Data
Search for Best Configuration
M1 <- 1000001
M2 <- 3000000
Xsum <- numeric(0)
Xsum <- sapply(M1:M2, red_and_black)
# 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)
names(Xsum) <- M1:M2
Xsum %>%
summary %>%
round(2)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 2.58 16.34 20.35 21.02 24.97 76.92
Xsum %>%
sd %>%
round(2)
## [1] 6.51
Xsum %>%
`<=`(5) %>%
which %>%
`[`(Xsum, .) %>%
round(2)
## 1005229 1019778 1022888 1026763 1035223 1051733 1055054 1056504 1057138 1062866
## 4.57 4.67 4.88 3.94 4.43 4.28 4.95 4.15 4.21 4.74
## 1067825 1071793 1074054 1081760 1099683 1109417 1114348 1119354 1120529 1127275
## 4.55 4.51 4.54 4.82 4.51 3.56 4.50 4.29 4.86 4.28
## 1132328 1139511 1141186 1154770 1162648 1167745 1182086 1187394 1210642 1222991
## 3.98 4.16 4.96 4.22 4.97 4.78 4.27 3.70 3.66 4.90
## 1254751 1255794 1277262 1287683 1323033 1350454 1368998 1372423 1373267 1380966
## 4.34 4.29 4.75 4.85 3.02 3.88 4.91 4.81 4.33 4.97
## 1386315 1388395 1396258 1397454 1404117 1415005 1415760 1421009 1423470 1437234
## 4.98 4.30 4.61 4.38 3.72 4.03 4.54 4.76 4.81 4.65
## 1438957 1442932 1454206 1477539 1480139 1484559 1524559 1526339 1535178 1550971
## 3.94 4.90 2.70 2.58 3.79 4.07 4.76 4.15 4.84 3.88
## 1560684 1566190 1568405 1585287 1589650 1593195 1613107 1625994 1632092 1659388
## 4.98 4.29 4.52 4.93 4.53 4.80 4.56 4.78 4.74 4.86
## 1668677 1673530 1681770 1683528 1690176 1714772 1715915 1730543 1730820 1731516
## 4.95 4.67 4.70 4.39 3.65 4.94 4.90 4.52 4.16 4.85
## 1749889 1758909 1791133 1794814 1796285 1802225 1817293 1818433 1825357 1831459
## 4.55 4.89 3.64 3.79 4.22 4.76 4.41 3.76 4.88 4.44
## 1857206 1857761 1861364 1865859 1870667 1876276 1880238 1889977 1896575 1903338
## 4.88 4.80 4.88 4.44 4.86 3.70 4.21 3.96 4.26 3.96
## 1915858 1916669 1920299 1921449 1924125 1927084 1933471 1936579 1938474 1941436
## 4.92 5.00 4.75 4.87 3.56 4.27 4.61 4.96 4.96 4.30
## 1948067 1970266 1972028 1972247 1977155 1982386 1999659 2000760 2014441 2018477
## 4.55 4.52 4.90 4.63 4.19 4.95 4.40 4.66 3.75 4.90
## 2029864 2042204 2042736 2052251 2071601 2076542 2080866 2082556 2085788 2097100
## 4.10 4.85 4.89 4.52 3.46 4.75 4.60 4.99 4.80 4.97
## 2098547 2122846 2127932 2138166 2138541 2158792 2161640 2166995 2171637 2171850
## 4.87 4.98 4.97 4.29 4.95 5.00 4.14 3.99 4.14 4.73
## 2176868 2190015 2192180 2204839 2214558 2223092 2223907 2227929 2233162 2236335
## 4.92 4.54 4.31 4.43 4.96 4.41 3.90 4.73 4.03 4.51
## 2244555 2251094 2258880 2283820 2286599 2295920 2328641 2347653 2365976 2366585
## 4.26 3.98 3.21 5.00 4.66 4.21 4.40 3.55 4.78 4.46
## 2377204 2389545 2403306 2408775 2412611 2426702 2439270 2442371 2442967 2443789
## 4.83 4.78 4.79 4.59 4.93 4.14 3.56 4.92 4.77 4.54
## 2467279 2473795 2477515 2497882 2500302 2503320 2512864 2514818 2526394 2527829
## 4.17 4.56 2.79 4.47 4.16 4.44 4.72 4.91 4.89 4.78
## 2540068 2541043 2548534 2548872 2553029 2563987 2571823 2577651 2580740 2600744
## 4.95 3.46 4.12 4.34 4.90 4.83 4.84 4.70 3.58 4.19
## 2627257 2655362 2660227 2665371 2669069 2677086 2677379 2682230 2701444 2703444
## 4.84 4.95 4.57 4.08 4.80 3.58 4.32 4.62 4.94 4.71
## 2706325 2716266 2719347 2722204 2722888 2739826 2755452 2755948 2757971 2772469
## 3.42 3.92 4.72 4.89 4.45 4.52 4.80 3.70 4.88 4.10
## 2779852 2787555 2802699 2816544 2819951 2827825 2830032 2849275 2852313 2857002
## 4.54 3.19 4.81 4.46 4.90 3.79 4.82 3.46 4.73 4.60
## 2873258 2876493 2880033 2881274 2882982 2894363 2898534 2923509 2932750 2933819
## 4.02 2.93 3.79 4.73 4.71 4.15 4.64 4.93 4.92 4.76
## 2947620 2951547 2952124 2959045 2961850 2963440 2977515 2977786 2982046 2988878
## 4.48 4.51 4.67 3.46 4.79 4.86 4.77 4.92 4.94 4.06
Xmin <- names(Xsum[which(Xsum == min(Xsum))])
Xmin
## [1] "1477539"
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(Xmin)
## [1] 2.578114
학번
class_roll$id_2 <-
class_roll$id %>%
ifelse(. <= 2016, "2016", .)
tbl1 <- class_roll %$%
table(.$group, .$id_2 %>% substr(1, 4)) %>%
`colnames<-`(c("2016 이전", 2017:2022))
tbl1 %>%
pander
| Red |
21 |
36 |
61 |
77 |
52 |
131 |
25 |
| Black |
20 |
35 |
60 |
77 |
49 |
138 |
25 |
X1min <- tbl1 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X1min
## X-squared
## 0.3167656
학번 홀짝
tbl2 <- class_roll$id %>%
as.numeric %>%
`%%`(2) %>%
factor(levels = c(1, 0), labels = c("홀", "짝")) %>%
table(class_roll$group, .)
tbl2 %>%
pander
| Red |
209 |
194 |
| Black |
211 |
193 |
X2min <- tbl2 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X2min
## X-squared
## 0.01086865
학적 상태
tbl3 <- class_roll$status %>%
table(class_roll$group, .)
tbl3 %>%
pander
X3min <- tbl3 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X3min
## X-squared
## 0.02730536
e-mail 서비스업체
tbl4 <- class_roll$email %>%
strsplit("@", fixed = TRUE) %>%
sapply("[", 2) %>%
`==`("naver.com") %>%
ifelse("네이버", "기타서비스") %>%
factor(levels = c("네이버", "기타서비스")) %>%
table(class_roll$group, .)
tbl4 %>%
pander
X4min <- tbl4 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X4min
## X-squared
## 0.01177796
전화번호의 분포
cut_label <- paste(paste0(0:9, "000"), paste0(0:9, "999"),
sep = "~")
tbl5 <- class_roll$cell_no %>%
substr(start = 8, stop = 11) %>%
sapply(as.numeric) %>%
cut(labels = cut_label,
breaks = seq(0, 10000, by = 1000)) %>%
table(class_roll$group, .)
tbl5 %>%
pander
| Red |
42 |
32 |
32 |
42 |
34 |
48 |
41 |
38 |
42 |
51 |
| Black |
39 |
33 |
36 |
43 |
30 |
50 |
43 |
39 |
40 |
51 |
X5min <- tbl5 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X5min
## X-squared
## 0.7687994
성씨 분포
f_name <- class_roll$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 |
70 |
65 |
32 |
236 |
| Black |
78 |
56 |
28 |
242 |
X6min <- tbl6 %>%
chisq.test(simulate.p.value = TRUE) %>%
`[[`(1)
X6min
## X-squared
## 1.442597
Sum of Chi_Squares
Xsum_min <- X1min + X2min + X3min + X4min + X5min + X6min
Xsum_min
## X-squared
## 2.578114