top nba single game scorers

assists.csv

assists.r

# NBA single-game assists leaders (Tufte-style).
# Data: nba_assists.csv from Wikipedia
#   https://en.wikipedia.org/wiki/List_of_NBA_single-game_assists_leaders
#   (22+ assists in a game; includes marked playoff games in CSV.)

library(ggplot2)
library(dplyr)
library(ggtext)
library(ggrepel)

df <- read.csv("nba_assists.csv", stringsAsFactors = FALSE)

counts_tbl <- df |>
  count(player, name = "games", sort = TRUE)

total_games <- nrow(df)
unique_players <- n_distinct(df$player)

cat("\n=== NBA assists CSV summary ===\n")
cat("Total games (rows): ", total_games, "\n", sep = "")
cat("Unique players: ", unique_players, "\n\n", sep = "")
cat("Top players by game count:\n")
print(utils::head(counts_tbl, 15), row.names = FALSE)
cat("\nTop 5 (strict rows 1–5):\n")
print(utils::head(counts_tbl, 5), row.names = FALSE)
if (nrow(counts_tbl) >= 6 && counts_tbl$games[6] == counts_tbl$games[5]) {
  cat("\nTied at rank 5 (same count as row 5):\n")
  tie_n <- counts_tbl$games[5]
  print(counts_tbl[counts_tbl$games == tie_n, ], row.names = FALSE)
}
cat("\n")

# Top three by volume; everyone else gray (Rondo, Westbrook, etc.).
# Distinct hues (avoid dark purple vs dark red): Stockton — Jazz green;
# Porter — bright Pistons red; Magic — Lakers purple.
star_players <- c(
  "John Stockton",
  "Kevin Porter",
  "Magic Johnson"
)

df <- df |>
  mutate(
    highlight_player = if_else(player %in% star_players, player, "Others"),
    highlight_player = factor(
      highlight_player,
      levels = c(star_players, "Others")
    )
  )

set.seed(42)
j_x <- 0.45
df <- df |>
  mutate(
    year_j = year + runif(n(), -j_x, j_x),
    assists_j = assists
  )

star_colors <- c(
  "John Stockton"  = "#00471B",
  "Kevin Porter"   = "#E31837",
  "Magic Johnson"  = "#552583",
  "Others"         = "#999999"
)

star_short <- c(
  "John Stockton" = "Stockton",
  "Kevin Porter"  = "Porter",
  "Magic Johnson" = "Johnson"
)

subtitle_md <- paste(
  vapply(star_players, function(sp) {
    sprintf(
      "<span style='color:%s'>%s %d</span>",
      unname(star_colors[sp]),
      unname(star_short[sp]),
      sum(df$player == sp)
    )
  }, character(1)),
  collapse = ", "
)

ymin <- 21.5  # pad so 22 tick sits cleanly; record label sits below y = 30
ymax <- max(df$assists) + 0.5

record_pt <- df |>
  slice_max(assists, n = 1, with_ties = FALSE)

p <- ggplot(df, aes(year_j, assists_j)) +
  geom_hline(
    yintercept = 22,
    linetype = "dotted",
    linewidth = 0.35,
    alpha = 0.55,
    colour = "#999999"
  ) +
  geom_point(aes(colour = highlight_player), size = 4.2, stroke = 0, alpha = 0.9) +
  ggrepel::geom_text_repel(
    data = record_pt,
    aes(label = player),
    family = "Palatino",
    size = 3.4,
    colour = "#333333",
    min.segment.length = 0,
    segment.colour = "#999999",
    segment.size = 0.35,
    box.padding = 0.35,
    point.padding = 0.35,
    nudge_y = -0.75,
    seed = 42
  ) +
  scale_colour_manual(values = star_colors) +
  guides(colour = "none") +
  scale_x_continuous(
    breaks = seq(floor(min(df$year) / 10) * 10, ceiling(max(df$year) / 10) * 10, by = 10),
    expand = expansion(mult = 0.02)
  ) +
  scale_y_continuous(
    limits = c(ymin, ymax),
    breaks = seq(22, floor(ymax), by = 1),
    expand = expansion(mult = 0.02)
  ) +
  labs(
    title = "Single-game NBA performances: 22+ player assists",
    subtitle = subtitle_md,
    x = "Year",
    y = "Assists",
    caption = "data wikipedia by @iamreddave"
  ) +
  coord_cartesian(clip = "on") +
  theme_minimal(base_size = 12, base_family = "Palatino") +
  theme(
    plot.background = element_rect(fill = "#fffff8", colour = NA),
    panel.background = element_rect(fill = "#fffff8", colour = NA),
    panel.grid.major.x = element_blank(),
    panel.grid.minor = element_blank(),
    panel.grid.major.y = element_line(colour = "#00000014", linewidth = 0.35),
    panel.border = element_blank(),
    axis.line.x.bottom = element_line(colour = "#cccccc", linewidth = 0.5),
    axis.line.y.left = element_line(colour = "#cccccc", linewidth = 0.5),
    axis.line.x.top = element_blank(),
    axis.line.y.right = element_blank(),
    axis.ticks.x.bottom = element_line(colour = "#bbbbbb", linewidth = 0.45),
    axis.ticks.y.left = element_line(colour = "#bbbbbb", linewidth = 0.45),
    axis.ticks.length = grid::unit(5.5, "pt"),
    plot.title = element_text(face = "bold", size = 15, colour = "#111111", margin = margin(b = 4)),
    plot.subtitle = element_markdown(
      size = 9,
      colour = "#555555",
      lineheight = 1.25,
      margin = margin(b = 10),
      family = "Palatino"
    ),
    plot.caption = element_text(hjust = 0, size = 8, colour = "#666666", margin = margin(t = 10)),
    axis.title = element_text(colour = "#333333"),
    axis.text = element_text(colour = "#444444"),
    plot.margin = margin(16, 24, 12, 16)
  )

print(p)

ggsave(
  "nba_assists_tufte.png",
  plot = p,
  width = 10,
  height = 6.67,
  dpi = 200,
  bg = "#fffff8"
)

nba_60plus.csv

rebound.r

# NBA rebounding leaders scatter (Tufte-style).
# Data: nba_rebounds.csv from Wikipedia
#   https://en.wikipedia.org/wiki/List_of_NBA_single-game_rebounding_leaders
#   — Table 1: 38+ rebounds in a game (all-time)
#   — Table 2: 30+ rebounds since NBA/ABA merger (1976)

library(ggplot2)
library(dplyr)
library(ggtext)

df <- read.csv("nba_rebounds.csv", stringsAsFactors = FALSE)

# --- Summary: top 5 by appearances (ties at rank 5 reported) ---
counts_tbl <- df |>
  count(player, name = "games", sort = TRUE)

total_games <- nrow(df)
unique_players <- n_distinct(df$player)

cat("\n=== NBA rebound CSV summary ===\n")
cat("Total games (rows): ", total_games, "\n", sep = "")
cat("Unique players: ", unique_players, "\n\n", sep = "")
cat("Top players by game count:\n")
print(utils::head(counts_tbl, 15), row.names = FALSE)
cat("\nTop 5 (strict rows 1–5):\n")
print(utils::head(counts_tbl, 5), row.names = FALSE)
if (nrow(counts_tbl) >= 6 && counts_tbl$games[6] == counts_tbl$games[5]) {
  cat("\nTied at rank 5 (same count as row 5):\n")
  tie_n <- counts_tbl$games[5]
  print(counts_tbl[counts_tbl$games == tie_n, ], row.names = FALSE)
}
cat("\n")

# Highlight only the three clear leaders (Nater / Malone / Willis stay gray).
# Jersey cues: Chamberlain — Warriors/Lakers gold; Russell — Celtics green;
# Rodman — Bulls red (his most iconic look).
star_players <- c(
  "Wilt Chamberlain",
  "Bill Russell",
  "Dennis Rodman"
)

df <- df |>
  mutate(
    highlight_player = if_else(player %in% star_players, player, "Others"),
    highlight_player = factor(
      highlight_player,
      levels = c(star_players, "Others")
    )
  )

set.seed(42)
j_x <- 0.55
df <- df |>
  mutate(
    year_j = year + runif(n(), -j_x, j_x),
    rebounds_j = rebounds
  )

star_colors <- c(
  "Wilt Chamberlain" = "#FDB927",
  "Bill Russell"     = "#007A33",
  "Dennis Rodman"    = "#CE1141",
  "Others"           = "#999999"
)

star_short <- c(
  "Wilt Chamberlain" = "Chamberlain",
  "Bill Russell"     = "Russell",
  "Dennis Rodman"    = "Rodman"
)

subtitle_md <- paste(
  vapply(star_players, function(sp) {
    sprintf(
      "<span style='color:%s'>%s %d</span>",
      unname(star_colors[sp]),
      unname(star_short[sp]),
      sum(df$player == sp)
    )
  }, character(1)),
  collapse = ", "
)

ymin <- floor(min(df$rebounds) / 5) * 5
ymax <- ceiling(max(df$rebounds) / 5) * 5

p <- ggplot(df, aes(year_j, rebounds_j)) +
  geom_point(aes(colour = highlight_player), size = 4.2, stroke = 0, alpha = 0.9) +
  scale_colour_manual(values = star_colors) +
  guides(colour = "none") +
  scale_x_continuous(
    breaks = seq(floor(min(df$year) / 10) * 10, ceiling(max(df$year) / 10) * 10, by = 10),
    expand = expansion(mult = 0.02)
  ) +
  scale_y_continuous(
    breaks = seq(ymin, ymax, by = 5),
    expand = expansion(mult = 0.03)
  ) +
  labs(
    title = "NBA single-game rebounding leaders",
    subtitle = subtitle_md,
    x = "Year",
    y = "Rebounds",
    caption = "data:wikipedia by @iamreddave"
  ) +
  coord_cartesian(clip = "on") +
  theme_minimal(base_size = 12, base_family = "Palatino") +
  theme(
    plot.background = element_rect(fill = "#fffff8", colour = NA),
    panel.background = element_rect(fill = "#fffff8", colour = NA),
    panel.grid.major.x = element_blank(),
    panel.grid.minor = element_blank(),
    panel.grid.major.y = element_line(colour = "#00000014", linewidth = 0.35),
    panel.border = element_blank(),
    axis.line.x.bottom = element_line(colour = "#cccccc", linewidth = 0.5),
    axis.line.y.left = element_line(colour = "#cccccc", linewidth = 0.5),
    axis.line.x.top = element_blank(),
    axis.line.y.right = element_blank(),
    axis.ticks.x.bottom = element_line(colour = "#bbbbbb", linewidth = 0.45),
    axis.ticks.y.left = element_blank(),
    axis.ticks.length = grid::unit(5.5, "pt"),
    plot.title = element_text(face = "bold", size = 15, colour = "#111111", margin = margin(b = 4)),
    plot.subtitle = element_markdown(
      size = 9,
      colour = "#555555",
      lineheight = 1.25,
      margin = margin(b = 10),
      family = "Palatino"
    ),
    plot.caption = element_text(hjust = 0, size = 8, colour = "#666666", margin = margin(t = 10)),
    axis.title = element_text(colour = "#333333"),
    axis.text = element_text(colour = "#444444"),
    plot.margin = margin(16, 24, 12, 16)
  )

print(p)

ggsave(
  "nba_rebounds_tufte.png",
  plot = p,
  width = 10,
  height = 6.67,
  dpi = 200,
  bg = "#fffff8"
)

rebounds.csv

scorer.r

library(ggplot2)
library(dplyr)
library(ggtext)
library(ggrepel)

df <- read.csv("nba_60plus.csv", stringsAsFactors = FALSE)

star_players <- c(
  "Wilt Chamberlain",
  "Kobe Bryant",
  "Damian Lillard",
  "Michael Jordan",
  "James Harden",
  "Elgin Baylor"
)

df <- df |>
  mutate(
    highlight_player = case_when(
      player == "Wilt Chamberlain" ~ "Wilt Chamberlain",
      player == "Kobe Bryant"      ~ "Kobe Bryant",
      player == "Damian Lillard"   ~ "Damian Lillard",
      player == "Michael Jordan"   ~ "Michael Jordan",
      player == "James Harden"     ~ "James Harden",
      player == "Elgin Baylor"     ~ "Elgin Baylor",
      TRUE                         ~ "Others"
    ),
    highlight_player = factor(highlight_player, levels = c(star_players, "Others"))
  )

# Horizontal jitter only: dot *centers* sit on true scores (y = points).
# Vertical jitter made e.g. the 100-pt game sit below the 100 gridline — ggplot
# always centers points on (x, y), never "top edge on value".
set.seed(42)
j_x <- 0.55
df <- df |>
  mutate(
    year_j = year + runif(n(), -j_x, j_x),
    points_j = points
  ) |>
  # Two 1987 MJ 61-pt rows: offset after jitter (L/up, R/down)
  group_by(year, points, player) |>
  mutate(
    mj_twin = if_else(
      player == "Michael Jordan" & points == 61 & year == 1987 & n() == 2,
      row_number(),
      NA_integer_
    )
  ) |>
  ungroup() |>
  mutate(
    year_j = case_when(
      mj_twin == 1L ~ year_j - 0.2,
      mj_twin == 2L ~ year_j + 0.2,
      TRUE ~ year_j
    ),
    points_j = case_when(
      mj_twin == 1L ~ points_j + 0.2,
      mj_twin == 2L ~ points_j - 0.2,
      TRUE ~ points_j
    )
  ) |>
  select(-mj_twin)

# Team-leaning colors for highlighted stars (+ gray Others). Baylor: Lakers-era navy.
star_colors <- c(
  "Wilt Chamberlain" = "#E6B800",
  "Kobe Bryant"      = "#552583",
  "Michael Jordan"   = "#CE1141",
  "James Harden"     = "#76b7b2",
  "Damian Lillard"   = "#1a1a1a",
  "Elgin Baylor"     = "#1c2e50",
  "Others"           = "#888888"
)

star_short <- c(
  "Wilt Chamberlain" = "Chamberlain",
  "Kobe Bryant"      = "Bryant",
  "Damian Lillard"   = "Lillard",
  "Michael Jordan"   = "Jordan",
  "James Harden"     = "Harden",
  "Elgin Baylor"     = "Baylor"
)

label_df <- df |>
  filter(player == "Bam Adebayo", points == 83) |>
  mutate(label = "Bam Adebayo")

subtitle_md <- paste(
  vapply(star_players, function(sp) {
    sprintf(
      "<span style='color:%s'>%s %d</span>",
      unname(star_colors[sp]),
      unname(star_short[sp]),
      sum(df$player == sp)
    )
  }, character(1)),
  collapse = ", "
)

p <- ggplot(df, aes(year_j, points_j)) +
  geom_hline(
    yintercept = 60,
    linetype = "dotted",
    linewidth = 0.35,
    alpha = 0.55,
    colour = "#999999"
  ) +
  geom_point(aes(colour = highlight_player), size = 4.8, stroke = 0, alpha = 0.92) +
  scale_colour_manual(values = star_colors) +
  guides(colour = "none") +
  geom_text_repel(
    data = label_df,
    aes(label = label),
    size = 3.4,
    family = "Palatino",
    colour = "#111111",
    min.segment.length = 0,
    box.padding = 0.45,
    max.overlaps = Inf,
    segment.color = "#666666",
    segment.size = 0.3,
    point.padding = 0
  ) +
  # Anchor speculative-era games at 2026; omit 2030 tick to avoid implying real timeline
  scale_x_continuous(
    breaks = c(seq(1950, 2020, by = 10), 2026),
    expand = expansion(mult = c(0.02, 0.12))
  ) +
  scale_y_continuous(
    breaks = seq(60, 100, by = 10),
    expand = expansion(mult = 0.03)
  ) +
  labs(
    title = "NBA games with 60 or more points",
    subtitle = subtitle_md,
    x = "Year",
    y = "Points scored",
    caption = "data: wikipedia by @iamreddave"
  ) +
  coord_cartesian(clip = "off") +
  theme_minimal(base_size = 12, base_family = "Palatino") +
  theme(
    plot.background = element_rect(fill = "#fffff8", colour = NA),
    panel.background = element_rect(fill = "#fffff8", colour = NA),
    panel.grid.major.x = element_blank(),
    panel.grid.minor = element_blank(),
    panel.grid.major.y = element_line(colour = "#00000014", linewidth = 0.35),
    panel.border = element_blank(),
    axis.line.x.bottom = element_line(colour = "#cccccc", linewidth = 0.5),
    axis.line.y.left = element_line(colour = "#cccccc", linewidth = 0.5),
    axis.line.x.top = element_blank(),
    axis.line.y.right = element_blank(),
    axis.ticks.x.bottom = element_line(colour = "#bbbbbb", linewidth = 0.45),
    axis.ticks.y.left = element_blank(),
    axis.ticks.length = grid::unit(5.5, "pt"),
    plot.title = element_text(
      face = "bold",
      size = 15,
      colour = "#111111",
      margin = margin(b = 4)
    ),
    plot.subtitle = element_markdown(
      size = 9.5,
      colour = "#555555",
      lineheight = 1.2,
      margin = margin(b = 10),
      family = "Palatino"
    ),
    plot.caption = element_text(
      hjust = 1,
      size = 9,
      colour = "#666666",
      margin = margin(t = 10)
    ),
    axis.title = element_text(colour = "#333333"),
    axis.text = element_text(colour = "#444444"),
    plot.margin = margin(16, 36, 12, 16)
  )

print(p)

# Tufte-style PNG; Bam Adebayo labeled (name only), segment to jittered point
ggsave(
  "nba_60plus_tufte.png",
  plot = p,
  width = 10,
  height = 6.67,
  dpi = 200,
  bg = "#fffff8"
)