使用pivot_wider后，我的列值显示为（列表）而不是（字符/数字/整数）

Question

在开始之前先声明一下，我对 R 还很陌生；因此，如果我使用了错误的术语，请随时纠正我，如果需要更多信息来解决此问题，请告诉我。

我目前正在研究一个数据集，下面是生成其中一小部分的代码（不包括一些变量和大多数观察结果）：

structure(list(ED1_SEN = c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
1L, 1L, 1L, 1L, 1L), Date = c("09/12/2020", "09/12/2020", "09/12/2020", 
"09/12/2020", "09/12/2020", "09/12/2020", "09/12/2020", "09/12/2020", 
"09/12/2020", "09/12/2020", "09/12/2020", "09/12/2020", "09/12/2020", 
"09/12/2020", "09/12/2020", "09/12/2020", "09/12/2020", "09/12/2020", 
"09/12/2020", "09/12/2020", "09/12/2020", "09/12/2020", "09/12/2020", 
"09/12/2020", "09/12/2020", "09/12/2020", "09/12/2020", "09/12/2020", 
"09/12/2020", "09/12/2020"), Household_ID = c(1L, 1L, 1L, 1L, 
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L), Trap = c("MET", "MET", 
"MET", "MET", "MET", "MET", "MET", "MET", "MET", "MET", "MET", 
"MET", "MET", "MET", "MET", "MET", "MET", "MET", "MET", "MET", 
"MET", "MET", "MET", "MET", "MET", "MET", "MET", "MET", "MET", 
"MET"), Trap_type = c("MET", "MET", "MET", "MET", "MET", "MET", 
"MET", "MET", "MET", "MET", "MET", "MET", "MET", "MET", "MET", 
"MET", "MET", "MET", "MET", "MET", "MET", "MET", "MET", "MET", 
"MET", "MET", "MET", "MET", "MET", "MET"), Location = c("Indoor", 
"Indoor", "Indoor", "Indoor", "Indoor", "Indoor", "Indoor", "Indoor", 
"Indoor", "Indoor", "Indoor", "Indoor", "Indoor", "Indoor", "Indoor", 
"Indoor", "Indoor", "Indoor", "Indoor", "Indoor", "Indoor", "Indoor", 
"Indoor", "Indoor", "Indoor", "Indoor", "Indoor", "Indoor", "Indoor", 
"Indoor"), Round = c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
1L, 1L, 1L, 1L), Season = c("Dry", "Dry", "Dry", "Dry", "Dry", 
"Dry", "Dry", "Dry", "Dry", "Dry", "Dry", "Dry", "Dry", "Dry", 
"Dry", "Dry", "Dry", "Dry", "Dry", "Dry", "Dry", "Dry", "Dry", 
"Dry", "Dry", "Dry", "Dry", "Dry", "Dry", "Dry"), Volunteer_initial = c("AY", 
"AY", "AY", "AY", "AY", "AY", "AY", "AY", "AY", "AY", "AY", "AY", 
"AY", "AY", "AY", "AY", "AY", "AY", "AY", "AY", "AY", "AY", "AY", 
"AY", "AY", "AY", "AY", "AY", "AY", "AY"), Temperature = c(29.2, 
29.2, 29.2, 29.2, 29.2, 29.2, 29.2, 29.2, 29.2, 29.2, 29.2, 29.2, 
29.2, 27.6, 27.6, 27.6, 27.6, 27.6, 27.6, 27.6, 27.6, 28.4, 28.4, 
28.4, 28.4, 28.4, 28.2, 28.2, 28.2, 28.2), Humidity = c(75L, 
75L, 75L, 75L, 75L, 75L, 75L, 75L, 75L, 75L, 75L, 75L, 75L, 83L, 
83L, 83L, 83L, 83L, 83L, 83L, 83L, 78L, 78L, 78L, 78L, 78L, 79L, 
79L, 79L, 79L), Wind_speed = c(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0), 
    Latitude = c(-8.1473, -8.1473, -8.1473, -8.1473, -8.1473, 
    -8.1473, -8.1473, -8.1473, -8.1473, -8.1473, -8.1473, -8.1473, 
    -8.1473, -8.1473, -8.1473, -8.1473, -8.1473, -8.1473, -8.1473, 
    -8.1473, -8.1473, -8.1473, -8.1473, -8.1473, -8.1473, -8.1473, 
    -8.1473, -8.1473, -8.1473, -8.1473), Longitude = c(39.1771, 
    39.1771, 39.1771, 39.1771, 39.1771, 39.1771, 39.1771, 39.1771, 
    39.1771, 39.1771, 39.1771, 39.1771, 39.1771, 39.1771, 39.1771, 
    39.1771, 39.1771, 39.1771, 39.1771, 39.1771, 39.1771, 39.1771, 
    39.1771, 39.1771, 39.1771, 39.1771, 39.1771, 39.1771, 39.1771, 
    39.1771), Elevation = c(NA_real_, NA_real_, NA_real_, NA_real_, 
    NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, 
    NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, 
    NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, 
    NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, 
    NA_real_, NA_real_), Grouped_species = c("CULEX", "CULEX", 
    "CULEX", "CULEX", "CULEX", "CULEX", "CULEX", "CULEX", "CULEX", 
    "CULEX", "CULEX", "CULEX", "CULEX", "CULEX", "CULEX", "CULEX", 
    "CULEX", "CULEX", "CULEX", "CULEX", "CULEX", "MANSONIA", 
    "MANSONIA", "MANSONIA", "MANSONIA", "MANSONIA", "MANSONIA", 
    "MANSONIA", "MANSONIA", "MANSONIA"), Group_malaria_transmissionC = c("Non_malaria_vectors", 
    "Non_malaria_vectors", "Non_malaria_vectors", "Non_malaria_vectors", 
    "Non_malaria_vectors", "Non_malaria_vectors", "Non_malaria_vectors", 
    "Non_malaria_vectors", "Non_malaria_vectors", "Non_malaria_vectors", 
    "Non_malaria_vectors", "Non_malaria_vectors", "Non_malaria_vectors", 
    "Non_malaria_vectors", "Non_malaria_vectors", "Non_malaria_vectors", 
    "Non_malaria_vectors", "Non_malaria_vectors", "Non_malaria_vectors", 
    "Non_malaria_vectors", "Non_malaria_vectors", "Non_malaria_vectors", 
    "Non_malaria_vectors", "Non_malaria_vectors", "Non_malaria_vectors", 
    "Non_malaria_vectors", "Non_malaria_vectors", "Non_malaria_vectors", 
    "Non_malaria_vectors", "Non_malaria_vectors")), row.names = c(NA, 
30L), class = "data.frame")

我希望 R 将“Grouped_species”列转置为不同的列，每个列代表不同的蚊子物种，并且我希望它在收集到特定物种的情况下给出值 1，如果没有收集到则给出值 0（稍后我将对数据进行分组）将不同房屋收集到的蚊子总数相加）。

为此，我使用了pivot_wider函数。然而，据我所知，数据集中的每一行=一只收集的蚊子，我想添加一个新列，将其命名为“Count”，并用“1”填充它，以便稍后将其用于“values_from”参数。为此，我使用了这段代码：

Count <- as.character('1')
house1_comp <- data.frame(cbind(house1_comp, Count))

添加新列后，我使用此代码来获取宽格式：

house1_comp_mod <- house1_comp %>% 
  pivot_wider(names_from = Grouped_species,
              values_from = Count)

结果表可以在附图中找到。

在这里，我可以看到新列“Culex”和“Mansonia”的值是一个列表，而不是一个字符。另外，我可以看到我丢失了大部分观察结果（在这个阶段我必须保留相同数量的观察结果）。

我尝试将新列的值添加为数字、字符和整数，当我使用pivot_wider时，所有值都变成了“列表”。

如果您对正在发生的事情有任何建议或帮助，我将不胜感激。

Answer 1

查看您的数据集，按家庭、温度和湿度进行分组是有意义的，因为这些列实际上有所不同。 然后，您可以计算每个物种的出现次数并扩大范围：

install.packages("rtools", "tidyr", "dplyr")

library(tidyr)
library(dplyr)

wider_list <- list %>%
  group_by(Household_ID, Temperature, Humidity) %>% # list all columns you want to include in the final table :)
  count(Grouped_species) %>% # Count occurrences of each species
  pivot_wider(
    names_from = Grouped_species, # New column names from Grouped_species
    values_from = n,              # Fill with the counts
    values_fill = 0               # Fill missing values with 0
  )

这将生成以下输出： 输出