Data
Search for Best Configuration
M1 <- 8000001
M2 <- 9000000
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 -0.0056 0.0229 0.0057 -0.0029 -0.0020
## X2 -0.0056 1.0000 -0.0021 0.0002 -0.0011 -0.0004
## X3 0.0229 -0.0021 1.0000 0.0018 -0.0025 -0.0033
## X4 0.0057 0.0002 0.0018 1.0000 -0.0032 0.0015
## X5 -0.0029 -0.0011 -0.0025 -0.0032 1.0000 -0.0043
## X6 -0.0020 -0.0004 -0.0033 0.0015 -0.0043 1.0000
names(Xsum) <- M1:M2
Xsum %>%
summary %>%
round(2)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 2.92 16.44 20.41 21.05 24.96 65.89
Xsum %>%
sd %>%
round(2)
## [1] 6.41
Xsum %>%
`<=`(5) %>%
which %>%
`[`(Xsum, .) %>%
round(2)
## 8006444 8013324 8013943 8018204 8019602 8021501 8029485 8032117 8046304 8053556
## 4.71 4.80 4.70 4.72 4.74 4.92 4.47 4.42 4.53 4.42
## 8061292 8065024 8066550 8075749 8081174 8083928 8093501 8106077 8114427 8123711
## 4.92 4.52 4.79 4.79 4.95 2.92 4.51 4.17 4.72 3.81
## 8136733 8186409 8192598 8204726 8205675 8245411 8252434 8259017 8266857 8271860
## 4.88 4.78 4.83 4.31 4.81 4.73 4.57 3.26 4.10 4.45
## 8283314 8295631 8297781 8309863 8320135 8325236 8330130 8332972 8350970 8356974
## 4.87 4.08 4.50 3.59 4.24 3.92 4.90 4.89 4.88 4.98
## 8370987 8400515 8401527 8411712 8428360 8430096 8441920 8448764 8448839 8453216
## 4.92 4.26 4.59 4.69 3.97 4.83 3.26 4.91 4.45 4.93
## 8453472 8458875 8463429 8464487 8470044 8471068 8481836 8499581 8502564 8504261
## 4.98 4.44 4.90 4.37 3.95 4.36 4.09 4.46 4.32 4.63
## 8504513 8505249 8524794 8527642 8533327 8555717 8557885 8564589 8566479 8567220
## 4.80 4.55 4.57 4.64 3.59 3.93 3.97 4.85 4.62 4.90
## 8571607 8573449 8591853 8598883 8610982 8617081 8629477 8641892 8651195 8652562
## 4.68 4.19 3.84 4.77 4.79 3.32 4.77 4.45 4.77 4.28
## 8653777 8662236 8666447 8671591 8673257 8674747 8679902 8694013 8704342 8705234
## 4.49 4.95 4.90 4.97 3.72 4.74 4.92 4.56 4.55 4.99
## 8705491 8705843 8708520 8708638 8723945 8726328 8729865 8734986 8782704 8789398
## 4.35 4.44 4.90 4.27 4.69 4.33 4.83 4.95 4.29 4.82
## 8791062 8797361 8802716 8810113 8828980 8834705 8843221 8845001 8851236 8865961
## 4.29 4.39 4.02 4.82 4.44 4.68 4.72 3.26 4.64 4.81
## 8872209 8874037 8877882 8910582 8921206 8923526 8923739 8932586 8951449 8964885
## 3.97 3.76 4.52 4.01 4.15 4.76 4.38 4.91 4.27 4.87
## 8966481 8966829 8972973 8974977 8976946 8980161 8989203 8999798
## 4.84 4.52 4.80 4.56 4.63 4.95 3.54 4.35
Xmin <- names(Xsum[which(Xsum == min(Xsum))])
Xmin
## [1] "8083928"
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] 0.5748313 0.2058171 0.0000000 0.1418978 0.8399829 1.1536754
##
## $Xsum
## [1] 2.916205
학번
class_roll$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 |
32 |
39 |
16 |
67 |
40 |
| Black |
16 |
35 |
32 |
35 |
19 |
65 |
41 |
X1min <- tbl1 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X1min
## X-squared
## 0.5748313
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 |
122 |
121 |
| Black |
117 |
126 |
X2min <- tbl2 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X2min
## X-squared
## 0.2058171
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
## 0.1418978
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 |
23 |
28 |
28 |
22 |
21 |
28 |
23 |
26 |
| Black |
19 |
21 |
22 |
25 |
31 |
22 |
21 |
30 |
26 |
26 |
X5min <- tbl5 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X5min
## X-squared
## 0.8399829
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 |
44 |
38 |
16 |
145 |
| Black |
48 |
45 |
15 |
135 |
X6min <- tbl6 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X6min
## X-squared
## 1.153675
Sum of Chi_Squares
Xsum_min <- X1min + X2min + X3min + X4min + X5min + X6min
Xsum_min
## X-squared
## 2.916205