Data
Search for Best Configuration
M1 <- 9000001
M2 <- 10000000
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 0.0011 0.0353 -0.0021 0.0032 -0.0027
## X2 0.0011 1.0000 -0.0004 0.0007 0.0010 -0.0008
## X3 0.0353 -0.0004 1.0000 -0.0010 0.0062 -0.0022
## X4 -0.0021 0.0007 -0.0010 1.0000 0.0011 -0.0005
## X5 0.0032 0.0010 0.0062 0.0011 1.0000 -0.0009
## X6 -0.0027 -0.0008 -0.0022 -0.0005 -0.0009 1.0000
names(Xsum) <- M1:M2
Xsum %>%
summary %>%
round(2)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 2.34 16.38 20.38 21.04 24.98 66.49
Xsum %>%
sd %>%
round(2)
## [1] 6.48
Xsum %>%
`<=`(5) %>%
which %>%
`[`(Xsum, .) %>%
round(2)
## 9004550 9006036 9008004 9049385 9051597 9055258 9060045 9066328 9086945 9087632
## 3.56 4.11 4.58 4.25 4.97 4.69 3.47 4.77 3.12 4.39
## 9126786 9129440 9147559 9149022 9155587 9161880 9169073 9183054 9189275 9191999
## 4.57 4.91 4.86 4.28 4.53 4.41 4.54 4.46 4.54 3.83
## 9194037 9204814 9216219 9227144 9231080 9232276 9235891 9244316 9260059 9272112
## 4.54 4.24 4.50 4.30 4.61 4.77 4.97 4.34 4.86 3.72
## 9276102 9280888 9282555 9287413 9288367 9296513 9298885 9300632 9320426 9320665
## 4.59 4.57 4.36 5.00 4.60 4.30 4.42 4.86 3.32 4.61
## 9320949 9321445 9323891 9325674 9331113 9345564 9346300 9348106 9357961 9363416
## 4.17 4.82 4.27 4.19 3.68 3.46 4.99 4.70 4.26 4.77
## 9371623 9385067 9408353 9409708 9413846 9420824 9427335 9446059 9448619 9450268
## 4.63 4.86 4.63 4.16 4.72 4.16 4.29 3.98 4.68 4.82
## 9455775 9458647 9461929 9462104 9464090 9470896 9475772 9477554 9503891 9505479
## 3.64 4.16 3.60 4.63 4.23 4.86 4.52 4.51 4.47 4.32
## 9506114 9507581 9509850 9519512 9534066 9545849 9550017 9555093 9560342 9575275
## 4.87 4.81 2.86 4.98 4.92 3.99 4.91 4.28 4.27 4.36
## 9587532 9588140 9592579 9594925 9597048 9600625 9609256 9613187 9618240 9619122
## 4.74 4.65 3.65 3.63 4.91 4.22 4.57 3.33 4.91 4.84
## 9621079 9635128 9650561 9660455 9669679 9671888 9680589 9688007 9692527 9724274
## 4.45 4.21 3.68 4.92 4.95 4.46 4.61 4.90 2.34 3.36
## 9728074 9728820 9752358 9753699 9756383 9765307 9777651 9785292 9794812 9800248
## 4.30 4.88 4.53 4.67 4.62 3.68 4.51 4.88 4.89 4.88
## 9835324 9845294 9847018 9848432 9856776 9859622 9876821 9877515 9882820 9888746
## 5.00 4.93 4.74 4.41 3.35 4.17 4.39 4.59 4.89 4.58
## 9897881 9922114 9933378 9948282 9959322 9986797 9989660 9991941
## 4.54 4.49 4.58 4.69 3.54 4.03 4.92 3.95
Xmin <- names(Xsum[which(Xsum == min(Xsum))])
Xmin
## [1] "9692527"
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] 0.331700980 0.006499056 0.000000000 0.436845008 1.211770077 0.356171939
##
## $Xsum
## [1] 2.342987
학번
class_roll$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 |
18 |
30 |
29 |
54 |
19 |
49 |
109 |
| Black |
19 |
28 |
26 |
54 |
19 |
49 |
113 |
X1min <- tbl1 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X1min
## X-squared
## 0.331701
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 |
150 |
158 |
| Black |
149 |
159 |
X2min <- tbl2 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X2min
## X-squared
## 0.006499056
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
## 0.436845
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 |
25 |
28 |
35 |
27 |
24 |
32 |
28 |
38 |
39 |
32 |
| Black |
22 |
34 |
33 |
26 |
27 |
32 |
27 |
36 |
37 |
34 |
X5min <- tbl5 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X5min
## X-squared
## 1.21177
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 |
63 |
49 |
26 |
170 |
| Black |
65 |
46 |
23 |
174 |
X6min <- tbl6 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X6min
## X-squared
## 0.3561719
Sum of Chi_Squares
Xsum_min <- X1min + X2min + X3min + X4min + X5min + X6min
Xsum_min
## X-squared
## 2.342987