# ---------------------
# 
# Other miscellaneous Fixes after the original cleaning process
# 
# Currently, the data has no way to determine how many points are
# scored at the end of a drive.
# 
# This R Script will read in the DRIVEPOINTS .csv file, and will: 
# 1. Rename GameId ot GameID
# 2. Remove the Variables that are not needed.
# 3. Make all Boolean variables TRUE/FALSE
# 4. Remove rows that aren't needed
# 5. Remove values that aren't needed (ex. Removing '2-pt successful' if not a 2-pt conversion)
# 6. Fix the instances of 'LA' occurring in the data (change them to the proper label of 'LAR')
# Once complete, will write data back to a clean .csv file
# 
# ---------------------

# Libraries to Use
library(tidyverse)

# Set the working directory to match where the files are pulled from
setwd("C:/Users/Ryant/Downloads/Capstone/Cleaned Data Files")

# Read in the data
Plays <- read_csv("pbpDrivePoints2021-2024.csv")

#################
#1.
Plays <- Plays %>% 
  rename('GameID' = 'GameId')

#2.
Plays <- Plays %>% 
  select(-DriveEnd,
         -SeriesFirstDown,
         -NextScore,
         -TeamWin,
         -IsRush,
         -IsPass,
         -Challenger,
         -IsMeasurement,
         -YardLineFixed,
         -YardLineDirection)

#3.
Plays <- Plays %>% 
  mutate(IsIncomplete = case_when(
    IsIncomplete == 0 ~ FALSE,
    TRUE ~ TRUE
  )) %>% 
  mutate(IsTouchdown = case_when(
    IsTouchdown == 0 ~ FALSE,
    TRUE ~ TRUE
  )) %>% 
  mutate(IsSack = case_when(
    IsSack == 0 ~ FALSE,
    TRUE ~ TRUE
  )) %>% 
  mutate(IsChallenge = case_when(
    IsChallenge == 0 ~ FALSE,
    TRUE ~ TRUE
  )) %>% 
  mutate(IsChallengeReversed = case_when(
    IsChallengeReversed == 0 ~ FALSE,
    TRUE ~ TRUE
  )) %>% 
  mutate(IsInterception = case_when(
    IsInterception == 0 ~ FALSE,
    TRUE ~ TRUE
  )) %>% 
  mutate(IsFumble = case_when(
    IsFumble == 0 ~ FALSE,
    TRUE ~ TRUE
  )) %>% 
  mutate(IsPenalty = case_when(
    IsPenalty == 0 ~ FALSE,
    TRUE ~ TRUE
  )) %>% 
  mutate(IsTwoPointConversion = case_when(
    IsTwoPointConversion == 0 ~ FALSE,
    TRUE ~ TRUE
  )) %>% 
  mutate(IsTwoPointConversionSuccessful = case_when(
    IsTwoPointConversionSuccessful == 0 ~ FALSE,
    TRUE ~ TRUE
  )) %>% 
  mutate(IsPenaltyAccepted = case_when(
    IsPenaltyAccepted == 0 ~ FALSE,
    TRUE ~ TRUE
  )) %>% 
  mutate(IsNoPlay = case_when(
    IsNoPlay == 0 ~ FALSE,
    TRUE ~ TRUE
  )) 

#4. 
NonPlays <- Plays %>% 
  filter(is.na(OffenseTeam) |
           is.na(DefenseTeam) |
           (
             is.na(PreviousPlayID) &
               is.na(NextPlayID)
           ))

NonPlays <- NonPlays %>% 
  filter(!IsPenalty)

Plays <- Plays %>% 
  anti_join(NonPlays)

#5. 
# IsTwoPointSuccessful - Remove value if not a 2-Point Conversion
temp <- Plays %>% 
  filter(!IsTwoPointConversion) %>% 
  mutate(IsTwoPointConversionSuccessful = NA)

Plays <- Plays %>% 
  filter(IsTwoPointConversion) %>% 
  rbind(temp) %>% 
  arrange(GameID, PlayID)

# IsIncomplete / IsInterception
temp <- Plays %>% 
  filter(PlayTypeUpdate != 'PASS') %>% 
  mutate(IsIncomplete = NA) %>% 
  mutate(IsInterception = NA)

Plays <- Plays %>% 
  filter(PlayTypeUpdate == 'PASS') %>% 
  rbind(temp) %>% 
  arrange(GameID, PlayID)

# IsChallengeReversed
temp <- Plays %>% 
  filter(!IsChallenge) %>% 
  mutate(IsChallengeReversed = NA)

Plays <- Plays %>% 
  filter(IsChallenge) %>% 
  rbind(temp) %>% 
  arrange(GameID, PlayID)

# IsPenaltyAccepted / PenaltyYards
temp <- Plays %>% 
  filter(!IsPenalty) %>% 
  mutate(IsPenaltyAccepted = NA) %>% 
  mutate(PenaltyYards = NA)

Plays <- Plays %>% 
  filter(IsPenalty) %>% 
  rbind(temp) %>% 
  arrange(GameID, PlayID)

#6.
Plays <- Plays %>% 
  mutate(OffenseTeam = case_when(
    OffenseTeam == 'LA' ~ 'LAR',
    TRUE ~ OffenseTeam
  )) %>% 
  mutate(DefenseTeam = case_when(
    DefenseTeam == 'LA' ~ 'LAR',
    TRUE ~ DefenseTeam
  )) %>% 
  mutate(PenaltyTeam = case_when(
    PenaltyTeam == 'LA' ~ 'LAR',
    TRUE ~ PenaltyTeam
  ))
#################

# Save the CSV
write_csv(Plays, "pbpFinal2021-2024.csv")

print("Done!")