我有一个学生属性和考试成绩的数据框，我正在尝试为每个年级(1 到 12(拟合一个线性模型。我正在使用扫帚包有效地为每个年级创建一个模型。下面是一个简化的示例数据集和我正在使用的代码。
#start df creation
grade <- rep(1:12, each = 40)
attendance_rate <- round(runif(480, min=25, max=100), 1)
test_growth <- round(runif(480, min = -12, max = 38))
binary_flag <- round(runif(480, min = 0, max = 1))
score <- round(runif(480, min = 92, max = 370))
survey_response <- round(runif(480, min = 1, max = 4))
df <- data.frame(grade, attendance_rate, test_growth, binary_flag, score, survey_response)
df$survey_response[df$grade == 1] <- NA
# end df creation
#create train test split for each grade level
set.seed(123)
df_train <- lapply(split(seq(1:nrow(df)), df$grade), function(x) sample(x, floor(.6*length(x))))
df_test <- mapply(function(x,y) setdiff(x,y), x = split(seq(1:nrow(df)), df$grade), y = df_train)
df_train <- df[unlist(df_train),]
df_test <- df[unlist(df_test),]
#create models
models_nested <- df_train %>%
group_by(grade) %>% nest() %>%
mutate(
fit = map(data, ~ lm(score ~ attendance_rate + test_growth + binary_flag + survey_response, data = .x)),
tidied = map(fit, tidy),
augmented = map(fit, augment),
glanced = map(fit, glance)
)
不幸的是，当我尝试运行以 models_nested 开头的代码块时，我收到以下错误：
Error in lm.fit(x, y, offset = offset, singular.ok = singular.ok, ...) : 0 (non-NA) cases
我知道这种情况正在发生，因为一年级的所有学生在survey_response列中都有一个 NA 值。我不知道如何在不对一年级运行单独的回归以完全删除调查响应列/变量的情况下解决此问题。有没有办法告诉 lm 函数简单地忽略一个变量，如果该特定等级子集只包含空值？我显然希望在其他年级模型的回归中保留该变量。
我尽力使这个问题变得清晰，但如有必要，我很乐意在评论中澄清。
编辑 6/9/2020：我不想为一年级模型返回 NA，我只想让一年级的线性模型在没有survey_response列的情况下运行。我希望survey_response列包含在所有其他年级模型中。
希望有人能帮忙！
我们可以在survey_response中检查NA值并相应地使用该模型。
library(broom)
library(dplyr)
library(tidyr)
library(purrr)
df_train %>%
group_by(grade) %>%
nest() %>%
mutate(fit = map(data, ~ if(all(is.na(.x$survey_response)))
lm(score ~ attendance_rate + test_growth + binary_flag, data = .x)
else lm(score ~ attendance_rate + test_growth + binary_flag + survey_response, data = .x)),
tidied = map(fit, tidy),
augmented = map(fit, augment),
glanced = map(fit, glance))
# grade data fit tidied augmented glanced
# <int> <list> <list> <list> <list> <list>
# 1 1 <tibble [24 × 5]> <lm> <tibble [4 × 5]> <tibble [24 × 11]> <tibble [1 × 11]>
# 2 2 <tibble [24 × 5]> <lm> <tibble [4 × 5]> <tibble [24 × 11]> <tibble [1 × 11]>
# 3 3 <tibble [24 × 5]> <lm> <tibble [4 × 5]> <tibble [24 × 11]> <tibble [1 × 11]>
# 4 4 <tibble [24 × 5]> <lm> <tibble [4 × 5]> <tibble [24 × 11]> <tibble [1 × 11]>
# 5 5 <tibble [24 × 5]> <lm> <tibble [4 × 5]> <tibble [24 × 11]> <tibble [1 × 11]>
# 6 6 <tibble [24 × 5]> <lm> <tibble [4 × 5]> <tibble [24 × 11]> <tibble [1 × 11]>
# 7 7 <tibble [24 × 5]> <lm> <tibble [4 × 5]> <tibble [24 × 11]> <tibble [1 × 11]>
# 8 8 <tibble [24 × 5]> <lm> <tibble [4 × 5]> <tibble [24 × 11]> <tibble [1 × 11]>
# 9 9 <tibble [24 × 5]> <lm> <tibble [4 × 5]> <tibble [24 × 11]> <tibble [1 × 11]>
#10 10 <tibble [24 × 5]> <lm> <tibble [4 × 5]> <tibble [24 × 11]> <tibble [1 × 11]>
#11 11 <tibble [24 × 5]> <lm> <tibble [4 × 5]> <tibble [24 × 11]> <tibble [1 × 11]>
#12 12 <tibble [24 × 5]> <lm> <tibble [4 × 5]> <tibble [24 × 11]> <tibble [1 × 11]>
我们可以使用purrr中的possibly
library(broom)
library(dplyr)
library(tidyr)
library(purrr)
poslm <- possibly(lm, otherwise = NA)
df_train %>%
group_by(grade) %>%
nest() %>%
mutate(fit = map(data, ~ poslm(score ~ attendance_rate + test_growth +
binary_flag + survey_response, data = .x)),
tidied = map(fit, possibly(tidy, otherwise = NA)),
augmented = map(fit, possibly(augment, otherwise = NA)),
glanced = map(fit, possibly(glance, otherwise = NA)))
# A tibble: 12 x 6
# Groups: grade [12]
# grade data fit tidied augmented glanced
# <int> <list> <list> <list> <list> <list>
# 1 1 <tibble [24 × 5]> <lgl [1]> <lgl [1]> <lgl [1]> <lgl [1]>
# 2 2 <tibble [24 × 5]> <lm> <tibble [5 × 5]> <tibble [24 × 12]> <tibble [1 × 11]>
# 3 3 <tibble [24 × 5]> <lm> <tibble [5 × 5]> <tibble [24 × 12]> <tibble [1 × 11]>
# 4 4 <tibble [24 × 5]> <lm> <tibble [5 × 5]> <tibble [24 × 12]> <tibble [1 × 11]>
# 5 5 <tibble [24 × 5]> <lm> <tibble [5 × 5]> <tibble [24 × 12]> <tibble [1 × 11]>
# 6 6 <tibble [24 × 5]> <lm> <tibble [5 × 5]> <tibble [24 × 12]> <tibble [1 × 11]>
# 7 7 <tibble [24 × 5]> <lm> <tibble [5 × 5]> <tibble [24 × 12]> <tibble [1 × 11]>
# 8 8 <tibble [24 × 5]> <lm> <tibble [5 × 5]> <tibble [24 × 12]> <tibble [1 × 11]>
# 9 9 <tibble [24 × 5]> <lm> <tibble [5 × 5]> <tibble [24 × 12]> <tibble [1 × 11]>
#10 10 <tibble [24 × 5]> <lm> <tibble [5 × 5]> <tibble [24 × 12]> <tibble [1 × 11]>
#11 11 <tibble [24 × 5]> <lm> <tibble [5 × 5]> <tibble [24 × 12]> <tibble [1 × 11]>
#12 12 <tibble [24 × 5]> <lm> <tibble [5 × 5]> <tibble [24 × 12]> <tibble [1 × 11]>