提高R中坏的/可能不必要的应用程序的性能

提前感谢您在这方面的帮助。我不确定我是否使用了错误的

apply

，或者仅仅是违反了使我的代码变慢的其他规则。感谢您的帮助

概述：我有篮球数据，其中每一排都是篮球比赛中的一个时刻，包括球场上的10名球员、他们的球队、比赛以及该排在比赛中的时间（1-40分钟）。利用这些数据，我计算了每名球员在1-40分钟内他们在球场上的比赛百分比

例如，如果乔的球队打了20场比赛，如果在其中13场比赛中，乔在比赛的第5分钟出现在数据中，那么我们可以说乔在他的球队65%的比赛中出现在第5分钟。我在计算每个球员，每个赛季，每个1-40分钟的时间，在我不太小的数据中，我遇到了性能问题。以下是我目前执行此操作的功能：

library(dplyr)

# Raw Data Is Play-By-Play Data - Each Row contains stats for a pl (combination of 5 basketball players)
sheets_url <- 'https://docs.google.com/spreadsheets/d/1xmzaF6tpzVpjOmgfwHwFM_JE8LUszofjj25A5P0P21o/export?format=csv&id=1xmzaF6tpzVpjOmgfwHwFM_JE8LUszofjj25A5P0P21o&gid=630752085'
on.ct.data <- httr::content(httr::GET(url = sheets_url))

computeOnCourtByMinutePcts <- function(on.ct.data) {

  # Create Dataframe With Number Of Games Played By Team Each Season
  num.home.team.games <- on.ct.data %>%
    dplyr::group_by(homeTeamId, season) %>%
    dplyr::summarise(count = length(unique(gameId)))

  num.away.team.games <- on.ct.data %>%
    dplyr::group_by(awayTeamId, season) %>%
    dplyr::summarise(count = length(unique(gameId)))

  num.team.games <- num.home.team.games %>%
    dplyr::full_join(num.away.team.games, by = c('homeTeamId'='awayTeamId', 'season'='season')) %>%
    dplyr::mutate(gamesPlayed = rowSums(cbind(count.x, count.y), na.rm = TRUE)) %>%
    dplyr::rename(teamId = homeTeamId) %>%
    dplyr::mutate(season = as.character(season)) %>%
    dplyr::select(teamId, season, gamesPlayed)

  # Create Dataframe With Players By Season - Seems kind of bulky as well
  all.player.season.apperances <- rbind(
    on.ct.data %>% dplyr::select(homeTeamId, onCtHomeId1, season) %>% dplyr::rename(playerId = onCtHomeId1, teamId = homeTeamId),
    on.ct.data %>% dplyr::select(homeTeamId, onCtHomeId2, season) %>% dplyr::rename(playerId = onCtHomeId2, teamId = homeTeamId),
    on.ct.data %>% dplyr::select(homeTeamId, onCtHomeId3, season) %>% dplyr::rename(playerId = onCtHomeId3, teamId = homeTeamId),
    on.ct.data %>% dplyr::select(homeTeamId, onCtHomeId4, season) %>% dplyr::rename(playerId = onCtHomeId4, teamId = homeTeamId),
    on.ct.data %>% dplyr::select(homeTeamId, onCtHomeId5, season) %>% dplyr::rename(playerId = onCtHomeId5, teamId = homeTeamId),
    on.ct.data %>% dplyr::select(awayTeamId, onCtAwayId1, season) %>% dplyr::rename(playerId = onCtAwayId1, teamId = awayTeamId),
    on.ct.data %>% dplyr::select(awayTeamId, onCtAwayId2, season) %>% dplyr::rename(playerId = onCtAwayId2, teamId = awayTeamId),
    on.ct.data %>% dplyr::select(awayTeamId, onCtAwayId3, season) %>% dplyr::rename(playerId = onCtAwayId3, teamId = awayTeamId),
    on.ct.data %>% dplyr::select(awayTeamId, onCtAwayId4, season) %>% dplyr::rename(playerId = onCtAwayId4, teamId = awayTeamId),
    on.ct.data %>% dplyr::select(awayTeamId, onCtAwayId5, season) %>% dplyr::rename(playerId = onCtAwayId5, teamId = awayTeamId)) %>%
    dplyr::distinct(teamId, playerId, season) %>%
    dplyr::filter(!is.na(playerId))

  # For Each Player-Season, Compute Number Of Games On Court at each minute in game - this is the bad Apply
  playing.time.breakdowns <- apply(X = all.player.season.apperances, MARGIN = 1, FUN = function(thisRow) {

    # Set Player / Season Variables
    thisPlayerId = thisRow[2]
    thisSeason = thisRow[3]

    # Filter for each unique minute of each game with this player on court
    on.court.df = on.ct.data %>% 
      dplyr::filter(onCtHomeId1 == thisPlayerId | onCtHomeId2 == thisPlayerId | onCtHomeId3 == thisPlayerId | onCtHomeId4 == thisPlayerId | onCtHomeId5 == thisPlayerId |
                      onCtAwayId1 == thisPlayerId | onCtAwayId2 == thisPlayerId | onCtAwayId3 == thisPlayerId | onCtAwayId4 == thisPlayerId | onCtAwayId5 == thisPlayerId) %>%
      dplyr::filter(season == thisSeason) %>%
      dplyr::filter(!duplicated(paste0(gameId, minNumIntoGame)))

    # Turn This Into a table of minutes on court by game
    thisTable <- table(on.court.df$minNumIntoGame)

    this.player.distrubution.df <- data.frame(
      playerId = thisRow[2],
      teamId = thisRow[1],
      season = thisRow[3],
      minNumIntoGame = as.integer(names(thisTable)),
      numGamesAtMinNum = unname(thisTable) %>% as.vector(),
      stringsAsFactors = FALSE
    )

    # 40 minutes in basketball game, so previous dataframe needs 40 rows
    if(length(which(!(1:40 %in% this.player.distrubution.df$minNumIntoGame))) > 0) {
      zero.mins.played.df <- data.frame(
        playerId = thisRow[2],
        teamId = thisRow[1],
        season = thisRow[3],
        minNumIntoGame = which(!(1:40 %in% this.player.distrubution.df$minNumIntoGame)),
        numGamesAtMinNum = 0,
        stringsAsFactors = FALSE
      )

      this.player.distrubution.df <- plyr::rbind.fill(this.player.distrubution.df, zero.mins.played.df) %>% dplyr::arrange(minNumIntoGame)
    }

    # and return
    return(this.player.distrubution.df)
  })

  # Combine the output into one dataframe
  playing.time.breakdowns <- playing.time.breakdowns %>% do.call("rbind", .)

  # Join on Team-Games played
  playing.time.breakdowns <- playing.time.breakdowns %>%
    dplyr::left_join(num.team.games, by = c("teamId"="teamId", "season"="season")) %>%
    dplyr::rename(teamGamesPlayed = gamesPlayed)

  # Compute pct of games played
  playing.time.breakdowns <- playing.time.breakdowns %>%
    dplyr::mutate(pctMinNumPlayed = round(numGamesAtMinNum / teamGamesPlayed, 3))

  # Handle OT (minNumIntoGame > 40) needs a lower gamesPlayed denominator...

  # And Return
  return(playing.time.breakdowns);
}
on.ct.by.min <- computeOnCourtByMinutePcts(on.ct.data)

库（dplyr）
#原始数据是逐场数据-每行包含一个pl（5名篮球运动员的组合）的统计数据
工作表\u url%
dplyr:：mutate（gamesPlayed=rowSums（cbind（count.x，count.y），na.rm=TRUE））%>%
dplyr:：重命名（teamId=homeTeamId）%>%
dplyr:：mutate（seasure=as.character（seasure））%>%
dplyr:：选择（团队ID、季节、游戏显示）
#按赛季为球员创建数据框——看起来也有点笨重
all.player.seasure.appearances%dplyr:：select（homeTeamId，onCtHomeId1，seasure）%%>%dplyr:：rename（playerId=onCtHomeId1，teamId=homeTeamId），
on.ct.data%>%dplyr:：select（homeTeamId，onCtHomeId2，seasure）%>%dplyr:：rename（playerId=onCtHomeId2，teamId=homeTeamId），
on.ct.data%>%dplyr:：select（homeTeamId，onCtHomeId3，seasure）%>%dplyr:：rename（playerId=onCtHomeId3，teamId=homeTeamId），
on.ct.data%>%dplyr:：select（homeTeamId，onCtHomeId4，seasure）%>%dplyr:：rename（playerId=onCtHomeId4，teamId=homeTeamId），
on.ct.data%>%dplyr:：select（homeTeamId，onCtHomeId5，seasure）%>%dplyr:：rename（playerId=onCtHomeId5，teamId=homeTeamId），
on.ct.data%>%dplyr:：select（awayTeamId，onctayedid1，seash）%>%dplyr:：rename（playerId=onctayedid1，teamId=awayTeamId），
on.ct.data%>%dplyr:：select（awayTeamId，onCtAwayId2，seash）%>%dplyr:：rename（playerId=onCtAwayId2，teamId=awayTeamId），
on.ct.data%>%dplyr:：select（awayTeamId，onCtAwayId3，seash）%>%dplyr:：rename（playerId=onCtAwayId3，teamId=awayTeamId），
on.ct.data%>%dplyr:：select（awayTeamId，onctayedid4，seasure）%>%dplyr:：rename（playerId=onctayedid4，teamId=awayTeamId），
on.ct.data%%>%dplyr:：select（awayTeamId，onctayedid5，seash）%%>%dplyr:：rename（playerId=onctayedid5，teamId=awayTeamId））%%>%
dplyr:：独特的（球队ID、球员ID、赛季）%>%
dplyr:：过滤器（！is.na（playerId））
#对于每个球员赛季，计算比赛中每分钟在场上的比赛次数——这是最糟糕的
播放.time.breakdowns%
dplyr:：filter（onCtHomeId1==thisPlayerId | onCtHomeId2==thisPlayerId | onCtHomeId3==thisPlayerId | onCtHomeId4==thisPlayerId | onCtHomeId5==thisPlayerId|
onCtAwayId1==thisPlayerId | onCtAwayId2==thisPlayerId | onCtAwayId3==thisPlayerId | onCtAwayId4==thisPlayerId | onCtAwayId5==thisPlayerId）%>%
dplyr:：筛选器（季节==此季节）%>%
dplyr:：筛选器（！已复制（paste0（gameId，MinnuminToName）））
#把这变成场上比赛的分钟表
（表0）{
0.mins.played.df%
dplyr:：重命名（teamGamesPlayed=gamesPlayed）
#计算所玩游戏的pct
播放.time.breakdowns%
dplyr:：mutate（pctMinNumPlayed=round（numGamesAtMinNum/teamGamesPlayed，3））
#句柄OT（Minnumitogame>40）需要较低的游戏显示分母。。。
#返回
返回（播放、时间、故障）；
}
on.ct.by.min我认为可以更简单地通过将数据转换为长格式和计算球员-分钟-团队-赛季组合来实现这一点。（从2008年开始，在这台旧电脑上运行大约需要5秒钟，这是大部分计算。）

库（tidyverse）
on.ct.data%>%
聚集（点、名称、onCtHomeId1:onCtAwayId5）%>%
变异（团队=如果其他（点%>%str）检测（“离开”），
awayTeamId，homeTeamId））%>%
选择（-spot）%>%#对于这部分，我只关心人和比赛时间。
distinct（）%>%#删除在一分钟内重新定位的重复和实例。
下拉菜单（）%>%
选择（-c（游戏ID:awayTeamId））%>%
计数（明尼苏达州名称、姓名、球队、赛季）
#A tibble:140581 x 5
明尼苏达州名称球队第n季
1 AahmaneSantos387c JAC 1819 1
2 1阿米尔西姆塞夫9克莱姆1819 13
3 1 AarenEdmead9cd6 NCAT 1718 1
4 AarenEdmead9cd6 NCAT 1819 1
5 1 AaronBrennanbee2 IUPU 1718 1
6 1 Aaroncalixte11d俄克拉荷马州1819 11
7 1 AaronCarver9cfa ODU 1819 2
8 1 AaronClarke3d67 SHU 1819 1
9 1 AaronFalzon213b西北1718 1
10 1加州大学洛杉矶分校奥隆假日酒店1718 11

现在我们有了这些，我们可以检查每个团队的游戏世界是什么样子的。在每个赛季的几场比赛中，每支球队每分钟踢多少场

on.ct.data.team.minutes <- on.ct.data.minute.counts %>%
  count(season, team, minNumIntoGame, gameId) %>%  
  count(season, team, minNumIntoGame) 

ggplot(on.ct.data.team.minutes %>% slice(1:1000),
       aes(minNumIntoGame, team, fill = n)) + 
  geom_tile() + facet_wrap(~season) + 
  labs(title = "# times each team played each minute (excerpt)")

on.ct.data.team.minutes%
计数（季节、团队、明尼苏达州比赛、玩家ID）%>%
计数（赛季、团队、明尼苏达州比赛）
ggplot（在.ct.data.team.minutes%>%切片上（1:1000），
aes（Minnumitogame，team，fill=n））+
geom_瓷砖（）+镶嵌面_包裹（~季节）+
实验室（title=“#每队每分钟比赛次数（节选）”）


…我们可以对每个球员做同样的事情，并与他们的球队进行比较，看看他们在每一分钟为他们的球队踢了多少球

# How many games each season did each player play a given minute for each team?
on.ct.data.player.minutes <- on.ct.data.minute.counts %>%
  count(season, team, name, minNumIntoGame) %>%
  rename(player_n = n) %>%
  left_join(on.ct.data.team.minutes) %>%
  rename(team_n = n) %>% 
  mutate(player_time = player_n / team_n)

ggplot(on.ct.data.player.minutes %>% filter(name %>% str_detect("Can")),
       aes(minNumIntoGame, player_time, color = name)) +
  geom_line() + facet_wrap(~season) +
  scale_y_continuous(labels = scales::percent_format(accuracy = 1))

#每个赛季有多少场比赛
# How many games each season did each player play a given minute for each team?
on.ct.data.player.minutes <- on.ct.data.minute.counts %>%
  count(season, team, name, minNumIntoGame) %>%
  rename(player_n = n) %>%
  left_join(on.ct.data.team.minutes) %>%
  rename(team_n = n) %>% 
  mutate(player_time = player_n / team_n)

ggplot(on.ct.data.player.minutes %>% filter(name %>% str_detect("Can")),
       aes(minNumIntoGame, player_time, color = name)) +
  geom_line() + facet_wrap(~season) +
  scale_y_continuous(labels = scales::percent_format(accuracy = 1))