| library(rgdal) | |
| library(dplyr) | |
| library(readr) | |
| library(stringi) | |
| library(stringr) | |
| library(tidyr) | |
| library(grid) | |
| library(scales) | |
| library(ggplot2) | |
| library(ggthemes) |
Press minus + shift + s and return to chop/fold long lines!
| # load the package and data set "Teams" | |
| install.packages("Lahman") | |
| library("Lahman") | |
| data(Teams) | |
| # | |
| # | |
| # CREATE LEAGUE SUMMARY TABLES | |
| # ============================ | |
| # | |
| # select a sub-set of teams from 1901 [the establishment of the American League] forward to 2012 |
| # Brian Abelson @brianabelson | |
| # Harmony Institute | |
| # December 5, 2012 | |
| # lda is a wrapper for lda.collapsed.gibbs.sampler in the "lda" package | |
| # it fits topic models using latent dirichlet allocation | |
| # it provides arguments for cleaning the input text and tuning the parameters of the model | |
| # it also returns alot of useful information about the topics/documents in a format that you can easily join back to your original data | |
| # this allows you to easily model outcomes based on the distribution of topics within a collection of texts |
| doInstall <- TRUE # Change to FALSE if you don't want packages installed. | |
| toInstall <- c("ggplot2", "reshape2", "RColorBrewer") | |
| if(doInstall){install.packages(toInstall, repos = "http://cran.us.r-project.org")} | |
| lapply(toInstall, library, character.only = TRUE) | |
| # Generate a random matrix | |
| # This can be any type of numeric matrix, | |
| # though we often see heatmaps of square correlation matrices. | |
| nRow <- 9 | |
| nCol <- 16 |
| library(maps) | |
| unemp <- read.csv('unemployment09.csv',header=FALSE, stringsAsFactors=FALSE, | |
| col.names=c("blsid", "stfips", "cofips", "name", "year", "pop1", "pop2", "unempraw", "unemppct")) | |
| unemp$mpname <- tolower(paste(state.name[match(sub("^.*([A-Z][A-Z])$","\\1",unemp$name,fixed=FALSE),state.abb)], | |
| sub("^(.*) (County|[Cc]ity|Parish), ..$","\\1", unemp$name),sep=",")) | |
| unemp$ri <- as.numeric(cut(unemp$unemppct,c(seq(0,10,by=2),max(unemp$unemppct)))) |
