我使用时遇到问题dplyr
and group_by
在管道函数调用中。
可重现的示例:
使用以下数据:
ex_data<- structure(list(word1 = c("no", "not", "not", "no", "not", "not",
"not", "not", "no", "not", "no", "not", "not", "not", "no", "not",
"no", "no", "not", "not", "not", "no", "not", "without", "never",
"no", "not", "no", "no", "not", "not", "not", "no", "no", "no",
"not", "not", "without", "never", "no", "not", "not", "not",
"not", "not", "never", "no", "no", "not", "not"), word2 = c("doubt",
"like", "help", "no", "want", "wish", "allow", "care", "harm",
"sorry", "great", "leave", "pretend", "worth", "pleasure", "love",
"danger", "want", "afraid", "doubt", "fail", "good", "forget",
"feeling", "forget", "matter", "avoid", "chance", "hope", "forgotten",
"miss", "perfectly", "bad", "better", "opportunity", "admit",
"fair", "delay", "failed", "wish", "dislike", "distress", "refuse",
"regret", "trust", "want", "evil", "greater", "better", "blame"
), score = c(-1L, 2L, 2L, -1L, 1L, 1L, 1L, 2L, -2L, -1L, 3L,
-1L, -1L, 2L, 3L, 3L, -2L, 1L, -2L, -1L, -2L, 3L, -1L, 1L, -1L,
1L, -1L, 2L, 2L, -1L, -2L, 3L, -3L, 2L, 2L, -1L, 2L, -1L, -2L,
1L, -2L, -2L, -2L, -2L, 1L, 1L, -3L, 3L, 2L, -2L), n = c(102L,
99L, 82L, 60L, 45L, 39L, 36L, 23L, 22L, 21L, 19L, 18L, 18L, 17L,
16L, 16L, 15L, 15L, 15L, 14L, 14L, 13L, 13L, 13L, 12L, 12L, 12L,
11L, 11L, 10L, 10L, 10L, 9L, 9L, 9L, 9L, 9L, 9L, 8L, 8L, 8L,
8L, 8L, 8L, 8L, 7L, 7L, 7L, 7L, 7L), contribution = c(-102L,
198L, 164L, -60L, 45L, 39L, 36L, 46L, -44L, -21L, 57L, -18L,
-18L, 34L, 48L, 48L, -30L, 15L, -30L, -14L, -28L, 39L, -13L,
13L, -12L, 12L, -12L, 22L, 22L, -10L, -20L, 30L, -27L, 18L, 18L,
-9L, 18L, -9L, -16L, 8L, -16L, -16L, -16L, -16L, 8L, 7L, -21L,
21L, 14L, -14L)), .Names = c("word1", "word2", "score", "n",
"contribution"), row.names = c(NA, -50L), class = c("tbl_df",
"tbl", "data.frame"))
常规的典型管道操作按预期工作:
outside_result<- ex_data %>%
mutate(word2=reorder(word2,contribution)) %>%
group_by(word1) %>%
top_n(10,abs(contribution)) %>%
group_by(word1,word2) %>%
arrange(desc(contribution)) %>%
ungroup() %>%
mutate(word2 = factor(paste(word2,word1, sep = "__"),
levels=rev(paste(word2,word1,sep="__"))))
我已将上述内容实现为函数,如下所示:
order_bars <- function(df,facetPanel,barCategory,value){
df %>% mutate(barCategory=reorder(barCategory,value)) %>%
group_by(facetPanel) %>%
top_n(10,abs(value)) %>%
group_by(facetPanel,barCategory) %>%
arrange(desc(value)) %>%
ungroup() %>%
mutate(barCategory = factor(paste(barCategory,facetPanel, sep = "__"),
levels=rev(paste(barCategory,facetPanel,sep="__"))))
}
并从中吸取建议post https://stackoverflow.com/questions/24606282/passing-data-frame-to-mutate-within-function, used $
在函数内的 mutate 操作期间引用 data.frame 的变量时的表示法。
inside_result<-order_bars(ex_data,ex_data$word1,ex_data$word2,ex_data$contribution)
R 抛出以下错误:
Error: unknown variable to group by : facetPanel
Called from: resolve_vars(new_groups, tbl_vars(.data))
我猜测group_by
需要调整以采用命名变量,否则我必须使用.dot
参考列的符号,尽管我只是把它扔到风中......