How to transform a sequential string of chess moves into a vertical dataframe?

We can splot the move string with a regular expression. Here I've used stringr::str_match_all to capture each part of the moves.

dd$moves |>
  stringr::str_match_all(r"{(\d+)\.(\S+) (\S+)}") |>
  lapply(function(x) data.frame(move_id=as.numeric(x[,2]), white=x[,3], black=x[,4])) |> 
  Map(cbind.data.frame, game_id=dd$game_id, m=_) |>
  do.call("rbind", args=_)

which will return

   game_id m.move_id m.white m.black
1      101         1      e4      c5
2      101         2     Nf3      d6
3      101         3      d4    cxd4
4      101         4    Nxd4     Nf6
5      101         5     Nc3     Nc6
6      101         6     Bc4      e6
7      101         7     Be3     Be7
8      102         1      e3      c5
9      102         2     Nf3     Nc6

The main part is the regular expression r"{(\d+)\.(\S+) (\S+)}" which finds a number followed by a period, then tries to find two non-space-containing piece names with a space between them.

Here's a very inelegant answer using the stringr, dplyr, and tidyr libraries.

First we split the character vector of moves into data.frame per each move using str_split_fixed from stringr. Then we append these columns to the existing data.frame.

Next we reshape the data using dplyr and tidyr. First, we pivot the "move" columns from wide to long form data. Then we infer the color of the "move" by the order given above, as well as the number of the move by the number of movement columns.

Then we pivot the newly created movement data by color. From there, we modify the moves are recorded so that one "move" corresponds to one "turn" (aka a move of each color). Then we group by move number and game type, and do a small clean up from leftover null columns from our pivot.

Not the most elegant answer in the world but it works? Note you'll need to update the select and pivot_longer statements to reflect larger numbers of moves

#load libs
library(stringr)
library(dplyr)
library(tidyr)

#create sample data
chess = data.frame(
  game_id = c(101,102),
  moves = c("1.e4 2Nf3 d6 Nf6","1.e3 2Nf4 nc6 cxd4")
)

#split characters vectors to columns
moves = data.frame(str_split_fixed(chess$moves," ",Inf)) #returns a matrix by default so coerce to data.frame to make binding easier
chess = bind_cols(chess,moves) #bind the new data

#melt the data into long form
chess %>%
  select(game_id,X1:X4) %>% #here we avoid selecting the default col we don't need, BUT- BE SURE to updated X1:X4 per length of moves
  pivot_longer(cols = X1:X4,names_to="move_no") %>% #melt/pivot split columns to one column
  mutate(color = rep(c("white","black"),ncol(chess)-2)) %>% #infer color by every other move, infer length by n of movement columns
  pivot_wider(names_from=color,values_from=value) %>% #pivot moves by color wider
  mutate(move_no = sort(rep(c(1:(ncol(chess)-2)),2))) %>% #update move_no colum to be accurate, note we use sort to get the needed order of moves
  group_by(game_id,move_no) %>% 
  summarise(
    white = last(na.omit(white)), #last will return the last non NA value, getting us to a valid data.frame
    black = last(na.omit(black))
  )

with base R

Data

x <- "
game_id  | moves
101      | 1.e4 c5 2.Nf3 d6 3.d4 cxd4 4.Nxd4 Nf6 5.Nc3 Nc6 6.Bc4 e6 7.Be3 Be7 
102      | 1.e3 c5 2.Nf3 Nc6 3.d4 cxd4 4.Nxd4 Nf6 5.Nc3 e5 6.Ndb5 d6 
"
df <- read.table(textConnection(x) , header = T , sep = "|")

using fn function

fn <- function(df) {
  lst <- list()
  id <- 1 ; L <- 1
  clmn <- strsplit(trimws(df$moves) , "[. ]")
  for (i in clmn) {
    for (j in 1:(length(i) / 3)) {
      j <- 3*j - 2
      lst[[id]] <- c(df$game_id[[L]] , clmn[[L]][j:(j + 2)])
      id <- id + 1
    }
    L <- L + 1
  }
  lst
}
#===================================

df <- data.frame(do.call(rbind , fn(df)))
colnames(df) <- c("game_id" , "move_no" , "white" , "black")

Output

df
#>    game_id move_no white black
#> 1      101       1    e4    c5
#> 2      101       2   Nf3    d6
#> 3      101       3    d4  cxd4
#> 4      101       4  Nxd4   Nf6
#> 5      101       5   Nc3   Nc6
#> 6      101       6   Bc4    e6
#> 7      101       7   Be3   Be7
#> 8      102       1    e3    c5
#> 9      102       2   Nf3   Nc6
#> 10     102       3    d4  cxd4
#> 11     102       4  Nxd4   Nf6
#> 12     102       5   Nc3    e5
#> 13     102       6  Ndb5    d6

^{Created on 2022-06-16 by the reprex package (v2.0.1)}

dd <- tibble(
  game_id = c(101, 102),
  moves = c(
    "1.e4 c5 2.Nf3 d6 3.d4 cxd4 4.Nxd4 Nf6 5.Nc3 Nc6 6.Bc4 e6 7.Be3 Be7",
    "1.e3 c5 2.Nf3 Nc6 3.d4 cxd4 4.Nxd4 Nf6 5.Nc3 e5 6.Ndb5 d6"
  )
)

pattern <- r"{(\d+)\.(\S+) (\S+)}"
dd |>
  mutate(moves = str_extract_all(moves, pattern)) |>
  unnest(moves) |>
  mutate(
    move_no = str_replace(moves, pattern, "\\1"),
    white = str_replace(moves, pattern, "\\2"),
    black = str_replace(moves, pattern, "\\3")
  ) |>
  select(-moves)