我有以下数据集：
> str(e.2015.1990)
'data.frame': 4813807 obs. of 42 variables:
$ GAME.ID : Factor w/ 60464 levels "ANA201504100",..: 1 1 1 1 1 1 1 1 1 1 ...
$ INNING : num 1 1 1 1 1 1 1 1 1 2 ...
$ BATTING.TEAM : Factor w/ 2 levels "0","1": 1 1 1 1 1 1 2 2 2 1 ...
$ OUTS : int 0 1 2 2 2 2 0 1 2 0 ...
$ BATTER : Factor w/ 5107 levels "abrej003","ackld001",..: 73 167 33 120 163 100 34 256 200 209 ...
$ BATTER.HAND : Factor w/ 2 levels "L","R": 2 1 2 1 2 1 1 2 2 2 ...
$ RES.BATTER : Factor w/ 5107 levels "abrej003","ackld001",..: 73 167 33 120 163 100 34 256 200 209 ...
$ RES.BATTER.HAND : Factor w/ 2 levels "L","R": 2 1 2 1 2 1 1 2 2 2 ...
$ PITCHER : Factor w/ 3481 levels "abadf001","albem001",..: 187 187 187 187 187 187 204 204 204 187 ...
$ PITCHER.HAND : Factor w/ 2 levels "L","R": 1 1 1 1 1 1 1 1 1 1 ...
$ RES.PITCHER : Factor w/ 3481 levels "abadf001","albem001",..: 187 187 187 187 187 187 204 204 204 187 ...
$ RES.PITCHER.HAND : Factor w/ 2 levels "L","R": 1 1 1 1 1 1 1 1 1 1 ...
$ FIRST.RUNNER : Factor w/ 4369 levels "","abrej003",..: 1 1 1 1 104 140 1 1 1 1 ...
$ SECOND.RUNNER : Factor w/ 4048 levels "","abrej003",..: 1 1 1 26 1 90 1 1 1 1 ...
$ THIRD.RUNNER : Factor w/ 3729 levels "","ackld001",..: 1 1 1 1 1 1 1 1 1 1 ...
$ EVENT.TEXT : chr "63/G" "6/P" "D8/L+" "S9/G.2-H" ...
$ EVENT.TYPE : num 1 1 19 18 18 1 1 1 1 1 ...
$ AB.FLAG : logi TRUE TRUE TRUE TRUE TRUE TRUE ...
$ HIT.VALUE : int 1 1 3 2 2 1 1 1 1 1 ...
$ SH.FLAG : logi FALSE FALSE FALSE FALSE FALSE FALSE ...
$ SF.FLAG : logi FALSE FALSE FALSE FALSE FALSE FALSE ...
$ DOUBLE.PLAY.FLAG : logi FALSE FALSE FALSE FALSE FALSE FALSE ...
$ TRIPLE.PLAY.FLAG : logi FALSE FALSE FALSE FALSE FALSE FALSE ...
$ RBI.ON.PLAY : num 0 0 0 1 0 0 0 0 0 0 ...
$ BATTED.BALL.TYPE : Factor w/ 5 levels "","F","G","L",..: 3 5 4 3 4 5 3 3 5 4 ...
$ BATTER.DEST : int 0 0 2 1 1 0 0 0 0 0 ...
$ RUNNER.ON.1ST.DEST : int 0 0 0 0 2 1 0 0 0 0 ...
$ RUNNER.ON.2ND.DEST : int 0 0 0 4 0 2 0 0 0 0 ...
$ RUNNER.ON.3RD.DEST : int 0 0 0 0 0 0 0 0 0 0 ...
$ SB.FOR.RUNNER.ON.1ST.FLAG : logi FALSE FALSE FALSE FALSE FALSE FALSE ...
$ SB.FOR.RUNNER.ON.2ND.FLAG : logi FALSE FALSE FALSE FALSE FALSE FALSE ...
$ SB.FOR.RUNNER.ON.3RD.FLAG : logi FALSE FALSE FALSE FALSE FALSE FALSE ...
$ CS.FOR.RUNNER.ON.1ST.FLAG : logi FALSE FALSE FALSE FALSE FALSE FALSE ...
$ CS.FOR.RUNNER.ON.2ND.FLAG : logi FALSE FALSE FALSE FALSE FALSE FALSE ...
$ CS.FOR.RUNNER.ON.3RD.FLAG : logi FALSE FALSE FALSE FALSE FALSE FALSE ...
$ PO.FOR.RUNNER.ON.1ST.FLAG : logi FALSE FALSE FALSE FALSE FALSE FALSE ...
$ PO.FOR.RUNNER.ON.2ND.FLAG : logi FALSE FALSE FALSE FALSE FALSE FALSE ...
$ PO.FOR.RUNNER.ON.3RD.FLAG : logi FALSE FALSE FALSE FALSE FALSE FALSE ...
$ RESPONSIBLE.PITCHER.FOR.RUNNER.ON.1ST: Factor w/ 3433 levels "","albua001",..: 1 1 1 1 161 161 1 1 1 1 ...
$ RESPONSIBLE.PITCHER.FOR.RUNNER.ON.2ND: Factor w/ 3408 levels "","abadf001",..: 1 1 1 133 1 133 1 1 1 1 ...
$ RESPONSIBLE.PITCHER.FOR.RUNNER.ON.3RD: Factor w/ 3337 levels "","abadf001",..: 1 1 1 1 1 1 1 1 1 1 ...
$ EVENT.NUM : Factor w/ 177 levels "1","10","100",..: 1 90 101 112 123 134 145 156 167 2 ...
我能够成功地创建以下数据集：
p.hit = aggregate(x = list(HIT = e.2015.1990$HIT.VALUE), by = list(GAME.ID = e.2015.1990$GAME.ID, PLAYER.ID = e.2015.1990$BATTER), FUN = function(x) sum(x > 1))
p.single = aggregate(x = list(SINGLE = e.2015.1990$HIT.VALUE), by = list(GAME.ID = e.2015.1990$GAME.ID, PLAYER.ID = e.2015.1990$BATTER), FUN = function(x) sum(x == 2))
p.double = aggregate(x = list(DOUBLE = e.2015.1990$HIT.VALUE), by = list(GAME.ID = e.2015.1990$GAME.ID, PLAYER.ID = e.2015.1990$BATTER), FUN = function(x) sum(x == 3))
p.triple = aggregate(x = list(TRIPLE = e.2015.1990$HIT.VALUE), by = list(GAME.ID = e.2015.1990$GAME.ID, PLAYER.ID = e.2015.1990$BATTER), FUN = function(x) sum(x == 4))
p.home.run = aggregate(x = list(HOME.RUN = e.2015.1990$HIT.VALUE), by = list(GAME.ID = e.2015.1990$GAME.ID, PLAYER.ID = e.2015.1990$BATTER), FUN = function(x) sum(x == 5))
p.at.bat = aggregate(x = list(AT.BAT = e.2015.1990$AB.FLAG), by = list(GAME.ID = e.2015.1990$GAME.ID, PLAYER.ID = e.2015.1990$BATTER), FUN = function(x) sum(x == "TRUE"))
p.rbi = aggregate(x = list(RBI = e.2015.1990$RBI.ON.PLAY), by = list(GAME.ID = e.2015.1990$GAME.ID, PLAYER.ID = e.2015.1990$BATTER), FUN = function(x) sum(x > 0))
p.sf = aggregate(x = list(SACRIFICE.FLY = e.2015.1990$SF.FLAG), by = list(GAME.ID = e.2015.1990$GAME.ID, PLAYER.ID = e.2015.1990$BATTER), FUN = function(x) sum(x == "TRUE"))
p.hbp = aggregate(x = list(HIT.BY.PITCH = e.2015.1990$EVENT.TYPE), by = list(GAME.ID = e.2015.1990$GAME.ID, PLAYER.ID = e.2015.1990$BATTER), FUN = function(x) sum(x == 16))
p.ibb = aggregate(x = list(INTENTIONAL.WALK = e.2015.1990$EVENT.TYPE), by = list(GAME.ID = e.2015.1990$GAME.ID, PLAYER.ID = e.2015.1990$BATTER), FUN = function(x) sum(x == 15))
但是，当我同样尝试创建以下数据集时：
p.sh = aggregate(x = list(SACRIFICE.HIT = e.2015.1990$SH.FLAG), by = list(GAME.ID = e.2015.1990$GAME.ID, PLAYER.ID = e.2015.1990$BATTER), FUN = function(x) sum(X == "TRUE"))
p.so = aggregate(x = list(STRIKE.OUT = e.2015.1990$EVENT.TYPE), by = list(GAME.ID = e.2015.1990$GAME.ID, PLAYER.ID = e.2015.1990$RES.PITCHER), FUN = function(x) sum(X == 3))
p.ha = aggregate(x = list(HITS.ALLOWED = e.2015.1990$EVENT.TYPE), by = list(GAME.ID = e.2015.1990$GAME.ID, PLAYER.ID = e.2015.1990$RES.PITCHER), FUN = function(x) sum(X > 1))
p.hb = aggregate(x = list(HIT.BATSMAN = e.2015.1990$EVENT.TYPE), by = list(GAME.ID = e.2015.1990$GAME.ID, PLAYER.ID = e.2015.1990$RES.PITCHER), FUN = function(x) sum(X == 16))
我收到相同的错误消息：
> p.sh = aggregate(x = list(SACRIFICE.HIT = e.2015.1990$SH.FLAG), by = list(GAME.ID = e.2015.1990$GAME.ID, PLAYER.ID = e.2015.1990$BATTER), FUN = function(x) sum(X == "TRUE"))
Error in FUN(X[[i]], ...) : object 'X' not found
> p.so = aggregate(x = list(STRIKE.OUT = e.2015.1990$EVENT.TYPE), by = list(GAME.ID = e.2015.1990$GAME.ID, PLAYER.ID = e.2015.1990$RES.PITCHER), FUN = function(x) sum(X == 3))
Error in FUN(X[[i]], ...) : object 'X' not found
> p.ha = aggregate(x = list(HITS.ALLOWED = e.2015.1990$EVENT.TYPE), by = list(GAME.ID = e.2015.1990$GAME.ID, PLAYER.ID = e.2015.1990$RES.PITCHER), FUN = function(x) sum(X > 1))
Error in FUN(X[[i]], ...) : object 'X' not found
> p.hb = aggregate(x = list(HIT.BATSMAN = e.2015.1990$EVENT.TYPE), by = list(GAME.ID = e.2015.1990$GAME.ID, PLAYER.ID = e.2015.1990$RES.PITCHER), FUN = function(x) sum(X == 16))
Error in FUN(X[[i]], ...) : object 'X' not found
区别是什么？这是怎么回事？而且，我该如何解决它？
在我发现的类似问题中，似乎这个错误与某种类型的身份违规有关，其中变量引用自身。但是，这不是这种情况。
感谢您的帮助！
答案 0 :(得分：1)
它似乎只是一个案例信件问题。
在您遇到错误的代码中，您在sum函数中将X替换为X.
请尝试以下方法：
p.sh = aggregate(x = list(SACRIFICE.HIT = e.2015.1990$SH.FLAG), by = list(GAME.ID = e.2015.1990$GAME.ID, PLAYER.ID = e.2015.1990$BATTER), FUN = function(x) sum(x == "TRUE"))
p.so = aggregate(x = list(STRIKE.OUT = e.2015.1990$EVENT.TYPE), by = list(GAME.ID = e.2015.1990$GAME.ID, PLAYER.ID = e.2015.1990$RES.PITCHER), FUN = function(x) sum(x == 3))
p.ha = aggregate(x = list(HITS.ALLOWED = e.2015.1990$EVENT.TYPE), by = list(GAME.ID = e.2015.1990$GAME.ID, PLAYER.ID = e.2015.1990$RES.PITCHER), FUN = function(x) sum(x > 1))
p.hb = aggregate(x = list(HIT.BATSMAN = e.2015.1990$EVENT.TYPE), by = list(GAME.ID = e.2015.1990$GAME.ID, PLAYER.ID = e.2015.1990$RES.PITCHER), FUN = function(x) sum(x == 16))