Data
Search for Best Configuration
M1 <- 3000001
M2 <- 4000000
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 0.0019 0.0387 -0.0003 0.0047 -0.0035
## X2 0.0019 1.0000 -0.0012 0.0004 0.0001 -0.0013
## X3 0.0387 -0.0012 1.0000 0.0001 0.0065 -0.0005
## X4 -0.0003 0.0004 0.0001 1.0000 0.0007 -0.0017
## X5 0.0047 0.0001 0.0065 0.0007 1.0000 -0.0002
## X6 -0.0035 -0.0013 -0.0005 -0.0017 -0.0002 1.0000
names(Xsum) <- M1:M2
Xsum %>%
summary %>%
round(2)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 2.68 16.37 20.38 21.04 24.98 68.83
Xsum %>%
sd %>%
round(2)
## [1] 6.49
Xsum %>%
`<=`(5) %>%
which %>%
`[`(Xsum, .) %>%
round(2)
## 3011945 3030895 3039337 3040677 3044581 3045770 3051949 3051986 3060492 3063843
## 4.82 4.93 4.11 4.18 4.45 3.28 4.92 4.27 2.68 3.27
## 3065739 3070389 3072720 3074713 3076562 3096410 3101859 3107242 3116285 3143850
## 4.65 4.26 4.93 4.73 3.91 4.84 4.94 4.63 4.29 4.88
## 3150515 3152354 3156043 3160597 3163335 3163847 3177010 3177921 3178744 3180123
## 4.61 4.85 4.77 4.13 4.78 4.55 3.91 4.87 4.52 4.20
## 3189991 3190029 3201026 3202681 3221696 3238242 3241767 3247887 3252356 3257166
## 4.04 4.91 3.79 4.42 4.99 4.76 3.46 3.70 4.93 4.49
## 3280105 3290978 3291019 3298764 3309464 3312312 3313069 3316078 3318179 3318278
## 4.31 3.30 4.80 4.92 4.89 4.59 4.33 4.92 4.88 4.56
## 3327376 3332417 3333690 3336511 3345489 3346823 3348100 3349351 3350109 3363828
## 4.76 4.10 4.68 4.65 4.46 4.77 4.95 4.20 4.98 4.98
## 3366213 3371733 3374012 3377187 3386277 3393644 3399958 3404522 3431784 3454906
## 2.82 4.65 4.49 4.88 4.46 4.40 4.47 4.98 3.54 3.79
## 3458658 3459389 3465054 3471415 3474796 3475907 3477293 3478384 3479520 3484488
## 3.62 4.82 3.82 4.74 4.99 4.52 3.83 4.80 4.79 2.94
## 3487735 3490250 3495135 3497840 3500345 3502344 3503172 3508084 3510898 3531962
## 4.76 4.59 4.85 4.39 4.95 4.77 4.60 4.78 4.82 4.96
## 3539210 3543080 3551141 3566929 3586848 3591154 3602706 3606106 3606490 3609735
## 3.36 4.20 4.50 4.75 4.48 3.94 4.41 4.18 4.87 4.23
## 3614914 3622783 3639852 3649366 3658805 3659079 3680942 3685760 3687726 3693944
## 4.54 3.60 4.74 4.32 4.97 2.96 4.51 3.99 4.10 4.47
## 3697590 3702463 3719552 3729782 3738667 3739164 3751741 3758205 3762712 3763100
## 4.35 4.89 4.54 4.50 4.97 4.00 4.97 4.53 4.87 4.72
## 3781304 3783655 3784356 3795987 3799284 3802008 3803378 3810370 3813612 3815134
## 4.91 3.07 3.35 4.84 4.83 4.35 3.36 4.85 4.90 3.72
## 3834890 3835684 3844642 3860317 3874658 3882736 3883208 3888548 3895360 3896939
## 3.19 4.17 4.25 4.12 4.32 4.90 4.55 4.74 4.35 4.90
## 3905118 3910233 3915893 3936759 3940864 3943956 3945835 3956867 3957451 3981733
## 4.24 4.86 4.26 4.84 4.09 4.60 4.80 4.62 4.15 4.80
## 3987305 3995198 3997030 3997482
## 4.89 4.99 4.41 3.66
Xmin <- names(Xsum[which(Xsum == min(Xsum))])
Xmin
## [1] "3060492"
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] 0.98112648 0.16247639 0.00000000 0.04853833 1.15611756 0.33010095
##
## $Xsum
## [1] 2.67836
학번
class_roll$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 |
28 |
25 |
55 |
18 |
49 |
115 |
| Black |
19 |
30 |
30 |
53 |
20 |
49 |
107 |
X1min <- tbl1 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X1min
## X-squared
## 0.9811265
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 |
34 |
26 |
26 |
33 |
28 |
34 |
40 |
34 |
| Black |
23 |
33 |
34 |
27 |
25 |
31 |
27 |
40 |
36 |
32 |
X5min <- tbl5 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X5min
## X-squared
## 1.156118
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 |
48 |
26 |
169 |
| Black |
63 |
47 |
23 |
175 |
X6min <- tbl6 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X6min
## X-squared
## 0.3301009
Sum of Chi_Squares
Xsum_min <- X1min + X2min + X3min + X4min + X5min + X6min
Xsum_min
## X-squared
## 2.67836