WOPR year over year stability analysis

WOPR Stability

############################################################################
#### Grab airyards data from airyards.com and test the year-to-year
#### stability of WOPR (Weighted Opportunity Rating)
############################################################################

library(tidyverse)
library(jsonlite)

## define a function that uses jsonlite to call the airyards.com
## API and returns the processed JSON as a dataframe.
get_air_yards <- function(year){
   uri <- paste0("http://api.airyards.com/", year, "/weeks")
   df_air <- fromJSON(uri) %>%
      mutate(season = year)
   return(df_air)
}

## initialize an empty data frame so we have something to work with
wopr_data <- data.frame()

## for loops are generally frowned upon in R, but this is fine and fuck the haters.
## we take each year of data and bind all the rows to create one large dataframe.
for (year in 2009:2017) {
   print(paste("Grabbing air yards data for", year))
   df_air <- get_air_yards(year)
   wopr_data <- rbind(wopr_data, df_air)
}

## group all the weekly data into player-seasons,
## re-calculate WOPR for each season, and add a column called season2
## to join on in the next step
wopr_data_seasons <- wopr_data %>%
   filter(tar >= 1) %>%
   group_by(player_id, full_name, season) %>%
   summarize(team_att = sum(tm_att),
             team_air = sum(team_air),
             targets = sum(tar),
             air_yards = sum(air_yards)) %>%
   mutate(wopr = round(0.7 * (air_yards / team_air) + 1.4 * (targets / team_att), 2),
          season2 = season + 1) %>%
   select(player_id, full_name, wopr, season, season2) %>%
   arrange(-wopr)

## join the dataframe on itself using the season + 1 column we just made
wopr_joined <- wopr_data_seasons %>% 
   left_join(wopr_data_seasons, by = c("player_id", 'season2' = 'season')) %>%
   na.omit()

## check the correlation by creating a simple linear model
model <- lm(data = wopr_joined, wopr.y ~ wopr.x)
summary(model)

## draw a quick scatter plot to see the relationship year over year
plot(wopr_joined$wopr.x, wopr_joined$wopr.y)