如何解决R 中死亡率指标的 7 天滚动平均值
我有一个医院患者的数据集，包括他们的入院日期和结果（死亡或出院）。 对于每一天，我想计算死亡率的 7 天滚动平均值。具体来说，我希望代码 a) 添加没有患者入院的缺失日期（直到现在我都是手动完成的 --> 是在此处创建第二个数据集和 left_join() 的最佳选择？） b) 对于每一天，确定过去 7 天内入院的所有患者（即过去 6 天加上手头的具体日期） c) 根据该 7 天窗口内入院患者的结果（=（死亡患者人数 / 所有患者人数）计算死亡率
例如：如果我查看 4 月 8 日，我想知道这一天和前六天入院的患者有哪些。然后我希望代码意识到该样本中有 x 个死亡患者和 y 个出院患者，并根据该 x/x+y 计算死亡率。
之前我将患者分配到第 1 周、第 2 周、第 3 周等，并使用 dplyr 的 group_by() 和 summary() 计算每周的死亡率。现在，我必须做一个滚动平均值，但我不知道该怎么做。我已经使用 R 有一段时间了，但有时仍然觉得自己像个初学者 ://
这是一些数据：
structure(list(Summary = c("Discharged","Discharged","Dead","Discharged"),Admission = structure(c(1578586420.224,1580147094.528,1580467041.28,1580482376.704,1581576565.76,1582319350.784,1582387115.008,1582472442.88,1582575203.328,1582861464.576,1583030023.168,1583160439.808,1583170532.352,1583178658.816,1583234757.632,1583471735.808,1583610278.912,1583645930.496,1583763633.152,1583833887.744,1583926817.792,1583934813.184,1583949231.104,1584037966.848,1584093803.52,1584104289.28,1584196039.68,1584211506.176,1584287003.648,1584290280.448,1584340218.88,1584449139.712,1584453989.376,1584522540.032,1584586503.168,1584596071.424,1584615994.368,1584620581.888,1584627266.56,1584636703.744,1584643388.416,1584646140.928,1584688477.184,1584701846.528,1584715215.872,1584737104.896,1584792941.568,1584803165.184,1584817976.32,1584874075.136,1584892949.504,1584953111.552,1584959403.008,1584962417.664,1584966480.896,1584990336,1584991253.504,1585006195.712,1585032147.968,1585044599.808,1585052595.2,1585057707.008,1585059804.16,1585066488.832,1585080775.68,1585082217.472,1585105286.144,1585108562.944,1585133990.912,1585140151.296,1585142903.808,1585150505.984,1585161122.816,1585168331.776,1585171084.288,1585219843.072,1585237406.72,1585245533.184,1585254315.008,1585267553.28,1585269781.504,1585279742.976,1585301107.712,1585376736.256,1585391285.248,1585393120.256,1585396134.912,1585397445.632,1585399542.784,1585412387.84,1585413436.416,1585422349.312,1585427592.192,1585432966.144,1585435456.512,1585464292.352,1585485394.944,1585505711.104,1585509512.192,1585516065.792,1585518162.944,1585524061.184,1585567183.872,1585567314.944,1585573999.616,1585578456.064,1585611355.136,1585615811.584,1585641763.84,1585643860.992,1585646482.432,1585660507.136,1585684886.528,1585686983.68,1585689605.12,1585729844.224,1585737446.4,1585740461.056,1585748718.592,1585751995.392,1585776374.784,1585778603.008,1585780962.304,1585788302.336,1585819759.616,1585836667.904,1585852920.832,1585863144.448,1585873761.28,1585930122.24,1585931301.888,1585942836.224,1585956336.64,1585997231.104,1586003522.56,1586007061.504,1586008503.296,1586018989.056,1586020561.92,1586092913.664,1586094486.528,1586094879.744,1586095928.32,1586099598.336,1586107200.512,1586107855.872,1586109821.952,1586121225.216,1586162643.968,1586171032.576,1586182042.624,1586182304.768,1586185188.352,1586193052.672,1586198819.84,1586205897.728,1586207732.736,1586264486.912,1586268812.288,1586273399.808,1586273924.096,1586274579.456,1586275234.816,1586281264.128,1586288342.016,1586290308.096,1586293715.968,1586337100.8,1586339460.096,1586343392.256,1586366854.144,1586370393.088,1586376422.4,1586379043.84,1586384024.576,1586393986.048,1586426229.76,1586433438.72,1586452050.944,1586465944.576,1586473808.896,1586513523.712,1586517980.16,1586523091.968,1586527417.344,1586531742.72,1586542359.552,1586544718.848,1586555073.536,1586595443.712,1586597671.936,1586609337.344,1586614973.44,1586617594.88,1586630702.08,1586636993.536,1586670941.184,1586681558.016,1586685883.392,1586703709.184,1586711966.72,1586722976.768,1586776978.432,1586779993.088,1586886423.552,1586891797.504,1586897302.528,1586924696.576,1586924958.72,1586937672.704,1586973062.144,1586982892.544,1586985251.84,1586988397.568,1587024180.224,1587024573.44,1587046855.68,1587075167.232,1587135198.208,1587137164.288,1587138081.792,1587142538.24,1587146994.688,1587169276.928,1587203879.936,1587232060.416,1587255129.088,1587257619.456,1587266925.568,1587277149.184,1587283309.568,1587305722.88,1587308475.392,1587330757.632,1587377419.264,1587379385.344,1587383448.576,1587397080.064,1587409925.12,1587413988.352,1587425391.616,1587442168.832,1587475198.976,1587475723.264,1587497874.432,1587510064.128,1587542963.2,1587559740.416,1587577959.424,1587582022.656,1587590149.12,1587596047.36,1587634844.672,1587657257.984,1587672593.408,1587711783.936,1587761460.224,1587766572.032,1587788723.2,1587831321.6,1587844297.728,1587864876.032,1587896202.24,1587915207.68,1587916387.328,1587919401.984,1587925824.512,1588001977.344,1588007613.44,1588010234.88,1588014560.256,1588028584.96,1588058076.16,1588084814.848,1588089664.512,1588105262.08,1588155986.944,1588159525.888,1588177220.608,1588243543.04,1588252455.936,1588274344.96,1588274476.032,1588275000.32,1588275524.608,1588291384.32,1588348138.496,1588393620.48,1588433204.224,1588433728.512,1588447491.072,1588448932.864,1588461122.56,1588509357.056,1588511978.496,1588518663.168,1588519711.744,1588596651.008,1588601631.744,1588608971.776,1588611462.144,1588625093.632,1588627846.144,1588696134.656,1588699411.456,1588700591.104,1588777006.08,1588777923.584,1588791686.144,1588792865.792,1588797060.096,1588855649.28,1588868363.264,1588874392.576,1588875047.936,1588882387.968,1588932588.544,1589023552.512,1589039936.512,1589078733.824,1589081355.264,1589126444.032,1589214524.416,1589230384.128,1589265511.424,1589275866.112,1589290808.32,1589292774.4,1589314139.136,1589404054.528,1589473653.76,1589476275.2,1589492397.056,1589495280.64,1589561209.856,1589603152.896,1589627270.144,1589632381.952,1589799236.608,1589806707.712,1590004626.432,1590227448.832,1590234133.504,1590398628.864,1590489068.544,1590494180.352,1590555915.264,1590707434.496,1590771266.56,1590934451.2,1591010997.248,1591383897.088,1591444452.352,1591984468.992,1592504038.4,1592553714.688,1592841679.872,1592929629.184,1592951256.064,1594128937.984,1594499347.456,1595402171.392,1595711370.24,1597937103.872,1598717768.704,1599060521.984,1599758087.168,1599815496.704,1600702198.784,1600719631.36,1601065923.584,1601119400.96,1601215476.736,1601236710.4,1601416934.4,1601499640.832,1601587328,1601741206.528,1601848423.424,1601901245.44,1601913828.352,1602092872.704,1602285417.472,1602362881.024,1602504963.072,1602518987.776,1602551231.488,1602782311.424,1602783491.072,1602785457.152,1602851124.224,1602856629.248,1602964501.504,1602974594.048,1603078140.928),class = c("POSIXct","POSIXt"),tzone = "UTC")),row.names = c(NA,-398L),class = c("tbl_df","tbl","data.frame"))
解决方法
这是一种 data.table 方法。代码说明在代码注释中
library( data.table )
#set data to data.table format
setDT( mydata )
#summarise by day
DT <- mydata[,.(total = .N),by = .(date = as.IDate( Admission ),Summary ) ]
#cast to wide
DT <- dcast(DT,date ~ Summary,value.var = "total",fill = 0 )
#create final based on min/max data in DT
final <- data.table( date = seq( min( DT$date ),max( DT$date ),by = 1 ) )
#initialise columns with zero-value
final[,`:=`( Dead = 0,Discharged = 0 ) ]
#update column values based on date
final[ DT,`:=`( Dead = i.Dead,Discharged = i.Discharged ),on = .(date) ][]
#calculate rolling 7 day mortality-rate
final[,mortality.rate := frollsum( Dead,n = 7 ) / ( frollsum( (Dead + Discharged),n = 7 ) ) ]
这里有一个整洁的方法。我也在使用 zoo 包。
计算每天的入院人数和死亡人数
library(tidyverse)
summaries <- df %>%
mutate(date = as.Date(Admission)) %>%
group_by(date) %>%
summarise(total_adm = n(),deaths = sum(Summary == "Dead"))
summaries
#> # A tibble: 129 x 3
#> date total_adm deaths
#> * <date> <int> <int>
#> 1 2020-01-09 1 0
#> 2 2020-01-27 1 0
#> 3 2020-01-31 2 0
#> 4 2020-02-13 1 0
#> 5 2020-02-21 1 1
#> 6 2020-02-22 1 0
#> 7 2020-02-23 1 0
#> 8 2020-02-24 1 0
#> 9 2020-02-28 1 1
#> 10 2020-03-01 1 1
#> # … with 119 more rows
计算滚动总和和死亡率
对于日期，我首先创建一个序列，然后是 left_join()。在 rollsum() 中使用 align = "right" 表示您获得前六天。
# sequence fro min to max date
date_seq <- seq.Date(from = min(summaries$date),to = max(summaries$date),by = 1)
tibble(date = date_seq) %>%
left_join(summaries) %>%
# Calculating rolling sums for admission and deaths,and mortality rate
mutate(
adm_7_days = zoo::rollsum(total_adm,k = 7,fill = NA,align = "right",na.rm = TRUE),deaths_7_days = zoo::rollsum(deaths,mortality_rate = deaths_7_days/adm_7_days
) %>%
print(n = 20)
#> Joining,by = "date"
#> # A tibble: 285 x 6
#> date total_adm deaths adm_7_days deaths_7_days mortality_rate
#> <date> <int> <int> <int> <int> <dbl>
#> 1 2020-01-09 1 0 NA NA NA
#> 2 2020-01-10 NA NA NA NA NA
#> 3 2020-01-11 NA NA NA NA NA
#> 4 2020-01-12 NA NA NA NA NA
#> 5 2020-01-13 NA NA NA NA NA
#> 6 2020-01-14 NA NA NA NA NA
#> 7 2020-01-15 NA NA 1 0 0
#> 8 2020-01-16 NA NA 0 0 NaN
#> 9 2020-01-17 NA NA 0 0 NaN
#> 10 2020-01-18 NA NA 0 0 NaN
#> 11 2020-01-19 NA NA 0 0 NaN
#> 12 2020-01-20 NA NA 0 0 NaN
#> 13 2020-01-21 NA NA 0 0 NaN
#> 14 2020-01-22 NA NA 0 0 NaN
#> 15 2020-01-23 NA NA 0 0 NaN
#> 16 2020-01-24 NA NA 0 0 NaN
#> 17 2020-01-25 NA NA 0 0 NaN
#> 18 2020-01-26 NA NA 0 0 NaN
#> 19 2020-01-27 1 0 1 0 0
#> 20 2020-01-28 NA NA 1 0 0
#> # … with 265 more rows
这里包 runner 也有帮助
library(dplyr)
library(tidyr)
library(runner)
df %>%
group_by(date = as.Date(strptime(Admission,format = "%Y-%m-%d"))) %>%
pivot_wider(id_cols = date,names_from = Summary,values_from = Admission,values_fn = length,values_fill = 0) %>%
ungroup() %>%
complete(date = seq.Date(min(.$date),max(.$date),by = 'day'),fill = list(Discharged = 0,Dead = 0)) %>%
mutate(Total = Discharged + Dead) %>%
mutate(mortality_rate = sum_run(Dead,k = 7)/sum_run(Total,k = 7))
# A tibble: 285 x 5
date Discharged Dead Total mortality_rate
<date> <dbl> <dbl> <dbl> <dbl>
1 2020-01-09 1 0 1 0
2 2020-01-10 0 0 0 0
3 2020-01-11 0 0 0 0
4 2020-01-12 0 0 0 0
5 2020-01-13 0 0 0 0
6 2020-01-14 0 0 0 0
7 2020-01-15 0 0 0 0
8 2020-01-16 0 0 0 NaN
9 2020-01-17 0 0 0 NaN
10 2020-01-18 0 0 0 NaN
# ... with 275 more rows
版权声明：本文内容由互联网用户自发贡献，该文观点与技术仅代表作者本人。本站仅提供信息存储空间服务，不拥有所有权，不承担相关法律责任。如发现本站有涉嫌侵权/违法违规的内容， 请发送邮件至 dio@foxmail.com 举报，一经查实，本站将立刻删除。