同名公主號：BBio

tidyverse包實際上就是一些常用R包的集合，包括ggplot2（可視化）、dplyr（數(shù)據(jù)操作）、tidyr（數(shù)據(jù)）對齊、tibble（更現(xiàn)代的數(shù)據(jù)框）、stringr（字符串操作）。加載tidyverse包后，其余包中函數(shù)都可以使用。

tidyverse.png

//如何理解tidyverse的工作流呢？，看完就會有答案。

diamonds %>% filter(carat < 3) %>% ggplot(mapping = aes(x = carat)) + geom_histogram(binwidth = 0.1)

diamonds2 <- diamonds %>% mutate(y = ifelse(y < 3 | y > 20, NA, y))

//具體應(yīng)用場景舉例

#從panglaodb單細胞marker基因數(shù)據(jù)庫中下載數(shù)據(jù)表格，每個細胞類型對應(yīng)多個marker基因，格式如下
#species official gene symbol    cell type       nicknames       ubiquitousness index    product description     gene type       canonical marker        germ la
#Mm Hs   CTRB1   Acinar cells    CTRB    0.017   chymotrypsinogen B1     protein-coding gene     1       Endoderm        Pancreas        1.0     0.957143
#Mm Hs   KLK1    Acinar cells    Klk6    0.013   kallikrein 1    protein-coding gene     1       Endoderm        Pancreas        0.833333        0.314286

#想要整理為每個組織類型對應(yīng)的細胞類型，以及對應(yīng)的所有marker list應(yīng)該怎么做
#常規(guī)操作，此處省略，方法有點笨：
data <- read.table("PanglaoDB_markers_27_Mar_2020.tsv.gz", head=T, sep='\t')
panglao_SMC <- data %>% filter(organ == "Smooth muscle", str_detect(species, "Hs")) %>% group_by(cell.type) %>% summarise(geneset = list(official.gene.symbol))
str(panglao_SMC)

#兩行代碼完成，tidyverse的魅力
#tibble [5 × 2] (S3: tbl_df/tbl/data.frame)
# $ cell.type: chr [1:5] "Airway smooth muscle cells" "Myoepithelial cells" "Myofibroblasts" "Pulmonary vascular smooth muscle cells" ...
# $ geneset  :List of 5
#  ..$ : chr [1:4] "NOG" "ACTA2" "FOXF1" "GATA5"
#  ..$ : chr [1:26] "SFN" "ACTA2" "CNN1" "CA3" ...
#  ..$ : chr [1:9] "CDH11" "DES" "PALLD" "ACTA2" ...
#  ..$ : chr [1:2] "ANGPT1" "PDGFRB"
#  ..$ : chr [1:6] "ACTA2" "MYH11" "PDGFRB" "SEMA3D" ...

//安裝及資料

#https://github.com/tidyverse/tidyverse
# Install from CRAN
install.packages("tidyverse")

# Or the development version from GitHub
# install.packages("devtools")
devtools::install_github("tidyverse/tidyverse")

#https://r4ds.had.co.nz/index.html:學(xué)習(xí)資源

#ls("package:dplyr")

//dplyr包的主要函數(shù)

library(nycflights13) #數(shù)據(jù)集
library(tidyverse)

flights #測試數(shù)據(jù)，tibble格式，后文詳細介紹

ls("package:dplyr") #查看dplyr包中所有函數(shù)

#%>%:管道符
#將數(shù)據(jù)從左邊傳入右邊，有大用處。x %>% f(y) 相當(dāng)于 f(x, y), x %>% f(y) %>% g(z) 相當(dāng)于 g(f(x, y), z)
c(1,2,3) %>% mean()

#filter：針對行的數(shù)據(jù)過濾
#可以支持多個篩選條件，以運算符作為標準
filter(flights, month == 1, day == 1)
filter(flights, month == 11 | month == 12)
filter(flights, month %in% c(11, 12))
filter(flights, !is.na(dep_delay))

#arrange：針對行的數(shù)據(jù)排序
#可以支持根據(jù)多列數(shù)據(jù)進行排序
arrange(flights, year, month, day)
arrange(flights, desc(dep_delay)) #降序

#select：針對列的數(shù)據(jù)篩選
#直接使用列名，支持多列篩選，切片篩選，或者去除某些列。也可以使用默認函數(shù)進行篩選。
select(flights, year, month, day)
select(flights, year:day)
select(flights, -(year:day))
select(flights, starts_with("abc"))
select(flights, contains("a"))

#rename：重命名列名
rename(flights, tail_num = tailnum)

#mutate：增加列
#可以基于已有數(shù)據(jù)，通過計算增加新列
flights_sml <- select(flights, year:day, ends_with("delay"), distance, air_time)
mutate(flights_sml, gain = dep_delay - arr_delay, speed = distance / air_time * 60)
mutate(flights_sml, gain = dep_delay - arr_delay, hours = air_time / 60, gain_per_hour = gain / hours)
transmute(flights, gain = dep_delay - arr_delay, hours = air_time / 60, gain_per_hour = gain / hours) #只保留新列

#min_rank：排名
y <- c(1, 2, 2, NA, 3, 4)
min_rank(y)

#summarise：總結(jié)
#和group_by連用對不同的分組數(shù)據(jù)進行總結(jié)。group_by改變原數(shù)據(jù)，只是添加了分組信息。
by_day <- group_by(flights, year, month, day)
summarise(by_day, delay = mean(dep_delay, na.rm = TRUE))

#管道符連接多個函數(shù)，可讀性瞬間提升
delays <- flights %>% 
  group_by(dest) %>% 
  summarise(
    count = n(),
    dist = mean(distance, na.rm = TRUE),
    delay = mean(arr_delay, na.rm = TRUE)
  ) %>% 
  filter(count > 20, dest != "HNL")

//dplyr包的其它函數(shù)

#between，返回邏輯值
between(1:12, 7, 9)

#group_split：分組
data.frame(celltype=rep(c("T cells", "B cells"), each=2), marker=c("CD3D", "CD2", "MS4A1", "CD79A")) %>% group_by(celltype) %>% group_split()

#across：選擇多列，并用函數(shù)處理
iris %>% as_tibble() %>% mutate(across(c(Sepal.Length, Sepal.Width), round))

#if_any，篩選
iris %>% filter(if_any(ends_with("Width"), ~ . > 4))
iris %>% filter(if_all(ends_with("Width"), ~ . > 2))

#inner_join：按列合并倆數(shù)據(jù)集中的行，取交集。其余為左合并，右合并，并集合并。
band_members %>% inner_join(band_instruments, by="name")
band_members %>% left_join(band_instruments)
band_members %>% right_join(band_instruments)
band_members %>% full_join(band_instruments)

#根據(jù)兩個數(shù)據(jù)集中匹配關(guān)系過濾行
#semi_join(x, y) keeps all observations in x that have a match in y.
#anti_join(x, y) drops all observations in x that have a match in y.
top_dest <- flights %>% count(dest, sort = TRUE) %>% head(10)
top_dest
flights %>% semi_join(top_dest)

#pull：提取某列，分別為最后一列，第一列，cyl列，并輸出為向量
mtcars %>% pull(-1)
mtcars %>% pull(1)
mtcars %>% pull(cyl)

#slice：切片，篩選行
slice(mtcars, -(1:4))
mtcars %>% slice_min(mpg, n = 5)

//tibble包中的主要函數(shù)

tibble格式的數(shù)據(jù)和data.frame非常相似，但是更加現(xiàn)代化，更方便使用。tibble格式數(shù)據(jù)默認只輸出前10行，以及適應(yīng)屏幕的列，對大數(shù)據(jù)友好。列名還支持特殊字符，非常人性化。

library(tidyverse)

#格式轉(zhuǎn)換
class(iris)
iris_tibble <- as_tibble(iris)
class(iris_tibble)
iris <- as.data.frame(iris_tibble)

#輸出所有列
nycflights13::flights %>% print(n = 10, width = Inf)

#取子集
df <- tibble(
  x = runif(5),
  y = rnorm(5)
)
df$x #向量
df[["x"]] #向量
df["x"] #tibble

#添加行列
df <- tibble(x = 1:3, y = 3:1)
df %>% add_row(x = 4, y = 0)
df %>% add_column(z = -1:1, w = 0)

#行名轉(zhuǎn)給為數(shù)據(jù)，列轉(zhuǎn)為行名
mtcars_tbl <- rownames_to_column(mtcars, var = "car") %>% as_tibble()
mtcars_tbl
column_to_rownames(mtcars_tbl, var = "car") %>% head()

//tidyr包中的主要函數(shù)

library(tidyverse)

#pivot_longer：寬數(shù)據(jù)轉(zhuǎn)為長數(shù)據(jù)
table4a
table4a %>% pivot_longer(c(`1999`, `2000`), names_to = "year", values_to = "cases")

#pivot_wider：寬數(shù)據(jù)轉(zhuǎn)為長數(shù)據(jù)
table2
table2 %>% pivot_wider(names_from = type, values_from = count)

#seprate：分割一列為多列，可以指定分隔符或者分割的位置
table3 %>% separate(rate, into = c("cases", "population"), sep="/")
table3 %>% separate(year, into = c("century", "year"), sep = 2)

//stringr中的主要函數(shù)

str_length(c("a", "R for data science", NA))

#str_c：連接字符串
str_c("x", "y")
str_c("x", "y", sep = ", ")
str_c("prefix-", c("a", "b", "c"), "-suffix")

#取子集
x <- c("Apple", "Banana", "Pear")
str_sub(x, 1, 3)

#
str_to_lower(x)
str_to_upper(c("i", "?"))
str_sort(x, locale = "en")

#匹配
x <- c("apple", "banana", "pear")
str_detect(x, "e")

#統(tǒng)計次數(shù)
x <- c("apple", "banana", "pear")
str_count(x, "a")

#替換
x <- c("apple", "pear", "banana")
str_replace(x, "[aeiou]", "-")
str_replace_all(x, "[aeiou]", "-")

#分割
sentences %>% head(5) %>% str_split(" ")