cmrivers

from nltk.corpus import stopwords
from nltk.stem.wordnet import WordNetLemmatizer
from nltk import SnowballStemmer
import string
import nltk
import re

lmt = WordNetLemmatizer()
stemmer = SnowballStemmer("english")
freqdist = nltk.FreqDist()

cmrivers

Data sources:
CDC data on vaccine coverage: http://www.cdc.gov/flu/professionals/vaccination/reporti1112/reporti/index.htm
CDC data on current influenza situation:  http://gis.cdc.gov/grasp/fluview/fluportaldashboard.html 
Historical flu data: http://www.cdc.gov/flu/weekly/pastreports.htm
Locations of hospitals in Boston: https://data.cityofboston.gov/Public-Health/Hospital-Locations/46f7-2snz
NetLogo, a simple agent based model: http://ccl.northwestern.edu/netlogo/ 
Nemsis, emergency medical services API (haven't used this one myself): http://www.nemsis.org/v3/downloads/v3Archive.html 
Written for R, but useful for epi basics in any language: cran.r-project.org/doc/contrib/Epicalc_Book.pdf
"Provides access to health statistics and information on hospital inpatient and emergency department utilization": http://hcupnet.ahrq.gov/
Healthcare Research and Quality data directory: http://www.ahrq.gov/data/dataresources.htm

cmrivers

DOCUMENTATION
Author: Caitlin Rivers
Date:   01102013
##############################
VARIABLE: explanation
    possible values
    and/or format
    
Missing: 999
###############################

cmrivers

computer:~$ howdoi matplotlib alternative x11
> import matplotlib
> # Force matplotlib to not use any Xwindows backend.
> matplotlib.use('Agg')

cmrivers

{
 "metadata": {
  "name": "open_access_impact_factor"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {

cmrivers

{
 "metadata": {
  "name": "open_access_impact_factor_Mar"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {

cmrivers

{
 "metadata": {
  "name": "words_in_title"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {

cmrivers

big4 <- read.csv("~/Dropbox/Open_source_journals/big4_titlelength.csv")
us <- big4[big4$Country == 'United States',]
germ <- big4[big4$Country == 'Germany',]
neth <- big4[big4$Country == 'Netherlands',]
uk <- big4[big4$Country == 'United Kingdom',]

ust <- tapply(us$X2011.SNIP2, us$title_wordcnt, mean, na.rm=TRUE)[1:7]
ukt <- tapply(uk$X2011.SNIP2, uk$title_wordcnt, mean, na.rm=TRUE)[1:7]
germt <- tapply(germ$X2011.SNIP2, germ$title_wordcnt, mean, na.rm=TRUE)[1:7]
netht <- tapply(neth$X2011.SNIP2, neth$title_wordcnt, mean, na.rm=TRUE)[1:7]

cmrivers

Link to github

###parameters for easy viz .header on .mode column

###basic queries select * from table limit 10; select column, column from table limit 10; select distinct column, column from table;

cmrivers