Data
Search for Best Configuration
M1 <- 6000001
M2 <- 7000000
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.
## 1.34 16.34 20.36 21.03 24.98 69.46
Xsum %>%
sd %>%
round(2)
## [1] 6.51
Xsum %>%
`<=`(5) %>%
which %>%
`[`(Xsum, .) %>%
round(2)
## 6010157 6010902 6011230 6011816 6014232 6045352 6049783 6049790 6052375 6068418
## 4.20 3.93 4.04 4.61 4.80 4.40 4.76 4.90 4.57 4.88
## 6077393 6078525 6080173 6083943 6086686 6088513 6098195 6100474 6119334 6122011
## 4.29 3.79 4.13 3.48 4.37 4.75 4.14 4.80 4.25 4.95
## 6128254 6139575 6142373 6156793 6171237 6173858 6178972 6180492 6184915 6191014
## 4.40 4.83 4.29 4.61 4.82 4.89 4.39 4.38 3.33 3.98
## 6193463 6207071 6215773 6217629 6221350 6228273 6230068 6230858 6233518 6240109
## 4.27 4.59 4.81 4.65 4.94 4.75 4.11 4.98 4.54 4.81
## 6241742 6251009 6270089 6276063 6308831 6310393 6314069 6319079 6339915 6342218
## 4.99 4.87 4.89 4.98 4.00 4.52 3.88 4.60 4.42 4.62
## 6342821 6353503 6354129 6361433 6368549 6368982 6391668 6398282 6399121 6402698
## 4.63 4.09 3.64 4.52 4.38 4.93 4.75 4.95 4.98 4.86
## 6409153 6412764 6423961 6425815 6436041 6439884 6441556 6445187 6448819 6454572
## 4.68 4.83 4.83 4.10 4.93 4.78 3.68 4.67 4.47 4.06
## 6465530 6469594 6481550 6482032 6488391 6500605 6518258 6518857 6530522 6535225
## 4.52 4.97 4.66 4.64 2.63 4.71 4.17 4.42 4.78 4.95
## 6539949 6543521 6544138 6549472 6556272 6557323 6561448 6570032 6571529 6591637
## 4.83 4.57 4.38 4.86 4.96 3.68 4.14 4.52 4.62 3.56
## 6592308 6594404 6600405 6625183 6639424 6644244 6652389 6653764 6661934 6663484
## 4.74 4.69 4.97 4.63 4.69 4.66 4.55 4.91 4.83 4.56
## 6674806 6685441 6686399 6714483 6719130 6728598 6740359 6744769 6761968 6766341
## 1.34 4.99 4.50 4.08 4.88 4.74 3.90 4.95 4.87 4.39
## 6773692 6777487 6782042 6784012 6785166 6787267 6788397 6805121 6808121 6808139
## 4.89 4.79 4.55 4.39 4.58 4.33 4.90 4.11 4.67 4.43
## 6817884 6842248 6845438 6852165 6853253 6859806 6869836 6872215 6874103 6876353
## 4.54 3.31 4.24 4.76 4.61 4.57 4.89 4.93 4.94 4.48
## 6899413 6903022 6927207 6936873 6941242 6942117 6947068 6950382 6950469 6953671
## 4.22 4.87 3.82 4.80 4.62 4.77 4.68 4.88 4.58 4.60
## 6955541 6957304 6961667 6970532 6973360 6975349 6985564 6987132 6988081 6988716
## 3.66 4.91 4.65 4.51 4.83 4.42 4.99 3.88 4.66 3.41
Xmin <- names(Xsum[which(Xsum == min(Xsum))])
Xmin
## [1] "6674806"
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] 1.336604
학번
class_roll$id_2 <-
class_roll$id %>%
ifelse(. <= 2016, "2016", .)
tbl1 <- class_roll %$%
table(.$group, .$id_2 %>% substr(1, 4)) %>%
`colnames<-`(c("2016 이전", 2017:2022))
tbl1 %>%
pander
| Red |
20 |
36 |
61 |
77 |
49 |
135 |
25 |
| Black |
21 |
35 |
60 |
77 |
52 |
134 |
25 |
X1min <- tbl1 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X1min
## X-squared
## 0.1383267
학번 홀짝
tbl2 <- class_roll$id %>%
as.numeric %>%
`%%`(2) %>%
factor(levels = c(1, 0), labels = c("홀", "짝")) %>%
table(class_roll$group, .)
tbl2 %>%
pander
| Red |
209 |
194 |
| Black |
211 |
193 |
X2min <- tbl2 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X2min
## X-squared
## 0.01086865
학적 상태
tbl3 <- class_roll$status %>%
table(class_roll$group, .)
tbl3 %>%
pander
X3min <- tbl3 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X3min
## X-squared
## 0.0002782937
e-mail 서비스업체
tbl4 <- class_roll$email %>%
strsplit("@", fixed = TRUE) %>%
sapply("[", 2) %>%
`==`("naver.com") %>%
ifelse("네이버", "기타서비스") %>%
factor(levels = c("네이버", "기타서비스")) %>%
table(class_roll$group, .)
tbl4 %>%
pander
X4min <- tbl4 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X4min
## X-squared
## 0.01177796
전화번호의 분포
cut_label <- paste(paste0(0:9, "000"), paste0(0:9, "999"),
sep = "~")
tbl5 <- class_roll$cell_no %>%
substr(start = 8, stop = 11) %>%
sapply(as.numeric) %>%
cut(labels = cut_label,
breaks = seq(0, 10000, by = 1000)) %>%
table(class_roll$group, .)
tbl5 %>%
pander
| Red |
42 |
33 |
36 |
43 |
31 |
47 |
42 |
37 |
39 |
53 |
| Black |
39 |
32 |
32 |
42 |
33 |
51 |
42 |
40 |
43 |
49 |
X5min <- tbl5 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X5min
## X-squared
## 1.068188
성씨 분포
f_name <- class_roll$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 |
74 |
61 |
31 |
237 |
| Black |
74 |
60 |
29 |
241 |
X6min <- tbl6 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X6min
## X-squared
## 0.1071649
Sum of Chi_Squares
Xsum_min <- X1min + X2min + X3min + X4min + X5min + X6min
Xsum_min
## X-squared
## 1.336604