从年度到月度爆炸式数据[重复]

Question

这是一个关于：

Exploding dates from annual to monthly

我尝试将数据集稍微更改为：

                 date type     bps
1 2012-06-28 16:00:00    A 2.44376
2 2012-06-28 16:00:00    B 1.73054
3 2012-06-28 16:00:00    C 1.68171
4 2013-06-27 16:00:00    A 2.07297
5 2013-06-27 16:00:00    B 1.77073

以下是数据集定义：

df = structure(list(date = structure(c(1340892000, 1340892000, 1340892000, 
                                       1372341600, 1372341600), class = c("POSIXct", "POSIXt"), tzone = ""), type = 
                      c("A", "B", "C", "A", "B"), bps = 
                      c(2.44376, 1.73054, 1.68171, 2.07297, 1.77073)), .Names = c("date", "type", 
                                                                                  "bps"), class = "data.frame", row.names = c(NA, 5L))

问题是以下代码失败：

df_tbl <- as_tibble(df)

df2_tbl <- df_tbl %>% mutate(date = ceiling_date(date, 'month'),
                             date = map2(date, 
                                         lead(date - 1, default = last(date)), 
                                         seq, by = 'month')) %>% 
  unnest() %>% 
  mutate(date = date - days(1))

出现以下错误：

Error: Problem with `mutate()` input `date`.
x wrong sign in 'by' argument
ℹ Input `date` is `map2(date, lead(date - 1, default = last(date)), seq, by = "month")`.
Run `rlang::last_error()` to see where the error occurred.

原始数据似乎已经包含月度数据，而此数据集是年度数据。

Answer 1

如果您查看第一 2 行，它们具有相同的 date，因此在相同日期之间创建每月序列是没有意义的。我认为您需要按组应用解决方案，即type。

library(tidyverse)
library(lubridate)

df_tbl %>% 
  mutate(date = as.Date(ceiling_date(date, 'month'))) %>%
  group_by(type) %>%
  mutate(date = map2(date, lead(date - 1, default = last(date)),
                     seq, by = 'month')) %>% 
  unnest(date) %>% 
  mutate(date = date - days(1))

#   date       type    bps
#   <date>     <chr> <dbl>
# 1 2012-06-29 A      2.44
# 2 2012-07-29 A      2.44
# 3 2012-08-29 A      2.44
# 4 2012-09-29 A      2.44
# 5 2012-10-29 A      2.44
# 6 2012-11-29 A      2.44
# 7 2012-12-29 A      2.44
# 8 2013-01-29 A      2.44
# 9 2013-03-01 A      2.44
#10 2013-03-29 A      2.44
# … with 17 more rows

Answer 2

我认为可以在这里找到解决方案：

Exploding dates from annual to monthly over multiple groups

如果你看好这个例子：

df = structure(list(sec_id = c(1572L, 1572L, 1572L, 1572L, 1572L, 1572L, 1572L, 1572L, 1572L, 1572L, 1572L, 1572L, 1572L, 1572L, 1572L, 1572L, 1572L, 1572L, 1572L, 1572L, 1572L, 1572L, 1572L, 1572L, 1572L, 1572L, 1572L, 1572L, 1572L, 1676L, 1676L, 1676L, 1676L, 1676L, 1676L, 1676L, 1676L, 1676L, 1676L, 1676L, 1676L, 1676L, 1676L, 1676L, 1676L, 1676L, 1676L, 1676L, 1676L, 1676L, 1676L, 1676L, 1676L, 1676L, 1676L, 1676L, 1676L, 1676L, 1572L, 1572L, 1572L, 1572L, 1572L, 1572L, 1572L, 1572L, 1572L, 1572L, 1572L, 1572L, 1572L, 1572L, 1572L, 1572L, 1572L, 1572L, 1572L, 1572L, 1572L, 1572L, 1572L, 1572L, 1572L, 1572L, 1572L, 1572L, 1572L, 1572L, 1572L, 1676L, 1676L, 1676L, 1676L, 1676L, 1676L, 1676L, 1676L, 1676L, 1676L, 1676L, 1676L, 1676L, 1676L, 1676L, 1676L, 1676L, 1676L, 1676L, 1676L, 1676L, 1676L, 1676L, 1676L, 1676L, 1676L, 1676L, 1676L, 1676L, 1676L), 
                    date = structure(c(6908, 7273, 7638, 8002, 8369, 8734, 9099, 9464, 9829, 10193, 10560, 10925, 11291, 11656, 12020, 12384, 12752, 13117, 13482, 13847, 14211, 14578, 14943, 15308, 15674, 16038, 16402, 16769, 17135, 6784, 7151, 7516, 7881, 8247, 8611, 8975, 9342, 9708, 10073, 10438, 10802, 11200, 11565, 11929, 12293, 12661, 13026, 13391, 13756, 14120, 14487, 14852, 15217, 15583, 15947, 16311, 16678, 17044, 6175, 6542, 6908, 7273, 7638, 8002, 8369, 8734, 9099,  9464, 9829, 10193, 10560, 10925, 11291, 11656, 12020, 12384, 12752, 13117, 13482, 13847, 14211, 14578, 14943, 15308, 15674, 16038, 16402, 16769, 17135, 6420, 6784, 7151, 7516, 7881, 8247, 8611, 8975, 9342, 9708, 10073, 10438, 10802, 11200, 11565, 11929, 12293, 12661, 13026, 13391, 13756, 14120, 14487, 14852, 15217, 15583, 15947, 16311, 16678, 17044), class = "Date"),    
                    value = c(0.291022, 0.197242, -0.470581, -0.406716, -3.294938, 1.22421, 3.140976, 0.250468, 0.091548, -0.100863, 0.058375, 0.24784, 0.178765, 0.099276, 0.25472, -0.033291, 0.124165, 0.050947, 0.243008, 0.1205, -0.239625, -0.231221, 0.365649, 0.163779, 0.024976, 0.08388, 0.154777, 0.016473, -0.272928, 0.237446, 0.391304, 0.064583, 0.286497, -0.571342, 1.05039, -0.001038, -0.018711, -0.162076, -0.599241, -4.071504, -0.37761, 1.694085, 0.045113, -0.064748, 0.098901, 0.823333, 0.793419, 0.759225, 0.329818, 0.199564, -0.616418, 1.164773, 0.877078, -0.325099, -0.294199, 0.272016, -0.706077, -2.57027, 0.129316, 0.131234, 0.143554, 0.131058, 0.099229, 0.057275, -0.121562, 0.051187, 0.15589, 0.188605, 0.186155, 0.154765, 0.153816, 0.166873, 0.181998, 0.183937, 0.211225, 0.186216, 0.177731, 0.161529, 0.187527, 0.199608, 0.136866, 0.10001, 0.13546, 0.148756, 0.143177, 0.144643, 0.153461, 0.140774, 0.099231, 0.117254, 0.141094, 0.166662, 0.154047, 0.172634, 0.062807, 0.145724, 0.13481, 0.11031, 0.087178, 0.033243, -0.122207, -0.22856, 0.171272, 0.187948, 0.186266, 0.154494, 0.238273, 0.352929, 0.494341, 0.50497, 0.459309, 0.178825, 0.270483, 0.43428, 0.254988, 0.149881, 0.187119, 0.048877, -0.111647), 
                    metric = c("EPS_GROWTH", "EPS_GROWTH", "EPS_GROWTH", "EPS_GROWTH", "EPS_GROWTH", "EPS_GROWTH", "EPS_GROWTH", "EPS_GROWTH", "EPS_GROWTH", "EPS_GROWTH", "EPS_GROWTH", "EPS_GROWTH", "EPS_GROWTH", "EPS_GROWTH", "EPS_GROWTH", "EPS_GROWTH", "EPS_GROWTH", "EPS_GROWTH", "EPS_GROWTH", "EPS_GROWTH", "EPS_GROWTH", "EPS_GROWTH", "EPS_GROWTH", "EPS_GROWTH", "EPS_GROWTH", "EPS_GROWTH", "EPS_GROWTH", "EPS_GROWTH", "EPS_GROWTH", "EPS_GROWTH", "EPS_GROWTH", "EPS_GROWTH", "EPS_GROWTH", "EPS_GROWTH", "EPS_GROWTH", "EPS_GROWTH", "EPS_GROWTH", "EPS_GROWTH", "EPS_GROWTH", "EPS_GROWTH", "EPS_GROWTH", "EPS_GROWTH", "EPS_GROWTH", "EPS_GROWTH", "EPS_GROWTH", "EPS_GROWTH", "EPS_GROWTH", "EPS_GROWTH", "EPS_GROWTH", "EPS_GROWTH", "EPS_GROWTH", "EPS_GROWTH", "EPS_GROWTH", "EPS_GROWTH", "EPS_GROWTH", "EPS_GROWTH", "EPS_GROWTH", "EPS_GROWTH", "ROE", "ROE", "ROE", "ROE", "ROE", "ROE", "ROE", "ROE", "ROE", "ROE", "ROE", "ROE", "ROE", "ROE", "ROE", "ROE", "ROE", "ROE", "ROE", "ROE", "ROE", "ROE", "ROE", "ROE", "ROE", "ROE", "ROE", "ROE", "ROE", "ROE", "ROE", "ROE", "ROE", "ROE", "ROE", "ROE", "ROE", "ROE", "ROE", "ROE", "ROE", "ROE", "ROE", "ROE", "ROE", "ROE", "ROE", "ROE", "ROE", "ROE", "ROE", "ROE", "ROE", "ROE", "ROE", "ROE", "ROE", "ROE", "ROE", "ROE", "ROE")), 
               class = c("tbl_df", "tbl", "data.frame"), 
               row.names = c(NA, -119L), .Names = c("sec_id", "date", "value", "metric"))


df3 <- df %>%
  group_by(sec_id, metric) %>%
  mutate(date = ceiling_date(date, 'month'),
         date = map2(date, lead(date - 1, default = last(date)), seq, by = 'month')) %>%
  unnest() %>%
  mutate(date = date - 1) %>%
  arrange(sec_id, metric, date)

然后你显示 df3 结构，你得到：

> str(df3)
tibble [1,386 × 4] (S3: grouped_df/tbl_df/tbl/data.frame)
 $ sec_id: int [1:1386] 1572 1572 1572 1572 1572 1572 1572 1572 1572 1572 ...
 $ date  : Date[1:1386], format: "1988-11-30" "1988-12-31" "1989-01-31" "1989-02-28" ...
 $ value : num [1:1386] 0.291 0.291 0.291 0.291 0.291 ...
 $ metric: chr [1:1386] "EPS_GROWTH" "EPS_GROWTH" "EPS_GROWTH" "EPS_GROWTH" ...
 - attr(*, "groups")= tibble [4 × 3] (S3: tbl_df/tbl/data.frame)
  ..$ sec_id: int [1:4] 1572 1572 1676 1676
  ..$ metric: chr [1:4] "EPS_GROWTH" "ROE" "EPS_GROWTH" "ROE"
  ..$ .rows : list<int> [1:4] 
  .. ..$ : int [1:337] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ : int [1:361] 338 339 340 341 342 343 344 345 346 347 ...
  .. ..$ : int [1:338] 699 700 701 702 703 704 705 706 707 708 ...
  .. ..$ : int [1:350] 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 ...
  .. ..@ ptype: int(0) 
  ..- attr(*, ".drop")= logi TRUE

这似乎不是一个简单的小标题，而是一个嵌套的小标题。 只需附加以下内容即可找到解决方案：

%>% as_tibble()