Data
Search for Best Configuration
M1 <- 7000001
M2 <- 8000000
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 -0.0036 0.0206 0.0039 -0.0029 -0.0049
## X2 -0.0036 1.0000 -0.0039 0.0016 -0.0025 -0.0009
## X3 0.0206 -0.0039 1.0000 0.0042 -0.0013 -0.0055
## X4 0.0039 0.0016 0.0042 1.0000 -0.0041 0.0017
## X5 -0.0029 -0.0025 -0.0013 -0.0041 1.0000 -0.0034
## X6 -0.0049 -0.0009 -0.0055 0.0017 -0.0034 1.0000
names(Xsum) <- M1:M2
Xsum %>%
summary %>%
round(2)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 2.83 16.45 20.43 21.05 24.97 64.93
Xsum %>%
sd %>%
round(2)
## [1] 6.41
Xsum %>%
`<=`(5) %>%
which %>%
`[`(Xsum, .) %>%
round(2)
## 7003777 7005310 7006261 7035360 7039425 7041563 7055511 7075363 7076071 7086460
## 4.32 4.73 2.83 4.94 4.06 4.57 4.66 4.68 4.71 4.86
## 7092874 7110654 7112706 7122439 7125454 7128302 7132278 7153138 7153776 7153990
## 4.86 5.00 4.84 4.68 4.84 4.44 4.98 4.11 4.35 4.83
## 7164872 7169998 7179972 7181278 7199354 7203441 7204925 7211838 7214189 7227181
## 4.44 4.90 3.83 3.93 4.55 4.72 3.98 4.43 4.74 3.80
## 7233202 7246392 7249477 7260904 7262823 7266448 7271276 7274452 7281704 7281731
## 4.71 4.53 4.32 4.16 4.41 4.66 4.74 4.85 3.66 4.96
## 7289417 7290574 7311633 7312194 7316044 7321097 7327825 7342852 7351561 7352786
## 3.56 4.71 4.11 4.59 4.57 2.87 4.69 4.75 3.23 4.27
## 7360820 7371823 7374870 7396890 7402727 7411133 7457577 7475400 7509745 7509861
## 4.94 3.76 4.26 4.71 4.12 4.83 4.02 3.94 4.02 4.25
## 7520974 7530871 7541978 7548719 7550265 7555696 7556886 7603484 7605059 7616059
## 3.59 4.99 3.21 4.73 4.38 4.43 4.90 3.86 3.78 4.75
## 7623709 7627716 7627882 7629134 7630731 7631192 7639628 7649962 7650981 7661529
## 4.98 4.96 4.56 4.82 4.58 4.46 4.43 4.91 4.80 4.80
## 7663536 7669978 7677458 7683978 7695065 7696867 7701462 7709894 7718467 7745345
## 4.68 4.43 3.70 4.41 5.00 4.07 4.05 4.10 4.85 4.90
## 7747192 7747739 7750077 7759388 7775458 7794076 7811452 7820204 7820374 7829607
## 4.99 3.86 4.88 4.92 4.81 4.63 4.85 4.78 4.95 4.96
## 7836934 7842392 7846090 7869674 7873911 7878083 7901898 7904315 7906958 7907744
## 4.78 4.83 4.81 4.05 4.25 4.68 4.82 4.08 3.28 4.74
## 7907946 7912319 7918511 7925682 7942471 7959464 7965533 7967335 7968870 7983056
## 4.91 3.99 4.88 3.88 4.40 4.49 4.86 4.21 4.84 4.84
## 7983713 7986875 7993104
## 4.79 3.24 4.92
Xmin <- names(Xsum[which(Xsum == min(Xsum))])
Xmin
## [1] "7006261"
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] 1.00135248 0.40340149 0.00000000 0.01576642 1.21165655 0.19845577
##
## $Xsum
## [1] 2.830633
학번
class_roll$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 |
16 |
33 |
31 |
35 |
17 |
67 |
44 |
| Black |
16 |
35 |
33 |
39 |
18 |
65 |
37 |
X1min <- tbl1 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X1min
## X-squared
## 1.001352
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 |
116 |
127 |
| Black |
123 |
120 |
X2min <- tbl2 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X2min
## X-squared
## 0.4034015
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
## 0.01576642
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 |
20 |
21 |
22 |
28 |
32 |
20 |
22 |
28 |
24 |
26 |
| Black |
21 |
22 |
23 |
25 |
27 |
24 |
20 |
30 |
25 |
26 |
X5min <- tbl5 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X5min
## X-squared
## 1.211657
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 |
47 |
40 |
15 |
141 |
| Black |
45 |
43 |
16 |
139 |
X6min <- tbl6 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X6min
## X-squared
## 0.1984558
Sum of Chi_Squares
Xsum_min <- X1min + X2min + X3min + X4min + X5min + X6min
Xsum_min
## X-squared
## 2.830633