John Ramey ramhiser

## impute-naive.r
#' Naive imputation of missing data
#'
#' Imputes missing data in a data frame a column at a time, e.g., univariate.
#' Missing numeric values are replaced with the median. Similarly, missing
#' factor values are replaced with the mode.
#'
#' If \code{draw} is set to \code{TRUE}, missing data are drawn from a basic
#' distribution to make the imputation slightly less naive. For continuous,
#' values are drawn from a uniform distribution ranging from the min to max
#' values observed within the column. For categorical, values are drawn from a

## austin-thd-stores.html

<!DOCTYPE html>
<html>
<head>
	<title>Leaflet Example -- Home Depot Stores</title>
	<meta charset="utf-8" />

	<meta name="viewport" content="width=device-width, initial-scale=1.0">

	 <link rel="stylesheet" href="http://cdn.leafletjs.com/leaflet-0.7.3/leaflet.css" />

## add-na-rows.r
# Useful for drawing polygons with leaflet
# Polygons are stored in a `tbl_df` object with a mandatory `NA` row between each
# polygon so that `leaflet` knows to stop drawing between each polygon.
# Rather than magic, I found a slick way to do this via `dplyr::arrange`
# See: (http://stackoverflow.com/a/25267681/234233).

# Example using Iris data set:
df_na <- matrix(NA, nrow=nlevels(iris$Species), ncol=ncol(iris) - 1)
df_na <- tbl_df(as.data.frame(df_na))
colnames(df_na) <- setdiff(colnames(iris), "Species")

## leaflet-county-explorer.r
# TODO: Add a Shiny dropdown to select demographic variable
library(leaflet)
library(noncensus)
library(dplyr)

data("counties", package="noncensus")
data("county_polygons", package="noncensus")
data("quick_facts", package="noncensus")

counties <- counties %>%

## exercise-4.7.r
library(dplyr)
library(BHH2)

df <- expand.grid(drivers=c('I', 'II', 'III', 'IV'),
                  cars=1:4)
df <- rbind(df, df) %>% arrange(drivers, cars)
df$treatment <- c(
  rep(c('A', 'B', 'D', 'C'), each=2),
  rep(c('D', 'C', 'A', 'B'), each=2),
  rep(c('B', 'D', 'C', 'A'), each=2),

## boundieboxes.py
import numpy as np
import matplotlib.pyplot as plt
import matplotlib.patches as mpatch
import matplotlib.cm as cm
import cv2
import csv
from sklearn import cluster


def find_points(gray_img, color_img, num_points):

## thd.py
%matplotlib inline
from yahoo_finance import Share
import matplotlib.pylab
import pandas as pd
import numpy as np

thd = Share('HD')
thd_prices = thd.get_historical('2010-01-01', '2015-06-01')

thd_prices = pd.DataFrame(thd_prices)

## sample.js
// Weighted random sample from a vector
//
// By default, the `weights` are set to 1. This equates to equal weighting.
// Loosely based on http://codereview.stackexchange.com/a/4265
//
// If any weight is `null`, revert to default weights (i.e., all 1).
//
// A random-number generator (RNG) seed is optionally set via seedrandom.js.
// NOTE: The JS file is loaded via jQuery.
// Details: https://github.com/davidbau/seedrandom

## sphinx2vtt.py
#!/usr/bin/env python
import argparse
import sys
import time
from itertools import izip, count


def parse_sphinx_line(line):
    '''Parse a line from Sphinx's closed captioning alignment'''
    line_split = line.split()

## RSQlite.r
library('RSQLite')

# Establishes a connection to the specified SQLite database file.
db_filename <- "choose_filename.db3"
db_driver <- dbDriver("SQLite")
db_conn <- dbConnect(db_driver, dbname = db_filename)

# An alternative is... (not sure about the difference)
# db_conn <- dbConnect(SQLite(), dbname = db_filename)
	#' Naive imputation of missing data
	#'
	#' Imputes missing data in a data frame a column at a time, e.g., univariate.
	#' Missing numeric values are replaced with the median. Similarly, missing
	#' factor values are replaced with the mode.
	#'
	#' If \code{draw} is set to \code{TRUE}, missing data are drawn from a basic
	#' distribution to make the imputation slightly less naive. For continuous,
	#' values are drawn from a uniform distribution ranging from the min to max
	#' values observed within the column. For categorical, values are drawn from a

	<!DOCTYPE html>
	<html>
	<head>
	<title>Leaflet Example -- Home Depot Stores</title>
	<meta charset="utf-8" />

	<meta name="viewport" content="width=device-width, initial-scale=1.0">

	<link rel="stylesheet" href="http://cdn.leafletjs.com/leaflet-0.7.3/leaflet.css" />
	# Useful for drawing polygons with leaflet
	# Polygons are stored in a `tbl_df` object with a mandatory `NA` row between each
	# polygon so that `leaflet` knows to stop drawing between each polygon.
	# Rather than magic, I found a slick way to do this via `dplyr::arrange`
	# See: (http://stackoverflow.com/a/25267681/234233).

	# Example using Iris data set:
	df_na <- matrix(NA, nrow=nlevels(iris$Species), ncol=ncol(iris) - 1)
	df_na <- tbl_df(as.data.frame(df_na))
	colnames(df_na) <- setdiff(colnames(iris), "Species")
	# TODO: Add a Shiny dropdown to select demographic variable
	library(leaflet)
	library(noncensus)
	library(dplyr)

	data("counties", package="noncensus")
	data("county_polygons", package="noncensus")
	data("quick_facts", package="noncensus")

	counties <- counties %>%
	library(dplyr)
	library(BHH2)

	df <- expand.grid(drivers=c('I', 'II', 'III', 'IV'),
	cars=1:4)
	df <- rbind(df, df) %>% arrange(drivers, cars)
	df$treatment <- c(
	rep(c('A', 'B', 'D', 'C'), each=2),
	rep(c('D', 'C', 'A', 'B'), each=2),
	rep(c('B', 'D', 'C', 'A'), each=2),
	import numpy as np
	import matplotlib.pyplot as plt
	import matplotlib.patches as mpatch
	import matplotlib.cm as cm
	import cv2
	import csv
	from sklearn import cluster


	def find_points(gray_img, color_img, num_points):
	%matplotlib inline
	from yahoo_finance import Share
	import matplotlib.pylab
	import pandas as pd
	import numpy as np

	thd = Share('HD')
	thd_prices = thd.get_historical('2010-01-01', '2015-06-01')

	thd_prices = pd.DataFrame(thd_prices)
	// Weighted random sample from a vector
	//
	// By default, the `weights` are set to 1. This equates to equal weighting.
	// Loosely based on http://codereview.stackexchange.com/a/4265
	//
	// If any weight is `null`, revert to default weights (i.e., all 1).
	//
	// A random-number generator (RNG) seed is optionally set via seedrandom.js.
	// NOTE: The JS file is loaded via jQuery.
	// Details: https://github.com/davidbau/seedrandom
	#!/usr/bin/env python
	import argparse
	import sys
	import time
	from itertools import izip, count


	def parse_sphinx_line(line):
	'''Parse a line from Sphinx's closed captioning alignment'''
	line_split = line.split()
	library('RSQLite')

	# Establishes a connection to the specified SQLite database file.
	db_filename <- "choose_filename.db3"
	db_driver <- dbDriver("SQLite")
	db_conn <- dbConnect(db_driver, dbname = db_filename)

	# An alternative is... (not sure about the difference)
	# db_conn <- dbConnect(SQLite(), dbname = db_filename)