问题描述
我有这张照片中的信息:
您可以在此处下载:https://drive.google.com/file/d/1pgO51NXtjpVSz-VxQEDNFFuQXVc4jVkt/view?usp=sharing
我想要的是将这些数据转换为个人数据,
例如
会转变成这个
另一个例子
会变成这个
因此,如果我们说n =“原始data.frame中所有数字的总和”,即所有个体的数量,则最终输出将是一个data.frame
,具有6列和n行。
我想在R中执行此操作,但我不知道如何执行。一旦有了这个,我想做的就是应用一个具有二项式族和link = probit的广义线性模型。
解决方法
尝试一下
library(readxl)
library(dplyr)
library(tidyr)
df <- read_xls("byssinosis.xls",range = cell_rows(c(4L,NA_integer_)),col_names = FALSE)
raw_nms <- read_xls("byssinosis.xls",range = cell_rows(c(1L,3L)),col_names = FALSE)
names(df) <- with(
fill(as.data.frame(t(raw_nms)[,-2L]),V1,V2),# replace any missing value in V1 and V2 (i.e. row 1 and 3 in your excel) with the last observation carrired forward
trimws(paste(V1,if_else(is.na(V2),"",V2))) # collapse these names into a single vector
)
df %>%
pivot_longer(contains(" "),names_to = c("Workplace","byssinosis"),names_pattern = "(\\d+) (.+)") %>%
slice(inverse.rle(list(lengths = value,values = seq_along(value)))) %>%
select(-value)
输出
# A tibble: 5,419 x 6
Employment Smoking Sex Race Workplace byssinosis
<chr> <chr> <chr> <chr> <chr> <chr>
1 <10 yes M W 1 yes
2 <10 yes M W 1 yes
3 <10 yes M W 1 yes
4 <10 yes M W 1 no
5 <10 yes M W 1 no
6 <10 yes M W 1 no
7 <10 yes M W 1 no
8 <10 yes M W 1 no
9 <10 yes M W 1 no
10 <10 yes M W 1 no
# ... with 5,409 more rows
,
好的...我有一个答案,但是...我想知道是否存在任何概括。在这里:
library(readxl)
library(dplyr)
# Información original ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
byssinosis <- read_xls(path = "byssinosis.xls",range = "B4:K27",col_names = F)
names(byssinosis) <- c("Employment","Smoking","Sex","Race","W1y","W1n","W2y","W2n","W3y","W3n")
# View(byssinosis)
# Procesando la información a individuos ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
# Primero pasamos las columnas a una sola.
datos <- reshape2::melt(byssinosis)
# Separamos estas columnas en las dos características deseadas.
datos <- datos %>%
mutate(Workplace = ifelse(variable %in% c("W1y","W1n"),1,ifelse(variable %in% c("W2y","W2n"),2,3)),Byssinosis = ifelse(variable %in% c("W1y","W3y"),"yes","no"))
# Repetimos con base en value.
individuos=rep(seq_len(nrow(datos)),datos$value)
datos <- datos[individuos,]
# Nos quedamos solo las columnas deseadas
datos <- datos %>% select(-c(variable,value))
# View(datos)
# Comprobación ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
tabla <-
table(datos) %>%
as.data.frame() %>%
arrange(Employment,desc(Smoking),desc(Sex),desc(Race),Workplace,desc(Byssinosis))
# View(tabla)