library(stringr)
library(ggplot2)
player_names="tournamentinfo.txt"
data=readLines(player_names)
## Warning in readLines(player_names): incomplete final line found on
## 'tournamentinfo.txt'
data[1:22]
## [1] "-----------------------------------------------------------------------------------------"
## [2] " Pair | Player Name |Total|Round|Round|Round|Round|Round|Round|Round| "
## [3] " Num | USCF ID / Rtg (Pre->Post) | Pts | 1 | 2 | 3 | 4 | 5 | 6 | 7 | "
## [4] "-----------------------------------------------------------------------------------------"
## [5] " 1 | GARY HUA |6.0 |W 39|W 21|W 18|W 14|W 7|D 12|D 4|"
## [6] " ON | 15445895 / R: 1794 ->1817 |N:2 |W |B |W |B |W |B |W |"
## [7] "-----------------------------------------------------------------------------------------"
## [8] " 2 | DAKSHESH DARURI |6.0 |W 63|W 58|L 4|W 17|W 16|W 20|W 7|"
## [9] " MI | 14598900 / R: 1553 ->1663 |N:2 |B |W |B |W |B |W |B |"
## [10] "-----------------------------------------------------------------------------------------"
## [11] " 3 | ADITYA BAJAJ |6.0 |L 8|W 61|W 25|W 21|W 11|W 13|W 12|"
## [12] " MI | 14959604 / R: 1384 ->1640 |N:2 |W |B |W |B |W |B |W |"
## [13] "-----------------------------------------------------------------------------------------"
## [14] " 4 | PATRICK H SCHILLING |5.5 |W 23|D 28|W 2|W 26|D 5|W 19|D 1|"
## [15] " MI | 12616049 / R: 1716 ->1744 |N:2 |W |B |W |B |W |B |B |"
## [16] "-----------------------------------------------------------------------------------------"
## [17] " 5 | HANSHI ZUO |5.5 |W 45|W 37|D 12|D 13|D 4|W 14|W 17|"
## [18] " MI | 14601533 / R: 1655 ->1690 |N:2 |B |W |B |W |B |W |B |"
## [19] "-----------------------------------------------------------------------------------------"
## [20] " 6 | HANSEN SONG |5.0 |W 34|D 29|L 11|W 35|D 10|W 27|W 21|"
## [21] " OH | 15055204 / R: 1686 ->1687 |N:3 |W |B |W |B |B |W |B |"
## [22] "-----------------------------------------------------------------------------------------"
line_vector<-str_detect(data,"\\-----")
chess_data<-data[!line_vector]
chess_data<-chess_data[3:length(chess_data)]
chess_data<-str_split(chess_data,"\\|")
ext_data<-str_extract_all(chess_data,"[[:alpha:]-?[:alpha:] ?]{2,}")
## Warning in stri_extract_all_regex(string, pattern, simplify = simplify, :
## argument is not an atomic vector; coercing
names_loc<-str_detect(unlist(ext_data),"[[:alpha:]]{3,}")
names<-unlist(ext_data)[names_loc]
head(names)
## [1] " GARY HUA " " DAKSHESH DARURI "
## [3] " ADITYA BAJAJ " " PATRICK H SCHILLING "
## [5] " HANSHI ZUO " " HANSEN SONG "
state_loc<-str_detect(unlist(ext_data),"[[:alpha:]]{2}")
state<-unlist(ext_data)[(state_loc)&(!names_loc)]
head(state)
## [1] " ON " " MI " " MI " " MI " " MI " " OH "
num_data<-str_extract_all(chess_data,"\\d{1,}+\\.?.?")
## Warning in stri_extract_all_regex(string, pattern, simplify = simplify, :
## argument is not an atomic vector; coercing
pt_loc<-str_detect(unlist(num_data),"\\d\\.\\d")
Points<-unlist(num_data)[(pt_loc)]
head(Points)
## [1] "6.0" "6.0" "6.0" "5.5" "5.5" "5.0"
rtg_data<-str_extract_all(chess_data,"(( \\:)|(\\>))?.?\\d{1,}P*\\.?")
## Warning in stri_extract_all_regex(string, pattern, simplify = simplify, :
## argument is not an atomic vector; coercing
pre_loc<-str_detect(unlist(rtg_data),"\\b\\d{3,4}P?\\b")
post_loc<-str_detect(unlist(rtg_data),"\\>.?\\b\\d{3,4}P?\\b")
pre_rating<-unlist(rtg_data)[(pre_loc)&(!post_loc)]
pre_rating<-str_replace_all(pre_rating,"P","")
post_rating<-unlist(rtg_data)[post_loc]
post_rating<-str_replace_all(post_rating,"([>P])","")
head(pre_rating)
## [1] " 1794" " 1553" " 1384" " 1716" " 1655" " 1686"
head(post_rating)
## [1] "1817" "1663" "1640" "1744" "1690" "1687"
head(post_rating)
## [1] "1817" "1663" "1640" "1744" "1690" "1687"
game_data<-str_extract_all(chess_data,"[WDL]...\\d{1,2}")
## Warning in stri_extract_all_regex(string, pattern, simplify = simplify, :
## argument is not an atomic vector; coercing
game_data<-str_extract_all(game_data,"\\.?\\d{1,2}")
## Warning in stri_extract_all_regex(string, pattern, simplify = simplify, :
## argument is not an atomic vector; coercing
game_data<-str_replace_all(game_data,"\\b[0]\\b",".")
## Warning in stri_replace_all_regex(string, pattern,
## fix_replacement(replacement), : argument is not an atomic vector; coercing
gm_zl<-str_detect(game_data,fixed("."))
game_data<-game_data[!(gm_zl)]
head(game_data)
## [1] "c(\"39\", \"21\", \"18\", \"14\", \"7\", \"12\", \"4\")"
## [2] "c(\"63\", \"58\", \"4\", \"17\", \"16\", \"20\", \"7\")"
## [3] "c(\"8\", \"61\", \"25\", \"21\", \"11\", \"13\", \"12\")"
## [4] "c(\"23\", \"28\", \"2\", \"26\", \"5\", \"19\", \"1\")"
## [5] "c(\"45\", \"37\", \"12\", \"13\", \"4\", \"14\", \"17\")"
## [6] "c(\"34\", \"29\", \"11\", \"35\", \"10\", \"27\", \"21\")"
Position<-seq(1,64,by=1)
Player_names<-str_trim(names,"both")
State<-str_trim(state,"both")
pre_rating<-str_trim(pre_rating,"both")
post_rating<-str_trim(post_rating,"both")
playerranks<-cbind(Position,Player_names,State,Points,pre_rating,post_rating)
playerranks<-as.data.frame(playerranks)
#numeric data are stored as factors, convert to numeric
playerranks$pts<-as.numeric(as.character(playerranks$Points))
playerranks$pre_rating<-as.numeric(as.character(playerranks$pre_rating))
playerranks$post_rating<-as.numeric(as.character(playerranks$post_rating))
head(playerranks)
## Position Player_names State Points pre_rating post_rating pts
## 1 1 GARY HUA ON 6.0 1794 1817 6.0
## 2 2 DAKSHESH DARURI MI 6.0 1553 1663 6.0
## 3 3 ADITYA BAJAJ MI 6.0 1384 1640 6.0
## 4 4 PATRICK H SCHILLING MI 5.5 1716 1744 5.5
## 5 5 HANSHI ZUO MI 5.5 1655 1690 5.5
## 6 6 HANSEN SONG OH 5.0 1686 1687 5.0
#calculate the mean of opponent rankings
result<-array(0,dim=nrow(playerranks))
#loop through all the players
for (i in 1:nrow(playerranks)){
#extract opponent data and query rankings
match_res<-as.numeric(str_split(unlist(str_extract_all(game_data[i],"\\d{1,2}"))," "))
#calcuate the average of opponent rankings
result[i]<-mean(playerranks[match_res,colnames(playerranks)=="pre_rating"])
};
playerranks$avg_rating<-result
head(playerranks)
## Position Player_names State Points pre_rating post_rating pts
## 1 1 GARY HUA ON 6.0 1794 1817 6.0
## 2 2 DAKSHESH DARURI MI 6.0 1553 1663 6.0
## 3 3 ADITYA BAJAJ MI 6.0 1384 1640 6.0
## 4 4 PATRICK H SCHILLING MI 5.5 1716 1744 5.5
## 5 5 HANSHI ZUO MI 5.5 1655 1690 5.5
## 6 6 HANSEN SONG OH 5.0 1686 1687 5.0
## avg_rating
## 1 1605.286
## 2 1469.286
## 3 1563.571
## 4 1573.571
## 5 1500.857
## 6 1518.714
ggplot(playerranks,aes(avg_rating,pts))+geom_point(size=3)+xlab("Average Opponent Rating")+ylab("Total Points")+ggtitle("Chess Players and Opponents")
write.csv(playerranks,"playerrank_clean",row.names=FALSE)