Project One Data 607

## import all the libraries 
library(readr)
library(stringr)
library(tidyverse)

## -- Attaching packages --------------------------------------- tidyverse 1.3.1 --

## v ggplot2 3.3.5     v purrr   0.3.4
## v tibble  3.1.6     v dplyr   1.0.7
## v tidyr   1.2.0     v forcats 0.5.1

## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()

data <- readLines("https://raw.githubusercontent.com/AldataSci/Project-One-Data-607/main/tournament.txt",n=-1)
head(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    |"

##Start the sequence at the 5th row in the list and count every 3 rows
Names <-data[seq(5,length(data),3)]
Names <-str_trim(str_extract(Names,'[A-Z].{1,26}'))
head(Names)

## [1] "GARY HUA"            "DAKSHESH DARURI"     "ADITYA BAJAJ"       
## [4] "PATRICK H SCHILLING" "HANSHI ZUO"          "HANSEN SONG"

## Start the sequence of the data at the 6 row and count every 3 rows 
subset <- data[seq(6,length(data),3)]
State <- str_extract(subset,"[A-Z]{2}")
head(State)

## [1] "ON" "MI" "MI" "MI" "MI" "OH"

## Extract all the floating digits and convert it as a numeric
points <- data[seq(5,length(data),3)]
totalpts <- str_extract(points,'(\\d{1})(\\.)(\\d{1})')
totalpts <- as.numeric(totalpts)
totalpts

##  [1] 6.0 6.0 6.0 5.5 5.5 5.0 5.0 5.0 5.0 5.0 4.5 4.5 4.5 4.5 4.5 4.0 4.0 4.0 4.0
## [20] 4.0 4.0 4.0 4.0 4.0 3.5 3.5 3.5 3.5 3.5 3.5 3.5 3.5 3.5 3.5 3.5 3.5 3.5 3.0
## [39] 3.0 3.0 3.0 3.0 3.0 3.0 3.0 3.0 2.5 2.5 2.5 2.5 2.5 2.5 2.0 2.0 2.0 2.0 2.0
## [58] 2.0 2.0 1.5 1.5 1.0 1.0 1.0

## use the specific regex to first get the numbers with the R: then extract the 4 digit elo from the previous string, filter out the na in the list and then convert the Elo as a integer value
Elo <- str_extract(data,"R: ....")
Elo <- str_extract(Elo,"....$")
ActualElo <- Elo[!is.na(Elo)]
ActualElo <-as.integer(ActualElo)
head(ActualElo)

## [1] 1794 1553 1384 1716 1655 1686

## calculate the individual person each player has faced, extract the subset extract all the matches now I have to get rid of the letters and white space next to the numbers, by extracting all the numbers and then checking if i got the values
round <- data[seq(5,length(data),3)]
round <- str_extract_all(round,'[A-Z]\\s{2,}\\d+')
round <- str_extract_all(round,'\\d{1,}')

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

head(round)

## [[1]]
## [1] "39" "21" "18" "14" "7"  "12" "4" 
## 
## [[2]]
## [1] "63" "58" "4"  "17" "16" "20" "7" 
## 
## [[3]]
## [1] "8"  "61" "25" "21" "11" "13" "12"
## 
## [[4]]
## [1] "23" "28" "2"  "26" "5"  "19" "1" 
## 
## [[5]]
## [1] "45" "37" "12" "13" "4"  "14" "17"
## 
## [[6]]
## [1] "34" "29" "11" "35" "10" "27" "21"

## Creating an empty list and finding the subset, convert it to integer and looped it to get the elo and append it to a position of a list, then rounded the list 

list <- c()
i <- 1
for(i in c(1:length(round))){
round[[i]]
as.integer(unlist(round[[i]]))
ActualElo[as.integer(unlist(round[[i]]))]
list[i] <- mean(ActualElo[as.integer(unlist(round[[i]]))])   ## list[i] helps append the number at a certain position
}
AvgElo <- round(list)
AvgElo

##  [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

project_1 <- data.frame(Names,State,totalpts,ActualElo,AvgElo)

write_csv(project_1,'project1.csv',append=FALSE)