jsonbecker

#!/usr/bin/python

import requests
import sys
from re import search
from subprocess import check_output

url = check_output('pbpaste')
r = requests.get(url)

jsonbecker

install.packages('rvest')
library(rvest)
library(dplyr)
page <- html('http://app.providencejournal.com/topics/special-reports/tables/firefigher-salaries-fy2014/firefighter-salaries.htm')
data <- page %>% 
        html_node('table') %>% 
        html_table() %>% 
        .[c(-1,-2,-3),] %>% 
        as.data.frame

jsonbecker

## Current pattern
function(myList){
  do_stuff_with(mylist$attribute1, myList$attribute2)
  do_stuff_with(mylist$attribute3, myList$attribute4)
}

## Desired pattern
function(myList){
  do_stuff_with(attribute1, attribute2)
  do_stuff_with(attribute4, attribute4)

jsonbecker

from sys import argv
import re

name, file_path = argv

p = re.compile(r"[\s]\(\((.*?[)]{0,1})\)\)[\s]{0,1}")
# The tricky part here is to match all text between (()), including as many as
# one set of (), which may even terminate ))). The {0,1} captures as many as
# one ). The trailing space is there because I often surrounded the (()) with
# a space to make it clear in the Wordpress editor.

jsonbecker

modal_person_attribute <- function(df, attribute){
  # df: rbind of all person tables from all years
  # attribute: vector name to calculate the modal value
  # Calculate the number of instances an attributed is associated with an id
  mode <- do.call(rbind, 
                  tapply(as.character(df[[attribute]]), df$sasid, 
                         function(x) data.frame(attribute=rle(x)$values, 
                                                counts=rle(x)$lengths)))
  names(mode) <- c(as.character(attribute), 'counts')
  # Clean up

jsonbecker

modal_person_attribute <- function(df, attribute){
  # df: rbind of all person tables from all years
  # attribute: vector name to calculate the modal value
  # Calculate the number of instances an attributed is associated with an id
  dt <- data.table(df)
  mode <- dt[, rle(as.character(.SD[[attribute]])), by=sasid]
  setnames(mode, c('sasid', 'counts', as.character(attribute)))
  setkeyv(mode, c('sasid', 'counts'))
  # Only include attributes with the maximum values. This is equivalent to the
  # mode with two records when there is a tie.

jsonbecker

cutoff_matrix <- function(df, classifier, outcome, breaks=seq(1,0,-.01)){
  results <- data.frame(cutoff=vector(mode='numeric', length=length(breaks)),
                        true_pos=vector(mode='numeric', length=length(breaks)),
                        true_neg=vector(mode='numeric', length=length(breaks)),
                        false_pos=vector(mode='numeric', length=length(breaks)),
                        false_neg=vector(mode='numeric', length=length(breaks)))
  for(i in seq(1, length(breaks))){
    value <- breaks[i]
    j <- data.frame(table(df[[classifier]]>value, df[[outcome]]))
    results[i,1] <- value

jsonbecker

<!-- In your content.md meta data include a link attribute like this -->

Link: http://www.getpelican.com


<!-- In your articles.html template -->
{% block content %}
    {% if article.link %} <!-- checks if article has link as a metadata attribute -->
      <h1 class="title"><a href='{{ article.link }}' title="Link">{{ article.title }}</a></h1>
    {% else %}

jsonbecker

import sys
import os, shutil, time
import subprocess
import os.path
import exifread
from datetime import datetime

def photoDateSIPS(f):
  "Return the date/time on which the given photo was taken."

jsonbecker

# Ever want to log how long someting takes? I know I do. timing()
# isn't about benchmarking, it's about getting feedback from long running
# tasks, especially if they are scheduled in production. Anyway, I love
# this function because it's a simple wrapper that can go around anything.
# I use it inside our tools at Allovue when extracting data to get things
# like this:

#> accounts <- extract_data(config_file$accounts)
# Starting queries/accounts.sql at: Mon Sep 19 15:27:34 2016 
# Completed at: Mon Sep 19 15:28:14 2016