Week 5 Project 1 - Data Analysis

library(dplyr)
library(stringr)

Read the data from text file.

# Read the text file
file_path <- "C:\\Users\\HP\\Downloads\\tournamentinfo.txt"
chess_data <- readLines(file_path, warn=FALSE)
head(chess_data)

## [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    |"

Processing the data

summary(chess_data)

##    Length     Class      Mode 
##       196 character character

# Extracting relevant data by row
name <- seq(5, 196, 3) 
state_point <- seq(6, 196, 3) 

#Extracting player ID and points from name
player <- as.integer(str_extract(chess_data[name], "\\d+")) 
name_player <- str_replace_all(str_extract(chess_data[name],"([|]).+?\\1"),"[|]","") 
points <- str_extract(chess_data[name], "\\d.\\d") 

#extracting state and rating
state <- str_extract(chess_data[state_point], "[A-Z]{2}" ) 
rating <- as.integer(str_replace_all(str_extract(chess_data[state_point], "R: \\s?\\d{3,4}"), "R:\\s", ""))

# Combining the vectors to form a file which has clean data
new_chess_data <- data.frame(player, name_player, state, points, rating) 
head(new_chess_data)

##   player                       name_player state points rating
## 1      1  GARY HUA                            ON    6.0   1794
## 2      2  DAKSHESH DARURI                     MI    6.0   1553
## 3      3  ADITYA BAJAJ                        MI    6.0   1384
## 4      4  PATRICK H SCHILLING                 MI    5.5   1716
## 5      5  HANSHI ZUO                          MI    5.5   1655
## 6      6  HANSEN SONG                         OH    5.0   1686

# Calculating average opponent rating:
opponent <- str_extract_all(str_extract_all(chess_data[name], "\\d+\\|"), "\\d+")

## Warning in stri_extract_all_regex(string, pattern, simplify = simplify, :
## argument is not an atomic vector; coercing

avg_opp <- length(name)

for (i in 1:length(name)) 
{ 
  avg_opp[i] <- round(mean(rating[as.numeric(unlist(opponent[player[i]]))]), digits = 0)
}
avg_opp

##  [1] 1605 1469 1564 1574 1501 1519 1372 1468 1523 1554 1468 1506 1498 1515 1484
## [16] 1386 1499 1480 1426 1411 1470 1300 1214 1357 1363 1507 1222 1522 1314 1144
## [31] 1260 1379 1277 1375 1150 1388 1385 1539 1430 1391 1248 1150 1107 1327 1152
## [46] 1358 1392 1356 1286 1296 1356 1495 1345 1206 1406 1414 1363 1391 1319 1330
## [61] 1327 1186 1350 1263

# Adding the avg variable to the new chess data
newchessdata <- data.frame(player, name, state, points, rating, avg_opp)
head(newchessdata)

##   player name state points rating avg_opp
## 1      1    5    ON    6.0   1794    1605
## 2      2    8    MI    6.0   1553    1469
## 3      3   11    MI    6.0   1384    1564
## 4      4   14    MI    5.5   1716    1574
## 5      5   17    MI    5.5   1655    1501
## 6      6   20    OH    5.0   1686    1519

Write to CSV

#Write data to csv
write.csv(newchessdata, file = "newchessdatainfo.csv")