NBA Analysis
John Ross
1/2/2021
library(rvest)
library(stringr)
library(tidyr)
library(dplyr)
library(ggplot2)
library(plotly)
library(crosstalk)#1225
#scrape the rotoguru site
dfs1225 <- read_html("http://rotoguru1.com/cgi-bin/hyday.pl?mon=12&day=25&year=2020&game=dk")#extract data table
dfs1225 <- dfs1225 %>%
html_nodes("table") %>%
.[9] %>%
html_table(fill = TRUE)
#convert to df
dfs1225 <- data.frame(dfs1225)
#remove top row
dfs1225 <- dfs1225[-1,]#1226
#scrape the rotoguru site
dfs1226 <- read_html("http://rotoguru1.com/cgi-bin/hyday.pl?mon=12&day=26&year=2020&game=dk")#extract data table
dfs1226 <- dfs1226 %>%
html_nodes("table") %>%
.[9] %>%
html_table(fill = TRUE)
#convert to df
dfs1226 <- data.frame(dfs1226)
#remove top row
dfs1226 <- dfs1226[-1,]#1227
#scrape the rotoguru site
dfs1227 <- read_html("http://rotoguru1.com/cgi-bin/hyday.pl?mon=12&day=27&year=2020&game=dk")#extract data table
dfs1227 <- dfs1227 %>%
html_nodes("table") %>%
.[9] %>%
html_table(fill = TRUE)
#convert to df
dfs1227 <- data.frame(dfs1227)
#remove top row
dfs1227 <- dfs1227[-1,]#1228
#scrape the rotoguru site
dfs1228 <- read_html("http://rotoguru1.com/cgi-bin/hyday.pl?mon=12&day=28&year=2020&game=dk")#extract data table
dfs1228 <- dfs1228 %>%
html_nodes("table") %>%
.[9] %>%
html_table(fill = TRUE)
#convert to df
dfs1228 <- data.frame(dfs1228)
#remove top row
dfs1228 <- dfs1228[-1,]#1229
#scrape the rotoguru site
dfs1229 <- read_html("http://rotoguru1.com/cgi-bin/hyday.pl?mon=12&day=29&year=2020&game=dk")#extract data table
dfs1229 <- dfs1229 %>%
html_nodes("table") %>%
.[9] %>%
html_table(fill = TRUE)
#convert to df
dfs1229 <- data.frame(dfs1229)
#remove top row
dfs1229 <- dfs1229[-1,]#1230
#scrape the rotoguru site
dfs1230 <- read_html("http://rotoguru1.com/cgi-bin/hyday.pl?mon=12&day=30&year=2020&game=dk")#extract data table
dfs1230 <- dfs1230 %>%
html_nodes("table") %>%
.[9] %>%
html_table(fill = TRUE)
#convert to df
dfs1230 <- data.frame(dfs1230)
#remove top row
dfs1230 <- dfs1230[-1,]#1231
#scrape the rotoguru site
dfs1231 <- read_html("http://rotoguru1.com/cgi-bin/hyday.pl?mon=12&day=31&year=2020&game=dk")#extract data table
dfs1231 <- dfs1231 %>%
html_nodes("table") %>%
.[9] %>%
html_table(fill = TRUE)
#convert to df
dfs1231 <- data.frame(dfs1231)
#remove top row
dfs1231 <- dfs1231[-1,]#0101
#scrape the rotoguru site
dfs0101 <- read_html("http://rotoguru1.com/cgi-bin/hyday.pl?mon=01&day=01&year=2021&game=dk")#extract data table
dfs0101 <- dfs0101 %>%
html_nodes("table") %>%
.[9] %>%
html_table(fill = TRUE)
#convert to df
dfs0101 <- data.frame(dfs0101)
#remove top row
dfs0101 <- dfs0101[-1,]#bind rows
todate <- rbind(dfs1225, dfs1226, dfs1227, dfs1228, dfs1229, dfs1230, dfs1231, dfs0101)#change col names
colnames(todate)[1] <- "Pos"
colnames(todate)[2] <- "Name"
colnames(todate)[3] <- "Pts"
colnames(todate)[4] <- "Salary"
colnames(todate)[5] <- "Team"
colnames(todate)[6] <- "Opp"
colnames(todate)[7] <- "Score"
colnames(todate)[8] <- "Min"
colnames(todate)[9] <- "Statline"#remove non player data
todate <- todate[ grep("RotoGuru", todate$Pos, invert = TRUE) , ]
todate <- todate[ grep("Unlisted", todate$Pos, invert = TRUE) , ]
todate <- todate[ grep("Guards", todate$Pos, invert = TRUE) , ]
todate <- todate[ grep("Centers", todate$Pos, invert = TRUE) , ]
todate <- todate[ grep("Forwards", todate$Pos, invert = TRUE) , ]
todate <- todate[ grep("DNP", todate$Min, invert = TRUE) , ]#remove na minutes
todate <- todate %>%
drop_na(Min)#use gsub to remove $ and comma from monetary values prior to data conversion to numeric (or you will get error)
todate$Salary <- gsub("\\$", "", todate$Salary)
todate$Salary <- gsub("\\,", "", todate$Salary)todate[, 3:4] <- lapply(todate[, 3:4], as.numeric)#create a new column to capture Points over Salary
todate <- todate %>%
mutate(Ppd = round(Pts/Salary,5))todate <- todate %>%
group_by(Name) %>%
mutate(Avg = round(mean(Pts),2), Games=n())#created a new todate df because of some NAs in salary. Need to figure out where NA's are coming from
todate1 <- todate %>%
drop_na(Salary)#drop the ^ character - need to use \\ to drop special characters
todate1$Name <- gsub("\\^", "", todate1$Name)today <- c("nyk", "ind", "okc", "orl", "cha", "phi", "cle", "atl", "tor", "no")
#filter for todays games
todate1 <- todate1 %>%
filter(Team %in% today)Using ggplot
#create a static plot
static <- todate1 %>%
ggplot(aes(x= Salary, y=Pts, color = Ppd)) +
geom_point()
static
using plotly
#add function using plotly
ggplotly(static)#Add opactity to the markers
todate1 %>%
plot_ly(x=~Salary, y=~Pts) %>%
add_markers(marker = list(opacity = 0.2))#change the symbol
todate1 %>%
plot_ly(x=~Salary, y=~Pts) %>%
add_markers(marker = list(symbol = "circle-open")) # Change symbol#Adding color as a factor for position
todate1 %>%
plot_ly(x=~Salary, y=~Pts, color = ~Pos,
hoverinfo = "text",
text = ~paste("Name:", Name, "<br>",
"Points:", Pts)
) %>%
add_markers()#add a second polynomial smoother
todate1 %>%
plot_ly(x=~Salary, y=~Pts, color = ~Pos,
hoverinfo = "text",
text = ~paste("Name:", Name, "<br>",
"Points:", Pts, "<br>",
"Salary:", Salary)) %>%
add_markers() %>%
layout(xaxis = list(title = "DK Salary", zeroline = FALSE, showgrid=FALSE),
yaxis = list(title = "DK Points", zeroline = FALSE, showgrid=FALSE),
title = "DK Rulez")#convert the position from a character string to a factor
todate1$Pos <- as.factor(todate1$Pos) todate1 %>%
group_by(Pos) %>%
do(p=plot_ly(., x= ~Salary, y= ~Pts, color = ~Pos, type="scatter", hoverinfo = "text",
text = ~paste("Name:", Name, "<br>",
"Points:", Pts, "<br>",
"Salary:", Salary))) %>%
subplot(nrows=4, shareX= FALSE, shareY= TRUE)#Adding color as a factor for Ppd and adding axis titles
todate1 %>%
plot_ly(x=~Salary, y=~Pts, color = ~Ppd,
hoverinfo = "text",
text = ~paste("Name:", Name, "<br>",
"Points:", Pts, "<br>",
"Team:", Team)) %>%
add_markers() %>%
layout(xaxis = list(title = "DK Salary", zeroline = FALSE, showgrid=FALSE),
yaxis = list(title = "DK Points", zeroline = FALSE, showgrid=FALSE),
title = "DK Rulez")m <- loess(Pts ~ Salary, data = todate1, span = 1.5)
#add a smoother
todate1 %>%
plot_ly(x=~Salary, y=~Pts, color = ~Ppd,
hoverinfo = "text",
text = ~paste("Name:", Name, "<br>",
"Points:", Pts, "<br>",
"Team:", Team)) %>%
add_markers() %>%
add_lines(y = ~fitted(m)) %>%
layout(xaxis = list(title = "DK Salary", zeroline = FALSE, showgrid=FALSE),
yaxis = list(title = "DK Points", zeroline = FALSE, showgrid=FALSE),
title = "DK Rulez")m2 <- lm(Pts ~ poly(Salary, 2), data = todate1)
#add a second polynomial smoother
todate1 %>%
plot_ly(x=~Salary, y=~Pts, color = ~Ppd,
hoverinfo = "text",
text = ~paste("Name:", Name, "<br>",
"Points:", Pts, "<br>",
"Salary:", Salary, "<br>",
"Team:", Team)) %>%
add_markers() %>%
add_lines(y = ~fitted(m), name = "LOESS") %>%
add_lines(y=~fitted(m2), name = "Polynomial") %>%
layout(xaxis = list(title = "DK Salary", zeroline = FALSE, showgrid=FALSE),
yaxis = list(title = "DK Points", zeroline = FALSE, showgrid=FALSE),
title = "DK Rulez")todate1 %>%
group_by(Pos) %>%
do(p=plot_ly(., x= ~Salary, y= ~Ppd, color = ~Pos, hoverinfo = "text",
text = ~paste("Name:", Name, "<br>",
"Points:", Pts, "<br>",
"Salary:", Salary, "<br>",
"Team:", Team))) %>%
subplot(nrows=4, shareY=TRUE)#change the size of the dot based on points per game metric (dk points/salary)
todate1 %>%
plot_ly(x=~Salary, y=~Pts, color = ~Ppd,
hoverinfo = "text",
text = ~paste("Name:", Name, "<br>",
"Points:", Pts, "<br>",
"Salary:", Salary, "<br>",
"Team:", Team)) %>%
add_markers(size = ~Ppd) %>%
layout(xaxis = list(title = "DK Salary", zeroline = FALSE, showgrid=FALSE),
yaxis = list(title = "DK Points", zeroline = FALSE, showgrid=FALSE),
title = "DK Rulez")#breakdown by position - Center eligible
center <- todate1 %>%
filter(Pos == "C"| Pos =="PF/C")
cplot <- center %>%
plot_ly(
x = ~Salary, y = ~Pts, hoverinfo = "text",
text = ~paste("Name:", Name, "<br>",
"Points:", Pts, "<br>",
"Salary:", Salary, "<br>",
"Team:", Team)) %>%
add_markers(
size = ~Ppd,
color = ~Pos,
marker = list(opacity = 0.3,
sizemode = "diameter",
sizeref = 2)) %>%
layout(xaxis = list(title = "DK Salary", zeroline = FALSE, showgrid=FALSE),
yaxis = list(title = "DK Points", zeroline = FALSE, showgrid=FALSE),
title = "Centers")
cplotcplotavg <- center %>%
plot_ly(
x = ~Salary, y = ~Avg, hoverinfo = "text",
text = ~paste("Name:", Name, "<br>",
"Average:", Avg, "<br>",
"Salary:", Salary, "<br>",
"Team:", Team)) %>%
add_markers(
size = ~Ppd,
color = ~Pos,
marker = list(opacity = 0.3,
sizemode = "diameter",
sizeref = 2)) %>%
layout(xaxis = list(title = "DK Salary", zeroline = FALSE, showgrid=FALSE),
yaxis = list(title = "AVG DK Points", zeroline = FALSE, showgrid=FALSE),
title = "Centers AVG")
cplotavg#breakdown by position - Forward Eligible
forward <- todate1 %>%
filter(Pos == "PF"| Pos =="PF/C" | Pos == "SF" | Pos == "SF/PF" | Pos == "SG/SF" | Pos == "PG/SF")
fplot <- forward %>%
plot_ly(
x = ~Salary, y = ~Pts, hoverinfo = "text",
text = ~paste("Name:", Name, "<br>",
"Points:", Pts, "<br>",
"Salary:", Salary, "<br>",
"Team:", Team)) %>%
add_markers(
size = ~Ppd,
color = ~Pos,
marker = list(opacity = 0.3,
sizemode = "diameter",
sizeref = 2)) %>%
layout(xaxis = list(title = "DK Salary", zeroline = FALSE, showgrid=FALSE),
yaxis = list(title = "DK Points", zeroline = FALSE, showgrid=FALSE),
title = "Forwards")
fplotfplotavg <- forward %>%
plot_ly(
x = ~Salary, y = ~Avg, hoverinfo = "text",
text = ~paste("Name:", Name, "<br>",
"Average:", Avg, "<br>",
"Salary:", Salary, "<br>",
"Team:", Team)) %>%
add_markers(
size = ~Ppd,
color = ~Pos,
marker = list(opacity = 0.3,
sizemode = "diameter",
sizeref = 2)) %>%
layout(xaxis = list(title = "DK Salary", zeroline = FALSE, showgrid=FALSE),
yaxis = list(title = "AVG DK Points", zeroline = FALSE, showgrid=FALSE),
title = "Forwards AVG")
fplotavg#breakdown by position - Guard Eligible
guard <- todate1 %>%
filter(Pos == "PG"| Pos =="PG/SF" | Pos == "PG/SG" | Pos == "SG" | Pos == "SG/SF")
gplot <- guard %>%
plot_ly(
x = ~Salary, y = ~Pts, hoverinfo = "text",
text = ~paste("Name:", Name, "<br>",
"Points:", Pts, "<br>",
"Salary:", Salary, "<br>",
"Team:", Team)) %>%
add_markers(
size = ~Ppd,
color = ~Pos,
marker = list(opacity = 0.3,
sizemode = "diameter",
sizeref = 2)) %>%
layout(xaxis = list(title = "DK Salary", zeroline = FALSE, showgrid=FALSE),
yaxis = list(title = "DK Points", zeroline = FALSE, showgrid=FALSE),
title = "Guards")
gplotgplotavg <- guard %>%
plot_ly(
x = ~Salary, y = ~Avg, hoverinfo = "text",
text = ~paste("Name:", Name, "<br>",
"Average:", Avg, "<br>",
"Salary:", Salary, "<br>",
"Team:", Team)) %>%
add_markers(
size = ~Ppd,
color = ~Pos,
marker = list(opacity = 0.3,
sizemode = "diameter",
sizeref = 2)) %>%
layout(xaxis = list(title = "DK Salary", zeroline = FALSE, showgrid=FALSE),
yaxis = list(title = "AVG DK Points", zeroline = FALSE, showgrid=FALSE),
title = "Guards AVG")
gplotavg#Create an animated object
ani <- center %>%
plot_ly(x = ~Salary, y = ~Pts, hoverinfo = "text",
text = ~paste("Name:", Name, "<br>",
"Points:", Pts, "<br>",
"Salary:", Salary, "<br>",
"Team:", Team)) %>%
add_markers(frame = ~Pts, ids=~Name, showlegend = FALSE) %>%
layout(xaxis = list(title = "DK Salary", zeroline = FALSE, showgrid=FALSE),
yaxis = list(title = "DK Points", zeroline = FALSE, showgrid=FALSE),
title = "Centers")Run Transition Animation from Lowest to Highest DK Points based on Salary
#toggle with animation options
#transition speed - lower is faster, must be lower than frame
#hide slider
ani %>%
animation_opts(frame = 100,
transition = 50) %>%
animation_slider(hide=TRUE)Linking tables
Crosstalk allows you to highlight a section of each table in the faceted chart and link the selections using Box Select or Lasso Select
#use subplot to facet out by Center, Forward and Guard
#Enable linked brushing via highlight()
subplot(cplot, fplot, gplot, titleX = TRUE, titleY = TRUE) %>%
hide_legend() %>%
highlight(on = "plotly_selected", persistent =TRUE)Making Shinier Charts
#create a shared data set for the Center position for points and Ppd values
#cplot is setup for Points, need to create a Ppd plot
cplot1 <- center %>%
plot_ly(
x = ~Salary, y = ~Ppd, hoverinfo = "text",
text = ~paste("Name:", Name, "<br>",
"Points:", Pts, "<br>",
"Salary:", Salary, "<br>",
"Team:", Team)) %>%
add_markers(
size = ~Ppd,
color = ~Pos,
marker = list(opacity = 0.3,
sizemode = "diameter",
sizeref = 2)) %>%
layout(xaxis = list(title = "DK Salary", zeroline = FALSE, showgrid=FALSE),
yaxis = list(title = "Points per Dollar", zeroline = FALSE, showgrid=FALSE),
title = "Centers")
cplot1bscols(cplot, cplot1)sharedcenter <- center %>%
SharedData$new(~Pos)c1 <- sharedcenter %>%
plot_ly(
x = ~Salary, y = ~Ppd, hoverinfo = "text",
text = ~paste("Name:", Name, "<br>",
"Points:", Pts, "<br>",
"Salary:", Salary, "<br>",
"Team:", Team)) %>%
add_markers(
size = ~Ppd,
color = ~Pos,
marker = list(opacity = 0.3,
sizemode = "diameter",
sizeref = 2)) %>%
layout(xaxis = list(title = "DK Salary", zeroline = FALSE, showgrid=FALSE),
yaxis = list(title = "Points per Dollar", zeroline = FALSE, showgrid=FALSE),
title = "Centers")c2 <- sharedcenter %>%
plot_ly(
x = ~Salary, y = ~Pts, hoverinfo = "text",
text = ~paste("Name:", Name, "<br>",
"Points:", Pts, "<br>",
"Salary:", Salary, "<br>",
"Team:", Team)) %>%
add_markers(
size = ~Ppd,
color = ~Pos,
marker = list(opacity = 0.3,
sizemode = "diameter",
sizeref = 2)) %>%
layout(xaxis = list(title = "DK Salary", zeroline = FALSE, showgrid=FALSE),
yaxis = list(title = "Points per Dollar", zeroline = FALSE, showgrid=FALSE),
title = "Centers")bscols(c1, c2)bscols(filter_checkbox(id= "Pos", label = "Pos",
sharedData=sharedcenter, group = ~Pos), c1)bscols(filter_select(id= "Pos", label = "Pos",
sharedData=sharedcenter, group = ~Pos), c1)bscols(filter_slider(id= "Pts", label = "Pts",
sharedData=sharedcenter, column = ~Pts), c1)