chengjun

require(plyr); require(stringr); require(ggplot2); require(lubridate); require(twitteR)

datout_1 <- searchTwitter("I work for the internet", n = 1500, since='2011-11-11', until='2011-12-12')
datout_2 <- searchTwitter("I work for the internet", n = 1500, since='2011-11-13', until='2011-12-14')
datoutdf <- ldply(c(datout_1, datout_2), function(x) x$toDataFrame(), .progress="text")

actual <- grep("I work for the internet", datoutdf[,1], ignore.case=T)
datoutdf2 <- datoutdf[actual,]

datoutdf2$newtime <- round_date(datoutdf2[,4], "hour")

chengjun

from BeautifulSoup import BeautifulSoup
import mechanize
import time

url = "http://www.r-bloggers.com/"

br = mechanize.Browser()

page = br.open(url)

chengjun

require(quantmod)

#get Japanese Yen daily from Fred http://research.stlouisfed.org/fred2
getSymbols("DEXJPUS",src="FRED")
#get US 10y Yield from Fred 
getSymbols("DGS10", src="FRED")

Yen10y <- na.omit(merge(DEXJPUS,DGS10))

#define colors

chengjun

'''
@author Michael J Bommarito II
@date Feb 26, 2011
@license Simplified BSD, (C) 2011.

This script demonstrates how to use Python to archive historical tweets.
'''

import codecs
import csv

chengjun

'''
@author Michael J Bommarito II
@date Feb 26, 2011
@license Simplified BSD, (C) 2011.

This script demonstrates how to use Python to archive historical tweets.
'''

import codecs
import csv

chengjun

#@author Michael J Bommarito
#@contact [email protected]
#@date Feb 20, 2011
#@ip Simplified BSD, (C) 2011.
# This is a simple example of an R script that will retrieve
# public tweets from a given hashtag.

library(RJSONIO)

# This function loads stored tag data to determine the current max_id.

chengjun

CC = Import["D://Mathematica//bbs.xls"]
DD = CC[[1]]
Tally[Transpose[DD][[4]]] // MatrixForm
ListLogLogPlot[Sort[Transpose[Tally[Transpose[DD][[4]]]][[2]], Greater]]
tt = Union[Transpose[DD][[1]]];
First[CC] // TableForm;
thread[n_] := Select[DD, #[[1]] == n &]

k = thread[2]
First[k][[3]]

chengjun

require(quantmod)

#get data from Japan Ministry of Finance website in csv form
url = "http://www.customs.go.jp/toukei/suii/html/data/d41ma.csv"
japantrade <- read.csv(url,skip=2,stringsAsFactors=FALSE)

#start cleaning data and getting in xts form
japantrade.xts <- japantrade[2:NROW(japantrade),]
#remove trailing 0 for future data
japantrade.xts <- japantrade.xts[which(japantrade.xts[,2]!=0),]

chengjun

# calculate the mixing matrix of in igraph graph object 'mygraph', by some vertex attribute 'attrib'
# can change the default use.density=FALSE to return a matrix with raw number of edges rather than density

mixmat <- function(mygraph, attrib, use.density=TRUE) {
  
  require(igraph)
  
  # get unique list of characteristics of the attribute
  attlist <- sort(unique(get.vertex.attribute(mygraph,attrib)))
  

chengjun

`r opts_chunk$set(cache=TRUE)`

This is a quick set of analyses of the California Test Score dataset.  The post was produced using R Markdown in RStudio 0.96.  The main purpose of this post is to provide a case study of using R Markdown to prepare a quick reproducible report.  It provides examples of using plots, output, in-line R code, and markdown. The post is designed to be read along side the R Markdown source code, which is available as a gist on github. 

<!-- more -->

### Preliminaries
* This post builds on my earlier post which provided a guide for [Getting Started with R Markdown, knitr, and RStudio 0.96](jeromyanglim.blogspot.com/2012/05/getting-started-with-r-markdown-knitr.html)
* The dataset analysed comes from the `AER` package which is an accompaniment to the book [Applied Econometrics with R](http://www.amazon.com/Applied-Econometrics-R-Use/dp/0387773169) written by [Christian Kleiber](http://wwz.unibas.ch/personen/profil/person/kleiber/) and [Achim Zeileis](http://eeecon.uibk.ac.at/~zeileis/