justgrimes

# publiclibraries.com scraper

import BeautifulSoup
import urllib2

l = [("http://www.publiclibraries.com/alabama.htm","AL"),
("http://www.publiclibraries.com/alaska.htm","AK"),
("http://www.publiclibraries.com/arizona.htm","AZ"),
("http://www.publiclibraries.com/arkansas.htm","AR"),
("http://www.publiclibraries.com/california.htm","CA"),

justgrimes

#script that attempts to match compare lat,long points two csv files, match by distance
#justin grimes (@justgrimes) 04/16/12

import math
import csv
import sys
import re

# takes two lat/long points and returns distance, modified code from -> http://www.johndcook.com/python_longitude_latitude.html
def distance_on_unit_sphere(lat1, long1, lat2, long2):

justgrimes

SELECT latitude,longitude, (3963.191 * ACOS(
(SIN(PI()* 40.7383040 /180)*SIN(PI()*latitude/180)) +
(COS(PI()* 40.7383040 /180)*cos(PI()*latitude/180)*COS(PI() * longitude/180-PI()* -73.99319 /180))
)) AS distance
FROM TABLE
WHERE 1=1
AND 3963.191 * ACOS( (SIN(PI()* 40.7383040 /180)*SIN(PI() * latitude/180)) +
(COS(PI()* 40.7383040 /180)*cos(PI()*latitude/180)*COS(PI() * longitude/180-PI()* -73.99319 /180))
) <= 1.5
ORDER BY 3963.191 * ACOS(

justgrimes

require(tm)
a <- Corpus(DirSource("C:/Users/jgrimes/Desktop/text/"), readerControl = list(language="lat"))
#summary(a)
a <- tm_map(a, function(x) iconv(enc2utf8(x), sub = "byte"))
a <- tm_map(a, removePunctuation)
a <- tm_map(a, removeNumbers)
a <- tm_map(a, stripWhitespace)
a <- tm_map(a, tolower)
a <- tm_map(a, removeWords, stopwords("english"))
a <- tm_map(a, stemDocument, language = "english")

justgrimes

# Load packages
library(maps)    # To draw map
library(maptools)

# download data files from IMLS website 
temp <- tempfile()
download.file("http://www.imls.gov/assets/1/AssetManager/pupld11b_csv.zip",temp)
pupld11b <- read.csv(unz(temp, "pupld11b.csv")) #file with library systems (admin buildings)
puout11b <- read.csv(unz(temp, "puout11b.csv")) #file with library outlets (all buildings)
unlink(temp)

justgrimes

#SDC Annual Meeting 2014 Introduction to R, R Studio, and Statistical Computing

# Load downloaded data from PLS 2012 survey, CSV format (comma seperated value)
pupld12a_csv <- read.csv("pupld12a_csv/pupld12a.csv", header = TRUE, sep=",", quote = "\"")
puout12a_csv <- read.csv("pupld12a_csv/puout12a.csv", header = TRUE, sep=",", quote = "\"")
pusum12a_csv <- read.csv("pupld12a_csv/pusum12a.csv", header = TRUE, sep=",", quote = "\"")

# Load downloaded data from PLS 2012 survey, Excel format (xls)
#install.packages("gdata")
library(gdata) #library to load xls data; if loading xlsx files use XLConnect library

justgrimes

justgrimes

# Script to load public public library data from the most recent 
# FY 2012 Public Library Survey  (PLS) from Institute of Museum and Library Services

# Data documentation -> http://www.imls.gov/assets/1/AssetManager/fy2012_pls_data_file_documentation.pdf
# More info about data & survey -> http://www.imls.gov/research/public_libraries_in_the_united_states_survey.aspx

install.packages("audiolyzR")
library("audiolyzR")

# Load PLS 2012 directly from the web

justgrimes

# Script to load public public library data from FY 2012 Public Library Survey (PLS) from Institute of Museum and Library Services
# and merge it with most recent broadband data from National Broadband Map Community Anchor Institution data 
# 
# FOR REFERENCE

# CAIID - Unique federal ID's associated with the CAICAT 
# CAICAT -these are the unique federal ID's associated with the CAICAT
# MAXADDOWN - Maximum Advertised Download Speed subscribed to at this CAI
# MAXADUP - Maximum Advertised Upload Speed subscribed to at this CAI
# BBSERVICE - Does institution subscribe to broadband service at location (ex. Y=Yes; N=No; U=Unknown),

justgrimes

#PLS Dot Density Map

library(maps)
library(mapproj)
library(maptools)
library(geosphere)
library(splancs)
library(foreign)

# Map just the points