Update app.R

app.R

@@ -1,26 +1,14 @@
 # Load required libraries
 library(shiny)
 library(plotly)
-# library(gridlayout)
 library(bslib)
 library(DT)
 library(rsconnect)
 library(baseballr)
 library(dplyr)
-# library(tidyverse)
-# library(rvest)
 library(ggplot2)
-# library(janitor)
-# library(ggthemes)
-# library(ggpubr)
-# library(jsonlite)
-# library(utils)
-# library(grid)
-# library(gridExtra)
-# library(png)
 library(xgboost)
 library(httr)
-# library(jpeg)
 
 #pdf(file = NULL)
 Sys.setenv(TZ='EST')
@@ -114,57 +102,8 @@ pitcher_summary <- function(game_pk,date){
   return(tmilb)
 }
 
-calculate_primary <- function(data){
-  data <- data %>%
-    # Group by pitch_name, Pitcher Name, Pitcher Id, and date
-    group_by(pitch_name, `Pitcher Name`, `Pitcher ID`, date) %>%
-    
-    # Count occurrences and calculate average start_speed, IVB, and HB for each group
-    mutate(
-      pitch_count = n(),
-      avg_start_speed = mean(start_speed, na.rm = TRUE),
-      avg_IVB = mean(IVB, na.rm = TRUE),
-      avg_HB = mean(HB, na.rm = TRUE)
-    ) %>%
-    
-    ungroup() %>%
-    # Group by Pitcher Name, Pitcher Id, and date
-    group_by(`Pitcher Name`, `Pitcher ID`, date) %>%
-    
-    # Add a column to identify the highest occurrence
-    mutate(
-      is_highest_occurrence = case_when(
-        pitch_count == max(pitch_count) ~ 1,
-        TRUE ~ 0
-      )
-    ) %>%
-    
-    # If there's a tie, use avg_start_speed as a tiebreaker
-    mutate(
-      is_highest_occurrence = case_when(
-        is_highest_occurrence == 1 & pitch_count == max(pitch_count[is_highest_occurrence == 1]) & 
-          avg_start_speed == max(avg_start_speed[is_highest_occurrence == 1]) ~ 1,
-        TRUE ~ 0
-      )
-    ) %>%
-    
-    # Calculate primary pitch metrics
-    mutate(
-      primary_speed = avg_start_speed[is_highest_occurrence == 1][1],
-      primary_IVB = avg_IVB[is_highest_occurrence == 1][1],
-      primary_HB = avg_HB[is_highest_occurrence == 1][1]
-    ) %>%
-    
-    # Ungroup to remove grouping structure
-    ungroup() %>%
-    mutate(primvelodiff = primary_speed - start_speed,
-          primivbdiff = primary_IVB - IVB,
-          primhbdiff = primary_HB - HB)
-  
-}
-
 calculate_timstuff <- function(game) {
-  game <- calculate_primary(game)
+ # game <- calculate_primary(game)
   game <- game %>%
     mutate(VAA = calculate_VAA(vz0, ay, az, vy0, y0),
            EAA = calculate_EAA(extension),
@@ -176,7 +115,7 @@ calculate_timstuff <- function(game) {
            ishandL = ifelse(phand == "L",1,0))
   # game <- calculate_primary(game)
   
-  feature_vars <- c("ishandL","start_speed", "IVB", "HB", "EAA", "x0", "z0", "spin_rate","SADiff","primvelodiff","primivbdiff","primhbdiff")
+  feature_vars <- c("ishandL","start_speed", "IVB", "HB", "EAA", "x0", "z0", "spin_rate","SADiff")
   complete_rows <- complete.cases(game[, feature_vars])
   game_complete <- game[complete_rows, ]
   game_na <- game[!complete_rows,]
@@ -188,7 +127,7 @@ calculate_timstuff <- function(game) {
   # 
   # lhp$TimStuff <- scale_TimStuff(predict(model, as.matrix(cbind(lhp$ishandL,lhp$start_speed, lhp$IVB, lhp$HB, lhp$EAA, lhp$x0, lhp$z0, lhp$spin_rate, lhp$SADiff,lhp$primary_speed,lhp$primary_IVB,lhp$primary_HB))), -0.00249975,  0.007566558)
   
-  rhp$TimStuff <- scale_TimStuff(predict(model, as.matrix(cbind(rhp$ishandL,rhp$start_speed, rhp$IVB, rhp$HB, rhp$EAA, rhp$x0, rhp$z0, rhp$spin_rate, rhp$SADiff,rhp$primvelodiff,rhp$primivbdiff,rhp$primhbdiff))),  -0.002491156,  0.0078211)
+  rhp$TimStuff <- scale_TimStuff(predict(model, as.matrix(cbind(rhp$ishandL,rhp$start_speed, rhp$IVB, rhp$HB, rhp$EAA, rhp$x0, rhp$z0, rhp$spin_rate, rhp$SADiff))),  -0.002549184,  0.006202895)
   
   game_complete <- rbind(rhp,game_na)
   return(game_complete)