- html - 出于某种原因,IE8 对我的 Sass 文件中继承的 html5 CSS 不友好?
- JMeter 在响应断言中使用 span 标签的问题
- html - 在 :hover and :active? 上具有不同效果的 CSS 动画
- html - 相对于居中的 html 内容固定的 CSS 重复背景?
我有一个大部分整洁的数据框,但有 2 列包含基准,而不是将基准合并为观察结果。我该如何整理,以便将“Facility_score”和“TTP”col_names 添加为每个独特的 FYQ 和 Metric 组合的“Facility_label”下的观察值?
输入数据:
library(zoo)
dd <- structure(list(Facility_label = structure(c(1L, 1L, 1L, 1L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
3L, 3L, 3L, 4L, 4L, 4L, 4L, 4L, 4L), .Label = c("A", "B", "C",
"D", "Nashville"), class = "factor"), FYQ = structure(c(2017.75,
2018, 2018.25, 2018.5, 2017.75, 2018, 2018.25, 2018.5, 2018.75,
2017.75, 2018, 2018.25, 2018.5, 2018.75, 2017.75, 2018, 2018.25,
2018.5, 2018.75, 2017.75, 2018, 2018.25, 2018.5, 2018.75, 2017.75,
2018, 2018.25, 2018.5, 2018.75, 2017.75), class = "yearqtr"),
Metric = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
2L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L,
1L, 1L, 1L, 1L, 1L, 2L), .Label = c("Safety Recall", "Turnaround days",
"Consult Active <= 30d", "Consult Pending <- 7d", "Consult Scheduling <- 90d",
"ICB Compliance Rate", "FCA Assessment", "Minor construction execution",
"NRM funding execution", "Deficincies", "%Deficienceis corrected among corrected or action plan",
"%Deficienceis corrected or action plan", "Ratio of Hospital Staff to HR FTE",
"Turnover Rate", "GEMS no Action", "Lost time claims", "RTMS risk score",
"DOC Control", "Loaner deficiencies", "Pretreatment", "RME rate",
"SPS staff vacany rate", "Stock Inactive", "MSPV-NG", "Days to close prosthetis consult",
"%Prosthetic PO using national contracts"), class = "factor"),
Facility_score = c(84.78802993, 95.59659091, 100, 100, 77.61732852,
57.87671233, 81.28898129, 33.33333333, 31.57894737, 10.2,
7.902356902, 8.62, 11.71, 13.15, 30.98236776, 33.26086957,
31.19584055, 54.54545455, 27.27272727, 11, 17.19132653, 26.02008197,
22.29, 30.41, 89.09090909, 93.47826087, 82.10735586, 91.66666667,
87.5, 3.2), `Facility mean` = c(85.35550152, 87.31899147,
93.11498231, 100, 85.35550152, 87.31899147, 93.11498231,
100, 100, 12, 13.06073298, 12.2, 11.51, 10.56, 85.35550152,
87.31899147, 93.11498231, 100, 100, 12, 13.06073298, 12.2,
11.51, 10.56, 85.35550152, 87.31899147, 93.11498231, 100,
100, 12), TTP_score = c(100, 100, 100, 100, 100, 100, 100,
100, 100, 5.65, 5.063953488, 4.779310345, 4.47, 4.545, 100,
100, 100, 100, 100, 5.65, 5.063953488, 4.779310345, 4.47,
4.545, 100, 100, 100, 100, 100, 5.65)), row.names = c(NA,
-30L), class = c("tbl_df", "tbl", "data.frame"))
期望的输出:
dd_output <- structure(list(Facility_label = c("A", "Facility mean", "TTP score",
"A", "Facility mean", "TTP score", "A", "Facility mean", "TTP score",
"A", "Facility mean", "TTP score", "B", "B", "B", "B", "B", "B",
"Facility mean", "TTP score", "B", "Facility mean", "TTP score",
"B", "Facility mean", "TTP score", "B", "Facility mean", "TTP score",
"B", "Facility mean", "TTP score", "C", "C", "C", "C", "C", "C",
"C", "C", "C", "C", "D", "D", "D", "D", "D", "D"), FYQ = c("2017 Q4",
"2017 Q4", "2017 Q4", "2018 Q1", "2018 Q1", "2018 Q1", "2018 Q2",
"2018 Q2", "2018 Q2", "2018 Q3", "2018 Q3", "2018 Q3", "2017 Q4",
"2018 Q1", "2018 Q2", "2018 Q3", "2018 Q4", "2017 Q4", "2017 Q4",
"2017 Q4", "2018 Q1", "2018 Q1", "2018 Q1", "2018 Q2", "2018 Q2",
"2018 Q2", "2018 Q3", "2018 Q3", "2018 Q3", "2018 Q4", "2018 Q4",
"2018 Q4", "2017 Q4", "2018 Q1", "2018 Q2", "2018 Q3", "2018 Q4",
"2017 Q4", "2018 Q1", "2018 Q2", "2018 Q3", "2018 Q4", "2017 Q4",
"2018 Q1", "2018 Q2", "2018 Q3", "2018 Q4", "2017 Q4"), Metric = c("Safety Recall",
"Safety Recall", "safety Recall", "Safety Recall", "Safety Recall",
"Safety Recall", "Safety Recall", "Safety Recall", "Safety Recall",
"Safety Recall", "Safety Recall", "Safety Recall", "Safety Recall",
"Safety Recall", "Safety Recall", "Safety Recall", "Safety Recall",
"Turnaround days", "Turnaround days", "Turnaround days", "Turnaround days",
"Turnaround days", "Turnaround days", "Turnaround days", "Turnaround days",
"Turnaround days", "Turnaround days", "Turnaround days", "Turnaround days",
"Turnaround days", "Turnaround days", "Turnaround days", "Safety Recall",
"Safety Recall", "Safety Recall", "Safety Recall", "Safety Recall",
"Turnaround days", "Turnaround days", "Turnaround days", "Turnaround days",
"Turnaround days", "Safety Recall", "Safety Recall", "Safety Recall",
"Safety Recall", "Safety Recall", "Turnaround days"), Facility_score = c(84.78802993,
85.35550152, 100, 95.59659091, 87.31899147, 100, 100, 93.11498231,
100, 100, 100, 100, 77.61732852, 57.87671233, 81.28898129, 33.33333333,
31.57894737, 10.2, 12, 5.65, 7.902356902, 13.06073298, 5.063953488,
8.62, 12.2, 4.779310345, 11.71, 11.51, 4.47, 13.15, 10.56, 4.545,
30.98236776, 33.26086957, 31.19584055, 54.54545455, 27.27272727,
11, 17.19132653, 26.02008197, 22.29, 30.41, 89.09090909, 93.47826087,
82.10735586, 91.66666667, 87.5, 3.2)), class = c("spec_tbl_df",
"tbl_df", "tbl", "data.frame"), row.names = c(NA, -48L), spec = structure(list(
cols = list(X1 = structure(list(), class = c("collector_skip",
"collector")), Facility_label = structure(list(), class = c("collector_character",
"collector")), FYQ = structure(list(), class = c("collector_character",
"collector")), Metric = structure(list(), class = c("collector_character",
"collector")), Facility_score = structure(list(), class = c("collector_double",
"collector"))), default = structure(list(), class = c("collector_guess",
"collector")), skip = 1), class = "col_spec"))
最佳答案
我们可以通过 tidyr::gather
和一些 dplyr::mutate
操作来做到这一点:
library(tidyverse)
dd %>%
mutate(ID = row_number()) %>%
gather(var, Facility_score, Facility_score:TTP_score) %>%
group_by(FYQ, Metric,
temp_ID = case_when(var == "Facility mean" ~ 1,
var == "TTP_score" ~ 2,
TRUE ~ 0)) %>%
slice(if(any(temp_ID == 0)) row_number() else 1) %>%
mutate(Facility_label = if_else(var == "Facility_score", as.character(Facility_label), var)) %>%
ungroup() %>%
arrange(ID, temp_ID) %>%
select(ID, everything(), -var, -temp_ID)
请注意,我添加了 ID
列以指示原始行号。当同一行中的所有分数合并时,这会减少困惑。
注意事项:
gather
将表格从宽格式 reshape 为长格式,处理 Facility_score
、Facility mean
和 TTP_score< 的条目
作为新的 Facility_score
。创建一个变量 var
来临时存储值标签。
然后我们创建了 group_by
FYQ
、Metric
和一个临时 ID 变量 (temp_ID
)通过将 Facility mean
设置为 1
,将 TTP_score
设置为 2
,以及 var
中的所有其他内容> 到 0
。
根据 temp_ID
,如果它是 0
,我们使用 slice
来抓取所有行,否则只抓取第一行。这有效地返回了对应于 Facility_score
的所有行,但在每个 FYQ
中只有 Facility mean
和 TTP_score
之一 + Metric
组合。
接下来,我们将 Facility_label
替换为 var
中的相应标签。
最后,取消分组
,按ID
和temp_ID
排列
,并重新排列列顺序,同时删除 var
和 temp_ID
(everything
当我们想把一个变量放在前面同时保持其他变量不变时很有用)。
输出:
# A tibble: 50 x 5
ID Facility_label FYQ Metric Facility_score
<int> <chr> <S3: yearqtr> <fct> <dbl>
1 1 A 2017 Q4 Safety Recall 84.8
2 1 Facility mean 2017 Q4 Safety Recall 85.4
3 1 TTP_score 2017 Q4 Safety Recall 100
4 2 A 2018 Q1 Safety Recall 95.6
5 2 Facility mean 2018 Q1 Safety Recall 87.3
6 2 TTP_score 2018 Q1 Safety Recall 100
7 3 A 2018 Q2 Safety Recall 100
8 3 Facility mean 2018 Q2 Safety Recall 93.1
9 3 TTP_score 2018 Q2 Safety Recall 100
10 4 A 2018 Q3 Safety Recall 100
11 4 Facility mean 2018 Q3 Safety Recall 100
12 4 TTP_score 2018 Q3 Safety Recall 100
13 5 B 2017 Q4 Safety Recall 77.6
14 6 B 2018 Q1 Safety Recall 57.9
15 7 B 2018 Q2 Safety Recall 81.3
16 8 B 2018 Q3 Safety Recall 33.3
17 9 B 2018 Q4 Safety Recall 31.6
18 9 Facility mean 2018 Q4 Safety Recall 100
19 9 TTP_score 2018 Q4 Safety Recall 100
20 10 B 2017 Q4 Turnaround days 10.2
# ... with 30 more rows
关于r - 整理 "Benchmark"列,我们在Stack Overflow上找到一个类似的问题: https://stackoverflow.com/questions/54753014/
我正在 csv 上使用 hadoop 来分析一些数据。我使用sql/mysql(不确定)来分析数据,现在陷入了僵局。 我花了好几个小时在谷歌上搜索,却没有找到任何相关的东西。我需要一个查询,在该查询中
我正在为 Bootstrap 网格布局的“简单”任务而苦苦挣扎。我希望在大视口(viewport)上有 4 列,然后在中型设备上有 2 列,最后在较小的设备上只有 1 列。 当我测试我的代码片段时,似
对于这个令人困惑的标题,我深表歉意,我想不出这个问题的正确措辞。相反,我只会给你背景信息和目标: 这是在一个表中,一个人可能有也可能没有多行数据,这些行可能包含相同的 activity_id 值,也可
具有 3 列的数据库表 - A int , B int , C int 我的问题是: 如何使用 Sequelize 结果找到 A > B + C const countTasks = await Ta
我在通过以下功能编写此查询时遇到问题: 首先按第 2 列 DESC 排序,然后从“不同的第 1 列”中选择 只有 Column1 是 DISTINCT 此查询没有帮助,因为它首先从第 1 列中进行选择
使用 Bootstrap 非常有趣和有帮助,目前我在创建以下需求时遇到问题。 “使用 bootstrap 在桌面上有 4 列,在平板电脑上有 2 列,在移动设备上有 1 列”谁能告诉我正确的结构 最佳
我是 R 新手,正在问一个非常基本的问题。当然,我在尝试从所提供的示例中获取指导的同时做了功课here和 here ,但无法在我的案例中实现这个想法,即可能是由于我的问题中的比较维度更大。 我的实
通常我会使用 R 并执行 merge.by,但这个文件似乎太大了,部门中的任何一台计算机都无法处理它! (任何从事遗传学工作的人的附加信息)本质上,插补似乎删除了 snp ID 的 rs 数字,我只剩
我有一个 df , delta1 delta2 0 -1 2 0 -1 0 0 0 我想知道如何分配 delt
您好,我想知道是否可以执行以下操作。显然,我已经尝试在 phpMyAdmin 中运行它,但出现错误。也许还有另一种方式来编写此查询。 SELECT * FROM eat_eat_restaurants
我有 2 个列表(标题和数据值)。我想要将数据值列 1 匹配并替换为头文件列 1,以获得与 dataValue 列 1 和标题值列 2 匹配的值 头文件 TotalLoad,M0001001 Hois
我有两个不同长度的文件,file2 是一个很大的引用文件,我从中提取文件 1 的数据。 我有一行 awk,我通常会对其进行调整以在我的文件中进行查找和替换,但它总是在同一列中进行查找和替换。 所以对于
假设我有两个表,如下所示。 create table contract( c_ID number(1) primary key, c_name varchar2(50) not
我有一个带有 varchar 列的 H2 表,其检查约束定义如下: CONSTRAINT my_constraint CHECK (varchar_field <> '') 以下插入语句失败,但当我删
这是最少量的代码,可以清楚地说明我的问题: One Two Three 前 2 个 div 应该是 2 个左列。第三个应该占据页面的其余部分。最后,我将添加选项来隐藏和
在 Azure 中的 Log Analytics 中,我为 VM Heartbeat 选择一个预定义查询,我在编辑器中运行查询正常,但当我去创建警报时,我不断收到警报“查询未返回 TimeGenera
在 Azure 中的 Log Analytics 中,我为 VM Heartbeat 选择一个预定义查询,我在编辑器中运行查询正常,但当我去创建警报时,我不断收到警报“查询未返回 TimeGenera
今天我开始使用 JexcelApi 并遇到了这个:当您尝试从特定位置获取元素时,不是像您通常期望的那样使用sheet.getCell(row,col),而是使用sheet.getCell(col,ro
我有一个包含 28 列的数据库。第一列是代码,第二列是名称,其余是值。 public void displayData() { con.Open(); MySqlDataAdapter
我很沮丧:每当我缩小这个网页时,一切都变得一团糟。我如何将网页居中,以便我可以缩小并且元素不会被错误定位。 (它应该是 2 列,但所有内容都合并为 1)我试过 但由于某种原因,这不起作用。 www.o
我是一名优秀的程序员,十分优秀!