缘由
生信之路，道阻且长，记录经验，但渡有缘人。
碎碎念
及时当勉励，岁月不饶人 ——陶渊明
示例数据
#示例数据 for问题1 2
df <- tibble(column_name = c("apple", "banana", "cherry", "date", "elderberry", NA, "", "--"))
my_vector <- c("ban", "dat")
data <- data.f(
a = 1:5,
b = c("red", "blue", "green", "yellow", "blue"),
c = c(2.5, 3.6, 1.9, 4.2, 5.0),
d = c("high", "low", "medium", "high", "medium")
)
#示例数据for问题3
rename_df <- tibble(oldname = c("a", "b", "c"), newname = c("alpha", "beta", "gamma"))
data_count <- tibble(a = 1:5, b = 6:10, c = 11:15)
# 示例数据for问题5
data <- tibble(
Protein.accession = c("P12345", "P67890", "P23456", "P98765"),
Gene = c("Gene1", "Gene2", "Gene3", "Gene4")
)
combined_data <- tibble(
Protein.accession = c("P12345", "P23456", "P11111"),
KEGG.pathway = c("pathway1", "pathway2", "pathway3")
)
代码
- 如何保留指定列中包含给定向量元素的行
library(dplyr)
library(stringr)
# 使用 filter 和 str_detect 来过滤包含子字符串的行，并保留 NA、空值或 "--"
filtered_df <- df %>%
filter(str_detect(column_name, paste(my_vector, collapse = "|")) #筛选给定的向量
)- 如何筛选某一列之后的所有列？ 筛选b列之后的所有列
data %>% select((match("b", names(data)) + 1):ncol(data))- 如何在R里面实现python中字典的更改列名 字典明明
col_map <- setNames(rename_df$newname, rename_df$oldname)
colnames(data_count) <- col_map[rename_df$oldname]
- 如何在R里面批量读取文件并记录文件的来源？
paths=listfiles(path = "your_folder")
df_list <- lapply(path, function(x) read.delim(x, check.names = FALSE) %>% mutate(source = x))- 如何合并两个数据框后将某kegg pathway不存在的行填充为”—”
# 方法1 基础版： 使用inner_join和antijoin 合并数据
data2 <- data %>%
inner_join(combined_data, by = "Protein.accession")
data_del <- data %>%
anti_join(combined_data, by = "Protein.accession") %>%
mutate(KEGG.pathway = "--")
data_org <- rbind(data2, data_del)
# 方法2 进阶版: Left join and mutate
data_org <- data %>%
left_join(combined_data, by = "Protein.accession") %>%
mutate(KEGG.pathway = coalesce(KEGG.pathway, "--"))