 4.14 4.88 4.42 3.92 4.91
Xmin <- names(Xsum[which(Xsum == min(Xsum))])
Xmin
## [1] "8712388"
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] 1.41143575 0.16247639 0.00000000 0.04853833 1.24612600 0.23707769
##
## $Xsum
## [1] 3.105654
학번
class_roll$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 |
18 |
29 |
30 |
57 |
18 |
50 |
106 |
| Black |
19 |
29 |
25 |
51 |
20 |
48 |
116 |
X1min <- tbl1 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X1min
## X-squared
## 1.411436
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 |
152 |
156 |
| Black |
147 |
161 |
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 |
29 |
35 |
26 |
27 |
33 |
29 |
34 |
38 |
33 |
| Black |
23 |
33 |
33 |
27 |
24 |
31 |
26 |
40 |
38 |
33 |
X5min <- tbl5 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X5min
## X-squared
## 1.246126
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 |
23 |
173 |
| Black |
63 |
48 |
26 |
171 |
X6min <- tbl6 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X6min
## X-squared
## 0.2370777
Sum of Chi_Squares
Xsum_min <- X1min + X2min + X3min + X4min + X5min + X6min
Xsum_min
## X-squared
## 3.105654