参考：datacamp

dplyr package

1. 通过filter 筛选符合某种情况的数据集，多个条件可以用逗号隔开

library(gapminder)
library(dplyr)

# Filter the gapminder dataset for the year 1957
gapminder %>%
  filter(year == "1957")

通过%in% 可以通过多个条件筛选。

# Filter for the names Steven, Thomas, and Matthew 
selected_names <- babynames %>%
  filter(name %in% c("Steven", "Thomas", "Matthew"))

2. arrange verb

通过arrange 排列数据集

# 按lifeExp递增排
gapminder %>%
  arrange(lifeExp)

或者

# 按lifeExp递减排
gapminder %>%
  arrange(desc(lifeExp))

还可以同时使用多个verb

gapminder %>%
  filter(year == "1957") %>%
    arrange(desc(pop))

3. mutate

通过mutate 处理变量数据。(增加、修改、删减)

library(gapminder)
library(dplyr)

# Use mutate to change lifeExp to be in months
gapminder %>%
  mutate(lifeExp = 12 * lifeExp)

# Use mutate to create a new column called lifeExpMonths
gapminder %>%
  mutate(lifeExpMonths = 12 * lifeExp)

4. summerize
   用于计算列表内数据的相关内容，如sum(), mean()，median,min, max
   如

library(gapminder)
library(dplyr)

# Summarize to find the median life expectancy
gapminder %>%
  summarize(medianLifeExp = median(lifeExp))

其他的summarize 函数中的运算。

5. group_by
   可以用分组将其和summarize巧妙结合起来。
   如依据year, continent 将数据分类，接着再在分类过的数据中找出平均、总、或者中间值等。

library(gapminder)
library(dplyr)

# Find median life expectancy and maximum GDP per capita in each year
gapminder %>%
  group_by(year) %>%
  summarize(medianLifeExp = median(lifeExp), maxGdpPercap = max(gdpPercap))

ggplot2 包

如下表示，表格gapminder_1952，以pop为x轴，gdpPercap 为y轴，构建散点图

ggplot(gapminder_1952, aes(x = pop, y = gdpPercap)) +
  geom_point()

输出

2. 调整数值的单位

如将x轴数值单位取lg。scale_x_log10

library(gapminder)
library(dplyr)
library(ggplot2)

gapminder_1952 <- gapminder %>%
  filter(year == 1952)

# Change this plot to put the x-axis on a log scale
ggplot(gapminder_1952, aes(x = pop, y = lifeExp)) +
  geom_point() + scale_x_log10()

3. 增加额外的显示（借助颜色表现更多分类）

   
   

# Add the size aesthetic to represent a country's gdpPercap
ggplot(gapminder_1952, aes(x = pop, y = lifeExp, color = continent, size = gdpPercap)) +
  geom_point() +
  scale_x_log10()

4. 通过Faceting，将图片数据切分为多个图片
   facet_wrap(~ name)

library(gapminder)
library(dplyr)
library(ggplot2)

# Scatter plot comparing gdpPercap and lifeExp, with color representing continent
# and size representing population, faceted by year
ggplot(gapminder, aes(x = gdpPercap, y = lifeExp, color = continent, size = pop)) +
  geom_point() +
  scale_x_log10() +
  facet_wrap(~ year)

5. expand_limits
   设定图表中起始点
   expand_limits(y = 0)，表示坐标轴从y = 0 开始。

结合gapminder 与ggplot2

如

library(gapminder)
library(dplyr)
library(ggplot2)

by_year <- gapminder %>%
  group_by(year) %>%
  summarize(medianLifeExp = median(lifeExp),
            maxGdpPercap = max(gdpPercap))

# Create a scatter plot showing the change in medianLifeExp over time
ggplot(by_year, aes(x = year, y = medianLifeExp)) +
  expand_limits(y = 0) +
  geom_point()

再复杂一点的例子

library(gapminder)
library(dplyr)
library(ggplot2)

# Summarize medianGdpPercap within each continent within each year: by_year_continent
by_year_continent <- gapminder %>%
  group_by(continent, year) %>%
  summarize(medianGdpPercap = median(gdpPercap))

# Plot the change in medianGdpPercap in each continent over time
ggplot(by_year_continent, aes(x = year, y = medianGdpPercap,color = continent)) + geom_point() + expand_limits(y = 0)

折线图

除了散点图外，ggplot 还可以做其他类型的图

直接将geom_point更改为geom_line即可
例如

library(gapminder)
library(dplyr)
library(ggplot2)

# Summarize the median gdpPercap by year & continent, save as by_year_continent
by_year_continent <- gapminder %>%
  group_by(year, continent) %>%
  summarize(medianGdpPercap = median(gdpPercap))

# Create a line plot showing the change in medianGdpPercap over time
ggplot(by_year_continent, aes(x = year, y = medianGdpPercap, color = continent)) + expand_limits(y = 0) + geom_line()

柱状图

也就是geom_col()
例子

library(gapminder)
library(dplyr)
library(ggplot2)

# Summarize the median gdpPercap by continent in 1952
by_continent <- gapminder %>%
  filter(year == "1952") %>%
  group_by(continent) %>%
  summarize(medianGdpPercap = median(gdpPercap))

ggplot(by_continent, aes(x = continent, y = medianGdpPercap)) + geom_col()

histogram 直方图

直方图一般会默认y轴数据，计算为count（对应数值大小）。其他则同理，也就是geom_histogram()

ggplot(gapminder_1952, aes(x = pop_by_mil)) + geom_histogram(bins = 50)

箱形图

相似的，也就是geom_boxplot()

library(gapminder)
library(dplyr)
library(ggplot2)

gapminder_1952 <- gapminder %>%
  filter(year == 1952)

# Add a title to this graph: "Comparing GDP per capita across continents"
ggplot(gapminder_1952, aes(x = continent, y = gdpPercap)) +
  geom_boxplot() +
  scale_y_log10() +
  ggtitle("Comparing GDP per capita across continents")

通过ggtitle(" ")可以为图像设置标题。

总结