This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see http://rmarkdown.rstudio.com.
When you click the Knit button a document will be generated that includes both content as well as the output of any embedded R code chunks within the document. You can embed an R code chunk like this:
data <- read.table("/Users/joycealdrich/Documents/SPS Data Science/Data 607/Project_1/tournamentinfo.txt", header =FALSE,
sep="+")library(dplyr)##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, uniondata <- data %>%
filter(V1 != "-----------------------------------------------------------------------------------------")row_odd <- seq_len(nrow(data)) %% 2
row_odd ## [1] 1 0 1 0 1 0 1 0 1 0 1 0 1 0 1 0 1 0 1 0 1 0 1 0 1 0 1 0 1 0 1 0 1 0 1 0 1
## [38] 0 1 0 1 0 1 0 1 0 1 0 1 0 1 0 1 0 1 0 1 0 1 0 1 0 1 0 1 0 1 0 1 0 1 0 1 0
## [75] 1 0 1 0 1 0 1 0 1 0 1 0 1 0 1 0 1 0 1 0 1 0 1 0 1 0 1 0 1 0 1 0 1 0 1 0 1
## [112] 0 1 0 1 0 1 0 1 0 1 0 1 0 1 0 1 0 1 0#subset odd rows
data_row_odd <- data[row_odd == 1, ]
data_row_odd ## [1] " Pair | Player Name |Total|Round|Round|Round|Round|Round|Round|Round| "
## [2] " 1 | GARY HUA |6.0 |W 39|W 21|W 18|W 14|W 7|D 12|D 4|"
## [3] " 2 | DAKSHESH DARURI |6.0 |W 63|W 58|L 4|W 17|W 16|W 20|W 7|"
## [4] " 3 | ADITYA BAJAJ |6.0 |L 8|W 61|W 25|W 21|W 11|W 13|W 12|"
## [5] " 4 | PATRICK H SCHILLING |5.5 |W 23|D 28|W 2|W 26|D 5|W 19|D 1|"
## [6] " 5 | HANSHI ZUO |5.5 |W 45|W 37|D 12|D 13|D 4|W 14|W 17|"
## [7] " 6 | HANSEN SONG |5.0 |W 34|D 29|L 11|W 35|D 10|W 27|W 21|"
## [8] " 7 | GARY DEE SWATHELL |5.0 |W 57|W 46|W 13|W 11|L 1|W 9|L 2|"
## [9] " 8 | EZEKIEL HOUGHTON |5.0 |W 3|W 32|L 14|L 9|W 47|W 28|W 19|"
## [10] " 9 | STEFANO LEE |5.0 |W 25|L 18|W 59|W 8|W 26|L 7|W 20|"
## [11] " 10 | ANVIT RAO |5.0 |D 16|L 19|W 55|W 31|D 6|W 25|W 18|"
## [12] " 11 | CAMERON WILLIAM MC LEMAN |4.5 |D 38|W 56|W 6|L 7|L 3|W 34|W 26|"
## [13] " 12 | KENNETH J TACK |4.5 |W 42|W 33|D 5|W 38|H |D 1|L 3|"
## [14] " 13 | TORRANCE HENRY JR |4.5 |W 36|W 27|L 7|D 5|W 33|L 3|W 32|"
## [15] " 14 | BRADLEY SHAW |4.5 |W 54|W 44|W 8|L 1|D 27|L 5|W 31|"
## [16] " 15 | ZACHARY JAMES HOUGHTON |4.5 |D 19|L 16|W 30|L 22|W 54|W 33|W 38|"
## [17] " 16 | MIKE NIKITIN |4.0 |D 10|W 15|H |W 39|L 2|W 36|U |"
## [18] " 17 | RONALD GRZEGORCZYK |4.0 |W 48|W 41|L 26|L 2|W 23|W 22|L 5|"
## [19] " 18 | DAVID SUNDEEN |4.0 |W 47|W 9|L 1|W 32|L 19|W 38|L 10|"
## [20] " 19 | DIPANKAR ROY |4.0 |D 15|W 10|W 52|D 28|W 18|L 4|L 8|"
## [21] " 20 | JASON ZHENG |4.0 |L 40|W 49|W 23|W 41|W 28|L 2|L 9|"
## [22] " 21 | DINH DANG BUI |4.0 |W 43|L 1|W 47|L 3|W 40|W 39|L 6|"
## [23] " 22 | EUGENE L MCCLURE |4.0 |W 64|D 52|L 28|W 15|H |L 17|W 40|"
## [24] " 23 | ALAN BUI |4.0 |L 4|W 43|L 20|W 58|L 17|W 37|W 46|"
## [25] " 24 | MICHAEL R ALDRICH |4.0 |L 28|L 47|W 43|L 25|W 60|W 44|W 39|"
## [26] " 25 | LOREN SCHWIEBERT |3.5 |L 9|W 53|L 3|W 24|D 34|L 10|W 47|"
## [27] " 26 | MAX ZHU |3.5 |W 49|W 40|W 17|L 4|L 9|D 32|L 11|"
## [28] " 27 | GAURAV GIDWANI |3.5 |W 51|L 13|W 46|W 37|D 14|L 6|U |"
## [29] " 28 | SOFIA ADINA STANESCU-BELLU |3.5 |W 24|D 4|W 22|D 19|L 20|L 8|D 36|"
## [30] " 29 | CHIEDOZIE OKORIE |3.5 |W 50|D 6|L 38|L 34|W 52|W 48|U |"
## [31] " 30 | GEORGE AVERY JONES |3.5 |L 52|D 64|L 15|W 55|L 31|W 61|W 50|"
## [32] " 31 | RISHI SHETTY |3.5 |L 58|D 55|W 64|L 10|W 30|W 50|L 14|"
## [33] " 32 | JOSHUA PHILIP MATHEWS |3.5 |W 61|L 8|W 44|L 18|W 51|D 26|L 13|"
## [34] " 33 | JADE GE |3.5 |W 60|L 12|W 50|D 36|L 13|L 15|W 51|"
## [35] " 34 | MICHAEL JEFFERY THOMAS |3.5 |L 6|W 60|L 37|W 29|D 25|L 11|W 52|"
## [36] " 35 | JOSHUA DAVID LEE |3.5 |L 46|L 38|W 56|L 6|W 57|D 52|W 48|"
## [37] " 36 | SIDDHARTH JHA |3.5 |L 13|W 57|W 51|D 33|H |L 16|D 28|"
## [38] " 37 | AMIYATOSH PWNANANDAM |3.5 |B |L 5|W 34|L 27|H |L 23|W 61|"
## [39] " 38 | BRIAN LIU |3.0 |D 11|W 35|W 29|L 12|H |L 18|L 15|"
## [40] " 39 | JOEL R HENDON |3.0 |L 1|W 54|W 40|L 16|W 44|L 21|L 24|"
## [41] " 40 | FOREST ZHANG |3.0 |W 20|L 26|L 39|W 59|L 21|W 56|L 22|"
## [42] " 41 | KYLE WILLIAM MURPHY |3.0 |W 59|L 17|W 58|L 20|X |U |U |"
## [43] " 42 | JARED GE |3.0 |L 12|L 50|L 57|D 60|D 61|W 64|W 56|"
## [44] " 43 | ROBERT GLEN VASEY |3.0 |L 21|L 23|L 24|W 63|W 59|L 46|W 55|"
## [45] " 44 | JUSTIN D SCHILLING |3.0 |B |L 14|L 32|W 53|L 39|L 24|W 59|"
## [46] " 45 | DEREK YAN |3.0 |L 5|L 51|D 60|L 56|W 63|D 55|W 58|"
## [47] " 46 | JACOB ALEXANDER LAVALLEY |3.0 |W 35|L 7|L 27|L 50|W 64|W 43|L 23|"
## [48] " 47 | ERIC WRIGHT |2.5 |L 18|W 24|L 21|W 61|L 8|D 51|L 25|"
## [49] " 48 | DANIEL KHAIN |2.5 |L 17|W 63|H |D 52|H |L 29|L 35|"
## [50] " 49 | MICHAEL J MARTIN |2.5 |L 26|L 20|D 63|D 64|W 58|H |U |"
## [51] " 50 | SHIVAM JHA |2.5 |L 29|W 42|L 33|W 46|H |L 31|L 30|"
## [52] " 51 | TEJAS AYYAGARI |2.5 |L 27|W 45|L 36|W 57|L 32|D 47|L 33|"
## [53] " 52 | ETHAN GUO |2.5 |W 30|D 22|L 19|D 48|L 29|D 35|L 34|"
## [54] " 53 | JOSE C YBARRA |2.0 |H |L 25|H |L 44|U |W 57|U |"
## [55] " 54 | LARRY HODGE |2.0 |L 14|L 39|L 61|B |L 15|L 59|W 64|"
## [56] " 55 | ALEX KONG |2.0 |L 62|D 31|L 10|L 30|B |D 45|L 43|"
## [57] " 56 | MARISA RICCI |2.0 |H |L 11|L 35|W 45|H |L 40|L 42|"
## [58] " 57 | MICHAEL LU |2.0 |L 7|L 36|W 42|L 51|L 35|L 53|B |"
## [59] " 58 | VIRAJ MOHILE |2.0 |W 31|L 2|L 41|L 23|L 49|B |L 45|"
## [60] " 59 | SEAN M MC CORMICK |2.0 |L 41|B |L 9|L 40|L 43|W 54|L 44|"
## [61] " 60 | JULIA SHEN |1.5 |L 33|L 34|D 45|D 42|L 24|H |U |"
## [62] " 61 | JEZZEL FARKAS |1.5 |L 32|L 3|W 54|L 47|D 42|L 30|L 37|"
## [63] " 62 | ASHWIN BALAJI |1.0 |W 55|U |U |U |U |U |U |"
## [64] " 63 | THOMAS JOSEPH HOSMER |1.0 |L 2|L 48|D 49|L 43|L 45|H |U |"
## [65] " 64 | BEN LI |1.0 |L 22|D 30|L 31|D 49|L 46|L 42|L 54|"#subset even rows
data_row_even <- data[row_odd == 0, ]
data_row_even ## [1] " Num | USCF ID / Rtg (Pre->Post) | Pts | 1 | 2 | 3 | 4 | 5 | 6 | 7 | "
## [2] " ON | 15445895 / R: 1794 ->1817 |N:2 |W |B |W |B |W |B |W |"
## [3] " MI | 14598900 / R: 1553 ->1663 |N:2 |B |W |B |W |B |W |B |"
## [4] " MI | 14959604 / R: 1384 ->1640 |N:2 |W |B |W |B |W |B |W |"
## [5] " MI | 12616049 / R: 1716 ->1744 |N:2 |W |B |W |B |W |B |B |"
## [6] " MI | 14601533 / R: 1655 ->1690 |N:2 |B |W |B |W |B |W |B |"
## [7] " OH | 15055204 / R: 1686 ->1687 |N:3 |W |B |W |B |B |W |B |"
## [8] " MI | 11146376 / R: 1649 ->1673 |N:3 |W |B |W |B |B |W |W |"
## [9] " MI | 15142253 / R: 1641P17->1657P24 |N:3 |B |W |B |W |B |W |W |"
## [10] " ON | 14954524 / R: 1411 ->1564 |N:2 |W |B |W |B |W |B |B |"
## [11] " MI | 14150362 / R: 1365 ->1544 |N:3 |W |W |B |B |W |B |W |"
## [12] " MI | 12581589 / R: 1712 ->1696 |N:3 |B |W |B |W |B |W |B |"
## [13] " MI | 12681257 / R: 1663 ->1670 |N:3 |W |B |W |B | |W |B |"
## [14] " MI | 15082995 / R: 1666 ->1662 |N:3 |B |W |B |B |W |W |B |"
## [15] " MI | 10131499 / R: 1610 ->1618 |N:3 |W |B |W |W |B |B |W |"
## [16] " MI | 15619130 / R: 1220P13->1416P20 |N:3 |B |B |W |W |B |B |W |"
## [17] " MI | 10295068 / R: 1604 ->1613 |N:3 |B |W | |B |W |B | |"
## [18] " MI | 10297702 / R: 1629 ->1610 |N:3 |W |B |W |B |W |B |W |"
## [19] " MI | 11342094 / R: 1600 ->1600 |N:3 |B |W |B |W |B |W |B |"
## [20] " MI | 14862333 / R: 1564 ->1570 |N:3 |W |B |W |B |W |W |B |"
## [21] " MI | 14529060 / R: 1595 ->1569 |N:4 |W |B |W |B |W |B |W |"
## [22] " ON | 15495066 / R: 1563P22->1562 |N:3 |B |W |B |W |W |B |W |"
## [23] " MI | 12405534 / R: 1555 ->1529 |N:4 |W |B |W |B | |W |B |"
## [24] " ON | 15030142 / R: 1363 ->1371 | |B |W |B |W |B |W |B |"
## [25] " MI | 13469010 / R: 1229 ->1300 |N:4 |B |W |B |B |W |W |B |"
## [26] " MI | 12486656 / R: 1745 ->1681 |N:4 |B |W |B |W |B |W |B |"
## [27] " ON | 15131520 / R: 1579 ->1564 |N:4 |B |W |B |W |B |W |W |"
## [28] " MI | 14476567 / R: 1552 ->1539 |N:4 |W |B |W |B |W |B | |"
## [29] " MI | 14882954 / R: 1507 ->1513 |N:3 |W |W |B |W |B |B |W |"
## [30] " MI | 15323285 / R: 1602P6 ->1508P12 |N:4 |B |W |B |W |W |B | |"
## [31] " ON | 12577178 / R: 1522 ->1444 | |W |B |B |W |W |B |B |"
## [32] " MI | 15131618 / R: 1494 ->1444 | |B |W |B |W |B |W |B |"
## [33] " ON | 14073750 / R: 1441 ->1433 |N:4 |W |B |W |B |W |B |W |"
## [34] " MI | 14691842 / R: 1449 ->1421 | |B |W |B |W |B |W |B |"
## [35] " MI | 15051807 / R: 1399 ->1400 | |B |W |B |B |W |B |W |"
## [36] " MI | 14601397 / R: 1438 ->1392 | |W |W |B |W |B |B |W |"
## [37] " MI | 14773163 / R: 1355 ->1367 |N:4 |W |B |W |B | |W |B |"
## [38] " MI | 15489571 / R: 980P12->1077P17 | | |B |W |W | |B |W |"
## [39] " MI | 15108523 / R: 1423 ->1439 |N:4 |W |B |W |W | |B |B |"
## [40] " MI | 12923035 / R: 1436P23->1413 |N:4 |B |W |B |W |B |W |W |"
## [41] " MI | 14892710 / R: 1348 ->1346 | |B |B |W |W |B |W |W |"
## [42] " MI | 15761443 / R: 1403P5 ->1341P9 | |B |W |B |W | | | |"
## [43] " MI | 14462326 / R: 1332 ->1256 | |B |W |B |B |W |W |B |"
## [44] " MI | 14101068 / R: 1283 ->1244 | |W |B |W |W |B |B |W |"
## [45] " MI | 15323504 / R: 1199 ->1199 | | |W |B |B |W |B |W |"
## [46] " MI | 15372807 / R: 1242 ->1191 | |W |B |W |B |W |B |W |"
## [47] " MI | 15490981 / R: 377P3 ->1076P10 | |B |W |B |W |B |W |W |"
## [48] " MI | 12533115 / R: 1362 ->1341 | |W |B |W |B |W |B |W |"
## [49] " MI | 14369165 / R: 1382 ->1335 | |B |W | |B | |W |B |"
## [50] " MI | 12531685 / R: 1291P12->1259P17 | |W |W |B |W |B | | |"
## [51] " MI | 14773178 / R: 1056 ->1111 | |W |B |W |B | |B |W |"
## [52] " MI | 15205474 / R: 1011 ->1097 | |B |W |B |W |B |W |W |"
## [53] " MI | 14918803 / R: 935 ->1092 |N:4 |B |W |B |W |B |W |B |"
## [54] " MI | 12578849 / R: 1393 ->1359 | | |B | |W | |W | |"
## [55] " MI | 12836773 / R: 1270 ->1200 | |B |B |W | |W |B |W |"
## [56] " MI | 15412571 / R: 1186 ->1163 | |W |B |W |B | |W |B |"
## [57] " MI | 14679887 / R: 1153 ->1140 | | |B |W |W | |B |W |"
## [58] " MI | 15113330 / R: 1092 ->1079 | |B |W |W |B |W |B | |"
## [59] " MI | 14700365 / R: 917 -> 941 | |W |B |W |B |W | |B |"
## [60] " MI | 12841036 / R: 853 -> 878 | |W | |B |B |W |W |B |"
## [61] " MI | 14579262 / R: 967 -> 984 | |W |B |B |W |B | | |"
## [62] " ON | 15771592 / R: 955P11-> 979P18 | |B |W |B |W |B |W |B |"
## [63] " MI | 15219542 / R: 1530 ->1535 | |B | | | | | | |"
## [64] " MI | 15057092 / R: 1175 ->1125 | |W |B |W |B |B | | |"
## [65] " MI | 15006561 / R: 1163 ->1112 | |B |W |W |B |W |B |B |"#creating a new data_frame to store tournament information
Info <- data_frame(Info_1= data_row_odd,
Info_2 = data_row_even)## Warning: `data_frame()` was deprecated in tibble 1.1.0.
## Please use `tibble()` instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was generated.library(stringr)
Info_2<- mutate ( Info, Tournamentinfo =str_c(Info$Info_1, " ", Info$Info_2))#removing the header from original txt
Info_2<- Info_2 [-c(1), ] ##checking each str length
str_length(Info_2$Info_1)## [1] 89 89 89 89 89 89 89 89 89 89 89 89 89 89 89 89 89 89 89 89 89 89 89 89 89
## [26] 89 89 89 89 89 89 89 89 89 89 89 89 89 89 89 89 89 89 89 89 89 89 89 89 89
## [51] 89 89 89 89 89 89 89 89 89 89 89 89 89 89str_length(Info_2$Info_2)## [1] 89 89 89 89 89 89 89 89 89 89 89 89 89 89 89 89 89 89 89 89 89 89 89 89 89
## [26] 89 89 89 89 89 89 89 89 89 89 89 89 89 89 89 89 89 89 89 89 89 89 89 89 89
## [51] 89 89 89 89 89 89 89 89 89 89 89 89 89 89text<-c(" 1 | GARY HUA |6.0 |W 39|W 21|W 18|W 14|W 7|D 12|D 4| ON | 15445895 / R: 1794 ->1817 |N:2 |W |B |W |B |W |B |W |")str_locate(text, pattern = " 1 ")## start end
## [1,] 1 6str_locate(text, pattern = "GARY HUA ")## start end
## [1,] 9 40str_locate(text, pattern = "6.0 ")## start end
## [1,] 42 46str_locate(text, pattern = "39")## start end
## [1,] 51 52str_locate(text, pattern = "21")## start end
## [1,] 57 58str_locate(text, pattern = "18")## start end
## [1,] 63 64str_locate(text, pattern = "14")## start end
## [1,] 69 70str_locate(text, pattern = " 7")## start end
## [1,] 74 76str_locate(text, pattern = "12")## start end
## [1,] 81 82str_locate(text, pattern = " 4")## start end
## [1,] 86 88str_locate(text, pattern = "ON")## start end
## [1,] 94 95str_locate(text, pattern = "1794")## start end
## [1,] 113 116Number <- substr(Info_2$Tournamentinfo,1,6)
Name <- substr(Info_2$Tournamentinfo,9,40)
Total_Points<- substr(Info_2$Tournamentinfo,42,46)
R1 <- substr(Info_2$Tournamentinfo,51,52)
R2 <- substr(Info_2$Tournamentinfo,57,58)
R3 <- substr(Info_2$Tournamentinfo,63,64)
R4 <- substr(Info_2$Tournamentinfo,69,70)
R5 <- substr(Info_2$Tournamentinfo,75,76)
R6 <- substr(Info_2$Tournamentinfo,81,82)
R7 <- substr(Info_2$Tournamentinfo,87,88)
state <- substr(Info_2$Tournamentinfo,94,95)
Pre_rating <- substr(Info_2$Tournamentinfo,113,116)#creating a data.frame to store tournament info
Tournament_Info <- data.frame(Play_ID = Number,
Name = Name,
State=state,
Total_Points =Total_Points,
Pre_R=Pre_rating,
R1=R1,
R2=R2,
R3=R3,
R4=R4,
R5=R5,
R6=R6,
R7=R7
)Ref_Table <- data.frame(PlayID=as.numeric(Number),
Pre_R= as.numeric(Pre_rating))##creating the round table to store each round’s opponent ID
R_Table <- data.frame(Play_ID=as.numeric(Number),
R1_ID=as.numeric(R1),
R2_ID=as.numeric(R2),
R3_ID=as.numeric(R3),
R4_ID=as.numeric(R4),
R5_ID=as.numeric(R5),
R6_ID=as.numeric(R6),
R7_ID=as.numeric(R7)
)#insert R1’s component’s pre_rating
library(dplyr)
Temp1<-left_join(R_Table,Ref_Table,by =c("R1_ID"="PlayID"))
colnames(Temp1)[9] <- "Pre_R_R1"#insert R2’s component’s pre_rating
library(dplyr)
Temp2<-left_join(Temp1,Ref_Table,by =c("R2_ID"="PlayID"))
colnames(Temp2)[10] <- "Pre_R_R2"#insert R3’s component’s pre_rating
library(dplyr)
Temp3<-left_join(Temp2,Ref_Table,by =c("R3_ID"="PlayID"))
colnames(Temp3)[11] <- "Pre_R_R3"#insert R4’s component’s pre_rating
library(dplyr)
Temp4<-left_join(Temp3,Ref_Table,by =c("R4_ID"="PlayID"))
colnames(Temp4)[12] <- "Pre_R_R4"#insert R5’s component’s pre_rating
library(dplyr)
Temp5<-left_join(Temp4,Ref_Table,by =c("R5_ID"="PlayID"))
colnames(Temp5)[13] <- "Pre_R_R5"#insert R6’s component’s pre_rating
library(dplyr)
Temp6<-left_join(Temp5,Ref_Table,by =c("R6_ID"="PlayID"))
colnames(Temp6)[14] <- "Pre_R_R6"#insert R7’s component’s pre_rating
library(dplyr)
Temp7<-left_join(Temp6,Ref_Table,by =c("R7_ID"="PlayID"))
colnames(Temp7)[15] <- "Pre_R_R7"Pre_Rating_Cal <- subset(Temp7, select= -c(2:8))Pre_Rating_Cal$CountNa <- rowSums(is.na(Pre_Rating_Cal))Pre_Rating_Cal[is.na(Pre_Rating_Cal)] =0Pre_Rating_Cal_Final <-mutate(Pre_Rating_Cal,Average_Pre_Rating_Opponents = (Pre_R_R1+Pre_R_R2+Pre_R_R3+Pre_R_R4+Pre_R_R5+Pre_R_R6+Pre_R_R7)/(7-CountNa)
)Project1 <- data_frame(Player_Name = Tournament_Info$Name,
Player_State = Tournament_Info$State,
Total_Points = Tournament_Info$Total_Points,
Player_Pre_Rating = Tournament_Info$Pre_R,
Average_Pre_Rating_Opponents = round(Pre_Rating_Cal_Final$Average_Pre_Rating_Opponents,0))##export to csv file
write.csv(Project1, file='/Users/joycealdrich/Documents/SPS Data Science/Data 607/Project_1/DATA607_Project_1.csv')Note that the echo = FALSE parameter was added to the
code chunk to prevent printing of the R code that generated the
plot.