a-paxton

#!/bin/sh

# download the Dockerfile
wget https://gist.githubusercontent.com/a-paxton/f7d6ddbddd02468372e6fdbccac1436a/raw/c314f625b65e13e25989d68877f938230d52d017/Dockerfile

# build the container
docker build -t pac-data_analysis_container .

# start the container
docker run --name pac-data_analysis -p 8787:8787 -v $(pwd):/home/rstudio/foobar -e GRANT_SUDO=yes -d pac-data_analysis_container

a-paxton

FROM rocker/rstudio:latest

RUN R -e "install.packages('plyr', repos = 'http://cran.us.r-project.org')"
RUN R -e "install.packages('dplyr', repos = 'http://cran.us.r-project.org')"
RUN R -e "install.packages('stringr', repos = 'http://cran.us.r-project.org')"
RUN R -e "install.packages('data.table', repos = 'http://cran.us.r-project.org')"
RUN R -e "install.packages('lme4', repos = 'http://cran.us.r-project.org')"
RUN R -e "install.packages('ggplot2', repos = 'http://cran.us.r-project.org')"
RUN R -e "install.packages('pander', repos = 'http://cran.us.r-project.org')"
RUN R -e "install.packages('gridExtra', repos = 'http://cran.us.r-project.org')"

a-paxton

d3 = function() {
  var d3 = {
    version: "3.2.7"
  };
  if (!Date.now) Date.now = function() {
    return +new Date();
  };
  var d3_document = document, d3_documentElement = d3_document.documentElement, d3_window = window;
  try {
    d3_document.createElement("div").style.setProperty("opacity", 0, "");

a-paxton

d3 = function() {
  var d3 = {
    version: "3.2.7"
  };
  if (!Date.now) Date.now = function() {
    return +new Date();
  };
  var d3_document = document, d3_documentElement = d3_document.documentElement, d3_window = window;
  try {
    d3_document.createElement("div").style.setProperty("opacity", 0, "");

a-paxton

#' Convert the output of a topicmodels Latent Dirichlet Allocation to JSON
#' for use with LDAvis
#'
#' @param fitted Output from a topicmodels \code{LDA} model.
#' @param corpus Corpus object used to create the document term
#' matrix for the \code{LDA} model. This should have been create with
#' the tm package's \code{Corpus} function.
#' @param doc_term The document term matrix used in the \code{LDA}
#' model. This should have been created with the tm package's 
#' \code{DocumentTermMatrix} function.

a-paxton

# preliminaries
from pymongo import MongoClient
from nltk.corpus import stopwords
from string import ascii_lowercase
import pandas as pd
import gensim, os, re, pymongo, itertools, nltk, snowballstemmer

# set the location where we'll save our model
savefolder = '/data'