これらは私が持っている巨大なファイルの最初の 10 行です: (これらの 10 行には 1 人のユーザーしかいませんが、何千ものユーザーがいることに注意してください)
dput(testd)
structure(list(user = c(0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L
), otime = structure(c(10L, 9L, 8L, 7L, 6L, 5L, 4L, 3L, 2L, 1L
), .Label = c("2010-10-12T19:56:49Z", "2010-10-13T03:57:23Z",
"2010-10-13T16:41:35Z", "2010-10-13T20:05:43Z", "2010-10-13T23:31:51Z",
"2010-10-14T00:21:47Z", "2010-10-14T18:25:51Z", "2010-10-16T03:48:54Z",
"2010-10-16T06:02:04Z", "2010-10-17T01:48:53Z"), class = "factor"),
lat = c(39.747652, 39.891383, 39.891077, 39.750469, 39.752713,
39.752508, 39.7513, 39.758974, 39.827022, 39.749934),
long = c(-104.99251, -105.070814, -105.068532, -104.999073,
-104.996337, -104.996637, -105.000121, -105.010853,
-105.143191, -105.000017),
locid = structure(c(5L, 4L, 9L, 6L, 1L, 2L, 8L, 3L, 10L, 7L),
.Label = c("2ef143e12038c870038df53e0478cefc",
"424eb3dd143292f9e013efa00486c907", "6f5b96170b7744af3c7577fa35ed0b8f",
"7a0f88982aa015062b95e3b4843f9ca2", "88c46bf20db295831bd2d1718ad7e6f5",
"9848afcc62e500a01cf6fbf24b797732f8963683", "b3d356765cc8a4aa7ac5cd18caafd393",
"d268093afe06bd7d37d91c4d436e0c40d217b20a", "dd7cd3d264c2d063832db506fba8bf79",
"f6f52a75fd80e27e3770cd3a87054f27"), class = "factor"),
dnt = structure(c(10L, 9L, 8L, 7L, 6L, 5L, 4L, 3L, 2L, 1L),
.Label = c("2010-10-12 19:56:49",
"2010-10-13 03:57:23", "2010-10-13 16:41:35", "2010-10-13 20:05:43",
"2010-10-13 23:31:51", "2010-10-14 00:21:47", "2010-10-14 18:25:51",
"2010-10-16 03:48:54", "2010-10-16 06:02:04", "2010-10-17 01:48:53"
), class = "factor"),
x = c(-11674.6344476781, -11683.3414552141,
-11683.0877083915, -11675.3642199817, -11675.0599906624,
-11675.0933491404, -11675.4807522648, -11676.6740962175,
-11691.3894104198, -11675.4691879924),
y = c(4419.73724843345, 4435.719406435, 4435.68538078744,
4420.05048454181, 4420.3000059572, 4420.27721099723,
4420.14288752585, 4420.99619739292, 4428.56278976123,
4419.99099525605),
cellx = structure(c(1L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 2L, 1L),
.Label = c("[-11682,-11672)", "[-11692,-11682)"
), class = "factor"),
celly = structure(c(1L, 2L, 2L, 1L,
1L, 1L, 1L, 1L, 1L, 1L), .Label = c("[4419,4429)", "[4429,4439)"
), class = "factor"),
cellxy = structure(c(1L, 3L, 3L, 1L,
1L, 1L, 1L, 1L, 2L, 1L), .Label = c("[-11682,-11672)[4419,4429)",
"[-11692,-11682)[4419,4429)", "[-11692,-11682)[4429,4439)"
), class = "factor")), .Names = c("user", "otime", "lat",
"long", "locid", "dnt", "x", "y", "cellx", "celly", "cellxy"), class = "data.frame", row.names = c(NA,
-10L))
理解を簡単にするために、データが何であるかについて少し説明します。x と y は、緯度と経度の座標の変換です。を使用して、x、y 位置をビンに離散化しましたcut
。ユーザーごとに最も訪問されたビンを取得したいので、を使用しますddply
。次のように:
cells = ddply(testd, .(user, cellxy), summarise, length(cellxy))
取得:
dput(cells)
structure(list(user = c(0, 0, 0), cellxy = structure(1:3, .Label = c("[-11682,-11672)[4419,4429)",
"[-11692,-11682)[4419,4429)", "[-11692,-11682)[4429,4439)"), class = "factor"),
count = c(7L, 1L, 2L)), .Names = c("user", "cellxy", "count"
), row.names = c(NA, -3L), class = "data.frame")
今私がやりたいことは、前の計算から得られた、ユーザーごとに最も訪問されたビンの最初のデータセットから平均 x、y を計算することです。これを効率的に行う方法がわかりません。私のデータセットが非常に大きいことを考えると、いくつかのガイダンスをいただければ幸いです。ありがとう!