pdisc analysis.Rmd

---
title: "bootcamp final project"
output: html_document
---

```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)
warning = FALSE
```

```{r packages}
#install.packages("dplyr")
#install.packages("tidyverse")
#install.packages("pracma")
library(dplyr)
library(tidyverse)
library(baseballr)
library(ggplot2)
library(kableExtra)
library(pracma)
```


```{r data reading}
# read in data
setwd("~/carolinabb1")
pdisc <- read.csv(file = "platedisc.csv", header = TRUE, sep = ",")
names(pdisc)[1] <- "Name"
pdiscavg <- read.csv(file = "pdiscavg.csv", header = TRUE, sep = ",")
full <- read.csv(file = "clutch leaderboard.csv", header = TRUE, sep =",")
names(full)[1]<-"Name"
full <- select(full, Name, Team, Clutch, playerid, WPA)
```


```{r percents formatting}
# format percentages as decimals
for (i in 3:11){
  pdisc[,i] = as.numeric(gsub("[\\%,]", "", pdisc[,i]))
  pdisc[,i] = pdisc[,i]*0.01
}

for (i in 2:10){
    pdiscavg[,i] = as.numeric(gsub("[\\%,]", "", pdiscavg[,i]))
    pdiscavg[,i] = pdiscavg[,i]*0.01
}
```


```{r standard dev. calc}
pdisctemp <- c()
for (i in 3:11){
  sdtemp <- sd(pdisc[,i])
  pdisctemp <- c(pdisctemp,sdtemp)
}

# move values into a csv file
pdiscsd <- read.csv(file = "pdiscsd.csv", header = TRUE, sep = ",")
```


```{r disc rating}
# numbers subbed in from the pdiscavg dataset
pdisc$dRating <- ((pdisc$O.Swing.-.316)/.0595) + ((pdisc$Z.Swing.-.685)/0.0584) + ((pdisc$Swing.- .470)/0.0496) - ((pdisc$O.Contact.-.627)/0.08) - ((pdisc$Z.Contact.-.849)/0.0443) - ((pdisc$Contact.-.762)/0.0529) - ((pdisc$Zone.-.418)/0.0202)+ ((pdisc$F.Strike.-.609)/0.0338)+ ((pdisc$SwStr.-.112)/0.0289)

```


```{r creation of dataset}

# creation of dataset with disc ratings
pdiscRatings <- select(pdisc, Name, Team, dRating, playerid)
arrange(pdiscRatings,desc(dRating))

# matchup with clutch data from full dataset
tempclutch <- c()
tempWPA <- c()
for(i in 1:135){
  tempID <- pdiscRatings[i,4]
  for (j in 1:135){
    if (full[j,4] == tempID){
      tempclutch <- c(tempclutch,full[j,3])
      tempWPA <- c(tempWPA, full[j,5])
    } else {
      next
    }
  }
}

# creating new pretty dataset with disc ratings and clutch values
pdiscRatings$clutch <- tempclutch
pdiscRatings$WPA <- tempWPA
```

```{r average addition}
# creation of dataset with disc ratings
avg <- read.csv(file = "averageData.csv", header = TRUE, sep = ",")

# matchup with average data from secondary dataset
tempBA <- c()
for(i in 1:135){
  tempID <- pdiscRatings[i,4]
  for (j in 1:135){
    if (avg[j,23] == tempID){
      tempBA <- c(tempBA,avg[j,22])
    } else {
      next
    }
  }
}

pdiscRatings$BA <- tempBA
```

```{r BA vs. Disc}
options(scipen = 999)
data("pdiscRatings", package = "ggplot2")
theme_set(theme_bw())
theme_update(plot.title = element_text(hjust = 0.5))
ggplot(data = pdiscRatings, mapping = aes(x = dRating, y= BA)) + geom_point() + geom_smooth(method = "loess", se = F) + labs(title = "Disc Rating vs. BA of Individual Players", x = "Disc Rating", y = "BA")
powerMod <- lm(BA~dRating, data = pdiscRatings)
summary(powerMod)

```


```{r comparison between drating & clutch}
options(scipen = 999)
data("pdiscRatings", package = "ggplot2")
theme_set(theme_bw())
theme_update(plot.title = element_text(hjust = 0.5))
ggplot(data = pdiscRatings, mapping = aes(x = dRating, y= clutch)) + geom_point() + geom_smooth(method = "loess", se = F) + labs(title = "Disc Rating vs. Clutch of Individual Players", x = "Disc Rating", y = "Clutch")
powerMod <- lm(clutch~dRating, data = pdiscRatings)
summary(powerMod)
```


```{r comparison of WPA vs. Disc Rating}
options(scipen = 999)
data("pdiscRatings", package = "ggplot2")
theme_set(theme_bw())
theme_update(plot.title = element_text(hjust = 0.5))
ggplot(data = pdiscRatings, mapping = aes(y = WPA, x= dRating)) + geom_point() + geom_smooth(method = "loess", se = F) + labs(title = "Disc Rating vs. WPA of Individual Players", x = "Disc Rating", y = "WPA")
powerMod <- lm(WPA~dRating, data = pdiscRatings)
summary(powerMod)
```

```{r comparison of WPA vs. Clutch}
options(scipen = 999)
data("pdiscRatings", package = "ggplot2")
theme_set(theme_bw())
ggplot(data = pdiscRatings, mapping = aes(x = clutch, y= WPA)) + geom_point() + geom_smooth(method = "loess", se = F) + labs(title = "Disc Rating vs. Clutch of Individual Players", y = "WPA", x = "Clutch")
powerMod <- lm(WPA~clutch, data = pdiscRatings)
summary(powerMod)
```


```{r}
teamData <- read.csv(file = "teamData.csv", header = TRUE, sep = ",")
names(teamData)[1]<-"Name"
updTeam <- select(teamData,Name,W)


combdRatings <- read.csv(file = "combDratings.csv", header = TRUE, sep = ",")
updTeam[,3] <- combdRatings$combined
```

```{r combined disc vs. total wins}
options(scipen = 999)
data("updTeam", package = "ggplot2")
theme_set(theme_bw())
theme_update(plot.title = element_text(hjust = 0.5))
p <- ggplot(data = updTeam, mapping = aes(y = W, x= V3)) + geom_point() + geom_smooth(method = "loess", se = F) + labs(title = "Combined Disc Ratings vs. Wins", x = "Disc Ratings", y = "Wins")

p + theme(
  panel.background = element_rect(fill = "lightblue",
                                colour = "lightblue",
                                size = 0.5, linetype = "solid"),
  panel.grid.major = element_line(size = 0.5, linetype = 'solid',
                                colour = "white"), 
  panel.grid.minor = element_line(size = 0.25, linetype = 'solid',
                                colour = "white")
  )

powerMod <- lm(V3~W, data = updTeam)
summary(powerMod)
```