gghatano gghatano

## pawapuro.R
library(data.table)
library(dplyr)
library(stringr)

# read data
dat = fread("all2013.csv")
fields = fread("fields.csv")
setnames(dat, fields$Header)

# processing datatable

## monte.r
library(Rcpp)
library(inline)

cpp_code = "
 using namespace Rcpp;
 double piSugar(int N){
   RNGScope scope;
   NumericVector x = runif(N);
   NumericVector y = runif(N);
   NumericVector d = sqrt(x*x + y*y);

## spin_rate_vs_hit_or_strike.r
library(dplyr)
library(magrittr)
library(data.table)
library(ggplot2)

# pitch f/x data 2013
dat = fread("2013.csv")
dat = dat %>% filter(sv_id !="NA")

# hit event

## linetype.R
d=data.frame(lt=c("blank", "solid", "dashed", "dotted", "dotdash", "longdash", "twodash", "1F", "F1", "4C88C488", "12345678"))
ggplot() +
scale_x_continuous(name="", limits=c(0,1), breaks=NA) +
scale_y_discrete(name="linetype") +
scale_linetype_identity() +
geom_segment(data=d, mapping=aes(x=0, xend=1, y=lt, yend=lt, linetype=lt))

## legends.csv

          
            playerID
            careerHit
            careerHit.x
            careerHit.y
            fullname

            
              aaronha01
              3771
              3771
              3771
              Hank Aaron

            
              ansonca01
              3418
              3418
              3418
              Cap Anson

            
              biggicr01
              3060
              3060
              3060
              Craig Biggio

            
              boggswa01
              3010
              3010
              3010
              Wade Boggs

            
              brettge01
              3154
              3154
              3154
              George Brett

            
              brocklo01
              3023
              3023
              3023
              Lou Brock

            
              carewro01
              3053
              3053
              3053
              Rod Carew

            
              clemero01
              3000
              3000
              3000
              Roberto Clemente

            
              cobbty01
              4189
              4189
              4189
              Ty Cobb

## season_HR_rate.R
library(Lahman)
library(dplyr)
library(magrittr)
library(pings)

# Batting: season stats data frame of all the players
all_dat <- Batting %>%
  select(yearID, AB, H, HR) %>%
  group_by(yearID) %>%
  dplyr::summarise(H = sum(H, na.rm = TRUE),

## df_merge.R
df1 = data.frame(a = 1:3, b = 4:6, c = 7:9)
df2 = data.frame(c = 10:12, a = 13:15,  b = 16:18)

merge(df1,df2, all=TRUE)
#    a  b  c
# 1  1  4  7
# 2  2  5  8
# 3  3  6  9
# 4 13 16 10
# 5 14 17 11

## game_analysis.R
library(data.table)
library(dplyr)
library(magrittr)

makedata = function(year = 2013){
  # set the path of data file
  filename = paste("../../../data/all", year, ".csv", sep="")
  dat = fread(filename, header=FALSE)
  colnames = fread("names.csv", header = FALSE) %>% unlist
  setnames(dat, colnames)

## combine.sh
for dir in  `ls | grep [0-9]`
do
  mv $dir"/"*.pdf $dir".pdf"
done

join.py --output out.pdf *.pdf

## hoge.tex
\documentclass{article}
\usepackage[round]{natbib}

\usepackage{filecontents}
\begin{filecontents}{\jobname.bib}
@article {Schimd1993,
author = {Schmid, Hans-Peter and McNeal, John E. and Stamey, Thomas A.},
title = {Observations on the doubling time of prostate cancer. The use of serial prostate-specific antigen in patients with untreated disease as a measure of increasing cancer volume},
journal = {Cancer},
volume = {71},
	library(data.table)
	library(dplyr)
	library(stringr)

	# read data
	dat = fread("all2013.csv")
	fields = fread("fields.csv")
	setnames(dat, fields$Header)

	# processing datatable
	library(Rcpp)
	library(inline)

	cpp_code = "
	using namespace Rcpp;
	double piSugar(int N){
	RNGScope scope;
	NumericVector x = runif(N);
	NumericVector y = runif(N);
	NumericVector d = sqrt(xx + yy);
	library(dplyr)
	library(magrittr)
	library(data.table)
	library(ggplot2)

	# pitch f/x data 2013
	dat = fread("2013.csv")
	dat = dat %>% filter(sv_id !="NA")

	# hit event
	d=data.frame(lt=c("blank", "solid", "dashed", "dotted", "dotdash", "longdash", "twodash", "1F", "F1", "4C88C488", "12345678"))
	ggplot() +
	scale_x_continuous(name="", limits=c(0,1), breaks=NA) +
	scale_y_discrete(name="linetype") +
	scale_linetype_identity() +
	geom_segment(data=d, mapping=aes(x=0, xend=1, y=lt, yend=lt, linetype=lt))
playerID	careerHit	careerHit.x	careerHit.y	fullname
aaronha01	3771	3771	3771	Hank Aaron
ansonca01	3418	3418	3418	Cap Anson
biggicr01	3060	3060	3060	Craig Biggio
boggswa01	3010	3010	3010	Wade Boggs
brettge01	3154	3154	3154	George Brett
brocklo01	3023	3023	3023	Lou Brock
carewro01	3053	3053	3053	Rod Carew
clemero01	3000	3000	3000	Roberto Clemente
cobbty01	4189	4189	4189	Ty Cobb
	library(Lahman)
	library(dplyr)
	library(magrittr)
	library(pings)

	# Batting: season stats data frame of all the players
	all_dat <- Batting %>%
	select(yearID, AB, H, HR) %>%
	group_by(yearID) %>%
	dplyr::summarise(H = sum(H, na.rm = TRUE),
	df1 = data.frame(a = 1:3, b = 4:6, c = 7:9)
	df2 = data.frame(c = 10:12, a = 13:15, b = 16:18)

	merge(df1,df2, all=TRUE)
	# a b c
	# 1 1 4 7
	# 2 2 5 8
	# 3 3 6 9
	# 4 13 16 10
	# 5 14 17 11
	for dir in `ls \| grep [0-9]`
	do
	mv $dir"/"*.pdf $dir".pdf"
	done

	join.py --output out.pdf *.pdf
	\documentclass{article}
	\usepackage[round]{natbib}

	\usepackage{filecontents}
	\begin{filecontents}{\jobname.bib}
	@article {Schimd1993,
	author = {Schmid, Hans-Peter and McNeal, John E. and Stamey, Thomas A.},
	title = {Observations on the doubling time of prostate cancer. The use of serial prostate-specific antigen in patients with untreated disease as a measure of increasing cancer volume},
	journal = {Cancer},
	volume = {71},