Thunder Analytics Project

library(readr)
shots<- read_csv("C:/Users/cjezr/Downloads/shots_data.csv")

## Parsed with column specification:
## cols(
##   team = col_character(),
##   x = col_double(),
##   y = col_double(),
##   fgmade = col_double()
## )

#create a new column in the data frame called "zone" that describes where the shot was taken.  either 2pt, nc3, or c3

zone=numeric()
i=1
while(i<=length(shots$team))
{
  dist=sqrt(shots$x[i]**2+shots$y[i]**2)  #dist is the distance from hoop to shot 
    
  if(abs(shots$x[i])>=22 & shots$y[i]<=7.8)  #critiria for corner three
  {
    zone[i]="c3"
  }
  else if(dist>=23.75 & shots$y[i] > 7.8) #criteria for non corner three
  {
    zone[i]="nc3"
  }
  else if(dist<23.75 & shots$y[i]>7.8)  #criteria for non corner 2
  {
    zone[i]="2pt"
  }
  else if(shots$y[i]<=7.8 & abs(shots$x[i])<22) #criteria for corner 2
  {
    zone[i]="2pt"
  }
  else  
  {
    zone[i]="error"  #if none of the previous then error
  }
 i=i+1
}
shots$zone=zone

#For Team A, what percentage of their shots were attempted in the 2PT zone? 
library(tidyverse)

## -- Attaching packages ------------------------------------------- tidyverse 1.3.0 --

## v ggplot2 3.3.0     v dplyr   0.8.5
## v tibble  3.0.1     v stringr 1.4.0
## v tidyr   1.0.2     v forcats 0.5.0
## v purrr   0.3.3

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

teamA=filter(shots,team=="Team A") #teamA is a dataframe of team A's shots
teamB=filter(shots,team=="Team B") #teamB is a dataframe of team B's shots

sum(teamA$zone=="2pt")/length(teamA$zone)#sum of 2pt shots divided by the total

## [1] 0.6071429

#For Team A, what percentage of their shots were attempted in the NC3 zone?

sum(teamA$zone=="nc3")/length(teamA$zone)#sum of nc3 shots divided by the total

## [1] 0.3214286

#For Team A, what percentage of their shots were attempted in the C3 zone?

sum(teamA$zone=="c3")/length(teamA$zone)#sum of c3 shots divided by the total

## [1] 0.07142857

#For Team A, what was the eFG in the 2PT zone? Rounded to 3 decimal places?

#since they are all 2pt it is just the fg percentage

sum(teamA$zone=="2pt" & teamA$fgmade==1)/sum(teamA$zone=="2pt")

## [1] 0.4

#For Team A, what was the eFG in the NC3 zone? Rounded to 3 decimal places?

#must adjust the equation for 3s by multiplying the threes made by 1.5

(1.5*sum(teamA$zone=="nc3" & teamA$fgmade==1))/sum(teamA$zone=="nc3")

## [1] 0.4833333

#For Team A, what was the eFG in the C3 zone? Rounded to 3 decimal places?

#must adjust the equation for 3s by multiplying the threes made by 1.5

(1.5*sum(teamA$zone=="c3" & teamA$fgmade==1))/sum(teamA$zone=="c3")

## [1] 0.6

#For Team B, what percentage of their shots were attempted in the 2PT zone? 
sum(teamB$zone=="2pt")/length(teamB$zone)#sum of 2pt shots divided by the total

## [1] 0.5821429

#For Team B, what percentage of their shots were attempted in the NC3 zone?

sum(teamB$zone=="nc3")/length(teamB$zone)#sum of nc3 shots divided by the total

## [1] 0.3428571

#For Team B, what percentage of their shots were attempted in the C3 zone?

sum(teamB$zone=="c3")/length(teamB$zone)#sum of c3 shots divided by the total

## [1] 0.075

#For Team B, what was the eFG in the 2PT zone? Rounded to 3 decimal places?

#since they are all 2pt it is just the fg percentage

sum(teamB$zone=="2pt" & teamB$fgmade==1)/sum(teamB$zone=="2pt")

## [1] 0.4601227

#For Team B, what was the eFG in the NC3 zone? Rounded to 3 decimal places?

#must adjust the equation for 3s by multiplying the threes made by 1.5

(1.5*sum(teamB$zone=="nc3" & teamB$fgmade==1))/sum(teamB$zone=="nc3")

## [1] 0.546875

#For Team B, what was the eFG in the C3 zone? Rounded to 3 decimal places?

#must adjust the equation for 3s by multiplying the threes made by 1.5

(1.5*sum(teamB$zone=="c3" & teamB$fgmade==1))/sum(teamB$zone=="c3")

## [1] 0.3571429