Data
Search for Best Configuration
M1 <- 8000001
M2 <- 9000000
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.
## 2.51 16.36 20.35 21.03 24.97 70.08
Xsum %>%
sd %>%
round(2)
## [1] 6.5
Xsum %>%
`<=`(5) %>%
which %>%
`[`(Xsum, .) %>%
round(2)
## 8002536 8014496 8020224 8034536 8034764 8037662 8043412 8056467 8071113 8077590
## 4.73 4.65 4.85 4.98 4.31 3.58 4.95 4.52 4.09 4.42
## 8086000 8089916 8098466 8102118 8103456 8104747 8118771 8132097 8136136 8143056
## 4.70 4.58 4.52 4.09 4.86 4.78 4.49 4.78 4.17 4.73
## 8146383 8153948 8159438 8168468 8169342 8176049 8177020 8177778 8179134 8184508
## 4.88 4.82 4.61 4.89 4.83 3.62 4.72 4.83 4.24 4.81
## 8191781 8193762 8196381 8197129 8213766 8216514 8217045 8259204 8279864 8281594
## 4.97 3.68 4.53 4.98 4.98 3.52 4.91 4.84 4.84 3.85
## 8286809 8291628 8295292 8296894 8301532 8311965 8318198 8328223 8343149 8351602
## 4.70 4.77 4.99 4.86 4.82 3.82 4.96 4.81 4.83 4.46
## 8370920 8383512 8385014 8387076 8399905 8407035 8409061 8410367 8428866 8440084
## 4.58 3.85 3.28 4.31 4.51 4.99 4.25 4.43 4.97 4.90
## 8456771 8460532 8464605 8472823 8480019 8480109 8481271 8486923 8494329 8504264
## 3.86 4.36 4.36 4.16 4.91 3.14 4.55 4.64 4.89 4.67
## 8506296 8507945 8512045 8516877 8517897 8519139 8522850 8539531 8540158 8541684
## 2.51 4.73 4.08 4.90 4.87 4.10 2.87 4.27 3.74 3.04
## 8544987 8558134 8561336 8568141 8576653 8580080 8585710 8598106 8604956 8614304
## 3.37 4.94 4.48 4.52 4.58 4.58 4.67 4.15 4.98 3.72
## 8621496 8622712 8635553 8642862 8652095 8666744 8667703 8680469 8686855 8688248
## 4.97 4.65 3.96 3.99 3.86 4.65 3.96 3.30 4.96 4.59
## 8696048 8697267 8714180 8728638 8734331 8737712 8738958 8740122 8741269 8743309
## 4.86 4.95 4.06 4.67 4.67 4.57 4.92 4.47 4.77 4.62
## 8756955 8766890 8768786 8774846 8797459 8806722 8811131 8820577 8821426 8826533
## 4.79 4.73 4.60 4.21 4.92 4.36 4.40 4.79 3.89 4.57
## 8833888 8836070 8836281 8837443 8844403 8847957 8848852 8877059 8882259 8884215
## 4.97 4.29 4.87 4.51 4.91 4.19 4.98 4.47 4.88 4.80
## 8886680 8939374 8949481 8958758 8961805 8975391 8977193 8984778 8987112 8997870
## 3.67 3.94 4.66 4.06 4.94 4.32 4.58 4.61 4.09 4.43
## 8999528
## 3.57
Xmin <- names(Xsum[which(Xsum == min(Xsum))])
Xmin
## [1] "8506296"
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] 2.512243
학번
class_roll$id_2 <-
class_roll$id %>%
ifelse(. <= 2016, "2016", .)
tbl1 <- class_roll %$%
table(.$group, .$id_2 %>% substr(1, 4)) %>%
`colnames<-`(c("2016 이전", 2017:2022))
tbl1 %>%
pander
| Red |
19 |
35 |
58 |
80 |
51 |
136 |
24 |
| Black |
22 |
36 |
63 |
74 |
50 |
133 |
26 |
X1min <- tbl1 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X1min
## X-squared
## 0.7960948
학번 홀짝
tbl2 <- class_roll$id %>%
as.numeric %>%
`%%`(2) %>%
factor(levels = c(1, 0), labels = c("홀", "짝")) %>%
table(class_roll$group, .)
tbl2 %>%
pander
| Red |
213 |
190 |
| Black |
207 |
197 |
X2min <- tbl2 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X2min
## X-squared
## 0.2110904
학적 상태
tbl3 <- class_roll$status %>%
table(class_roll$group, .)
tbl3 %>%
pander
X3min <- tbl3 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X3min
## X-squared
## 0.2799408
e-mail 서비스업체
tbl4 <- class_roll$email %>%
strsplit("@", fixed = TRUE) %>%
sapply("[", 2) %>%
`==`("naver.com") %>%
ifelse("네이버", "기타서비스") %>%
factor(levels = c("네이버", "기타서비스")) %>%
table(class_roll$group, .)
tbl4 %>%
pander
X4min <- tbl4 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X4min
## X-squared
## 0.005753858
전화번호의 분포
cut_label <- paste(paste0(0:9, "000"), paste0(0:9, "999"),
sep = "~")
tbl5 <- class_roll$cell_no %>%
substr(start = 8, stop = 11) %>%
sapply(as.numeric) %>%
cut(labels = cut_label,
breaks = seq(0, 10000, by = 1000)) %>%
table(class_roll$group, .)
tbl5 %>%
pander
| Red |
42 |
35 |
32 |
42 |
32 |
48 |
42 |
38 |
41 |
50 |
| Black |
39 |
30 |
36 |
43 |
32 |
50 |
42 |
39 |
41 |
52 |
X5min <- tbl5 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X5min
## X-squared
## 0.8308467
성씨 분포
f_name <- class_roll$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 |
76 |
58 |
31 |
238 |
| Black |
72 |
63 |
29 |
240 |
X6min <- tbl6 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X6min
## X-squared
## 0.388516
Sum of Chi_Squares
Xsum_min <- X1min + X2min + X3min + X4min + X5min + X6min
Xsum_min
## X-squared
## 2.512243