R数据框如何按salience列阈值将type列的M值替换为L

需求说明 #

需对给定R数据框执行条件替换操作：当type列取值为M，且对应行salience列取值小于3时，将该行type值从M替换为L。 #

实现代码 #

方式1：基础R实现 #

# 首先构造示例数据框
df <- structure(list(id = c(591, 503, 839, 426, 436, 777, 224, 665, 
112, 201, 796, 569, 669, 344, 640, 749, 658, 181, 571, 350, 294, 
397, 270, 77, 803, 652, 466, 41, 564, 236, 11, 619, 110, 94, 
313, 348, 437, 202, 422, 284, 91, 734, 576, 22, 499, 351, 115, 
680, 608, 766, 97, 293, 148, 33, 509, 609, 59, 578, 197, 727, 
71, 521, 642, 326, 738, 417, 67, 192, 520, 719, 30, 57, 279, 
199, 388, 567, 596, 63, 99, 404, 611, 669, 98, 264, 61, 52, 230, 
316, 279, 529, 77, 631, 299, 95, 235, 717, 515, 331, 222, 384
), type = c("O", "L", "O", "L", "O", "O", "L", "L", "M", "M", 
"O", "O", "L", "L", "L", "L", "O", "M", "O", "L", "L", "L", "L", 
"M", "L", "O", "L", "M", "L", "L", "M", "O", "M", "M", "L", "L", 
"O", "L", "O", "L", "M", "L", "O", "M", "O", "L", "M", "L", "L", 
"L", "M", "O", "L", "M", "O", "O", "M", "L", "L", "O", "M", "L", 
"L", "L", "O", "L", "O", "L", "L", "O", "L", "M", "L", "O", "L", 
"O", "L", "L", "M", "L", "O", "L", "M", "L", "L", "M", "L", "O", 
"L", "O", "L", "L", "L", "M", "M", "O", "O", "L", "L", "O"), 
    salience = c(NA, NA, NA, NA, NA, NA, NA, NA, 4.91, 3.86, 
    NA, NA, NA, NA, NA, NA, NA, 4.95, NA, NA, NA, NA, NA, 2.4, 
    NA, NA, NA, 3.43, NA, NA, 3.65, NA, 3.29, 3.95, NA, NA, NA, 
    NA, NA, NA, 4.9, NA, NA, 2.68, NA, NA, 3.6, NA, NA, NA, 3.45, 
    NA, NA, 3.7, NA, NA, 4.05, NA, NA, NA, 3, NA, NA, NA, NA, 
    NA, NA, NA, NA, NA, NA, 3.45, NA, NA, NA, NA, NA, NA, 4.86, 
    NA, NA, NA, 3.45, NA, NA, 3.86, NA, NA, NA, NA, NA, NA, NA, 
    4.29, 2.05, NA, NA, NA, NA, NA), active = c(5.85, 7.73, 5.75, 
    8.25, 5.7, 5.8, 2.1, 6.1, 1.8, 2.25, 5.25, 4.85, 6.75, 1.45, 
    6.45, 6.3, 5.85, 8.5, 5.55, 1.45, 6.63, 2.33, 2.2, 6.3, 6.28, 
    6, 6.75, 2.13, 6.72, 3.5, 2.33, 5.55, 3.05, 3.43, 2.75, 2.05, 
    5.88, 7, 4.7, 2.25, 2.65, 6.45, 5.1, 2.73, 5.05, 8.5, 2.15, 
    7.65, 7.05, 6.5, 2.15, 4.65, 7.8, 4.2, 5.05, 5.52, 3.15, 
    6.4, 7.3, 4.95, 3.03, 6.72, 6.3, 1.9, 5.3, 6.2, 4.03, 7.04, 
    6.15, 4.15, 2.33, 2.15, 6.95, 4.7, 7.13, 5.9, 6.4, 3.36, 
    2.1, 2.33, 4.6, 6.05, 2.15, 2.45, 7.52, 2.13, 6.05, 5.4, 
    7.33, 5.95, 6.4, 6.73, 6.75, 2.3, 7.15, 5.85, 6, 6.35, 2.08, 
    5.88)), row.names = c(NA, -100L), class = c("tbl_df", "tbl", 
"data.frame"))

# 执行条件替换
# 加!is.na判断是为了过滤salience为NA的行，避免NA值参与判断导致异常
df$type[df$type == "M" & !is.na(df$salience) & df$salience < 3] <- "L"

方式2：tidyverse（dplyr）实现 #

library(dplyr)

df <- df %>%
  mutate(type = case_when(
    # 匹配替换条件
    type == "M" & !is.na(salience) & salience < 3 ~ "L",
    # 其余情况保持原值不变
    .default = type
  ))

效果验证 #

执行以下代码可查看替换结果：

# 筛选涉及替换逻辑的行查看结果
df %>% filter(type %in% c("M","L") & !is.na(salience)) %>% head(10)

内容的提问来源于stack exchange，提问作者Ajrhjnd