r - 为什么过滤到 ggplot() 中的数据集样本会返回不正确的样本?
问题描述
上下文是我有许多id
s 和 many band
s 的时间序列,并且我已经包含了 9 id
s 和 2 band
s 的样本。在这里我们可以看到我可以轻松地绘制所有id
s 的时间序列:
library(tidyverse)
df <- structure(list(id = c(1001L, 1001L, 1001L, 1001L, 1001L, 1001L, 1001L, 1001L, 1001L, 1001L, 1002L, 1002L, 1002L, 1002L, 1002L, 1002L, 1002L, 1002L, 1002L, 1002L, 1004L, 1004L, 1004L, 1004L, 1004L, 1004L, 1004L, 1004L, 1004L, 1004L, 1005L, 1005L, 1005L, 1005L, 1005L, 1005L, 1005L, 1005L, 1005L, 1005L, 1007L, 1007L, 1007L, 1007L, 1007L, 1007L, 1007L, 1007L, 1007L, 1007L, 1009L, 1009L, 1009L, 1009L, 1009L, 1009L, 1009L, 1009L, 1009L, 1009L, 1010L, 1010L, 1010L, 1010L, 1010L, 1010L, 1010L, 1010L, 1010L, 1010L, 1011L, 1011L, 1011L, 1011L, 1011L, 1011L, 1011L, 1011L, 1011L, 1011L, 1013L, 1013L, 1013L, 1013L, 1013L, 1013L, 1013L, 1013L, 1013L, 1013L), date = structure(c(1488884400, 1490612474, 1507460497, 1502276146, 1514372627, 1512644789, 1500980863, 1503572707, 1513940711, 1496660730, 1495796861, 1512644789, 1488884400, 1504436115, 1502276146, 1495796118, 1494068453, 1504868786, 1513940711, 1511780307, 1511348810, 1503572707, 1497524848, 1507028336, 1491476744, 1503572707, 1492340161, 1501844755, 1505300762, 1503140790, 1509620381, 1488884400, 1487156167, 1510052273, 1491476744, 1494068453, 1513940711, 1489748810, 1498388749, 1509620381, 1500980120, 1511780307, 1502708860, 1489748810, 1501412778, 1504436115, 1495796861, 1493204748, 1510484382, 1487156167, 1508324436, 1500548201, 1513940711, 1505732183, 1490612474, 1496660730, 1511348810, 1514372627, 1494068453, 1510052273, 1500548201, 1513076347, 1508756553, 1510484382, 1504436858, 1504004193, 1494932749, 1508324436, 1512644789, 1504868786, 1507460497, 1504004193, 1503140790, 1500980120, 1512212632, 1491476744, 1513940711, 1508756553, 1504436115, 1490612474, 1495796861, 1509188631, 1508756553, 1486292805, 1504004193, 1498388749, 1495796861, 1486292805, 1513940711, 1499684790), class = c("POSIXct", "POSIXt"), tzone = "UTC"), band = c("fit1", "fit1", "fit1", "fit1", "fit1", "fit5", "fit5", "fit5", "fit5", "fit5", "fit1", "fit1", "fit1", "fit1", "fit1", "fit5", "fit5", "fit5", "fit5", "fit5", "fit1", "fit1", "fit1", "fit1", "fit1", "fit5", "fit5", "fit5", "fit5", "fit5", "fit1", "fit1", "fit1", "fit1", "fit1", "fit5", "fit5", "fit5", "fit5", "fit5", "fit1", "fit1", "fit1", "fit1", "fit1", "fit5", "fit5", "fit5", "fit5", "fit5", "fit1", "fit1", "fit1", "fit1", "fit1", "fit5", "fit5", "fit5", "fit5", "fit5", "fit1", "fit1", "fit1", "fit1", "fit1", "fit5", "fit5", "fit5", "fit5", "fit5", "fit1", "fit1", "fit1", "fit1", "fit1", "fit5", "fit5", "fit5", "fit5", "fit5", "fit1", "fit1", "fit1", "fit1", "fit1", "fit5", "fit5", "fit5", "fit5", "fit5"), value = c(0.496538754230172, 0.503271496428091, 0.97387311299285, 0.580658673638122, 0.55924511798107, 0.832069876834949, 0.669456383223215, 1.12835570514478, 0.650077806710299, 0.380956367547047, 0.315803532869213, 0.792491389890908, 0.542150595815071, 1.03016500582205, 0.761751198659722, 0.367933240661702, 0.478285303617102, 1.68901870452092, 0.740965064159661, 1.09028738312622, 0.822334909416119, 0.758342181009204, 0.404208383270466, 0.892795714415756, 0.452540219822814, 1.15220190981348, 0.522093412373678, 0.953592910857701, 1.27850667816495, 1.10756222303339, 0.722797148902218, 0.465842402588039, 0.524130056243481, 0.724757971315511, 0.401849347220063, 0.455169211763473, 0.736683498842155, 0.530595901306756, 0.598435246507131, 0.855911625573028, 0.459872179640563, 0.851473466057886, 0.600348304937791, 0.484896112230185, 0.491357621589034, 1.21884821937325, 0.408355867626313, 0.541537217668289, 1.20173675518489, 0.61126928681528, 1.02122136799224, 0.489289990779144, 0.829092258901136, 0.88152853467569, 0.528559966420024, 0.544164467022259, 1.15093592993106, 0.876559089290843, 0.582149928218707, 1.26592404446571, 0.479960992971744, 0.840894959543198, 1.00459298341354, 0.98285777345435, 0.754965044767638, 1.14971147250154, 0.678568628236206, 1.38981008816777, 0.989354634818581, 1.25116433808614, 1.2142398253614, 1.03201975237089, 0.928602154928637, 0.642961745200205, 0.842888403466734, 0.649606669375906, 0.724490820076092, 1.68294181717141, 1.83216850101507, 0.69741924948021, 0.268972923828825, 1.16584414990533, 1.20604228862346, 0.586060027904748, 1.16356144256577, 0.52670838257608, 0.382147314320451, 0.668308513834733, 0.78509264848017, 0.733357618207109)), row.names = c(NA, -90L), class = c("grouped_df", "tbl_df", "tbl", "data.frame"), vars = c("id", "band"), drop = TRUE, indices = list(0:4, 5:9, 10:14, 15:19, 20:24, 25:29, 30:34, 35:39, 40:44, 45:49, 50:54, 55:59, 60:64, 65:69, 70:74, 75:79, 80:84, 85:89), group_sizes = c(5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L), biggest_group_size = 5L, labels = structure(list(id = c(1001L, 1001L, 1002L, 1002L, 1004L, 1004L, 1005L, 1005L, 1007L, 1007L, 1009L, 1009L, 1010L, 1010L, 1011L, 1011L, 1013L, 1013L), band = c("fit1", "fit5", "fit1", "fit5", "fit1", "fit5", "fit1", "fit5", "fit1", "fit5", "fit1", "fit5", "fit1", "fit5", "fit1", "fit5", "fit1", "fit5")), row.names = c(NA, -18L), class = "data.frame", vars = c("id", "band"), drop = TRUE, indices = list(0:4, 5:9, 10:14, 15:19, 20:24, 25:29, 30:34, 35:39, 40:44, 45:49, 50:54, 55:59, 60:64, 65:69, 70:74, 75:79, 80:84, 85:89), group_sizes = c(5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L), biggest_group_size = 5L, labels = structure(list(merge_id = c(1001L, 1001L, 1002L, 1002L, 1004L, 1004L, 1005L, 1005L, 1007L, 1007L, 1009L, 1009L, 1010L, 1010L, 1011L, 1011L, 1013L, 1013L), band = c("fit1", "fit5", "fit1", "fit5", "fit1", "fit5", "fit1", "fit5", "fit1", "fit5", "fit1", "fit5", "fit1", "fit5", "fit1", "fit5", "fit1", "fit5")), row.names = c(NA, -18L), class = "data.frame", vars = c("merge_id", "band"), drop = TRUE)))
ggplot(df, aes(x = date, y = value, colour = band)) +
geom_point() +
geom_line() +
facet_wrap(~id)
但是,这变得笨拙并且当有太多时图变得太小id
,所以我想直观地检查一个随机子集。我希望以下内容只返回三个id
s,但我们得到了四个id
s,我们甚至没有得到每个band
s 的所有 s id
。我在这里选择种子 1234,但如果您继续使用不同的种子重新运行,您会得到不同的结果,并使用不同的 band-id 组合安排。
set.seed(1234)
ggplot(
data = df %>% filter(id %in% sample(unique(df$id), 3)), # filtering to subset of 3 ids
mapping = aes(x = date, y = value, colour = band)
) +
geom_point() +
geom_line() +
facet_wrap(~id)
请注意,如果我在ggplot()
通话之外进行采样,它会起作用。(这将是期望的结果)
set.seed(1234)
some_ids <- sample(unique(df$id), 3) # moved sample() outside of ggplot()
ggplot(
data = df %>% filter(id %in% some_ids),
mapping = aes(x = date, y = value, colour = band)
) +
geom_point() +
geom_line() +
facet_wrap(~id)
为什么会这样?我看不出这两个选项之间的逻辑差异。它肯定与零件有关,sample
而不是unique(df$id)
零件,因为您可以用它替换它,c(1001, 1002, 1004, 1005, 1007, 1009, 1010, 1011, 1013)
但仍然会遇到问题。我也意识到这可能与我的特定数据有关,因为我确实尝试使用内置数据集制作类似的表示,但我无法想象那会是什么,因为这已经是一个非常有限的子集。
编辑:例如,如果我使用这个更加精简的数据集,我将无法重现此错误。dput
我很困惑,因为除了实际值之外,我无法区分这个数据集和我的数据集之间的任何区别。
df2 <- tibble(
id = rep(1:9, each = 5, times = 2),
date = rep(seq(as.POSIXct("2018-01-01 00:00:00"), by = "month", length.out = 5), times = 18),
band = rep(c("b1", "b2"), each = 45),
value = c(rnorm(45, 0), rnorm(45, 1))
)
解决方案
TLDR:过滤器表达式被多次评估,因此您不应使用非确定性表达式。
不确定这是否足以作为答案,但如果您尝试使用不同的种子运行示例,您会注意到图表数量随每个种子而变化。这表明我们过滤数据帧的 id 数量随每个种子而变化,这表明sample
实际上被多次调用。我们可以通过创建一个代替 的函数来确认这一点sample
:
sample_out <- function(data, n) {
print("running sample_out ")
return (sample(data, n))
}
然后用它代替sample
:
ggplot(
data = df %>% filter(id %in% sample_out(unique(df$id), 3)),
mapping = aes(x = date, y = value, colour = band)
)
你会看到它sample_out
实际上被多次调用。在我的会话中,无论种子如何,都会使用上面的数据调用 18 次。尝试不同的数据帧大小,似乎sample
会被调用 (row_count / 5) 次。这意味着以filter
某种方式多次评估其论点。一个完整的答案将解释为什么会发生这种情况,filter
但这是我有点迷失的地方。我相信相关来源在这里:
https://github.com/tidyverse/dplyr/blob/master/R/tbl-df.r#L55
filter.tbl_df <- function(.data, ..., .preserve = TRUE) {
// elided
out <- filter_impl(.data, quo)
filter_impl
基本上调用了一个 C++ 实现,我认为关键是:
https://github.com/tidyverse/dplyr/blob/master/src/filter.cpp#L408
template <typename SlicedTibble>
SEXP filter_template(const SlicedTibble& gdf, const NamedQuosure& quo) {
// elided
Proxy call_proxy(quo.expr(), gdf, quo.env()) ;
// elided
int ngroups = gdf.ngroups() ;
// elided
for (int i = 0; i < ngroups; i++, ++git) {
// elided
LogicalVector g_test = check_result_lgl_type(call_proxy.get(indices));
// elided
}
// elided
}
请注意,对于每组 tibble,call_proxy.get
都会执行。我假设我们看到sample_out
被调用了 18 次,因为相应的 tibble 中有 18 个组。
无论如何,这可能可以通过发布到相关的 dplyr 社区联系人来快速和权威地回答。在我学习 dyplr 的冒险中,我找不到关于这个的警告,所以可能是我遗漏了一些东西。dplyr
的文档讨论了它的评估与可能使用的有点不同:https ://dplyr.tidyverse.org/articles/programming.html 。
大多数 dplyr 函数使用非标准评估 (NSE)。这是一个包罗万象的术语,意味着它们不遵循通常的 R 评估规则。相反,它们捕获您键入的表达式并以自定义方式对其进行评估。
推荐阅读
- excel - 如何计算数据透视表中的文本 - EXCEL?
- django - PyDev 可以自动补全继承的方法名,但不能自动补全字段名
- azure - Azure 应用程序规模错误:无法更改为目标 SKU“免费”,因为公共证书计数将超过“0”的新限制
- javascript - 我可以在剑道对话动作中插入 IF 语句吗?
- logging - 如何使 Wildfly 的行为类似于 spring-cloud-sleuth
- asp.net - 在 MVC 中发布到服务器后,如何阻止弹出窗口提示输入凭据?
- python - 是否有一种最佳方法可以找到从椭圆到某个点的最小距离,而无需遍历 Python 中的每个点
- python - 如何修复返回 TypeError 的 Python 代码:'str' object is not callable?
- node.js - 与来自 JSON 文件的数据的所有可能组合
- google-apps-script - 我放入垃圾箱的邮件返回我的收件箱,直到我完全从垃圾箱中删除