Data Manipulation with dplyr in R
Data Manipulation with dplyr in R
select
select(data，变量名）
The filter and arrange verbs
arrange
counties_selected <- counties %>%
select(state, county, population, private_work, public_work, self_employed)
# Add a verb to sort in descending order of public_work
counties_selected %>%arrange(desc(public_work))
filter
counties_selected <- counties %>%
select(state, county, population)
# Filter for counties in the state of California that have a population above 1000000
counties_selected %>%
filter(state == "California",
population > 1000000)
#筛选多个变量
filter(id %in% c("a","b","c"...)) 存在
filter(id %in% c("a","b","c"...)) 不存在
fct_relevel {forcats}
Reorder factor levels by hand
排序，order不好使的时候
f <- factor(c("a", "b", "c", "d"), levels = c("b", "c", "d", "a"))
fct_relevel(f)
fct_relevel(f, "a")
fct_relevel(f, "b", "a")
# Move to the third position
fct_relevel(f, "a", after = 2)
# Relevel to the end
fct_relevel(f, "a", after = Inf)
fct_relevel(f, "a", after = 3)
# Revel with a function
fct_relevel(f, sort)
fct_relevel(f, sample)
fct_relevel(f, rev)
Filtering and arranging
counties_selected <- counties %>%
select(state, county, population, private_work, public_work, self_employed)
>
> # Filter for Texas and more than 10000 people; sort in descending order of private_work
> counties_selected %>%filter(state=='Texas',population>10000)%>%arrange(desc(private_work))
# A tibble: 169 x 6
state county population private_work public_work self_employed
<chr> <chr> <dbl> <dbl> <dbl> <dbl>
1 Texas Gregg 123178 84.7 9.8 5.4
2 Texas Collin 862215 84.1 10 5.8
3 Texas Dallas 2485003 83.9 9.5 6.4
4 Texas Harris 4356362 83.4 10.1 6.3
5 Texas Andrews 16775 83.1 9.6 6.8
6 Texas Tarrant 1914526 83.1 11.4 5.4
7 Texas Titus 32553 82.5 10 7.4
8 Texas Denton 731851 82.2 11.9 5.7
9 Texas Ector 149557 82 11.2 6.7
10 Texas Moore 22281 82 11.7 5.9
# ... with 159 more rows
Mutate
counties_selected <- counties %>%
select(state, county, population, public_work)
# Sort in descending order of the public_workers column
counties_selected %>%
mutate(public_workers = public_work * population / 100) %>%arrange(desc(public_workers))
counties %>%
# Select the five columns
select(state, county, population, men, women) %>%
# Add the proportion_men variable
mutate(proportion_men = men / population) %>%
# Filter for population of at least 10,000
filter(population >= 10000) %>%
# Arrange proportion of men in descending order
arrange(desc(proportion_men))
The count verb
counties_selected %>%count(region,sort=TRUE)
counties_selected %>%count(state,wt=citizens,sort=TRUE)
Summarizing
# Summarize to find minimum population, maximum unemployment, and average income
counties_selected %>%summarize(
min_population=min(population),
max_unemployment=max(unemployment),
average_income=mean(income)
)
# Add a density column, then sort in descending order
counties_selected %>%
group_by(state) %>%
summarize(total_area = sum(land_area),
total_population = sum(population),
density=total_population/total_area) %>%arrange(desc(density))
发现了，归根到底是一种函数关系，看看该怎样处理这个函数比较简单，如果写不出来，可能和小学的时候应用题写不出来有关系
top_n
按照优先级来筛选
# Extract the most populated row for each state
counties_selected %>%
group_by(state, metro) %>%
summarize(total_pop = sum(population)) %>%
top_n(1, total_pop)
Selecting
Using the select verb, we can answer interesting questions about our dataset by focusing in on related groups of verbs.
The colon (
最新文章
热门文章