ob = read.csv("C:\\Thach\\VN trips\\2024_2Aug\\Data Analysis workshop (Hospital 108)\\Datasets\\obesity data.csv")
library(table1)
##
## Attaching package: 'table1'
## The following objects are masked from 'package:base':
##
## units, units<-
table1(~ age + gender + bmi + WBBMC + wbbmd + fat + lean + hypertension + diabetes, data = ob)
Overall (N=1217) |
|
---|---|
age | |
Mean (SD) | 47.2 (17.3) |
Median [Min, Max] | 48.0 [13.0, 88.0] |
gender | |
F | 862 (70.8%) |
M | 355 (29.2%) |
bmi | |
Mean (SD) | 22.4 (3.06) |
Median [Min, Max] | 22.2 [14.5, 37.1] |
WBBMC | |
Mean (SD) | 1720 (363) |
Median [Min, Max] | 1710 [695, 3040] |
wbbmd | |
Mean (SD) | 1.01 (0.113) |
Median [Min, Max] | 1.01 [0.650, 1.35] |
fat | |
Mean (SD) | 17300 (5210) |
Median [Min, Max] | 17000 [4280, 40800] |
lean | |
Mean (SD) | 35500 (7030) |
Median [Min, Max] | 33600 [19100, 63100] |
hypertension | |
Mean (SD) | 0.507 (0.500) |
Median [Min, Max] | 1.00 [0, 1.00] |
diabetes | |
Mean (SD) | 0.111 (0.314) |
Median [Min, Max] | 0 [0, 1.00] |
table1(~ age + bmi + WBBMC + wbbmd + fat + lean + as.factor(hypertension) + as.factor(diabetes) | gender, data = ob)
F (N=862) |
M (N=355) |
Overall (N=1217) |
|
---|---|---|---|
age | |||
Mean (SD) | 48.6 (16.4) | 43.7 (18.8) | 47.2 (17.3) |
Median [Min, Max] | 49.0 [14.0, 85.0] | 44.0 [13.0, 88.0] | 48.0 [13.0, 88.0] |
bmi | |||
Mean (SD) | 22.3 (3.05) | 22.7 (3.04) | 22.4 (3.06) |
Median [Min, Max] | 22.1 [15.2, 37.1] | 22.5 [14.5, 34.7] | 22.2 [14.5, 37.1] |
WBBMC | |||
Mean (SD) | 1600 (293) | 2030 (336) | 1720 (363) |
Median [Min, Max] | 1610 [695, 2660] | 2030 [1190, 3040] | 1710 [695, 3040] |
wbbmd | |||
Mean (SD) | 0.988 (0.111) | 1.06 (0.101) | 1.01 (0.113) |
Median [Min, Max] | 0.990 [0.650, 1.35] | 1.06 [0.780, 1.34] | 1.01 [0.650, 1.35] |
fat | |||
Mean (SD) | 18200 (4950) | 15000 (5110) | 17300 (5210) |
Median [Min, Max] | 17700 [6220, 40800] | 15100 [4280, 29900] | 17000 [4280, 40800] |
lean | |||
Mean (SD) | 32000 (3970) | 43800 (5820) | 35500 (7030) |
Median [Min, Max] | 31500 [19100, 53400] | 43400 [28600, 63100] | 33600 [19100, 63100] |
as.factor(hypertension) | |||
0 | 430 (49.9%) | 170 (47.9%) | 600 (49.3%) |
1 | 432 (50.1%) | 185 (52.1%) | 617 (50.7%) |
as.factor(diabetes) | |||
0 | 760 (88.2%) | 322 (90.7%) | 1082 (88.9%) |
1 | 102 (11.8%) | 33 (9.3%) | 135 (11.1%) |
library(compareGroups)
createTable(compareGroups(gender ~ age + bmi + WBBMC + wbbmd + fat + lean + hypertension + diabetes, data = ob))
##
## --------Summary descriptives table by 'gender'---------
##
## ________________________________________________
## F M p.overall
## N=862 N=355
## ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
## age 48.6 (16.4) 43.7 (18.8) <0.001
## bmi 22.3 (3.05) 22.7 (3.04) 0.013
## WBBMC 1599 (293) 2030 (336) <0.001
## wbbmd 0.99 (0.11) 1.06 (0.10) <0.001
## fat 18240 (4954) 14978 (5113) <0.001
## lean 32045 (3966) 43762 (5819) <0.001
## hypertension 0.50 (0.50) 0.52 (0.50) 0.527
## diabetes 0.12 (0.32) 0.09 (0.29) 0.181
## ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
ob$hypert = as.factor(ob$hypertension)
ob$dm = as.factor(ob$diabetes)
createTable(compareGroups(gender ~ age + bmi + WBBMC + wbbmd + fat + lean + hypert + dm, data = ob))
##
## --------Summary descriptives table by 'gender'---------
##
## ___________________________________________
## F M p.overall
## N=862 N=355
## ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
## age 48.6 (16.4) 43.7 (18.8) <0.001
## bmi 22.3 (3.05) 22.7 (3.04) 0.013
## WBBMC 1599 (293) 2030 (336) <0.001
## wbbmd 0.99 (0.11) 1.06 (0.10) <0.001
## fat 18240 (4954) 14978 (5113) <0.001
## lean 32045 (3966) 43762 (5819) <0.001
## hypert: 0.569
## 0 430 (49.9%) 170 (47.9%)
## 1 432 (50.1%) 185 (52.1%)
## dm: 0.238
## 0 760 (88.2%) 322 (90.7%)
## 1 102 (11.8%) 33 (9.30%)
## ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
library(ggplot2)
library(gridExtra)
p = ggplot(data = ob, aes(x = pcfat))
p1 = p + geom_histogram()
p2 = p + geom_histogram(fill = "blue", col = "white") + labs(x = "Tỉ trọng mỡ (%)", y = "Số người", title = "Phân bố tỉ trọng mỡ")
grid.arrange(p1, p2, ncol = 2)
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
p = ggplot(data = ob, aes(x = pcfat, fill = gender))
p1 = p + geom_histogram(col="white") + labs(x = "Tỉ trọng mỡ", y = "Số người", title = "Phân bố tỉ trọng mỡ")
p2 = p + geom_density(alpha = 0.5) + labs(x = "Tỉ trọng mỡ", y = "Số người", title = "Phân bố tỉ trọng mỡ")
grid.arrange(p1, p2, ncol = 2)
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
ob$OB[ob$bmi< 18.5] = "Underweight"
ob$OB[ob$bmi>= 18.5 & ob$bmi< 25] = "Normal"
ob$OB[ob$bmi>= 25 & ob$bmi< 30] = "Overweight"
ob$OB[ob$bmi>= 30] = "Obese"
p = ggplot(data = ob, aes(x = OB, fill = OB, col = OB))
p + geom_bar(position = "dodge")
p = ggplot(data = ob, aes(x = OB, y = pcfat, fill = gender, group = gender))
p + geom_bar(stat = "identity", position = "dodge")
Tính tỉ lệ %:
library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.3 ✔ readr 2.1.4
## ✔ forcats 1.0.0 ✔ stringr 1.5.0
## ✔ lubridate 1.9.3 ✔ tibble 3.2.1
## ✔ purrr 1.0.2 ✔ tidyr 1.3.0
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::combine() masks gridExtra::combine()
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
temp = ob %>% group_by(gender) %>% count(OB) %>% mutate(pct = n/sum(n))
temp$pct = round(temp$pct*100, 1)
Thêm % vào biểu đồ
p = ggplot(data = temp, aes(x = OB, y = pct, fill = gender, group = gender))
p1 = p + geom_bar(stat = "identity", position = "dodge") + geom_text(aes(x = OB, y = pct, label = pct, group = gender), position = position_dodge(width = 1), vjust = -0.5, col = "blue")
p1
p = ggplot(data = temp, aes(x = OB, y = pct, fill = gender, label = pct))
p2 = p + geom_bar(stat = "identity") + geom_text(size = 3, position = position_stack(vjust = 0.5))
p2
grid.arrange(p1, p2, ncol = 2)
Tạo tập dữ liệu chỉ gồm nữ
women = subset(ob, gender == "F")
dim(women)
## [1] 862 16
Vẽ biểu đồ hộp
p = ggplot(data = women, aes(x = OB, y = pcfat, fill = OB, col = OB))
p1 = p + geom_boxplot(col = "black") + geom_jitter(alpha = 0.05) + labs(x = "Tình trạng béo phì", y = "Tỉ trọng mỡ (%)") + ggtitle("Tỉ trọng mỡ theo tình trạng béo phì ở nữ")
p1
women$OB.n = factor(women$OB, levels = c("Underweight", "Normal", "Overweight", "Obese"))
p = ggplot(data = women, aes(x = OB.n, y = pcfat, fill = OB.n, col = OB.n))
p2 = p + geom_boxplot(col = "black") + geom_jitter(alpha = 0.05) + labs(x = "Tình trạng béo phì", y = "Tỉ trọng mỡ (%)") + ggtitle("Tỉ trọng mỡ theo tình trạng béo phì ở nữ")
p2
grid.arrange(p1, p2, ncol = 2)
Tạo tập dữ liệu chỉ gồm nam
men = subset(ob, gender == "M")
dim(men)
## [1] 355 16
Vẽ biểu đồ hộp
p = ggplot(data = men, aes(x = OB, y = pcfat, fill = OB, col = OB))
p1 = p + geom_boxplot(col = "black") + geom_jitter(alpha = 0.05) + labs(x = "Tình trạng béo phì", y = "Tỉ trọng mỡ (%)") + ggtitle("Tỉ trọng mỡ theo tình trạng béo phì ở nam")
p1
men$OB.n = factor(men$OB, levels = c("Underweight", "Normal", "Overweight", "Obese"))
p = ggplot(data = men, aes(x = OB.n, y = pcfat, fill = OB.n, col = OB.n))
p2 = p + geom_boxplot(col = "black") + geom_jitter(alpha = 0.05) + labs(x = "Tình trạng béo phì", y = "Tỉ trọng mỡ (%)") + ggtitle("Tỉ trọng mỡ theo tình trạng béo phì ở nam")
p2
grid.arrange(p1, p2, ncol = 2)
ob$OB.n = factor(ob$OB, levels = c("Underweight", "Normal", "Overweight", "Obese"))
p = ggplot(data = ob, aes(x = OB.n, y = pcfat, fill = gender, col = gender))
p1 = p + geom_boxplot(col = "black") + geom_jitter(alpha = 0.05) + labs(x = "Tình trạng béo phì", y = "Tỉ trọng mỡ (%)") + ggtitle("Tỉ trọng mỡ theo tình trạng béo phì và giới tính")
p1
p = ggplot(data = ob, aes(x = bmi, y = pcfat))
p1 = p + geom_point()
p2 = p + geom_point() + geom_smooth()
grid.arrange(p1, p2, ncol = 2)
## `geom_smooth()` using method = 'gam' and formula = 'y ~ s(x, bs = "cs")'
p = ggplot(data = ob, aes(x = bmi, y = pcfat, fill = gender, col = gender))
p1 = p + geom_point() + geom_smooth() + labs(x = "Chỉ số khối cơ thể (kg/m2)", y = "Tỉ trọng mỡ (%)") + ggtitle("Liên quan giữa chỉ số khối cơ thể và tỉ trọng mỡ theo giới tính")
p1
## `geom_smooth()` using method = 'loess' and formula = 'y ~ x'
p = ggplot(data = ob, aes(x = bmi, y = pcfat, fill = gender, col = gender))
p2 = p + geom_point() + geom_smooth(method = "lm", formula = y ~ x + I(x^2)) + labs(x = "Chỉ số khối cơ thể (kg/m2)", y = "Tỉ trọng mỡ (%)") + ggtitle("Liên quan giữa chỉ số khối cơ thể và tỉ trọng mỡ theo giới tính")
p2
grid.arrange(p1, p2, ncol = 2)
## `geom_smooth()` using method = 'loess' and formula = 'y ~ x'