DATA607 PROJECT 1 - CHESS_TOURNAMENT_RESULT
Title: CUNY SPS MDS Data607_Project1"
Date: “9/12/2021”
Load Required Package
library(tidyverse)## Warning: package 'tidyverse' was built under R version 4.1.1## -- Attaching packages --------------------------------------- tidyverse 1.3.1 --## v ggplot2 3.3.5 v purrr 0.3.4
## v tibble 3.1.4 v dplyr 1.0.7
## v tidyr 1.1.3 v stringr 1.4.0
## v readr 2.0.1 v forcats 0.5.1## Warning: package 'tibble' was built under R version 4.1.1## Warning: package 'readr' was built under R version 4.1.1## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()library(knitr)Read Tournament Data
theurl <- "https://raw.githubusercontent.com/omocharly/DATA607_LABS/main/tournamentinfo.txt"
chess_data.df <- readLines(theurl)## Warning in readLines(theurl): incomplete final line found on 'https://
## raw.githubusercontent.com/omocharly/DATA607_LABS/main/tournamentinfo.txt'Take a brief look at the head of the data
head(chess_data.df)## [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 |"Cleanup the header by removing first 4 rows:
chess_data1.df <- chess_data.df[c(-1:-4, 0)]
head(chess_data1.df)## [1] " 1 | GARY HUA |6.0 |W 39|W 21|W 18|W 14|W 7|D 12|D 4|"
## [2] " ON | 15445895 / R: 1794 ->1817 |N:2 |W |B |W |B |W |B |W |"
## [3] "-----------------------------------------------------------------------------------------"
## [4] " 2 | DAKSHESH DARURI |6.0 |W 63|W 58|L 4|W 17|W 16|W 20|W 7|"
## [5] " MI | 14598900 / R: 1553 ->1663 |N:2 |B |W |B |W |B |W |B |"
## [6] "-----------------------------------------------------------------------------------------"Create two data frames to capture the two lines of data for each player from the original frame. Every player information is in lines of three with the third line being the row delimiter:
#created empty objects:
data1.df <- c()
data2.df <- c()
#Run a loop to get the split:
k <- 1
for (i in 1:length(chess_data1.df) ) {
if ( i == 1 | i%%3 == 1 ) { data1.df[k] <- chess_data1.df[i] }
else if (i == 2 | i%%3 == 2) { data2.df[k] <- chess_data1.df[i] }
if (i%%3 == 0) {
k <- k + 1
}
}# Sample rows from the dataset:
head(data1.df)## [1] " 1 | GARY HUA |6.0 |W 39|W 21|W 18|W 14|W 7|D 12|D 4|"
## [2] " 2 | DAKSHESH DARURI |6.0 |W 63|W 58|L 4|W 17|W 16|W 20|W 7|"
## [3] " 3 | ADITYA BAJAJ |6.0 |L 8|W 61|W 25|W 21|W 11|W 13|W 12|"
## [4] " 4 | PATRICK H SCHILLING |5.5 |W 23|D 28|W 2|W 26|D 5|W 19|D 1|"
## [5] " 5 | HANSHI ZUO |5.5 |W 45|W 37|D 12|D 13|D 4|W 14|W 17|"
## [6] " 6 | HANSEN SONG |5.0 |W 34|D 29|L 11|W 35|D 10|W 27|W 21|"head(data2.df)## [1] " ON | 15445895 / R: 1794 ->1817 |N:2 |W |B |W |B |W |B |W |"
## [2] " MI | 14598900 / R: 1553 ->1663 |N:2 |B |W |B |W |B |W |B |"
## [3] " MI | 14959604 / R: 1384 ->1640 |N:2 |W |B |W |B |W |B |W |"
## [4] " MI | 12616049 / R: 1716 ->1744 |N:2 |W |B |W |B |W |B |B |"
## [5] " MI | 14601533 / R: 1655 ->1690 |N:2 |B |W |B |W |B |W |B |"
## [6] " OH | 15055204 / R: 1686 ->1687 |N:3 |W |B |W |B |B |W |B |"# Splitting with pattern as the delimiter "|" :
data1.cols.df <- str_split(data1.df, pattern = fixed("|"), simplify = TRUE, n=11)
data2.cols.df <- str_split(data2.df, pattern = fixed("|"), simplify = TRUE, n=11)
#Trimming the values for values in all rows and columns:
data1.cols.df <- trimws(data1.cols.df )
data2.cols.df <- trimws(data2.cols.df )Sample rows from the dataset:
head(data1.cols.df)## [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8]
## [1,] "1" "GARY HUA" "6.0" "W 39" "W 21" "W 18" "W 14" "W 7"
## [2,] "2" "DAKSHESH DARURI" "6.0" "W 63" "W 58" "L 4" "W 17" "W 16"
## [3,] "3" "ADITYA BAJAJ" "6.0" "L 8" "W 61" "W 25" "W 21" "W 11"
## [4,] "4" "PATRICK H SCHILLING" "5.5" "W 23" "D 28" "W 2" "W 26" "D 5"
## [5,] "5" "HANSHI ZUO" "5.5" "W 45" "W 37" "D 12" "D 13" "D 4"
## [6,] "6" "HANSEN SONG" "5.0" "W 34" "D 29" "L 11" "W 35" "D 10"
## [,9] [,10] [,11]
## [1,] "D 12" "D 4" ""
## [2,] "W 20" "W 7" ""
## [3,] "W 13" "W 12" ""
## [4,] "W 19" "D 1" ""
## [5,] "W 14" "W 17" ""
## [6,] "W 27" "W 21" ""head(data2.cols.df)## [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9]
## [1,] "ON" "15445895 / R: 1794 ->1817" "N:2" "W" "B" "W" "B" "W" "B"
## [2,] "MI" "14598900 / R: 1553 ->1663" "N:2" "B" "W" "B" "W" "B" "W"
## [3,] "MI" "14959604 / R: 1384 ->1640" "N:2" "W" "B" "W" "B" "W" "B"
## [4,] "MI" "12616049 / R: 1716 ->1744" "N:2" "W" "B" "W" "B" "W" "B"
## [5,] "MI" "14601533 / R: 1655 ->1690" "N:2" "B" "W" "B" "W" "B" "W"
## [6,] "OH" "15055204 / R: 1686 ->1687" "N:3" "W" "B" "W" "B" "B" "W"
## [,10] [,11]
## [1,] "W" ""
## [2,] "B" ""
## [3,] "W" ""
## [4,] "B" ""
## [5,] "B" ""
## [6,] "B" ""We will create the final data set having the merged data from the above two data sets with each row in this final data set representing a single player information:
# Creating of an empty dataset with column names and number of rows as the length of final dataset:
final.dataset<-data.frame(id=character(nrow(data1.cols.df)), name=character(nrow(data1.cols.df)), state=character(nrow(data1.cols.df)), total.points=numeric(nrow(data1.cols.df)), pre.rating=numeric(nrow(data1.cols.df)), avg.pre.rating.oppo=numeric(nrow(data1.cols.df)), rd1=character(nrow(data1.cols.df)),rd2=character(nrow(data1.cols.df)), rd3=character(nrow(data1.cols.df)), rd4=character(nrow(data1.cols.df)), rd5=character(nrow(data1.cols.df)), rd6=character(nrow(data1.cols.df)), rd7=character(nrow(data1.cols.df)) )
# Assigning valve to each column in the final dataset [except for average opponent rating, which we will calculate in next step]:
final.dataset$id <- trimws(data1.cols.df[, 1])
final.dataset$name <- data1.cols.df[, 2]
final.dataset$state <- data2.cols.df[, 1]
final.dataset$total.points <- as.double(data1.cols.df[, 3] )
final.dataset$pre.rating <- as.integer( sub('P', '.', trimws( substr(data2.cols.df[,2], regexpr('R:', data2.cols.df[,2] ) +2 , regexpr("->", data2.cols.df[,2])-1) ) ))
final.dataset$rd1 <- sub('[[:alpha:]]', '', data1.cols.df[,4])
final.dataset$rd2 <- sub('[[:alpha:]]', '', data1.cols.df[,5])
final.dataset$rd3 <- sub('[[:alpha:]]', '', data1.cols.df[,6])
final.dataset$rd4 <- sub('[[:alpha:]]', '', data1.cols.df[,7])
final.dataset$rd5 <- sub('[[:alpha:]]', '', data1.cols.df[,8])
final.dataset$rd6 <- sub('[[:alpha:]]', '', data1.cols.df[,9])
final.dataset$rd7 <- sub('[[:alpha:]]', '', data1.cols.df[,10])
#Assigning valve to column avg.pre.rating.oppo:
for (i in 1:nrow(data1.cols.df) ) {
final.dataset$avg.pre.rating.oppo[i] <- as.integer( mean( c(final.dataset$pre.rating[final.dataset$id == trimws(final.dataset$rd1[i])] , final.dataset$pre.rating[final.dataset$id == trimws(final.dataset$rd2[i])] , final.dataset$pre.rating[final.dataset$id == trimws(final.dataset$rd3[i])] , final.dataset$pre.rating[final.dataset$id == trimws(final.dataset$rd4[i])] , final.dataset$pre.rating[final.dataset$id == trimws(final.dataset$rd5[i])] , final.dataset$pre.rating[final.dataset$id == trimws(final.dataset$rd6[i])] , final.dataset$pre.rating[final.dataset$id == trimws(final.dataset$rd7[i])] ) , na.rm = TRUE ) )
}# Sample rows from the dataset:
head(final.dataset)## id name state total.points pre.rating avg.pre.rating.oppo rd1
## 1 1 GARY HUA ON 6.0 1794 1605 39
## 2 2 DAKSHESH DARURI MI 6.0 1553 1469 63
## 3 3 ADITYA BAJAJ MI 6.0 1384 1563 8
## 4 4 PATRICK H SCHILLING MI 5.5 1716 1573 23
## 5 5 HANSHI ZUO MI 5.5 1655 1500 45
## 6 6 HANSEN SONG OH 5.0 1686 1518 34
## rd2 rd3 rd4 rd5 rd6 rd7
## 1 21 18 14 7 12 4
## 2 58 4 17 16 20 7
## 3 61 25 21 11 13 12
## 4 28 2 26 5 19 1
## 5 37 12 13 4 14 17
## 6 29 11 35 10 27 21Creating of the csv file with some selected columns:
final.csv.dataset <- subset(final.dataset, select= c(name, state, total.points, pre.rating,avg.pre.rating.oppo ))Analysis and Visualization
Player’s Pre Ratings compared to Opponent’s Average Ratings
rating <- lm(pre.rating~ avg.pre.rating.oppo, data=final.dataset)
summary(rating)##
## Call:
## lm(formula = pre.rating ~ avg.pre.rating.oppo, data = final.dataset)
##
## Residuals:
## Min 1Q Median 3Q Max
## -988.2 -138.0 50.6 201.0 376.0
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 516.5114 371.7458 1.389 0.1697
## avg.pre.rating.oppo 0.6254 0.2687 2.327 0.0232 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 256.6 on 62 degrees of freedom
## Multiple R-squared: 0.08035, Adjusted R-squared: 0.06552
## F-statistic: 5.417 on 1 and 62 DF, p-value: 0.02322plot(final.dataset$`pre.rating`, final.dataset$`avg.pre.rating.oppo`, xlim=c(800,1800), ylim=c(1000,1800), main="PreRating vs Oppononent avg Rating", xlab="Player PreRating", ylab="Opponent Average PreRating", abline(rating))
Write into a csv file in current working directory
getwd()## [1] "C:/Users/omocharly/Documents/CUNY_SPS_MDS"write.csv(final.csv.dataset,'chess_players_info.csv')