jfaganUK

library(sqldf)

# there is a default dataset called iris that is always loaded into the R scope
# let's say I want to break it into two randomly using sqldf

# assign id's to the rows
my.iris <- iris
my.iris$id <- 1:nrow(my.iris)
ran.split <- data.frame(rs = sample(1:max(my.iris$id), floor(max(my.iris$id) / 2), replace=F))
sqldf("select * from `my.iris` as x inner join `ran.split` as y on x.id = y.rs")

jfaganUK

twoModeProject <- function(w, m=1, ...) {
  if(!require(parallel)) {
    stop("Requires the parallel package.")
  }
  if(!require(data.table)) {
    stop("Requires the data.table package.")
  }
  
  if(!("data.table" %in% class(w))) {
    w <- data.table(w)

jfaganUK

#' ## Storing R Objects in a SQLite Database

#' Two packages we are using. The first is the ```RSQLite``` which will be used to create and manage an in-memory SQLite database. The second is ```igraph``` which I will use to create and visualize a random network. Some of the work I do is on network simulation. I often don't know the metrics I need from a simulated network when it's created, so I want to be able to store the networks that are created so that I can go back later and analyze them.
library(RSQLite)
library(igraph)

#' Create a database in memory.
con <- dbConnect(SQLite(), ":memory:")

#' The table has two columns, an *id* column and a column called *graph* which is a **blob** type. This type just stores binary data.

jfaganUK

library(data.table)
library(igraph)

x <- fread("all_networks_140923.csv")

igraph.options(vertex.label = NA, edge.arrow.size = 0, vertex.size = 5)

g <- graph.data.frame(x[,list(source, target, weight, type, survey)])

jfaganUK

library(XML)
library(data.table)
library(ggplot2)
library(ggmap)

args <- commandArgs(trailingOnly = T)

cat(args)

x <- readLines('http://realtime.lextran.com/InfoPoint/map/GetVehicleXml.ashx?RouteId=3')

jfaganUK

### Functions for connecting and running uclassify text

#' Create an output dataset
#'
#' @param text_vec The vector of text that will be used
#' @return A data.table
uclassify_output_dt <- function(text_vec) {
  N <- length(text_vec)
  data.table(txt = text_vec, text_coverage = numeric(N))
}

jfaganUK

library(dplyr)
library(igraph)

clean_graph <- function(teamID, el) {
  e <- el %>%  filter(id == teamID) %>%
    select(source, target)
  g <- graph_from_data_frame(e) %>%
    as.undirected(mode = 'collapse', edge.attr.comb = 'max') %>%
    simplify
  return(g)

jfaganUK

reduce.tdm <- function(m, rs = 1, cs = 100) {
  repeat {
    i <- sum(dim(m))
    cat("Min row sum\t", min(rowSums(m)),"\tMin col sum\t",min(colSums(m)), "\n")
    m <- m[rowSums(m) >= rs, colSums(m) >= cs]
    if(sum(dim(m)) == i) break
  }
  return(m)
}
m <- reduce.tdm(m)

jfaganUK

## Animate optim ordinary least squares

rm(list=ls())
gc()
library(ggplot2)
library(tidyverse)
library(foreign)
library(gganimate)
library(transformr)
library(data.table)

jfaganUK

## Animate fitting ordinary least squares
# Author: Jesse Michael Fagan, PhD
# Date: 2020-02-10T19:29

## Packages ########################################
rm(list=ls())
gc()
library(magick)
library(gganimate)
library(transformr)