In PHP2560-Statistical-Programming-R/r-framingham: a grammer for framingham study based risk scores calculation
devtools::install_github("ricardo-bion/ggradar",
dependencies=TRUE)
one patient risk visualization
sample_size <- 1
# simulate patients data
dd <- data.frame(age=sample(30:70,sample_size,rep=TRUE),
gender=sample(c("M","F"),sample_size,rep=TRUE),
bmi=sample(16:48, sample_size, rep = TRUE),
hdl=sample(10:100,sample_size,rep=TRUE),
chl=sample(100:400,sample_size,rep=TRUE),
sbp=sample(90:200,sample_size,rep=TRUE),
isSbpTreated=sample(c(TRUE,FALSE),sample_size,rep=TRUE),
smoking=sample(c(TRUE,FALSE),sample_size,rep=TRUE),
diabetes=sample(c(TRUE,FALSE),sample_size,rep=TRUE)
)
patient1 <- calc_card_10_one( age=dd$"age",
gender=dd$"gender",
bmi=NA,
cholesterol=dd$"chl",
hdl=dd$"hdl", sbp=dd$"sbp",
is_sbp_under_treatment=dd$"isSbpTreated",
smoking_status=dd$"smoking",
diabetes_status=dd$"diabetes"
)
library(ggplot2)
library(ggradar)
library(scales)
library(dplyr)
library(janitor)
pp <- as.data.frame(patient1) %>%
remove_empty_cols() %>%
subset(select = -c(risk, heart_age))
#Example 1
ggradar(pp,
axis.labels = colnames(pp)[-1],
centre.y = -5,
label.centre.y = TRUE,
grid.min = 0,
grid.mid = 8,
grid.max = 15,
values.radar = c("0", "8", "15"),
grid.line.width = 0.3,
grid.label.size = 4,
gridline.label.offset = 0,
axis.label.size = 3,
axis.line.colour = "gray40",
gridline.max.colour = "black",
plot.legend = TRUE,
legend.text.size = 10,
font.radar = "Arial")
3D Analysis of the effects hdl, sbp and chl on CVD Risk for 100 patients
# install plotly for this to work
library(dplyr)
library(plotly)
library(frisk)
sample_size <- 100
# simulate patients data
sample <- data.frame(age=sample(30:70,sample_size,rep=TRUE),
gender=sample(c("M","F"),sample_size,rep=TRUE),
bmi=sample(16:48, sample_size, rep = TRUE),
hdl=sample(10:100,sample_size,rep=TRUE),
chl=sample(100:400,sample_size,rep=TRUE),
sbp=sample(90:200,sample_size,rep=TRUE),
isSbpTreated=sample(c(TRUE,FALSE),sample_size,rep=TRUE),
smoking=sample(c(TRUE,FALSE),sample_size,rep=TRUE),
diabetes=sample(c(TRUE,FALSE),sample_size,rep=TRUE)
)
# call frisk function case no bmi
patients <-calc_card_10(sample, age="age", gender="gender", cholesterol="chl",
hdl="hdl", sbp="sbp", is_sbp_under_treatment="isSbpTreated",
smoking_status="smoking", diabetes_status="diabetes"
)
#plot the graph
plot_ly(patients, x = ~chl, y = ~sbp, z = ~hdl,
marker = list(color = ~points, colorscale = c('#FFE1A1', '#683531'), showscale = TRUE)) %>%
add_markers() %>%
layout(scene = list(xaxis = list(title = 'cholesterol'),
yaxis = list(title = 'sbp'),
zaxis = list(title = 'hdl')),
annotations = list(
x = 1.13,
y = 1.05,
text = 'Effects of hdl, chl and sbp on CVD Risk',
xref = 'paper',
yref = 'paper',
showarrow = FALSE
))
title: "Capstone"
author: "Triet Tran"
date: "November 1, 2017"
output: html_document
knitr::opts_chunk$set(echo = TRUE)
install.packages("XML")
install.packages("rebus")
install.packages("ggplot2")
install.packages("dplyr")
install.packages("stringr")
install.packages("lawstat")
install.packages("knitr")
install.packages("broom")
install.packages("survey")
install.packages("ResourceSelection")
install.packages("expm")
install.packages("markovchain")
install.packages("diagram")
install.packages("pracma")
library(XML)
library(stringr)
library(rebus)
library(dplyr)
library(ggplot2)
library(lawstat)
library(broom)
library(knitr)
library(survey)
library(MASS)
library(ResourceSelection)
library(expm)
library(markovchain)
library(diagram)
library(pracma)
Raw data
setwd("C:/Users/Triet Tran/Desktop/Capstone")
ARI<-"http://www.espn.com/mlb/team/stats/batting/_/name/ari/year/2012/seasontype/2/split/37"
ATL<-"http://www.espn.com/mlb/team/stats/batting/_/name/atl/year/2012/seasontype/2/split/37"
BAL<-"http://www.espn.com/mlb/team/stats/batting/_/name/bal/year/2012/seasontype/2/split/37"
BOS<-"http://www.espn.com/mlb/team/stats/batting/_/name/bos/year/2012/seasontype/2/split/37"
CHC<-"http://www.espn.com/mlb/team/stats/batting/_/name/chc/year/2012/seasontype/2/split/37"
CHW<-"http://www.espn.com/mlb/team/stats/batting/_/name/chw/year/2012/seasontype/2/split/37"
CIN<-"http://www.espn.com/mlb/team/stats/batting/_/name/cin/year/2012/seasontype/2/split/37"
CLE<-"http://www.espn.com/mlb/team/stats/batting/_/name/cle/year/2012/seasontype/2/split/37"
COL<-"http://www.espn.com/mlb/team/stats/batting/_/name/col/year/2012/seasontype/2/split/37"
DET<-"http://www.espn.com/mlb/team/stats/batting/_/name/det/year/2012/seasontype/2/split/37"
HOU<-"http://www.espn.com/mlb/team/stats/batting/_/name/hou/year/2012/seasontype/2/split/37"
KC<-"http://www.espn.com/mlb/team/stats/batting/_/name/kc/year/2012/seasontype/2/split/37"
LAA<-"http://www.espn.com/mlb/team/stats/batting/_/name/laa/year/2012/seasontype/2/split/37"
LAD<-"http://www.espn.com/mlb/team/stats/batting/_/name/lad/year/2012/seasontype/2/split/37"
MIA<-"http://www.espn.com/mlb/team/stats/batting/_/name/mia/year/2012/seasontype/2/split/37"
MIL<-"http://www.espn.com/mlb/team/stats/batting/_/name/mil/year/2012/seasontype/2/split/37"
MIN<-"http://www.espn.com/mlb/team/stats/batting/_/name/min/year/2012/seasontype/2/split/37"
NYM<-"http://www.espn.com/mlb/team/stats/batting/_/name/nym/year/2012/seasontype/2/split/37"
NYY<-"http://www.espn.com/mlb/team/stats/batting/_/name/nyy/year/2012/seasontype/2/split/37"
OAK<-"http://www.espn.com/mlb/team/stats/batting/_/name/oak/year/2012/seasontype/2/split/37"
PHI<-"http://www.espn.com/mlb/team/stats/batting/_/name/phi/year/2012/seasontype/2/split/37"
PIT<-"http://www.espn.com/mlb/team/stats/batting/_/name/pit/year/2012/seasontype/2/split/37"
SD<-"http://www.espn.com/mlb/team/stats/batting/_/name/sd/year/2012/seasontype/2/split/37"
SF<-"http://www.espn.com/mlb/team/stats/batting/_/name/sf/year/2012/seasontype/2/split/37"
SEA<-"http://www.espn.com/mlb/team/stats/batting/_/name/sea/year/2012/seasontype/2/split/37"
STL<-"http://www.espn.com/mlb/team/stats/batting/_/name/stl/year/2012/seasontype/2/split/37"
TB<-"http://www.espn.com/mlb/team/stats/batting/_/name/tb/year/2012/seasontype/2/split/37"
TEX<-"http://www.espn.com/mlb/team/stats/batting/_/name/tex/year/2012/seasontype/2/split/37"
TOR<-"http://www.espn.com/mlb/team/stats/batting/_/name/tor/year/2012/seasontype/2/split/37"
WSH<-"http://www.espn.com/mlb/team/stats/batting/_/name/wsh/year/2012/seasontype/2/split/37"
Data collection function
create_data<-function(link){
for(i in 2002:2017){
for(j in c(37,38,39,185,94)){
pattern_year<-capture (DGT %R% DGT %R% DGT %R% DGT)
link<-gsub(pattern_year, i, link)
pattern_situ<-capture ("t/" %R% one_or_more(DGT))
temp_link<-str_replace(link,pattern_situ,"t/")
link<-paste(temp_link,j,sep="")
df <- readHTMLTable(gsub(pattern_year, i, link), header=T, which=1,skip.rows=1, stringsAsFactors=T, na.rm=T)
df$YEAR=i
if(j==37){
df$SITU="NO"
} else if(j==38){
df$SITU="RO"
} else if(j==39){
df$SITU="SP"
} else if(j==185){
df$SITU="SP2O"
} else {
df$SITU="BL"
}
write.table(df, file="storage.csv", append=T, sep=",", dec=".", col.names = NA, row.names = T)
}
}
data<-read.table("storage.csv", sep=",", header=T)
unlink("storage.csv")
data$OWAR<-NULL
data$SB<-NULL
data$X.1<-NULL
data$X<-NULL
data<-subset(data, data$NAME != "NAME" & data$NAME != "Totals" & data$NAME != "Opponents")
return(data)
}
#List of teams: ARI,ATL,BAL,BOS,CHC,CHW,CIN,CLE,COL,DET,HOU,KC,LAA,LAD,MIA,MIL,MIN,NYM,NYY,OAK,PHI,PIT,SD,SF,SEA,STL,TB,TEX,TOR,WSH
data1<-create_data(ARI)
data1$TEAM<-"ARI"
data2<-create_data(ATL)
data2$TEAM<-"ATL"
data3<-create_data(BAL)
data3$TEAM<-"BAL"
data4<-create_data(BOS)
data4$TEAM<-"BOS"
data5<-create_data(CHC)
data5$TEAM<-"CHC"
data6<-create_data(CHW)
data6$TEAM<-"CHW"
data7<-create_data(CIN)
data7$TEAM<-"CIN"
data8<-create_data(CLE)
data8$TEAM<-"CLE"
data9<-create_data(COL)
data9$TEAM<-"COL"
data10<-create_data(DET)
data10$TEAM<-"DET"
data11<-create_data(HOU)
data11$TEAM<-"HOU"
data12<-create_data(KC)
data12$TEAM<-"KC"
data13<-create_data(LAA)
data13$TEAM<-"LAA"
data14<-create_data(LAD)
data14$TEAM<-"LAD"
data15<-create_data(MIA)
data15$TEAM<-"MIA"
data16<-create_data(MIL)
data16$TEAM<-"MIL"
data17<-create_data(MIN)
data17$TEAM<-"MIN"
data18<-create_data(NYM)
data18$TEAM<-"NYM"
data19<-create_data(NYY)
data19$TEAM<-"NYY"
data20<-create_data(OAK)
data20$TEAM<-"OAK"
data21<-create_data(PHI)
data21$TEAM<-"PHI"
data22<-create_data(PIT)
data22$TEAM<-"PIT"
data23<-create_data(SD)
data23$TEAM<-"SD"
data24<-create_data(SF)
data24$TEAM<-"SF"
data25<-create_data(SEA)
data25$TEAM<-"SEA"
data26<-create_data(STL)
data26$TEAM<-"STL"
data27<-create_data(TB)
data27$TEAM<-"TB"
data28<-create_data(TEX)
data28$TEAM<-"TEX"
data29<-create_data(TOR)
data29$TEAM<-"TOR"
data30<-create_data(WSH)
data30$TEAM<-"WSH"
data<-rbind(data1,data2,data3,data4,data5,data6,data7,data8,data9,data10,data11,data12,data13,data14,data15,data16,data17,data18,data19,data20,data21,data22,data23,data24,data25,data26,data27,data28,data29,data30)
save(data,file="data.rda")
create_overall<-function(link){
unlink("storage.csv")
for(i in 2015:2017){
pattern_year<-capture (DGT %R% DGT %R% DGT %R% DGT)
link<-gsub(pattern_year, i, link)
df <- readHTMLTable(link, header=T, which=1,skip.rows=1, stringsAsFactors=T, na.rm=T)
df$YEAR=i
write.table(df, file="storage.csv", append=T, sep=",", dec=".", col.names = NA, row.names = T)
data<-read.table("storage.csv", sep=",", header=T)
}
data$OWAR<-NULL
data$X<-NULL
data<-read.table("storage.csv", sep=",", header=T)
data<-subset(data, data$NAME != "NAME" & data$NAME != "Totals" & data$NAME != "Opponents")
return(data)
}
ARI<-"http://www.espn.com/mlb/team/stats/batting/_/name/ari/year/2015"
ATL<-"http://www.espn.com/mlb/team/stats/batting/_/name/atl/year/2015"
BAL<-"http://www.espn.com/mlb/team/stats/batting/_/name/bal/year/2015"
BOS<-"http://www.espn.com/mlb/team/stats/batting/_/name/bos/year/2015"
CHC<-"http://www.espn.com/mlb/team/stats/batting/_/name/chc/year/2015"
CHW<-"http://www.espn.com/mlb/team/stats/batting/_/name/chw/year/2015"
CIN<-"http://www.espn.com/mlb/team/stats/batting/_/name/cin/year/2015"
CLE<-"http://www.espn.com/mlb/team/stats/batting/_/name/cle/year/2015"
COL<-"http://www.espn.com/mlb/team/stats/batting/_/name/col/year/2015"
DET<-"http://www.espn.com/mlb/team/stats/batting/_/name/det/year/2015"
HOU<-"http://www.espn.com/mlb/team/stats/batting/_/name/hou/year/2015"
KC<-"http://www.espn.com/mlb/team/stats/batting/_/name/kc/year/2015"
LAA<-"http://www.espn.com/mlb/team/stats/batting/_/name/laa/year/2015"
LAD<-"http://www.espn.com/mlb/team/stats/batting/_/name/lad/year/2015"
MIA<-"http://www.espn.com/mlb/team/stats/batting/_/name/mia/year/2015"
MIL<-"http://www.espn.com/mlb/team/stats/batting/_/name/mil/year/2015"
MIN<-"http://www.espn.com/mlb/team/stats/batting/_/name/min/year/2015"
NYM<-"http://www.espn.com/mlb/team/stats/batting/_/name/nym/year/2015"
NYY<-"http://www.espn.com/mlb/team/stats/batting/_/name/nyy/year/2015"
OAK<-"http://www.espn.com/mlb/team/stats/batting/_/name/oak/year/2015"
PHI<-"http://www.espn.com/mlb/team/stats/batting/_/name/phi/year/2015"
PIT<-"http://www.espn.com/mlb/team/stats/batting/_/name/pit/year/2015"
SD<-"http://www.espn.com/mlb/team/stats/batting/_/name/sd/year/2015"
SF<-"http://www.espn.com/mlb/team/stats/batting/_/name/sf/year/2015"
SEA<-"http://www.espn.com/mlb/team/stats/batting/_/name/sea/year/2015"
STL<-"http://www.espn.com/mlb/team/stats/batting/_/name/stl/year/2015"
TB<-"http://www.espn.com/mlb/team/stats/batting/_/name/tb/year/2015"
TEX<-"http://www.espn.com/mlb/team/stats/batting/_/name/tex/year/2015"
TOR<-"http://www.espn.com/mlb/team/stats/batting/_/name/tor/year/2015"
WSH<-"http://www.espn.com/mlb/team/stats/batting/_/name/wsh/year/2015"
#List of teams: ARI,ATL,BAL,BOS,CHC,CHW,CIN,CLE,COL,DET,HOU,KC,LAA,LAD,MIA,MIL,MIN,NYM,NYY,OAK,PHI,PIT,SD,SF,SEA,STL,TB,TEX,TOR,WSH
data1<-create_overall(ARI)
data1$TEAM<-"ARI"
data2<-create_overall(ATL)
data2$TEAM<-"ATL"
data3<-create_overall(BAL)
data3$TEAM<-"BAL"
data4<-create_overall(BOS)
data4$TEAM<-"BOS"
data5<-create_overall(CHC)
data5$TEAM<-"CHC"
data6<-create_overall(CHW)
data6$TEAM<-"CHW"
data7<-create_overall(CIN)
data7$TEAM<-"CIN"
data8<-create_overall(CLE)
data8$TEAM<-"CLE"
data9<-create_overall(COL)
data9$TEAM<-"COL"
data10<-create_overall(DET)
data10$TEAM<-"DET"
data11<-create_overall(HOU)
data11$TEAM<-"HOU"
data12<-create_overall(KC)
data12$TEAM<-"KC"
data13<-create_overall(LAA)
data13$TEAM<-"LAA"
data14<-create_overall(LAD)
data14$TEAM<-"LAD"
data15<-create_overall(MIA)
data15$TEAM<-"MIA"
data16<-create_overall(MIL)
data16$TEAM<-"MIL"
data17<-create_overall(MIN)
data17$TEAM<-"MIN"
data18<-create_overall(NYM)
data18$TEAM<-"NYM"
data19<-create_overall(NYY)
data19$TEAM<-"NYY"
data20<-create_overall(OAK)
data20$TEAM<-"OAK"
data21<-create_overall(PHI)
data21$TEAM<-"PHI"
data22<-create_overall(PIT)
data22$TEAM<-"PIT"
data23<-create_overall(SD)
data23$TEAM<-"SD"
data24<-create_overall(SF)
data24$TEAM<-"SF"
data25<-create_overall(SEA)
data25$TEAM<-"SEA"
data26<-create_overall(STL)
data26$TEAM<-"STL"
data27<-create_overall(TB)
data27$TEAM<-"TB"
data28<-create_overall(TEX)
data28$TEAM<-"TEX"
data29<-create_overall(TOR)
data29$TEAM<-"TOR"
data30<-create_overall(WSH)
data30$TEAM<-"WSH"
data_overall<-rbind(data1,data2,data3,data4,data5,data6,data7,data8,data9,data10,data11,data12,data13,data14,data15,data16,data17,data18,data19,data20,data21,data22,data23,data24,data25,data26,data27,data28,data29,data30)
save(data,file="data_overall.rda")
PHP2560-Statistical-Programming-R/r-framingham documentation built on May 23, 2019, 4:23 p.m.
R Package Documentation
Browse R Packages
We want your feedback!
Note that we can't provide technical support on individual packages. You should contact the package authors for that.
devtools::install_github("ricardo-bion/ggradar", dependencies=TRUE)
one patient risk visualization
sample_size <- 1 # simulate patients data dd <- data.frame(age=sample(30:70,sample_size,rep=TRUE), gender=sample(c("M","F"),sample_size,rep=TRUE), bmi=sample(16:48, sample_size, rep = TRUE), hdl=sample(10:100,sample_size,rep=TRUE), chl=sample(100:400,sample_size,rep=TRUE), sbp=sample(90:200,sample_size,rep=TRUE), isSbpTreated=sample(c(TRUE,FALSE),sample_size,rep=TRUE), smoking=sample(c(TRUE,FALSE),sample_size,rep=TRUE), diabetes=sample(c(TRUE,FALSE),sample_size,rep=TRUE) ) patient1 <- calc_card_10_one( age=dd$"age", gender=dd$"gender", bmi=NA, cholesterol=dd$"chl", hdl=dd$"hdl", sbp=dd$"sbp", is_sbp_under_treatment=dd$"isSbpTreated", smoking_status=dd$"smoking", diabetes_status=dd$"diabetes" ) library(ggplot2) library(ggradar) library(scales) library(dplyr) library(janitor) pp <- as.data.frame(patient1) %>% remove_empty_cols() %>% subset(select = -c(risk, heart_age)) #Example 1 ggradar(pp, axis.labels = colnames(pp)[-1], centre.y = -5, label.centre.y = TRUE, grid.min = 0, grid.mid = 8, grid.max = 15, values.radar = c("0", "8", "15"), grid.line.width = 0.3, grid.label.size = 4, gridline.label.offset = 0, axis.label.size = 3, axis.line.colour = "gray40", gridline.max.colour = "black", plot.legend = TRUE, legend.text.size = 10, font.radar = "Arial")
3D Analysis of the effects hdl, sbp and chl on CVD Risk for 100 patients
# install plotly for this to work library(dplyr) library(plotly) library(frisk) sample_size <- 100 # simulate patients data sample <- data.frame(age=sample(30:70,sample_size,rep=TRUE), gender=sample(c("M","F"),sample_size,rep=TRUE), bmi=sample(16:48, sample_size, rep = TRUE), hdl=sample(10:100,sample_size,rep=TRUE), chl=sample(100:400,sample_size,rep=TRUE), sbp=sample(90:200,sample_size,rep=TRUE), isSbpTreated=sample(c(TRUE,FALSE),sample_size,rep=TRUE), smoking=sample(c(TRUE,FALSE),sample_size,rep=TRUE), diabetes=sample(c(TRUE,FALSE),sample_size,rep=TRUE) ) # call frisk function case no bmi patients <-calc_card_10(sample, age="age", gender="gender", cholesterol="chl", hdl="hdl", sbp="sbp", is_sbp_under_treatment="isSbpTreated", smoking_status="smoking", diabetes_status="diabetes" ) #plot the graph plot_ly(patients, x = ~chl, y = ~sbp, z = ~hdl, marker = list(color = ~points, colorscale = c('#FFE1A1', '#683531'), showscale = TRUE)) %>% add_markers() %>% layout(scene = list(xaxis = list(title = 'cholesterol'), yaxis = list(title = 'sbp'), zaxis = list(title = 'hdl')), annotations = list( x = 1.13, y = 1.05, text = 'Effects of hdl, chl and sbp on CVD Risk', xref = 'paper', yref = 'paper', showarrow = FALSE ))
title: "Capstone" author: "Triet Tran" date: "November 1, 2017" output: html_document
knitr::opts_chunk$set(echo = TRUE)
install.packages("XML") install.packages("rebus") install.packages("ggplot2") install.packages("dplyr") install.packages("stringr") install.packages("lawstat") install.packages("knitr") install.packages("broom") install.packages("survey") install.packages("ResourceSelection") install.packages("expm") install.packages("markovchain") install.packages("diagram") install.packages("pracma")
library(XML) library(stringr) library(rebus) library(dplyr) library(ggplot2) library(lawstat) library(broom) library(knitr) library(survey) library(MASS) library(ResourceSelection) library(expm) library(markovchain) library(diagram) library(pracma)
Raw data
setwd("C:/Users/Triet Tran/Desktop/Capstone") ARI<-"http://www.espn.com/mlb/team/stats/batting/_/name/ari/year/2012/seasontype/2/split/37" ATL<-"http://www.espn.com/mlb/team/stats/batting/_/name/atl/year/2012/seasontype/2/split/37" BAL<-"http://www.espn.com/mlb/team/stats/batting/_/name/bal/year/2012/seasontype/2/split/37" BOS<-"http://www.espn.com/mlb/team/stats/batting/_/name/bos/year/2012/seasontype/2/split/37" CHC<-"http://www.espn.com/mlb/team/stats/batting/_/name/chc/year/2012/seasontype/2/split/37" CHW<-"http://www.espn.com/mlb/team/stats/batting/_/name/chw/year/2012/seasontype/2/split/37" CIN<-"http://www.espn.com/mlb/team/stats/batting/_/name/cin/year/2012/seasontype/2/split/37" CLE<-"http://www.espn.com/mlb/team/stats/batting/_/name/cle/year/2012/seasontype/2/split/37" COL<-"http://www.espn.com/mlb/team/stats/batting/_/name/col/year/2012/seasontype/2/split/37" DET<-"http://www.espn.com/mlb/team/stats/batting/_/name/det/year/2012/seasontype/2/split/37" HOU<-"http://www.espn.com/mlb/team/stats/batting/_/name/hou/year/2012/seasontype/2/split/37" KC<-"http://www.espn.com/mlb/team/stats/batting/_/name/kc/year/2012/seasontype/2/split/37" LAA<-"http://www.espn.com/mlb/team/stats/batting/_/name/laa/year/2012/seasontype/2/split/37" LAD<-"http://www.espn.com/mlb/team/stats/batting/_/name/lad/year/2012/seasontype/2/split/37" MIA<-"http://www.espn.com/mlb/team/stats/batting/_/name/mia/year/2012/seasontype/2/split/37" MIL<-"http://www.espn.com/mlb/team/stats/batting/_/name/mil/year/2012/seasontype/2/split/37" MIN<-"http://www.espn.com/mlb/team/stats/batting/_/name/min/year/2012/seasontype/2/split/37" NYM<-"http://www.espn.com/mlb/team/stats/batting/_/name/nym/year/2012/seasontype/2/split/37" NYY<-"http://www.espn.com/mlb/team/stats/batting/_/name/nyy/year/2012/seasontype/2/split/37" OAK<-"http://www.espn.com/mlb/team/stats/batting/_/name/oak/year/2012/seasontype/2/split/37" PHI<-"http://www.espn.com/mlb/team/stats/batting/_/name/phi/year/2012/seasontype/2/split/37" PIT<-"http://www.espn.com/mlb/team/stats/batting/_/name/pit/year/2012/seasontype/2/split/37" SD<-"http://www.espn.com/mlb/team/stats/batting/_/name/sd/year/2012/seasontype/2/split/37" SF<-"http://www.espn.com/mlb/team/stats/batting/_/name/sf/year/2012/seasontype/2/split/37" SEA<-"http://www.espn.com/mlb/team/stats/batting/_/name/sea/year/2012/seasontype/2/split/37" STL<-"http://www.espn.com/mlb/team/stats/batting/_/name/stl/year/2012/seasontype/2/split/37" TB<-"http://www.espn.com/mlb/team/stats/batting/_/name/tb/year/2012/seasontype/2/split/37" TEX<-"http://www.espn.com/mlb/team/stats/batting/_/name/tex/year/2012/seasontype/2/split/37" TOR<-"http://www.espn.com/mlb/team/stats/batting/_/name/tor/year/2012/seasontype/2/split/37" WSH<-"http://www.espn.com/mlb/team/stats/batting/_/name/wsh/year/2012/seasontype/2/split/37"
Data collection function
create_data<-function(link){ for(i in 2002:2017){ for(j in c(37,38,39,185,94)){ pattern_year<-capture (DGT %R% DGT %R% DGT %R% DGT) link<-gsub(pattern_year, i, link) pattern_situ<-capture ("t/" %R% one_or_more(DGT)) temp_link<-str_replace(link,pattern_situ,"t/") link<-paste(temp_link,j,sep="") df <- readHTMLTable(gsub(pattern_year, i, link), header=T, which=1,skip.rows=1, stringsAsFactors=T, na.rm=T) df$YEAR=i if(j==37){ df$SITU="NO" } else if(j==38){ df$SITU="RO" } else if(j==39){ df$SITU="SP" } else if(j==185){ df$SITU="SP2O" } else { df$SITU="BL" } write.table(df, file="storage.csv", append=T, sep=",", dec=".", col.names = NA, row.names = T) } } data<-read.table("storage.csv", sep=",", header=T) unlink("storage.csv") data$OWAR<-NULL data$SB<-NULL data$X.1<-NULL data$X<-NULL data<-subset(data, data$NAME != "NAME" & data$NAME != "Totals" & data$NAME != "Opponents") return(data) }
#List of teams: ARI,ATL,BAL,BOS,CHC,CHW,CIN,CLE,COL,DET,HOU,KC,LAA,LAD,MIA,MIL,MIN,NYM,NYY,OAK,PHI,PIT,SD,SF,SEA,STL,TB,TEX,TOR,WSH data1<-create_data(ARI) data1$TEAM<-"ARI" data2<-create_data(ATL) data2$TEAM<-"ATL" data3<-create_data(BAL) data3$TEAM<-"BAL" data4<-create_data(BOS) data4$TEAM<-"BOS" data5<-create_data(CHC) data5$TEAM<-"CHC" data6<-create_data(CHW) data6$TEAM<-"CHW" data7<-create_data(CIN) data7$TEAM<-"CIN" data8<-create_data(CLE) data8$TEAM<-"CLE" data9<-create_data(COL) data9$TEAM<-"COL" data10<-create_data(DET) data10$TEAM<-"DET" data11<-create_data(HOU) data11$TEAM<-"HOU" data12<-create_data(KC) data12$TEAM<-"KC" data13<-create_data(LAA) data13$TEAM<-"LAA" data14<-create_data(LAD) data14$TEAM<-"LAD" data15<-create_data(MIA) data15$TEAM<-"MIA" data16<-create_data(MIL) data16$TEAM<-"MIL" data17<-create_data(MIN) data17$TEAM<-"MIN" data18<-create_data(NYM) data18$TEAM<-"NYM" data19<-create_data(NYY) data19$TEAM<-"NYY" data20<-create_data(OAK) data20$TEAM<-"OAK" data21<-create_data(PHI) data21$TEAM<-"PHI" data22<-create_data(PIT) data22$TEAM<-"PIT" data23<-create_data(SD) data23$TEAM<-"SD" data24<-create_data(SF) data24$TEAM<-"SF" data25<-create_data(SEA) data25$TEAM<-"SEA" data26<-create_data(STL) data26$TEAM<-"STL" data27<-create_data(TB) data27$TEAM<-"TB" data28<-create_data(TEX) data28$TEAM<-"TEX" data29<-create_data(TOR) data29$TEAM<-"TOR" data30<-create_data(WSH) data30$TEAM<-"WSH" data<-rbind(data1,data2,data3,data4,data5,data6,data7,data8,data9,data10,data11,data12,data13,data14,data15,data16,data17,data18,data19,data20,data21,data22,data23,data24,data25,data26,data27,data28,data29,data30) save(data,file="data.rda")
create_overall<-function(link){ unlink("storage.csv") for(i in 2015:2017){ pattern_year<-capture (DGT %R% DGT %R% DGT %R% DGT) link<-gsub(pattern_year, i, link) df <- readHTMLTable(link, header=T, which=1,skip.rows=1, stringsAsFactors=T, na.rm=T) df$YEAR=i write.table(df, file="storage.csv", append=T, sep=",", dec=".", col.names = NA, row.names = T) data<-read.table("storage.csv", sep=",", header=T) } data$OWAR<-NULL data$X<-NULL data<-read.table("storage.csv", sep=",", header=T) data<-subset(data, data$NAME != "NAME" & data$NAME != "Totals" & data$NAME != "Opponents") return(data) }
ARI<-"http://www.espn.com/mlb/team/stats/batting/_/name/ari/year/2015" ATL<-"http://www.espn.com/mlb/team/stats/batting/_/name/atl/year/2015" BAL<-"http://www.espn.com/mlb/team/stats/batting/_/name/bal/year/2015" BOS<-"http://www.espn.com/mlb/team/stats/batting/_/name/bos/year/2015" CHC<-"http://www.espn.com/mlb/team/stats/batting/_/name/chc/year/2015" CHW<-"http://www.espn.com/mlb/team/stats/batting/_/name/chw/year/2015" CIN<-"http://www.espn.com/mlb/team/stats/batting/_/name/cin/year/2015" CLE<-"http://www.espn.com/mlb/team/stats/batting/_/name/cle/year/2015" COL<-"http://www.espn.com/mlb/team/stats/batting/_/name/col/year/2015" DET<-"http://www.espn.com/mlb/team/stats/batting/_/name/det/year/2015" HOU<-"http://www.espn.com/mlb/team/stats/batting/_/name/hou/year/2015" KC<-"http://www.espn.com/mlb/team/stats/batting/_/name/kc/year/2015" LAA<-"http://www.espn.com/mlb/team/stats/batting/_/name/laa/year/2015" LAD<-"http://www.espn.com/mlb/team/stats/batting/_/name/lad/year/2015" MIA<-"http://www.espn.com/mlb/team/stats/batting/_/name/mia/year/2015" MIL<-"http://www.espn.com/mlb/team/stats/batting/_/name/mil/year/2015" MIN<-"http://www.espn.com/mlb/team/stats/batting/_/name/min/year/2015" NYM<-"http://www.espn.com/mlb/team/stats/batting/_/name/nym/year/2015" NYY<-"http://www.espn.com/mlb/team/stats/batting/_/name/nyy/year/2015" OAK<-"http://www.espn.com/mlb/team/stats/batting/_/name/oak/year/2015" PHI<-"http://www.espn.com/mlb/team/stats/batting/_/name/phi/year/2015" PIT<-"http://www.espn.com/mlb/team/stats/batting/_/name/pit/year/2015" SD<-"http://www.espn.com/mlb/team/stats/batting/_/name/sd/year/2015" SF<-"http://www.espn.com/mlb/team/stats/batting/_/name/sf/year/2015" SEA<-"http://www.espn.com/mlb/team/stats/batting/_/name/sea/year/2015" STL<-"http://www.espn.com/mlb/team/stats/batting/_/name/stl/year/2015" TB<-"http://www.espn.com/mlb/team/stats/batting/_/name/tb/year/2015" TEX<-"http://www.espn.com/mlb/team/stats/batting/_/name/tex/year/2015" TOR<-"http://www.espn.com/mlb/team/stats/batting/_/name/tor/year/2015" WSH<-"http://www.espn.com/mlb/team/stats/batting/_/name/wsh/year/2015" #List of teams: ARI,ATL,BAL,BOS,CHC,CHW,CIN,CLE,COL,DET,HOU,KC,LAA,LAD,MIA,MIL,MIN,NYM,NYY,OAK,PHI,PIT,SD,SF,SEA,STL,TB,TEX,TOR,WSH data1<-create_overall(ARI) data1$TEAM<-"ARI" data2<-create_overall(ATL) data2$TEAM<-"ATL" data3<-create_overall(BAL) data3$TEAM<-"BAL" data4<-create_overall(BOS) data4$TEAM<-"BOS" data5<-create_overall(CHC) data5$TEAM<-"CHC" data6<-create_overall(CHW) data6$TEAM<-"CHW" data7<-create_overall(CIN) data7$TEAM<-"CIN" data8<-create_overall(CLE) data8$TEAM<-"CLE" data9<-create_overall(COL) data9$TEAM<-"COL" data10<-create_overall(DET) data10$TEAM<-"DET" data11<-create_overall(HOU) data11$TEAM<-"HOU" data12<-create_overall(KC) data12$TEAM<-"KC" data13<-create_overall(LAA) data13$TEAM<-"LAA" data14<-create_overall(LAD) data14$TEAM<-"LAD" data15<-create_overall(MIA) data15$TEAM<-"MIA" data16<-create_overall(MIL) data16$TEAM<-"MIL" data17<-create_overall(MIN) data17$TEAM<-"MIN" data18<-create_overall(NYM) data18$TEAM<-"NYM" data19<-create_overall(NYY) data19$TEAM<-"NYY" data20<-create_overall(OAK) data20$TEAM<-"OAK" data21<-create_overall(PHI) data21$TEAM<-"PHI" data22<-create_overall(PIT) data22$TEAM<-"PIT" data23<-create_overall(SD) data23$TEAM<-"SD" data24<-create_overall(SF) data24$TEAM<-"SF" data25<-create_overall(SEA) data25$TEAM<-"SEA" data26<-create_overall(STL) data26$TEAM<-"STL" data27<-create_overall(TB) data27$TEAM<-"TB" data28<-create_overall(TEX) data28$TEAM<-"TEX" data29<-create_overall(TOR) data29$TEAM<-"TOR" data30<-create_overall(WSH) data30$TEAM<-"WSH" data_overall<-rbind(data1,data2,data3,data4,data5,data6,data7,data8,data9,data10,data11,data12,data13,data14,data15,data16,data17,data18,data19,data20,data21,data22,data23,data24,data25,data26,data27,data28,data29,data30) save(data,file="data_overall.rda")
R Package Documentation
Browse R Packages
We want your feedback!
Note that we can't provide technical support on individual packages. You should contact the package authors for that.
Embedding an R snippet on your website
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.