Data
Search for Best Configuration
M1 <- 1000001
M2 <- 2000000
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 0.0362 -0.0023 0.0044 -0.0015
## X2 0.0036 1.0000 -0.0014 0.0006 0.0007 0.0000
## X3 0.0362 -0.0014 1.0000 -0.0007 0.0053 0.0003
## X4 -0.0023 0.0006 -0.0007 1.0000 -0.0010 -0.0015
## X5 0.0044 0.0007 0.0053 -0.0010 1.0000 0.0002
## X6 -0.0015 0.0000 0.0003 -0.0015 0.0002 1.0000
names(Xsum) <- M1:M2
Xsum %>%
summary %>%
round(2)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 2.93 16.38 20.38 21.04 24.98 70.07
Xsum %>%
sd %>%
round(2)
## [1] 6.49
Xsum %>%
`<=`(5) %>%
which %>%
`[`(Xsum, .) %>%
round(2)
## 1001139 1008696 1009858 1011534 1015981 1016532 1021738 1022941 1035569 1044040
## 4.78 4.85 4.58 3.51 4.99 4.75 4.38 4.32 4.54 4.67
## 1046296 1052086 1065283 1068872 1080835 1081410 1086498 1106284 1114904 1119765
## 4.96 4.95 4.70 3.47 4.90 4.81 4.96 4.96 4.89 4.81
## 1128852 1132146 1160629 1162117 1163546 1190415 1192311 1206690 1210439 1213532
## 4.49 4.49 3.82 4.51 4.58 4.54 4.17 4.98 4.57 4.48
## 1219315 1223167 1234419 1238027 1254511 1257750 1260601 1261903 1263390 1263954
## 4.49 4.99 3.13 4.89 4.31 3.72 4.36 4.80 4.69 4.88
## 1269014 1277153 1283620 1294506 1299762 1303196 1308076 1310064 1315777 1320685
## 4.37 4.68 3.56 4.74 4.70 4.69 4.94 4.64 4.70 4.70
## 1322839 1340258 1343173 1347185 1374904 1383657 1386417 1387639 1406441 1415341
## 4.29 3.32 4.81 4.84 4.78 3.16 4.79 4.60 4.78 4.84
## 1416778 1430962 1437591 1452458 1453088 1455857 1463696 1476804 1479341 1487865
## 4.33 4.96 4.36 4.17 4.89 3.98 4.25 4.71 4.83 4.24
## 1495089 1508636 1518001 1531259 1532619 1539451 1540974 1569435 1575316 1575965
## 3.58 4.89 3.93 4.29 4.14 4.93 4.84 4.11 4.83 5.00
## 1592291 1594482 1600085 1603176 1604479 1611235 1621200 1624775 1635499 1664923
## 4.29 3.49 4.95 4.26 4.99 4.10 4.04 3.79 4.01 4.82
## 1667557 1675782 1698802 1711374 1711702 1716032 1722791 1762626 1778234 1790767
## 4.61 4.27 4.78 4.59 3.86 4.95 4.60 4.12 4.60 4.05
## 1792086 1792331 1793554 1798466 1803518 1821708 1835875 1838593 1844216 1857490
## 4.87 4.83 4.31 3.97 4.97 4.71 2.93 4.89 4.33 4.23
## 1859958 1861424 1862177 1870509 1871528 1886229 1891255 1892600 1900106 1901396
## 4.53 4.08 4.92 4.12 4.67 4.52 4.41 4.95 4.99 4.76
## 1908412 1908915 1913308 1919183 1923725 1930878 1931947 1937684 1941614 1948506
## 5.00 4.83 4.91 4.87 4.72 4.77 4.28 4.64 4.76 4.78
## 1948604 1964003 1964221 1968129 1976106 1982999 1995103
## 4.73 4.87 4.31 4.73 4.69 4.87 4.11
Xmin <- names(Xsum[which(Xsum == min(Xsum))])
Xmin
## [1] "1835875"
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] 1.01247976 0.05849150 0.00000000 0.04853833 1.35934104 0.44992194
##
## $Xsum
## [1] 2.928773
학번
class_roll$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 |
17 |
30 |
27 |
52 |
21 |
48 |
113 |
| Black |
20 |
28 |
28 |
56 |
17 |
50 |
109 |
X1min <- tbl1 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X1min
## X-squared
## 1.01248
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 |
148 |
160 |
| Black |
151 |
157 |
X2min <- tbl2 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X2min
## X-squared
## 0.0584915
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
## 0.04853833
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 |
22 |
31 |
33 |
25 |
24 |
34 |
29 |
36 |
39 |
35 |
| Black |
25 |
31 |
35 |
28 |
27 |
30 |
26 |
38 |
37 |
31 |
X5min <- tbl5 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X5min
## X-squared
## 1.359341
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 |
62 |
49 |
23 |
174 |
| Black |
66 |
46 |
26 |
170 |
X6min <- tbl6 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X6min
## X-squared
## 0.4499219
Sum of Chi_Squares
Xsum_min <- X1min + X2min + X3min + X4min + X5min + X6min
Xsum_min
## X-squared
## 2.928773