Data
Search for Best Configuration
M1 <- 2000001
M2 <- 3000000
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 -0.0035 0.0222 0.0045 -0.0022 -0.0056
## X2 -0.0035 1.0000 -0.0028 0.0017 -0.0032 -0.0001
## X3 0.0222 -0.0028 1.0000 0.0033 -0.0016 -0.0037
## X4 0.0045 0.0017 0.0033 1.0000 -0.0046 0.0022
## X5 -0.0022 -0.0032 -0.0016 -0.0046 1.0000 -0.0034
## X6 -0.0056 -0.0001 -0.0037 0.0022 -0.0034 1.0000
names(Xsum) <- M1:M2
Xsum %>%
summary %>%
round(2)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 3.28 16.43 20.41 21.04 24.95 61.79
Xsum %>%
sd %>%
round(2)
## [1] 6.42
Xsum %>%
`<=`(5) %>%
which %>%
`[`(Xsum, .) %>%
round(2)
## 2007659 2016250 2021405 2022872 2025782 2032480 2032952 2045821 2062154 2071267
## 4.85 4.06 4.75 4.58 3.61 4.33 5.00 4.89 4.72 4.33
## 2092702 2101855 2117533 2128211 2133695 2144706 2150503 2158765 2167082 2174910
## 4.56 4.64 4.72 4.79 4.60 4.21 4.70 4.86 5.00 4.72
## 2175349 2181871 2184510 2188837 2228259 2228979 2237708 2243169 2255821 2263311
## 3.76 4.79 4.57 3.83 3.48 4.15 3.78 4.69 4.75 4.74
## 2275172 2278878 2289582 2302608 2351392 2354106 2360956 2370359 2374812 2377544
## 4.80 4.83 4.38 3.70 4.49 4.38 3.76 4.97 4.53 4.92
## 2387771 2392338 2405555 2414050 2427136 2468470 2484005 2504268 2506035 2510677
## 4.89 4.27 3.75 4.36 4.37 4.73 4.67 4.63 4.69 4.75
## 2518096 2523005 2536412 2537043 2540550 2551791 2555280 2571434 2578130 2580564
## 4.47 4.60 4.93 4.59 3.42 4.48 4.72 4.65 4.86 4.17
## 2616984 2631517 2633308 2666333 2668740 2669867 2670036 2674190 2685704 2695794
## 4.19 4.68 4.30 3.49 4.94 4.94 4.97 3.28 4.07 4.54
## 2701924 2706817 2710241 2716673 2725843 2739162 2740753 2746634 2752347 2756708
## 4.44 4.82 4.94 4.86 4.66 4.74 4.56 4.04 4.75 4.27
## 2770257 2782756 2782973 2794838 2825281 2826824 2836739 2848839 2854173 2869921
## 4.80 4.95 3.71 4.55 4.59 3.82 4.14 4.90 3.99 4.89
## 2888945 2900261 2910370 2922902 2927655 2939288 2962610 2996913 2998907
## 4.01 4.11 4.87 4.97 4.41 4.72 4.39 4.91 4.63
Xmin <- names(Xsum[which(Xsum == min(Xsum))])
Xmin
## [1] "2674190"
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] 0.616530711 0.008232683 0.000000000 0.015766423 2.278199212 0.360134749
##
## $Xsum
## [1] 3.278864
학번
class_roll$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 |
15 |
36 |
31 |
36 |
17 |
66 |
42 |
| Black |
17 |
32 |
33 |
38 |
18 |
66 |
39 |
X1min <- tbl1 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X1min
## X-squared
## 0.6165307
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 |
119 |
124 |
| Black |
120 |
123 |
X2min <- tbl2 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X2min
## X-squared
## 0.008232683
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 |
22 |
22 |
22 |
29 |
27 |
20 |
19 |
31 |
24 |
27 |
| Black |
19 |
21 |
23 |
24 |
32 |
24 |
23 |
27 |
25 |
25 |
X5min <- tbl5 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X5min
## X-squared
## 2.278199
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 |
45 |
42 |
17 |
139 |
| Black |
47 |
41 |
14 |
141 |
X6min <- tbl6 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X6min
## X-squared
## 0.3601347
Sum of Chi_Squares
Xsum_min <- X1min + X2min + X3min + X4min + X5min + X6min
Xsum_min
## X-squared
## 3.278864