如何根据两个地理多边形之间的移动来组织/分析位置数据？答案

【问题标题】：How to organize/analyze location data based on movement between two geographic polygons?如何根据两个地理多边形之间的移动来组织/分析位置数据？
【发布时间】：2019-06-10 16:23:03
【问题描述】：

我有一个小数据框，其中包含我的学习系统两侧的两个多边形的点，如下图所示（东为蓝色，西为红色）。这是数据框。

structure(list(Shore = structure(c(2L, 2L, 2L, 2L, 2L, 2L, 2L, 
2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
1L), .Label = c("East", "West"), class = "factor"), Lat = c(72.45604629, 
72.44350398, 72.41516226, 72.36734761, 72.33600228, 72.31760236, 
72.29050994, 72.26066187, 72.2680832, 72.47144353, 72.45604629, 
72.45604629, 72.44816356, 72.37238665, 72.24127983, 72.26066187, 
72.29050994, 72.31760236, 72.33600228, 72.36734761, 72.41516226, 
72.44350398, 72.45604629, 72.45604629), Long = c(-80.89019727, 
-80.91753044, -80.9496172, -81.0363703, -81.1243118, -81.15639857, 
-81.16947095, -81.27702103, -81.33465836, -80.90326966, -80.89019727, 
-80.89019727, -80.84860332, -80.94367521, -81.28474562, -81.27702103, 
-81.16947095, -81.15639857, -81.1243118, -81.0363703, -80.9496172, 
-80.91753044, -80.89019727, -80.89019727)), class = "data.frame", row.names = c(NA, 
-24L))

我还有一个动物运动数据框，可以在地图上显示的每个点上检测到。我想知道的是在系统内何时何地，动物从红色跨越到蓝色，反之亦然。下面是我数据的一小部分。所有数据都应落在两个多边形之一（红色或蓝色）内。 ID 列是个体动物 ID，Station 列指示哪个接收器（A 位于最北端，1 个位于最西端）。我想最后我会寻找一个新的数据框，其中的列显示这些事件发生的日期/时间、发生移动的站点以及移动的个人。

structure(list(DateTime = structure(c(1503006715, 1503006880, 
1503007037, 1503007108, 1503007185, 1503007255, 1503007331, 1503007399, 
1503007554, 1503007633, 1503007709, 1503007775, 1503007845, 1503007987, 
1503008057, 1503008132, 1503008199, 1503008269, 1503008392, 1503008412, 
1503008544, 1503008620, 1503009148, 1503009217, 1503009291, 1503009356, 
1503009376, 1503009421, 1503009488, 1503009508, 1503009558, 1503009578, 
1503009634, 1503009702, 1503009722, 1503009774, 1503009854, 1503009875, 
1503009932, 1503010003, 1503010023, 1503010081, 1503010101, 1503010153, 
1503010234, 1503010254, 1503010312, 1503010332, 1503010383, 1503010463, 
1503010483, 1503010538, 1503015897, 1503015963, 1503016024, 1503016873, 
1503017027, 1503017229, 1503022094, 1503022380, 1503022393, 1503022476, 
1503022559, 1503022641, 1503022721, 1503022785, 1503022798, 1503022855, 
1503022868, 1503022931, 1503022944, 1503023000, 1503023013, 1503023073, 
1503023086, 1503023155, 1503023168, 1503023235, 1503023313, 1503023383, 
1503023397, 1503023461, 1503023474, 1503023533, 1503023612, 1503023625, 
1503023686, 1503023816, 1503024252, 1502754012, 1502754224, 1502754364, 
1502754444, 1502754588, 1502754661, 1502754742, 1502754822, 1502758872, 
1502758944, 1502758971), class = c("POSIXct", "POSIXt"), tzone = "America/New_York"), 
    ID = c(1657L, 1657L, 1657L, 1657L, 1657L, 1657L, 1657L, 1657L, 
    1657L, 1657L, 1657L, 1657L, 1657L, 1657L, 1657L, 1657L, 1657L, 
    1657L, 1657L, 1657L, 1657L, 1657L, 1657L, 1657L, 1657L, 1657L, 
    1657L, 1657L, 1657L, 1657L, 1657L, 1657L, 1657L, 1657L, 1657L, 
    1657L, 1657L, 1657L, 1657L, 1657L, 1657L, 1657L, 1657L, 1657L, 
    1657L, 1657L, 1657L, 1657L, 1657L, 1657L, 1657L, 1657L, 1657L, 
    1657L, 1657L, 1657L, 1657L, 1657L, 1657L, 1657L, 1657L, 1657L, 
    1657L, 1657L, 1657L, 1657L, 1657L, 1657L, 1657L, 1657L, 1657L, 
    1657L, 1657L, 1657L, 1657L, 1657L, 1657L, 1657L, 1657L, 1657L, 
    1657L, 1657L, 1657L, 1657L, 1657L, 1657L, 1657L, 1657L, 1657L, 
    1658L, 1658L, 1658L, 1658L, 1658L, 1658L, 1658L, 1658L, 1658L, 
    1658L, 1658L), Station = c("TRD1", "TRD1", "TRD1", "TRD1", 
    "TRD1", "TRD1", "TRD1", "TRD1", "TRD1", "TRD1", "TRD1", "TRD1", 
    "TRD1", "TRD1", "TRD1", "TRD1", "TRD1", "TRD1", "TRD2", "TRD1", 
    "TRD2", "TRD2", "TRD2", "TRD2", "TRD2", "TRD2", "TRD1", "TRD2", 
    "TRD2", "TRD1", "TRD2", "TRD1", "TRD2", "TRD2", "TRD1", "TRD2", 
    "TRD2", "TRD1", "TRD2", "TRD2", "TRD1", "TRD2", "TRD1", "TRD2", 
    "TRD2", "TRD1", "TRD2", "TRD1", "TRD2", "TRD2", "TRD1", "TRD2", 
    "TRE5", "TRE5", "TRE4", "TRE4", "TRE4", "TRE4", "TRF3", "TRF4", 
    "TRF3", "TRF3", "TRF3", "TRF3", "TRF3", "TRF4", "TRF3", "TRF4", 
    "TRF3", "TRF4", "TRF3", "TRF4", "TRF3", "TRF4", "TRF3", "TRF4", 
    "TRF3", "TRF4", "TRF4", "TRF4", "TRF3", "TRF4", "TRF3", "TRF4", 
    "TRF4", "TRF3", "TRF4", "TRF4", "TRF4", "TRD1", "TRD1", "TRD1", 
    "TRD1", "TRD1", "TRD1", "TRD1", "TRD1", "TRE2", "TRE2", "TRE1"
    ), Latitude = c(72.35019, 72.35019, 72.35019, 72.35019, 72.35019, 
    72.35019, 72.35019, 72.35019, 72.35019, 72.35019, 72.35019, 
    72.35019, 72.35019, 72.35019, 72.35019, 72.35019, 72.35019, 
    72.35019, 72.34705, 72.35019, 72.34705, 72.34705, 72.34705, 
    72.34705, 72.34705, 72.34705, 72.35019, 72.34705, 72.34705, 
    72.35019, 72.34705, 72.35019, 72.34705, 72.34705, 72.35019, 
    72.34705, 72.34705, 72.35019, 72.34705, 72.34705, 72.35019, 
    72.34705, 72.35019, 72.34705, 72.34705, 72.35019, 72.34705, 
    72.35019, 72.34705, 72.34705, 72.35019, 72.34705, 72.32009, 
    72.32009, 72.32195, 72.32195, 72.32195, 72.32195, 72.29368, 
    72.29111, 72.29368, 72.29368, 72.29368, 72.29368, 72.29368, 
    72.29111, 72.29368, 72.29111, 72.29368, 72.29111, 72.29368, 
    72.29111, 72.29368, 72.29111, 72.29368, 72.29111, 72.29368, 
    72.29111, 72.29111, 72.29111, 72.29368, 72.29111, 72.29368, 
    72.29111, 72.29111, 72.29368, 72.29111, 72.29111, 72.29111, 
    72.35019, 72.35019, 72.35019, 72.35019, 72.35019, 72.35019, 
    72.35019, 72.35019, 72.32544, 72.32544, 72.32738), Longitude = c(-81.09397, 
    -81.09397, -81.09397, -81.09397, -81.09397, -81.09397, -81.09397, 
    -81.09397, -81.09397, -81.09397, -81.09397, -81.09397, -81.09397, 
    -81.09397, -81.09397, -81.09397, -81.09397, -81.09397, -81.08279, 
    -81.09397, -81.08279, -81.08279, -81.08279, -81.08279, -81.08279, 
    -81.08279, -81.09397, -81.08279, -81.08279, -81.09397, -81.08279, 
    -81.09397, -81.08279, -81.08279, -81.09397, -81.08279, -81.08279, 
    -81.09397, -81.08279, -81.08279, -81.09397, -81.08279, -81.09397, 
    -81.08279, -81.08279, -81.09397, -81.08279, -81.09397, -81.08279, 
    -81.08279, -81.09397, -81.08279, -81.11921, -81.11921, -81.13219, 
    -81.13219, -81.13219, -81.13219, -81.16389, -81.16127, -81.16389, 
    -81.16389, -81.16389, -81.16389, -81.16389, -81.16127, -81.16389, 
    -81.16127, -81.16389, -81.16127, -81.16389, -81.16127, -81.16389, 
    -81.16127, -81.16389, -81.16127, -81.16389, -81.16127, -81.16127, 
    -81.16127, -81.16389, -81.16127, -81.16389, -81.16127, -81.16127, 
    -81.16389, -81.16127, -81.16127, -81.16127, -81.09397, -81.09397, 
    -81.09397, -81.09397, -81.09397, -81.09397, -81.09397, -81.09397, 
    -81.15897, -81.15897, -81.17314)), row.names = c(41276L, 
41277L, 41278L, 41279L, 41280L, 41281L, 41282L, 41283L, 41284L, 
41285L, 41286L, 41287L, 41288L, 41289L, 41290L, 41291L, 41292L, 
41293L, 41294L, 41295L, 41296L, 41297L, 41298L, 41299L, 41300L, 
41301L, 41302L, 41303L, 41304L, 41305L, 41306L, 41307L, 41309L, 
41310L, 41311L, 41312L, 41313L, 41314L, 41315L, 41316L, 41317L, 
41318L, 41319L, 41320L, 41323L, 41324L, 41326L, 41328L, 41329L, 
41330L, 41331L, 41332L, 41432L, 41433L, 41434L, 41436L, 41437L, 
41438L, 41441L, 41447L, 41448L, 41452L, 41454L, 41458L, 41460L, 
41463L, 41464L, 41465L, 41466L, 41467L, 41469L, 41471L, 41472L, 
41474L, 41475L, 41476L, 41477L, 41478L, 41479L, 41480L, 41481L, 
41482L, 41483L, 41484L, 41485L, 41486L, 41487L, 41488L, 41489L, 
36498L, 36504L, 36510L, 36515L, 36521L, 36524L, 36528L, 36530L, 
36765L, 36769L, 36775L), class = "data.frame")

【问题讨论】：

标签： r location

【解决方案1】：

假设您的第二个数据集已加载到名为 df 的变量中，并且每个 Station 都明确映射到 East 或 West，您只需将每个站点编码到其各自的 shore 并使用 @987654326 @ 声明如下：

library(tidyverse)
df %>%
  mutate(
    shore = case_when(
      Station %in% c("TRD1", "TRE1", "TRE2") ~ "West",
      TRUE ~ "East"
    )
  ) %>%
  group_by(ID) %>%
  arrange(DateTime) %>%
  mutate(
    shore_change = shore != lag(shore, 1, default = first(shore))
  )

在这个链的末端，我们group_by(ID) 和arrange(DateTime) 说“对于每个ID，按时间顺序排列它们”，然后我们创建一个新变量shore_change 来检查thisshore 不等于 (!=) 之前的 shore（即 lag(shore, 1)）。 default = first(shore) 用于消除 NA 以检查 ID 的第一岸值。

如果您想获取发生这种情况的所有时间，只需将：filter(shore_change == TRUE) 附加到管道末尾即可。

【讨论】：