Data
Search for Best Configuration
M1 <- 6000001
M2 <- 7000000
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 0.0028 0.0356 -0.0032 0.0036 -0.0012
## X2 0.0028 1.0000 -0.0010 0.0005 0.0003 -0.0003
## X3 0.0356 -0.0010 1.0000 0.0002 0.0055 0.0009
## X4 -0.0032 0.0005 0.0002 1.0000 -0.0008 -0.0026
## X5 0.0036 0.0003 0.0055 -0.0008 1.0000 0.0022
## X6 -0.0012 -0.0003 0.0009 -0.0026 0.0022 1.0000
names(Xsum) <- M1:M2
Xsum %>%
summary %>%
round(2)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 2.34 16.38 20.37 21.04 24.98 62.66
Xsum %>%
sd %>%
round(2)
## [1] 6.49
Xsum %>%
`<=`(5) %>%
which %>%
`[`(Xsum, .) %>%
round(2)
## 6006793 6035732 6042800 6045105 6046704 6048669 6056226 6062504 6074178 6077413
## 2.34 4.78 4.00 4.99 4.49 4.87 4.67 4.78 4.54 4.96
## 6083687 6092746 6099327 6104729 6105175 6127518 6136712 6154477 6162447 6163866
## 4.87 4.78 4.98 4.83 4.54 4.86 4.45 4.18 3.99 4.61
## 6164354 6180486 6183641 6196543 6204094 6209861 6211412 6212923 6230249 6233107
## 4.92 4.37 3.98 4.99 4.75 4.58 4.12 4.69 4.87 4.88
## 6240529 6252563 6257968 6260446 6262994 6273822 6277963 6278442 6279450 6285514
## 4.71 4.90 4.96 3.60 4.89 4.15 3.18 4.29 4.55 4.08
## 6292152 6294049 6297767 6302130 6304737 6308341 6332600 6338444 6340437 6352855
## 4.91 4.64 4.18 4.77 4.56 4.92 3.46 4.56 4.74 4.61
## 6353197 6368958 6383032 6388080 6389417 6393455 6394483 6400991 6404664 6406241
## 3.34 4.50 4.90 4.45 4.63 4.45 4.44 4.30 4.78 4.22
## 6429248 6431556 6439065 6441485 6442577 6447095 6450903 6464071 6470779 6483886
## 4.54 4.66 4.41 4.37 3.21 4.88 4.83 4.99 4.93 3.84
## 6489159 6500354 6503264 6519456 6520367 6521936 6530044 6531366 6550569 6551738
## 4.12 4.91 4.51 4.87 4.61 4.36 4.98 4.97 4.46 4.90
## 6558534 6559431 6559467 6563347 6573405 6595190 6601656 6611619 6614172 6626548
## 4.52 4.92 4.08 2.95 4.04 4.06 3.58 4.10 3.86 4.82
## 6634825 6636123 6637879 6640472 6670865 6687186 6691086 6692690 6705198 6705458
## 4.27 3.89 4.90 4.99 4.83 4.81 4.91 4.85 4.78 4.07
## 6707330 6713683 6717340 6732782 6741032 6743134 6746098 6751815 6754113 6772384
## 4.92 4.18 4.95 4.85 4.58 4.92 4.35 4.62 4.64 4.29
## 6796909 6799948 6808846 6811235 6816264 6823136 6824480 6855722 6864225 6867702
## 3.93 4.53 4.41 4.97 4.89 4.89 4.91 4.73 4.80 4.83
## 6872281 6872928 6899646 6920507 6921686 6923109 6923961 6940779 6951899 6953678
## 4.60 4.97 4.19 4.15 4.90 4.61 5.00 4.70 4.10 4.83
## 6963103 6963538 6970489 6972746 6974106 6981370 6981589 6984584 6988382 6994830
## 4.73 4.51 4.62 4.70 4.73 4.75 4.15 4.73 4.39 4.02
## 6996259
## 4.66
Xmin <- names(Xsum[which(Xsum == min(Xsum))])
Xmin
## [1] "6006793"
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] 0.45477490 0.52642351 0.07386091 0.04853833 1.03852916 0.20244611
##
## $Xsum
## [1] 2.344573
학번
class_roll$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 |
19 |
30 |
27 |
54 |
18 |
51 |
109 |
| Black |
18 |
28 |
28 |
54 |
20 |
47 |
113 |
X1min <- tbl1 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X1min
## X-squared
## 0.4547749
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 |
145 |
163 |
| Black |
154 |
154 |
X2min <- tbl2 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X2min
## X-squared
## 0.5264235
학적 상태
tbl3 <- class_roll$status %>%
table(class_roll$group, .)
tbl3 %>%
pander
X3min <- tbl3 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X3min
## X-squared
## 0.07386091
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
## 0.04853833
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 |
24 |
32 |
32 |
24 |
26 |
33 |
29 |
37 |
38 |
33 |
| Black |
23 |
30 |
36 |
29 |
25 |
31 |
26 |
37 |
38 |
33 |
X5min <- tbl5 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X5min
## X-squared
## 1.038529
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 |
66 |
48 |
24 |
170 |
| Black |
62 |
47 |
25 |
174 |
X6min <- tbl6 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X6min
## X-squared
## 0.2024461
Sum of Chi_Squares
Xsum_min <- X1min + X2min + X3min + X4min + X5min + X6min
Xsum_min
## X-squared
## 2.344573