title: “Mo ta bien ngay 2” author: “Ngoc Khanh” date: “2024-09-09” output: html_document
ob=read.csv("D:\\Lóp học NCKH\\obesity data.csv")Viec 2. Mo ta dac diem mau nghien cuu
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] |
Viec 3. Mo ta cac dac diem mau nghien cuu theo gioi tinh
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%) |
Viec 4. So sanh dac diem mau nghien cuu giua nam va nu
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%)
## ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯Viec 5. Bieu do histogram
Phan bo ti trong mo
library(ggplot2)
library(gridExtra)
p = ggplot(data = ob, aes(x=pcfat))
p1 = p = 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`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
### Phan bo ti trong mo theo gioi tinh
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`.
# Viec 5 Ve bieu do thanh ### Tao bien so OB tu bien bmi
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"Phan bo cua tinh trang beo phi
p = ggplot(data = ob, aes(x = OB, fill = OB, col = OB))
p + geom_bar(position = "dodge")
### Phan bo tinh trang beo phi theo gioi tinh
p = ggplot(data = ob, aes(x = OB, y = pcfat, fill = gender, group = gender))
p + geom_bar(stat = "identity", position = "dodge")
Them ti le %
library(tidyverse)## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.5
## ✔ forcats 1.0.0 ✔ stringr 1.5.1
## ✔ lubridate 1.9.3 ✔ tibble 3.2.1
## ✔ purrr 1.0.2 ✔ tidyr 1.3.1
## ── 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 errorstemp = ob %>% group_by(gender) %>% count(OB) %>% mutate(pct = n/sum(n))
temp$pct = round(temp$pct*100, 1)
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)
### Viec 6 Soan bieu do hop ### So sanh phan bo ty le mo giua cac nhom
beo phi o phu nu
women = subset(ob, gender == "F")
dim(women)## [1] 862 16p = 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)
### So sanh phan bo ti trong mo giua nam va nu Tao tap du lieu chi gom
nam
men = subset(ob, gender == "M")
dim(men)## [1] 355 16Ve bieu do hop
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
Xep theo thu tu can nang
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)
### Trinh bay trong cung 1 bieu do
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
### 7 Viec soan bieu do tuong quan ### 7.1. Moi tuong quan giua chi so
khoi co the va ty trong mo
R Markdown
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")'
## `geom_smooth()` using method = 'gam' and formula = 'y ~ s(x, bs = "cs")'7.2 Moi tuong quan giua chi so khoi co the va ty trong mo theo gioi tinh
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'
## `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'
## `geom_smooth()` using method = 'loess' and formula = 'y ~ x'This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see http://rmarkdown.rstudio.com.
When you click the Knit button a document will be generated that includes both content as well as the output of any embedded R code chunks within the document. You can embed an R code chunk like this:
summary(cars)## speed dist
## Min. : 4.0 Min. : 2.00
## 1st Qu.:12.0 1st Qu.: 26.00
## Median :15.0 Median : 36.00
## Mean :15.4 Mean : 42.98
## 3rd Qu.:19.0 3rd Qu.: 56.00
## Max. :25.0 Max. :120.00Including Plots
You can also embed plots, for example:
Note that the echo = FALSE parameter was added to the
code chunk to prevent printing of the R code that generated the
plot.