baseball_analysis.R

setwd("/Users/josep2/Desktop/blogs/baseball/")

library(ggplot2)
library(dplyr)
library(lubridate)
library(scales)
library(grid) 
library(RColorBrewer)
library(extrafont)
library(reshape)
library(ggthemes)
library(tidyr)
library(reshape2)


my_theme <- function() {
  
  
  # Generate the colors for the chart procedurally with RColorBrewer
  palette <- brewer.pal("Greys", n=9)
  color.background = palette[2]
  color.grid.major = palette[3]
  color.axis.text = palette[6]
  color.axis.title = palette[7]
  color.title = palette[9]
  
  
  # Begin construction of chart
  theme_bw(base_size=9) +
    
    
    # Set the entire chart region to a light gray color
    theme(panel.background=element_rect(fill=color.background, color=color.background)) +
    theme(plot.background=element_rect(fill=color.background, color=color.background)) +
    theme(panel.border=element_rect(color=color.background)) +
    
    
    # Format the grid
    theme(panel.grid.major=element_line(color=color.grid.major,size=.25)) +
    theme(panel.grid.minor=element_blank()) +
    theme(axis.ticks=element_blank()) +
    
    
    # Format the legend, but hide by default
    theme(legend.position="none") +
    theme(legend.background = element_rect(fill=color.background)) +
    theme(legend.text = element_text(size=7,color=color.axis.title)) +
    
    
    # Set title and axis labels, and format these and tick marks
    theme(plot.title=element_text(color=color.title, size=15, vjust=1.25,face="bold", family="Hack")) +
    theme(axis.text.x=element_text(size=9,color=color.axis.text)) +
    theme(axis.text.y=element_text(size=7,color=color.axis.text)) +
    theme(axis.title.x=element_text(size=10,color=color.axis.title, vjust=0, face="bold", family= "Hack")) +
    theme(axis.title.y=element_text(size=10,color=color.axis.title, vjust=1.25, face="bold", family = "Hack")) + 
    theme(strip.text.y = element_text(size = 8, colour = "black", face="bold", family = "Hack")) +
    theme(strip.background = element_rect(fill=color.background, color=color.background, size=1)) +
    
    # Plot margins
    theme(plot.margin = unit(c(0.35, 0.2, 0.3, 0.35), "cm"))
}


baseball_data = read.csv("baseballdata.csv", header=TRUE)

baseball_cost_data <- select(baseball_data,team, ticket_price, hot_dog, beer, parking)

baseball_cost_data = melt(baseball_cost_data)

facet_names <-c(
  'ticket_price' = "Ticket Price",
  'hot_dog' = "Hot Dog",
  'beer' = "Beer",
  'parking' = "Parking"
)

### Distribution of costs / histogram and density 
ggplot()+geom_histogram(binwidth=10,data=subset(baseball_cost_data, variable=="ticket_price"), aes(value), fill="orange", alpha=.5)+
  geom_histogram(binwidth=1,data=subset(baseball_cost_data, variable=="hot_dog"), aes(value), fill= "orange", alpha=.5)+
  geom_histogram(binwidth=1, data=subset(baseball_cost_data, variable=="beer"), aes(value), fill= "orange", alpha=.5)+
  geom_histogram(binwidth=5, data=subset(baseball_cost_data, variable=="parking"), aes(value), fill = "orange", alpha=.5)+
  facet_wrap(~variable, scales = "free", labeller = as_labeller(facet_names))+
  my_theme()+
  scale_x_continuous(labels=scales::dollar)+
  labs(x = "Dollars", y= "Count", title="Distribution of MLB Game Costs")


ggsave("blog_vis1.png", dpi=300, width=10, height=9)

### Concessions 
ggplot()+geom_bar(stat= "identity", data=subset(baseball_cost_data, variable=="hot_dog"), aes(team, value), fill="purple", alpha=.5)+
  geom_bar(stat= "identity", data=subset(baseball_cost_data, variable=="beer"), aes(team, value), fill="purple", alpha=.5)+
  facet_wrap(~variable, labeller =as_labeller((facet_names)))+
  coord_flip()+my_theme()+
  scale_y_continuous(labels=scales::dollar)+
  labs(x="Team", y= "Dollars", title="MLB Beer & Hot Dog Costs by Team")

ggplotly()
ggsave("blog_vis2.png", dpi=300, width=10, height=9)
## Parking

ggplot(baseball_data, aes(x=reorder(team, +parking), y=parking))+
  geom_bar(stat="identity", alpha=.5, fill="#9999ff")+coord_flip()+
  labs(x="Team", y="Dollars", title="Parking Costs By MLB Team")+
  scale_y_continuous(labels=scales::dollar, breaks=seq(0,50,5))+
  my_theme()

ggsave("blog_vis3.png", dpi=300, width=10, height=9)
  
### Tickets Prices 

ggplot(baseball_data, aes(x=reorder(team, +ticket_price), y=ticket_price))+
  geom_bar(stat="identity", alpha=.5, fill="#00cc99")+coord_flip()+
  labs(x="Team", y="Dollars", title="Ticket Costs By MLB Team")+
  scale_y_continuous(labels=scales::dollar, breaks=seq(0,50,5))+
  my_theme()

ggsave("blog_vis4.png", dpi=300, width=10, height=9)
## Populations / Median Income / Percent In Poverty (Plotly)

library(plotly)

g<-plot_ly(baseball_data, x = county_population, y = median_income, text = paste("Team: ", team),
        mode = "markers", color=percent_in_poverty)

plotly_POST(g, filename="median_income")

##Edit the rest in plotly UI

## Highest percent of pay check for Game + Hotdog + beer and parking

ggplot(baseball_data, aes(x=reorder(team, +game_burden), y=game_burden))+
  geom_bar(stat="identity", alpha=.75, fill="#ffc019")+coord_flip()+
  labs(x="Team", y="Percent Of Check", title="Ticket, Parking, Beer and Hotdog by Team")+
  scale_y_continuous(labels=scales::percent, breaks=seq(0,.08,.005))+
  my_theme()

ggsave("blog_vis5.png", dpi=300, width=10, height=9)