Data
Search for Best Configuration
M1 <- 5000001
M2 <- 6000000
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.
## 2.25 16.36 20.37 21.04 24.98 73.53
Xsum %>%
sd %>%
round(2)
## [1] 6.51
Xsum %>%
`<=`(5) %>%
which %>%
`[`(Xsum, .) %>%
round(2)
## 5005986 5015646 5018256 5027165 5027493 5032040 5037010 5039118 5041481 5043701
## 4.79 4.37 4.85 4.88 3.62 4.93 4.76 3.79 4.32 3.55
## 5047653 5063439 5068830 5072285 5072939 5075190 5090652 5094507 5095157 5099156
## 4.18 4.93 4.36 4.52 4.33 4.51 4.60 3.65 4.05 4.87
## 5117935 5119380 5121691 5121814 5122731 5135559 5152468 5167220 5173241 5184867
## 4.51 4.31 4.92 3.79 4.76 4.93 4.96 4.78 4.95 4.87
## 5184974 5192717 5198463 5208036 5208517 5215077 5216871 5220184 5232942 5233468
## 4.07 4.83 4.13 4.52 3.81 4.91 4.79 4.78 4.68 3.87
## 5236841 5239901 5243263 5262530 5270648 5279369 5284233 5293711 5293718 5294220
## 4.92 4.20 4.86 4.60 4.20 4.80 3.73 4.85 4.52 4.76
## 5302335 5308033 5310315 5321619 5323548 5327151 5327695 5330491 5331389 5332751
## 4.67 4.48 4.79 4.95 4.79 4.33 2.25 4.32 2.61 4.07
## 5345977 5350775 5351937 5353729 5362536 5375279 5400099 5406532 5427147 5432095
## 3.53 4.80 4.62 4.85 4.60 3.78 4.14 4.94 3.67 2.78
## 5445374 5454273 5459888 5478968 5514217 5525870 5527252 5534082 5538753 5540111
## 4.38 4.67 3.21 4.70 4.70 4.22 4.61 3.67 4.78 4.12
## 5552168 5570346 5580500 5592694 5604206 5605117 5607453 5641210 5641291 5641402
## 4.53 4.65 4.63 4.76 3.82 4.35 4.99 3.74 4.40 4.14
## 5643538 5643798 5653031 5670321 5676982 5688499 5688772 5697810 5703744 5709071
## 4.82 3.97 4.70 4.34 4.95 4.88 4.92 3.93 4.96 4.66
## 5710962 5739725 5741663 5749246 5749416 5749553 5754055 5762105 5772039 5777114
## 3.86 4.17 3.47 4.08 4.45 4.93 4.77 3.73 4.68 4.76
## 5782816 5783134 5783571 5790848 5791883 5792491 5796531 5799212 5812145 5819936
## 4.43 4.74 4.80 4.65 4.63 4.27 3.88 4.83 4.95 4.03
## 5823898 5830713 5833858 5843517 5848004 5851741 5858625 5862069 5862415 5863435
## 4.99 4.70 4.12 4.54 3.95 4.86 4.80 4.72 3.46 4.99
## 5865249 5872140 5889253 5915682 5919367 5931564 5939434 5942458 5968561 5976278
## 4.49 4.52 4.38 4.57 4.81 4.08 4.10 4.70 4.61 4.86
## 5978086 5983400 5994863 5995175
## 4.79 4.95 4.29 4.97
Xmin <- names(Xsum[which(Xsum == min(Xsum))])
Xmin
## [1] "5327695"
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] 2.254616
학번
class_roll$id_2 <-
class_roll$id %>%
ifelse(. <= 2016, "2016", .)
tbl1 <- class_roll %$%
table(.$group, .$id_2 %>% substr(1, 4)) %>%
`colnames<-`(c("2016 이전", 2017:2022))
tbl1 %>%
pander
| Red |
20 |
36 |
60 |
78 |
51 |
133 |
25 |
| Black |
21 |
35 |
61 |
76 |
50 |
136 |
25 |
X1min <- tbl1 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X1min
## X-squared
## 0.1148325
학번 홀짝
tbl2 <- class_roll$id %>%
as.numeric %>%
`%%`(2) %>%
factor(levels = c(1, 0), labels = c("홀", "짝")) %>%
table(class_roll$group, .)
tbl2 %>%
pander
| Red |
214 |
189 |
| Black |
206 |
198 |
X2min <- tbl2 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X2min
## X-squared
## 0.3604447
학적 상태
tbl3 <- class_roll$status %>%
table(class_roll$group, .)
tbl3 %>%
pander
X3min <- tbl3 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X3min
## X-squared
## 0.3163597
e-mail 서비스업체
tbl4 <- class_roll$email %>%
strsplit("@", fixed = TRUE) %>%
sapply("[", 2) %>%
`==`("naver.com") %>%
ifelse("네이버", "기타서비스") %>%
factor(levels = c("네이버", "기타서비스")) %>%
table(class_roll$group, .)
tbl4 %>%
pander
X4min <- tbl4 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X4min
## X-squared
## 0.06772211
전화번호의 분포
cut_label <- paste(paste0(0:9, "000"), paste0(0:9, "999"),
sep = "~")
tbl5 <- class_roll$cell_no %>%
substr(start = 8, stop = 11) %>%
sapply(as.numeric) %>%
cut(labels = cut_label,
breaks = seq(0, 10000, by = 1000)) %>%
table(class_roll$group, .)
tbl5 %>%
pander
| Red |
39 |
34 |
31 |
43 |
32 |
50 |
41 |
40 |
42 |
51 |
| Black |
42 |
31 |
37 |
42 |
32 |
48 |
43 |
37 |
40 |
51 |
X5min <- tbl5 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X5min
## X-squared
## 1.044848
성씨 분포
f_name <- class_roll$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 |
71 |
60 |
31 |
241 |
| Black |
77 |
61 |
29 |
237 |
X6min <- tbl6 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X6min
## X-squared
## 0.3504086
Sum of Chi_Squares
Xsum_min <- X1min + X2min + X3min + X4min + X5min + X6min
Xsum_min
## X-squared
## 2.254616