Data 607 Project 1

Retrieve chess data

chessdata <- read.csv(file="https://raw.githubusercontent.com/AjayArora35/Project-1/master/tournamentinfo.txt", header=TRUE)
head(chessdata)

##   X.........................................................................................
## 1  Pair | Player Name                     |Total|Round|Round|Round|Round|Round|Round|Round| 
## 2  Num  | USCF ID / Rtg (Pre->Post)       | Pts |  1  |  2  |  3  |  4  |  5  |  6  |  7  | 
## 3  -----------------------------------------------------------------------------------------
## 4      1 | GARY HUA                        |6.0  |W  39|W  21|W  18|W  14|W   7|D  12|D   4|
## 5     ON | 15445895 / R: 1794   ->1817     |N:2  |W    |B    |W    |B    |W    |B    |W    |
## 6  -----------------------------------------------------------------------------------------

1. Get rid of the first few lines of data, not needed

Reference: https://www.statmethods.net/input/datatypes.html

       https://www.r-tutor.com/r-introduction/matrix
       
       https://dzone.com/articles/learn-r-how-extract-rows
       
       https://www.r-statistics.com/tag/transpose/   
       
       https://stackoverflow.com/questions/20791877/convert-character-matrix-into-numeric-matrix   
       
       https://astrostatistics.psu.edu/su07/R/html/base/html/colSums.html  
       
       https://www.gastonsanchez.com/Handling_and_Processing_Strings_in_R.pdf

Observation of data: Every 4, 7, 10, 13, etc. is a line separator; the data is in between the separator

#Get rid of the first few rows
chessdata2 <- chessdata[-c(1:2),]
#For debugging: #head(chessdata2)

#Get the data rows from the first data and second data row; alternating sequences
topdatarow <- chessdata2[seq(2, length(chessdata2), 3)]
bottomdatarow <- chessdata2[seq(3, length(chessdata2), 3)]

#For debugging: #head(firstdatarow)
#For debugging: #head(seconddatarow)

#Start to extract out individual pieces of data from the data rows using Regular Expression
library(stringr)
prerating <- unlist(str_extract_all(bottomdatarow, "(R:\\s*)(\\d+)"))
prerating <- as.numeric(unlist(str_extract_all(prerating, "(\\d+)")))
#For debugging: #prerating
#For debugging: #is.atomic(prerating)

state <- unlist(str_trim(str_extract(bottomdatarow, "\\w+")))
#For debugging: #is.atomic(state)

player <- unlist(str_trim(str_extract_all(topdatarow, "(\\w+\\s){2,3}")))
#For debugging: #is.atomic(player)

challenger <- unlist(str_extract_all(topdatarow, "\\|[0-9].*"))
challenger <- str_replace_all(challenger, "\\s{1,2}\\|","00|")
challenger <- (str_extract_all(challenger, "\\s\\d{1,2}"))
#For debugging: #challenger
#For debugging: #is.atomic(challenger)

points <- unlist(as.numeric(str_trim(str_extract(topdatarow, "\\d+\\.\\d+"))))
#For debugging: #is.atomic(points)

#We need to substitute the challenger's prerating into a temp2 matrix so we can
#perform an AVG on the data.

temp2 <- matrix(unlist(challenger), byrow=TRUE, nrow=length(challenger)) 
temp2 <- apply(temp2, 2, as.numeric)
#For debugging: #is.atomic(temp2)

#Substitute prerating values
for (x in 1:nrow(temp2)){
  for (y in 1:ncol(temp2)){
    if (temp2[x,y] == 0){temp2[x,y] = NA}
      temp2[x,y] <- prerating[temp2[x,y]]
  }
}

#For debugging: #temp2
#Get prerating averages
averages <- c(rowMeans(temp2))
output <- data.frame(player,state, points, prerating, averages)
#For debugging: #output

#Create proper header names
colnames(output) <- c("Players", "State", "Total Points", "PreRating", "Challenger's Ratings")
head(output)

##               Players State Total Points PreRating Challenger's Ratings
## 1            GARY HUA    ON          6.0      1794             1605.286
## 2     DAKSHESH DARURI    MI          6.0      1553             1469.286
## 3        ADITYA BAJAJ    MI          6.0      1384             1563.571
## 4 PATRICK H SCHILLING    MI          5.5      1716             1573.571
## 5          HANSHI ZUO    MI          5.5      1655             1500.857
## 6         HANSEN SONG    OH          5.0      1686             1518.714

#Finally, write out csv file
write.csv(output, "Chess_Summary.csv", row.names=FALSE)

#Let's create some graphs to better visualize the data
#Graph challenger's rating for all players
library(ggplot2)

## Warning: package 'ggplot2' was built under R version 3.5.3

ggplot(output,
       aes(x=output$`Challenger's Ratings`,
           y=output$Players
           ))+
  geom_point()

## Warning: Removed 23 rows containing missing values (geom_point).

#Graph all players prerating
ggplot(output,
       aes(x=output$PreRating,
           y=output$Players
           ))+
  geom_point()

#Graph all players location
ggplot(output,
       aes(x=output$State,
           y=output$Players
           ))+
  geom_point()

#Graph all players total points
ggplot(output,
       aes(x=output$`Total Points`,
           y=output$Players
           ))+
  geom_point()