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. :120.00
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.
Ngày 2: Hiển thị dữ liệu # Việc 1. Đọc dữ liệu “CHNS data full.csv” vào
R và gọi dữ liệu là “df”
df = read.csv("D:\\NGHIEN CUU KHOA HOC\\15. R\\CHNS data full.csv")
head(df)
## id whours wgroup dead fu.time gender age edu marital residence income occu
## 1 1 35 1 0 4 2 52 3 3 1 116000 1
## 2 2 48 3 0 4 1 36 3 2 1 25200 1
## 3 3 40 1 0 4 2 31 3 2 1 27000 1
## 4 4 48 3 0 4 2 51 2 2 1 27600 2
## 5 5 32 2 0 4 1 58 2 2 1 34800 2
## 6 6 40 1 0 4 1 42 3 2 1 77000 1
## smoking drinking height weight bmi sys1 sys2 sys3 dias1 dias2 dias3 tsf1
## 1 0 0 168 83.5 29.58 120 126 120 80 82 76 28
## 2 1 0 173 85.0 28.40 120 120 120 90 80 80 25
## 3 0 1 167 50.0 17.93 110 108 110 70 70 70 18
## 4 0 0 164 80.0 29.74 120 110 120 80 82 80 27
## 5 0 0 175 65.0 21.22 120 120 120 80 82 80 23
## 6 0 1 179 75.0 23.41 110 112 110 72 76 70 24
## tsf2 tsf3 uac hc wc
## 1 27 28 36 111 103
## 2 44 25 35 102 95
## 3 17 18 25 96 72
## 4 26 27 32 104 97
## 5 22 22 35 102 90
## 6 23 24 28 96 90
library(ggplot2)
library(gridExtra)
## Warning: package 'gridExtra' was built under R version 4.3.3
p = ggplot(data = df, aes(x = income))
p1 = p + geom_histogram()
p2 = p + geom_histogram(fill = "blue", col = "white") + labs(x = "Thu nhập", y = "Số người", title = "Phân bố thu nhập")
grid.arrange(p1, p2, ncol = 2)
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## Warning: Removed 224 rows containing non-finite outside the scale range
## (`stat_bin()`).
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## Warning: Removed 224 rows containing non-finite outside the scale range
## (`stat_bin()`).
## Nhận xét: Phân bố lệch, không rõ ràng. ## 2.2 Thể hiện phân bố thu
nhập (income) rõ ràng hơn bằng biểu đồ histogram:
p = ggplot(data = df, aes(x = log(income)))
p1 = p + geom_histogram(fill = "blue", col = "white") + labs(x = "Thu nhập (logarithm scale)", y = "Số người", title = "Phân bố thu nhập")
p1
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## Warning: Removed 241 rows containing non-finite outside the scale range
## (`stat_bin()`).
## 2.3 Hãy vẽ biểu đồ phân bố thu nhập (income) theo giới tính
(gender):
p = ggplot(data = df, aes(x = log(income), fill = factor(gender)))
p1 = p + geom_histogram(col="white") + labs(x = "Thu nhập (logarithm scale)", y = "Số người", title = "Phân bố thu nhập")
p2 = p + geom_density(alpha = 0.5) + labs(x = "Thu nhập (logarithm scale)", y = "Tỉ lệ", title = "Phân bố thu nhập")
grid.arrange(p1, p2, ncol = 2)
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## Warning: Removed 241 rows containing non-finite outside the scale range
## (`stat_bin()`).
## Warning: Removed 241 rows containing non-finite outside the scale range
## (`stat_density()`).
# Việc 3: Soạn biểu đồ thanh thể hiện thu nhập (income) theo trình độ
học vấn (edu) ## 3.1 Thể hiện thu nhập (income) theo trình độ học vấn
(edu) ## Gọi lệnh đếm
library(tidyverse)
## Warning: package 'tidyverse' was built under R version 4.3.3
## Warning: package 'tibble' was built under R version 4.3.3
## Warning: package 'tidyr' was built under R version 4.3.3
## Warning: package 'readr' was built under R version 4.3.3
## Warning: package 'purrr' was built under R version 4.3.3
## Warning: package 'dplyr' was built under R version 4.3.3
## Warning: package 'stringr' was built under R version 4.3.3
## Warning: package 'forcats' was built under R version 4.3.3
## Warning: package 'lubridate' was built under R version 4.3.3
## ── 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 1.9.4 ✔ tibble 3.2.1
## ✔ purrr 1.0.4 ✔ 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 errors
library(tidyverse)
temp = df %>% group_by(edu) %>% summarise(income = median(income, na.rm = T))
temp
## # A tibble: 3 × 2
## edu income
## <int> <dbl>
## 1 1 1750.
## 2 2 6420
## 3 3 31200
df$edu = as.character(factor(df$edu, levels = c(1, 2, 3), labels = c("Primary", "Secondary", "Tertary")))
p = ggplot(data = temp, aes(x = edu, y = income, fill = edu))
p1 = p + geom_bar(stat = "identity") + labs(x = "Education", y = "Income") + theme(legend.position = "none")
p1
p + geom_bar(stat = "identity") + geom_text(aes(label = income, vjust = -0.5)) + geom_bar(stat = "identity") + labs(x = "Education", y = "Income") + theme(legend.position="none")
df$gender = as.character(factor(df$gender, levels = c(1, 2), labels = c("Men", "Women")))
p = ggplot(data = df, aes(x = factor(gender), y = log(income), col = factor(gender)))
p + geom_boxplot() + geom_jitter(alpha = 0.05) + labs(x = "Giới tính", y = "Thu nhập (logarithm scale)") + ggtitle("Thu nhập theo giới tính")
## Warning: Removed 241 rows containing non-finite outside the scale range
## (`stat_boxplot()`).
## Warning: Removed 224 rows containing missing values or values outside the scale range
## (`geom_point()`).