map内部map2-如何正确引用参数(purrr)

时间:2018-08-04 13:01:09

标签: r nested purrr

ex <- structure(list(group = c("group B", "group B", "group C", "group B","group C", "group B", "group B", "group A", "group C", "group C", "group C", "group B", "group A", "group A", "group A", "group B", "group A", "group A", "group B", "group C", "group B", "group A", "group C", "group C", "group C", "group C", "group B", "group A", "group A", "group C", "group B", "group A", "group A", "group B", "group C", "group C", "group A", "group C", "group C", "group A", "group B", "group B", "group A", "group B", "group C", "group C","group A", "group B", "group C", "group C"), A1 = c(0.765913072274998, 0.167720616329461, 0.282011203467846, 0.16467465297319, 0.407501850277185, 0.33958561392501, 0.117573569528759, 0.267871993361041, 0.930967768887058, 0.286146199563518, 0.741841563722119, 0.637853658990934, 0.137378493556753, 0.820813736645505, 0.249520575627685, 0.275153698632494, 0.916794545250013, 0.316050065914169, 0.393918378278613, 0.342175736324862, 0.0177193265408278, 0.178873546421528, 0.376545072998852, 0.411527326330543, 0.904074088903144, 0.487975180381909, 0.491365089081228, 0.591370195383206, 0.319207336986437, 0.98943907325156, 0.916014631278813, 0.0347612821497023, 0.323899461887777, 0.155270972754806, 0.436683354899287, 0.316902073565871, 0.734995431266725, 0.584133808733895, 0.515310257440433, 0.921727291075513, 0.0689518100116402, 0.659549278207123, 0.894137248862535, 0.00174906081520021, 0.873320956015959, 0.77207364118658, 0.637504813494161, 0.473099726485088, 0.557896945858374, 0.632965805241838), A2 = c(0.782154354499653, 0.718993512215093, 0.391234505455941, 0.337346265325323, 0.141482090810314, 0.587817938998342, 0.384924706770107, 0.0679492244962603, 0.0509498412720859, 0.786300176288933, 0.00685039279051125, 0.361857839627191, 0.851737944642082, 0.333896369440481, 0.521961389342323, 0.761324436869472, 0.486214824952185, 0.249763275263831, 0.536617708392441, 0.982582966331393, 0.879302836721763, 0.0212801641318947, 0.999207010492682, 0.661623647902161, 0.514440550701693, 0.748157452791929, 0.609151393873617, 0.581557413795963, 0.495366840157658, 0.595225095050409, 0.694380027009174, 0.419036868494004, 0.618371620541438, 0.406731882831082, 0.947823651600629, 0.182527825701982, 0.365398081485182, 0.307149735512212, 0.905119536910206, 0.657605888554826, 0.706386201782152, 0.461993521312252, 0.637554163113236, 0.280387100065127, 0.454221101710573, 0.0712104975245893, 0.914795317919925, 0.951028517214581, 0.645093881059438, 0.754043457563967), A3 = c(0.590488174697384, 0.876135899219662, 0.349565496202558, 0.365676332963631, 0.709230658365414, 0.584304825868458, 0.391973132034764, 0.464247716590762, 0.00831679091788828, 0.282901889178902, 0.842566592851654, 0.141866789199412, 0.278708242345601, 0.680587171344087, 0.256092368392274, 0.535304376389831, 0.803430012892932, 0.336343225324526, 0.320332229137421, 0.809689761372283, 0.588527292944491, 0.767302295425907, 0.124350237427279, 0.605355758452788, 0.619420127244666, 0.326774680987, 0.917224677512422, 0.710018905811012, 0.892817938234657, 0.149181636283174, 0.65066168922931, 0.433064805110916, 0.167979725869372, 0.809581968234852, 0.803237372776493, 0.703188817715272, 0.507392750121653, 0.372131450567394, 0.0688441153615713, 0.928956841118634, 0.960712827509269, 0.37454927386716, 0.753415656508878, 0.687665716046467, 0.05052674934268, 0.155349446227774, 0.806162646971643, 0.725155076943338, 0.537310504587367, 0.674253351520747), A4 = c(0.426875792676583, 0.168233293108642, 0.38692078506574, 0.673673333134502, 0.221049380488694, 0.142470651771873, 0.505352358799428, 0.579006788786501, 0.809476702939719, 0.343090934911743, 0.136329119792208, 0.881694708252326, 0.142607795307413, 0.658202062360942, 0.0624804550316185, 0.938871977152303, 0.477995269699022, 0.989794839406386, 0.307003591908142, 0.40553830191493, 0.0249065780080855, 0.321581491269171, 0.432656849268824, 0.578710418893024, 0.482647196389735, 0.72430428257212, 0.611029474530369, 0.748521578731015, 0.939656358910725, 0.803305297158659, 0.339922665851191, 0.919090943178162, 0.0926963407546282, 0.671128012472764, 0.634122629882768, 0.219061656622216, 0.376445228001103, 0.468331813113764, 0.131768246181309, 0.258267979836091, 0.651934198103845, 0.678243630565703, 0.663701833924279, 0.678762876661494, 0.524524878012016, 0.380242201732472, 0.433922954136506, 0.795754680642858, 0.383180371485651, 0.160383063135669)), .Names = c("group", "A1", "A2", "A3", "A4"), row.names = c(NA, -50L), class = c("tbl_df", "tbl", "data.frame"))

使用上述示例数据,我想在组内执行msClustering。此群集需要调整参数h,因此我在列h.cand中定义了几个值。然后,我想用后续的msClustering值调用h并将输出存储在列表列中。从理论上讲,purrr应该是可行的,但是我认为它需要嵌套map,确切地说是map内的map2。这是我的问题,我不确定如何引用不同的列表参数。我已经尝试过以下内容:

ex %>% 
  group_by(group) %>% 
  nest() %>% 
  h.cand = map(data, ~quantile(dist(.x), seq(0.05, 0.40, by = 0.05))) %>% 
  mutate(cluster = map2(h.cand, data, ~map(.x, ~msClustering(
    .y, # data (second argument of outter map2)
    h = .x # h.cand element (first argument of inner map)
  ))))

并出现错误:

  

错误:无法分配大小为1681.9 Gb的向量

如何为每个map执行8个(长度为h.cand向量的聚类)的外部元素和内部group的元素?

1 个答案:

答案 0 :(得分:4)

对于像这样的复杂匿名函数,最好使用^而不是lambda / function(x)语法传递给~的{​​{1}}参数。

清理数据:

map()

使用.f代替map(ex, length) # make element5 same length ex[[5]] <- c(ex[[5]], runif(16)) # make into data frame ex <- dplyr::bind_cols(ex)

function(x)

结果检查:

~