Data
Search for Best Configuration
M1 <- 3000001
M2 <- 4000000
Xsum <- numeric(0)
Xsum <- sapply(M1:M2, red_and_black)
# 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)
names(Xsum) <- M1:M2
Xsum %>%
summary %>%
round(2)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 2.31 16.36 20.36 21.03 24.97 66.13
Xsum %>%
sd %>%
round(2)
## [1] 6.5
Xsum %>%
`<=`(5) %>%
which %>%
`[`(Xsum, .) %>%
round(2)
## 3009483 3011117 3018886 3020631 3034605 3037557 3044259 3046926 3051869 3075537
## 4.89 4.74 4.31 4.71 4.43 4.51 4.38 3.68 4.96 4.76
## 3092784 3094291 3097028 3102754 3102772 3103892 3105140 3111181 3119539 3122751
## 4.28 5.00 4.94 4.01 4.43 4.62 4.52 3.82 4.36 4.42
## 3125471 3141376 3152454 3153442 3153808 3155303 3160132 3179564 3182188 3189013
## 4.50 4.92 4.93 4.11 4.77 4.66 4.74 4.55 4.38 4.59
## 3190786 3214328 3241172 3258853 3260022 3260557 3266792 3270824 3276824 3282553
## 4.99 4.81 4.72 4.65 4.47 3.63 3.64 4.98 4.96 4.89
## 3290146 3295676 3301294 3310065 3317181 3321149 3334457 3336022 3351484 3364349
## 4.63 4.83 4.56 4.27 4.74 4.84 4.27 3.65 4.76 4.64
## 3366948 3376143 3382405 3385525 3403712 3408111 3422229 3469536 3471341 3494683
## 4.98 4.84 4.97 4.16 4.59 4.77 3.93 4.85 4.54 4.96
## 3494834 3502835 3508390 3510854 3512919 3527276 3548372 3561619 3567664 3569185
## 4.61 4.28 4.72 4.53 3.98 4.76 2.31 4.71 5.00 4.37
## 3599407 3602043 3607648 3613655 3618196 3627599 3635230 3656455 3657658 3658047
## 5.00 4.47 4.48 4.63 4.54 4.44 4.53 4.57 4.83 4.14
## 3670003 3672762 3674856 3678624 3682584 3683196 3689428 3694354 3695475 3697194
## 4.81 3.41 4.99 4.76 4.46 4.82 4.97 4.84 4.88 4.62
## 3698254 3717665 3719705 3721453 3725811 3729635 3733793 3749360 3750495 3754083
## 4.48 5.00 4.89 4.64 4.78 3.70 4.58 4.94 4.11 4.95
## 3759142 3766078 3766678 3768477 3770089 3778074 3786008 3788442 3791653 3803889
## 4.54 4.79 4.78 4.43 4.85 4.38 4.80 4.40 3.93 4.16
## 3804829 3824911 3841997 3853271 3872721 3877829 3881787 3886152 3892930 3901068
## 4.70 4.41 4.35 3.15 4.70 4.38 4.45 4.44 4.90 4.09
## 3903402 3906803 3924867 3938865 3940583 3940719 3943701 3947074 3956643 3965366
## 4.01 4.93 4.68 4.48 4.43 4.51 4.74 4.60 3.98 4.01
## 3968312 3972173 3987262 3988167
## 4.09 3.61 4.66 4.09
Xmin <- names(Xsum[which(Xsum == min(Xsum))])
Xmin
## [1] "3548372"
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(Xmin)
## [1] 2.311112
학번
class_roll$id_2 <-
class_roll$id %>%
ifelse(. <= 2016, "2016", .)
tbl1 <- class_roll %$%
table(.$group, .$id_2 %>% substr(1, 4)) %>%
`colnames<-`(c("2016 이전", 2017:2022))
tbl1 %>%
pander
| Red |
19 |
35 |
60 |
76 |
51 |
138 |
24 |
| Black |
22 |
36 |
61 |
78 |
50 |
131 |
26 |
X1min <- tbl1 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X1min
## X-squared
## 0.538654
학번 홀짝
tbl2 <- class_roll$id %>%
as.numeric %>%
`%%`(2) %>%
factor(levels = c(1, 0), labels = c("홀", "짝")) %>%
table(class_roll$group, .)
tbl2 %>%
pander
| Red |
207 |
196 |
| Black |
213 |
191 |
X2min <- tbl2 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X2min
## X-squared
## 0.1490748
학적 상태
tbl3 <- class_roll$status %>%
table(class_roll$group, .)
tbl3 %>%
pander
X3min <- tbl3 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X3min
## X-squared
## 0.1205262
e-mail 서비스업체
tbl4 <- class_roll$email %>%
strsplit("@", fixed = TRUE) %>%
sapply("[", 2) %>%
`==`("naver.com") %>%
ifelse("네이버", "기타서비스") %>%
factor(levels = c("네이버", "기타서비스")) %>%
table(class_roll$group, .)
tbl4 %>%
pander
X4min <- tbl4 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X4min
## X-squared
## 0.2278032
전화번호의 분포
cut_label <- paste(paste0(0:9, "000"), paste0(0:9, "999"),
sep = "~")
tbl5 <- class_roll$cell_no %>%
substr(start = 8, stop = 11) %>%
sapply(as.numeric) %>%
cut(labels = cut_label,
breaks = seq(0, 10000, by = 1000)) %>%
table(class_roll$group, .)
tbl5 %>%
pander
| Red |
42 |
30 |
35 |
44 |
30 |
50 |
41 |
39 |
42 |
50 |
| Black |
39 |
35 |
33 |
41 |
34 |
48 |
43 |
38 |
40 |
52 |
X5min <- tbl5 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X5min
## X-squared
## 1.099851
성씨 분포
f_name <- class_roll$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 |
73 |
59 |
31 |
240 |
| Black |
75 |
62 |
29 |
238 |
X6min <- tbl6 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X6min
## X-squared
## 0.1752032
Sum of Chi_Squares
Xsum_min <- X1min + X2min + X3min + X4min + X5min + X6min
Xsum_min
## X-squared
## 2.311112