取依赖于R中同一行中多个其他列的一组数据的平均值

我想每4个样方取动物数量的平均值。站点和区域控制应匹配平均样方组

对R来说相当陌生

我的尝试：

错误：拆分器\u a.data、.margins、.expand中出错： “pairlist”对象不能强制为“integer”类型

---

我认为你想做的事情可以简单地像这样完成：

如果您有：

commData <- structure(list(areaContro = c(29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L), station = c(1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 4L, 4L, 4L, 4L, 5L, 5L, 5L, 5L, 6L, 6L, 6L, 6L, 7L, 7L, 7L, 7L, 8L, 8L), quadrat = c(1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L), latitude = c(42.12521667, 42.12658333, 42.12681667, 42.12705, 42.12466667, 42.12631667, 42.12671667, 42.1272, 42.12671667, 42.12682833, 42.12726166, 42.12794499, 42.12771667, 42.1285, 42.12871667, 42.12896667, 42.12691667, 42.12748333, 42.12763333, 42.12785, 42.127, 42.12711818, 42.12735152, 42.12755152, 42.1264341, 42.1265095, 42.12664427, 42.12679211, 42.12703333, 42.12725), longitude = c(-67.33001667, -67.32823333, -67.3281, -67.3279, -67.31041667, -67.30906667, -67.30876667, -67.30843333, -67.29326667, -67.2942027, -67.29311937, -67.2929027, -67.27731667, -67.2768, -67.27655, -67.27628333, -67.25879572, -67.25684572, -67.25647905, -67.25616238, -67.2359, -67.23562265, -67.23512265, -67.23472265, -67.21841245, -67.21825004, -67.21814781, -67.21796007, -67.19853333, -67.19653333), scallops = c(1L, 0L, 0L, 0L, 4L, 0L, 7L, 3L, 3L, 3L, 1L, 2L, 2L, 1L, 2L, 0L, 2L, 2L, 2L, 2L, 45L, 11L, 4L, 8L, 12L, 9L, 11L, 11L, 4L, 10L), clappers = c(0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 2L, 0L, 0L, 0L, 0L)), .Names = c("areaContro", "station", "quadrat", "latitude", "longitude", "scallops", "clappers" ), row.names = c(NA, 30L), class = "data.frame")

对于所有请求的变量：

full_scallop <- aggregate(commData$scallops, by = list(commData$quadrat, commData$areaContro, commData$station), FUN = mean)

如果您是R新手，我强烈建议您看看dplyr，尤其是用于常见数据操作任务的dplyr

你的第二个aaply参数是不正确的。根据文档，它接受给定下标的向量来分割数据，例如1行。还要注意，它接受一个数组并生成一个数组

我不知道你想平均哪些变量，平均值应该以什么为条件。我想你想要的是按站点、样方和面积控制分组的平均值，但这是常数

基准R：

dplyr：

按站平均

commData <- structure(list(areaContro = c(29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L), station = c(1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 4L, 4L, 4L, 4L, 5L, 5L, 5L, 5L, 6L, 6L, 6L, 6L, 7L, 7L, 7L, 7L, 8L, 8L), quadrat = c(1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L), latitude = c(42.12521667, 42.12658333, 42.12681667, 42.12705, 42.12466667, 42.12631667, 42.12671667, 42.1272, 42.12671667, 42.12682833, 42.12726166, 42.12794499, 42.12771667, 42.1285, 42.12871667, 42.12896667, 42.12691667, 42.12748333, 42.12763333, 42.12785, 42.127, 42.12711818, 42.12735152, 42.12755152, 42.1264341, 42.1265095, 42.12664427, 42.12679211, 42.12703333, 42.12725), longitude = c(-67.33001667, -67.32823333, -67.3281, -67.3279, -67.31041667, -67.30906667, -67.30876667, -67.30843333, -67.29326667, -67.2942027, -67.29311937, -67.2929027, -67.27731667, -67.2768, -67.27655, -67.27628333, -67.25879572, -67.25684572, -67.25647905, -67.25616238, -67.2359, -67.23562265, -67.23512265, -67.23472265, -67.21841245, -67.21825004, -67.21814781, -67.21796007, -67.19853333, -67.19653333), scallops = c(1L, 0L, 0L, 0L, 4L, 0L, 7L, 3L, 3L, 3L, 1L, 2L, 2L, 1L, 2L, 0L, 2L, 2L, 2L, 2L, 45L, 11L, 4L, 8L, 12L, 9L, 11L, 11L, 4L, 10L), clappers = c(0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 2L, 0L, 0L, 0L, 0L)), .Names = c("areaContro", "station", "quadrat", "latitude", "longitude", "scallops", "clappers" ), row.names = c(NA, 30L), class = "data.frame")

scallop <- aggregate(commData$scallops, by = list(commData$quadrat), FUN = mean)

full_scallop <- aggregate(commData$scallops, by = list(commData$quadrat, commData$areaContro, commData$station), FUN = mean)

aggregate(cbind(commData$scallops, commData$clappers)~commData$quadrat+commData$areaContro+commData$station,  FUN = mean)

tapply(data$scallops, data[c("station", "quadrat")], mean)

data %>% group_by(station, quadrat) %>% 
summarise(scallops_mean = mean(scallops))