library(ggplot2)
Mô hình nhiều lớp
library(gapminder)
data(gapminder)
head(gapminder)
## # A tibble: 6 × 6
## country continent year lifeExp pop gdpPercap
## <fct> <fct> <int> <dbl> <int> <dbl>
## 1 Afghanistan Asia 1952 28.8 8425333 779.
## 2 Afghanistan Asia 1957 30.3 9240934 821.
## 3 Afghanistan Asia 1962 32.0 10267083 853.
## 4 Afghanistan Asia 1967 34.0 11537966 836.
## 5 Afghanistan Asia 1972 36.1 13079460 740.
## 6 Afghanistan Asia 1977 38.4 14880372 786.
p=ggplot(data=gapminder, aes (x=gdpPercap, y=lifeExp))
p
p=p + geom_point()
p
p=p+geom_line()
p
p=p+geom_point() + geom_smooth()
p
## `geom_smooth()` using method = 'gam' and formula = 'y ~ s(x, bs = "cs")'
p=ggplot(data=gapminder, aes (x=gdpPercap, y=lifeExp, color=continent))
p = p +geom_point()
p
p=p+geom_smooth (method="loess")
p
## `geom_smooth()` using formula = 'y ~ x'
p = p+scale_x_log10()
p
## `geom_smooth()` using formula = 'y ~ x'
p = ggplot (data=gapminder, aes(x=gdpPercap, y =lifeExp))
p=p+geom_point(aes(color=continent))
p=p+geom_smooth(method="loess")
p + scale_x_log10()
## `geom_smooth()` using formula = 'y ~ x'
p=p+labs(x="Log GDP per Capita", y="Life Expectancy")
p=p+ggtitle("Association between GDP Per Capota and Life Expectancy")
p
## `geom_smooth()` using formula = 'y ~ x'
library(ggthemes)
p+theme_economist()
## `geom_smooth()` using formula = 'y ~ x'
Biểu đồ phân bố
df=read.csv('/Users/vothainguyetcam/Downloads/CHNS data full.csv')
p=ggplot(data=df, aes(x=income))
p+geom_histogram()
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## Warning: Removed 224 rows containing non-finite outside the scale range
## (`stat_bin()`).
p+geom_histogram(fill="blue", col="white")
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## Warning: Removed 224 rows containing non-finite outside the scale range
## (`stat_bin()`).
p=ggplot (data=df, aes(x=log(income)))
p+geom_histogram(fill="blue", col="white") +labs(x="Income (log scale", y="Frequency")
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## Warning: Removed 241 rows containing non-finite outside the scale range
## (`stat_bin()`).
p = ggplot(data=df, aes(x =
log(income), fill =factor(gender)))
p
p + geom_histogram(col="white") +
labs(x="Income log(scale)",
y="Frequency", title="Phân bố thu
nhập")
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## Warning: Removed 241 rows containing non-finite outside the scale range
## (`stat_bin()`).
p+geom_density () + labs (x="Income log(scale)", y="Frequency", title = "Phan bo thu nhap")
## Warning: Removed 241 rows containing non-finite outside the scale range
## (`stat_density()`).
p+geom_density (alpha=0.5) + labs (x="Income log(scale)", y="Frequency", title = "Phan bo thu nhap")
## Warning: Removed 241 rows containing non-finite outside the scale range
## (`stat_density()`).
Biểu đồ thanh
df=read.csv('/Users/vothainguyetcam/Downloads/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
Biểu đồ hộp
p = ggplot(data=df,
aes(x=factor(gender), y=log(income),
col=factor(gender)))
p + geom_boxplot() +
geom_jitter(alpha=0.05)
## 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()`).
Biểu đồ tương quan
df=read.csv('/Users/vothainguyetcam/Downloads/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
p = ggplot(data=df, aes(x=age,
y=log(income), col=factor(gender)))
p + geom_point() +
geom_smooth(method="lm",
formula=y~x+I(x^2)+I(x^3))
## Warning: Removed 243 rows containing non-finite outside the scale range
## (`stat_smooth()`).
## Warning: Removed 226 rows containing missing values or values outside the scale range
## (`geom_point()`).
