NBA Lineup Data
A preliminary visual investigation using data of the relationship between the performance of NBA lineups and the players within them.
Getting NBA Data
The pages at stats.nba.com are backed by a great set of json APIs, making it easy to work with their data. They have an extensive stats for lineups, players, and a lot more.
Some Libraries Weโll Need
library(rjson)
library(dplyr)
Getting data from stats.nba.com into R
I used the rjson library to download the json and convert it into an R data frame. The following helper function, given a url, the number of columns, and a list of numeric columns, will fetch the json, convert the data into a matrix, then convert it into a data frame.
df_from_url = function(url, ncol, number_columns) {
json = fromJSON(file = url, method = "C")
df = data.frame(matrix(unlist(json$resultSets[[1]][[3]]), ncol = ncol, byrow = TRUE),
stringsAsFactors = FALSE)
colnames(df) = json$resultSets[[1]][[2]]
df[, number_columns] = apply(df[, number_columns], 2, function(x) as.numeric(as.character(x)))
return(df)
}
Some Setup
Years
The APIs take seasons as strings, so we need to convert from the years in question to the formatted season strings. 2007 is the first year for which they have lineup data.
years = sapply(2007:2015, function(year) sprintf("%4d-%02d", year, (year + 1)%%100))
Team Ids
This is absolute overkill, because none of the team ids have changed over the year range weโre interested in, but I didnโt know that for sure until after Iโd ran it.
team_fmt = "http://stats.nba.com/stats/leaguedashteamstats?Conference=&DateFrom=&DateTo=&Division=&GameScope=&GameSegment=&LastNGames=0&LeagueID=00&Location=&MeasureType=Base&Month=0&OpponentTeamID=0&Outcome=&PORound=0&PaceAdjust=N&PerMode=Per100Plays&Period=0&PlayerExperience=&PlayerPosition=&PlusMinus=N&Rank=N&Season=%s&SeasonSegment=&SeasonType=Regular+Season&ShotClockRange=&StarterBench=&TeamID=0&VsConference=&VsDivision="
team_urls = sapply(years, function(year) sprintf(team_fmt, year))
team_dfs = sapply(team_urls, function(url) df_from_url(url, 30, c(1, 3:29)))
team_ids = Reduce(union, team_dfs[1, ])
Player Data
First, we download the player data. Weโll loop over the years and NBA stat collections, and then combine all the data together with merge and rbind into one big data frame. We request stats per 100 plays, but the API seems to intelligently determine when to respect that.
columns = c(35, 32, 24, 27, 30)
stat_types = c("Base", "Advanced", "Misc", "Scoring", "Usage")
player_fmt = "http://stats.nba.com/stats/leaguedashplayerstats?College=&Conference=&Country=&DateFrom=&DateTo=&Division=&DraftPick=&DraftYear=&GameScope=&GameSegment=&Height=&LastNGames=0&LeagueID=00&Location=&MeasureType=%s&Month=0&OpponentTeamID=0&Outcome=&PORound=0&PaceAdjust=N&PerMode=Per100Plays&Period=0&PlayerExperience=&PlayerPosition=&PlusMinus=N&Rank=N&Season=%s&SeasonSegment=&SeasonType=Regular+Season&ShotClockRange=&StarterBench=&TeamID=0&VsConference=&VsDivision=&Weight="
players = NULL
for (year in years) {
season_df = NULL
for (i in 1:length(stat_types)) {
stat_type = stat_types[i]
c = columns[i]
numeric_columns = c(1, 3, 5:(c - 1))
url = sprintf(player_fmt, stat_type, year)
df = df_from_url(url, c, numeric_columns)
if (is.null(season_df)) {
season_df = df
} else {
season_df = merge(season_df, df, by = 1, all.x = TRUE, suffixes = c("",
sprintf("_%s", stat_type)))
}
}
season_df$SEASON = factor(year)
if (is.null(players)) {
players = season_df
} else {
players = rbind(players, season_df)
}
}
Lineup Data
Fetching lineup data is similar; however, the API is limited to 250 entries per response, so we loop through the years, teams, and stat groups. This results in well over a thousand API calls, and can take a very long time to run.
stat_types = c("Base", "Advanced", "Four+Factors", "Misc", "Scoring", "Opponent")
columns = c(31, 24, 18, 18, 25, 31)
lineup_fmt = "http://stats.nba.com/stats/leaguedashlineups?Conference=&DateFrom=&DateTo=&Division=&GameID=&GameSegment=&GroupQuantity=5&LastNGames=0&LeagueID=00&Location=&MeasureType=%s&Month=0&OpponentTeamID=0&Outcome=&PORound=0&PaceAdjust=N&PerMode=Per100Plays&Period=0&PlusMinus=N&Rank=N&Season=%s&SeasonSegment=&SeasonType=Regular+Season&ShotClockRange=&TeamID=%d&VsConference=&VsDivision="
lineups = NULL
for (year in years) {
for (team in team_ids) {
season_df = NULL
for (i in 1:length(stat_types)) {
stat_type = stat_types[i]
c = columns[i]
numeric_columns = c(4, 6:c)
url = sprintf(lineup_fmt, stat_type, year, team)
df = df_from_url(url, c, numeric_columns)
if (is.null(season_df)) {
season_df = df
} else {
season_df = merge(season_df, df, by = 2, all.x = TRUE, suffixes = c("",
sprintf("_%s", stat_type)))
}
}
season_df$SEASON = factor(year)
if (is.null(lineups)) {
lineups = season_df
} else {
lineups = rbind(lineups, season_df)
}
}
}
Player Cleanup
The API treats minutes differently depending upon the stat group requested. Advanced appears to return minutes per game while Usage returns total minutes. We rename these appropriately.
players = mutate(players, MIN_TOTAL = MIN_Usage, MIN_GAME = MIN_Advanced)
players = select(players, -X, -matches("CFID|CFPARAMS|_[A-Z][a-z]", FALSE))
Lineup Cleanup
For lineups, however, Advanced seems to return the total minutes. Once again, we rename the column.
lineups = tbl_df(lineups)
lineups = mutate(lineups, MIN_TOTAL = MIN_Advanced)
lineups = select(lineups, -X, -matches("GROUP_SET|CFID|CFPARAMS|_[A-Z][a-z]", FALSE))
lineups = Filter(function(x) !all(is.na(x)), lineups)
Identifying players
To match the lineup data to the player data, we need to identify the players in each lineup. Parsing the GROUP_ID allows us to do that.
lineups$PLAYERS = t(sapply(lineups$GROUP_ID, function(x) {
as.integer(unlist(strsplit(as.character(x), split = " - ")))
}))
Calculating Player Averages for a Lineup
For a given lineup, we find the stats for the players in the lineup and average them. For some stats, this makes sense. For others, it wonโt. In many cases, weโll be more interested in the sum, but we can get that later by multiplying by 5.
season_col = grep("SEASON", colnames(lineups))
player_col = grep("PLAYERS", colnames(lineups))
numeric_player_columns = as.vector(which(sapply(players, is.numeric)))
lineup_averages = data.frame(t(apply(lineups, 1, function(x) {
srows = players$SEASON == x[season_col]
prows = players$PLAYER_ID %in% as.numeric(x[player_col:player_col + 4])
sapply(players[srows & prows, numeric_player_columns], mean)
})))
Calculating Usage-Weighted Averages for a Lineup
We do something similar to calculate the usage-weighted averages for a lineup. This wonโt make any sense for most stats, but for many offensive stats, it should provide a more reasonable estimate than a straight average.
usg_weighted = data.frame(t(apply(lineups, 1, function(x) {
srows = players$SEASON == x[season_col]
prows = players$PLAYER_ID %in% as.numeric(x[player_col:player_col + 4])
stats = players[srows & prows, numeric_player_columns]
tot_usg = sum(stats$USG_PCT_PCT)
sapply(stats, function(y) sum(y * stats$USG_PCT_PCT)/tot_usg)
})))
Putting it all together
Finally, we add suffixes to our lineups, averages, and usage-weighted averages, and merge them all together into a gigantic data frame.
colnames(lineups) = paste(names(lineups), "lineup", sep = ".")
colnames(lineup_averages) = paste(names(lineup_averages), "player", sep = ".")
colnames(usg_weighted) = paste(names(usg_weighted), "usage", sep = ".")
nba = merge(merge(lineups, lineup_averages, by = 0), usg_weighted, by = 0)
nba$Row.names = NULL
nba$Row.names = NULL
dim(nba)
## [1] 66784 259
Net Rating
In the end, what we really care about is the Net Rating of lineups. Will our lineup score more points than their opponents? Itโs important to note stats.nba.com formulation of Net Rating (and hence Offensive Rating and Defensive Rating) for players is essentially scaled +/-, and is distinct from the Dean Oliver version of these stats.
It seems that the volume of 3 pointers made by a lineup doesnโt really depend upon the volume of 3 pointers taken by the players in that lineup. It may be that this is far more dependent on strategy, but this definitely needs more investigation.