***** soodoku

## mturk.ipynb

      
              1 file
            
          
              0 forks
            
          
              0 comments
            
          
              1 star
            
          
                soodoku
                / mturk.ipynb
            
            
              Created Aug 31, 2018
            
          
      View mturk.ipynb
  
    
      Sorry, something went wrong. Reload?
      Sorry, we cannot display this file.
      Sorry, this file is invalid so it cannot be displayed.
      
          Viewer requires iframe.
      
    
## get_unique_domain_names_from_comscore.py
#
# Get All Unique Domain Names from comScore
#
# INPUT: comScore browsing data file
#
# OUTPUT: a text file containing a list of unique domains
#
# PAREMETERS:
#   + INTERNET_USAGE_FILE: path to the comScore browsing data
#   + FINAL_OUTPUT_FILE: path to intended output file

## county_dma_2016.R

library(readr)
library(dplyr)
a_string <- read_file("nielsen_2016")
split_lines <- strsplit(a_string, "\r\n")[[1]]
split_cols  <- strsplit(split_lines, "--")
dat_frame <- ldply(split_cols)
names(dat_frame) <- c("dma", "counties")
write.csv(dat_frame, file = "dma_counties_2016.csv", row.names = F)

## state_leg_twitter_handles_shor_mccarty_scores.csv

          
            State
            Position
            Name
            @Twitter Handle
            Part Affiliation
            Boris Shor's Score

            
              AZ
              Senator
              David Bradley
              @Bradley4AZ
              Democrat
              -1.253

            
              AZ
              Senator
              Katie Hobbs
              @katiehobbs
              Democrat
              -1.684

            
              AZ
              Senator
              Ed Ableser
              @SenatorAbleser
              Democrat
              -1.606

            
              AZ
              Senator
              Barbara McGuire
              @SenBarbMcGuire
              Democrat
              -0.672

            
              AZ
              Senator
              Steve Farley
              @SteveFarleyAZ
              Democrat
              -1.413

            
              AZ
              Senator
              Adam Driggs
              @AdamDriggs
              Republican
              0.738

            
              AZ
              Senator
              Bob Worsley
              @bob_worsley
              Republican
              0.46

            
              AZ
              Senator
              Kelli Ward
              @kelliwardaz
              Republican
              1.144

            
              AZ
              Senator
              Nancy Barto
              @NancyBarto
              Republican
              0.996

## cces_2006_fairest.R

# Output = http://gbytes.gsood.com/2013/11/02/the-fairest-of-them-all/

# Uses cces_recode.R here: https://github.com/soodoku/in-n-out/scripts/cces_recode.R

# Plotting the fairest of all media
library(lattice)
png("fairmedia.png")
dotplot(t(t(table(droplevels(cces06$fairmedia[cces06$fairmedia != "Don't know"]), cces06$pid3[cces06$fairmedia != "Don't know"]))/colSums(table(droplevels(cces06$v2112[cces06$fairmedia != "Don't know"]), cces06$pid3[cces06$fairmedia != "Don't know"]))),
main = "Which network do you think provides the \n fairest coverage of national news?",

## fun.md

      
              1 file
            
          
              0 forks
            
          
              0 comments
            
          
              0 stars
            
          
                soodoku
                / fun.md
            
            
              Last active Oct 30, 2017
            
              
                Fun Math
              
          
      View fun.md
  
    
    Fun Math
Fun Fact 1

1 - 1 + 1 - 1 + 1 - 1 + .... = 1/2
Proof (1) by Luigi Grandi:

S  = 1 - 1 + 1 - 1 + 1 - 1 + ...

1 - S = 1 - (1 - 1 + 1 - 1 + 1 - 1 + ...)

= 1 - 1 + 1 - 1 + 1 - 1 + ...

  
## approval.csv
Last,First,N,Mode,Date Start,Date End,TotApp,TotDis,TotDK,DemApp,DemDis,DemDK,RepApp,RepDis,RepDK,IndApp,IndDis,IndDK,LibApp,LibDis,LibDK,ModApp,ModDis,ModDK,ConApp,ConDis,ConDK,Source,Link,,,,,,,,,
Bachmann,Michelle,928,Phone,07/15/11,07/17/11,29,45,26,16,58,26,45,27,28,28,47,24,15,64,21,17,53,30,50,24,26,PPP,http://www.publicpolicypolling.com/pdf/2011/PPP_Release_National_720925.pdf,,,,,,,,,
Bachmann,Michelle,700,Phone,10/07/11,10/10/11,27,56,17,15,68,17,43,36,21,23,64,13,11,77,12,14,62,23,49,34,17,PPP,http://www.publicpolicypolling.com/pdf/2011/PPP_Release_US_1011513.pdf,,,,,,,,,
Bachmann,Michelle,700,Phone,12/16/11,12/18/11,30,54,16,22,65,13,41,39,19,26,59,16,21,71,8,20,67,12,42,34,23,PPP,http://www.publicpolicypolling.com/pdf/2011/PPP_Release_National_1220925.pdf,,,,,,,,,
Bloomberg,Michael,707,Phone,11/19/10,11/21/10,19,38,44,24,30,46,12,48,40,19,37,44,28,29,43,24,28,48,9,53,39,PPP,http://publicpolicypolling.blogspot.com/2010/11/americans-not-impressed-with-bloomberg.html,,,,,,,,,
Bloomberg,Michael,700,P

## tp_trelli.r
devtools::install_github("abresler/gdeltr2")
devtools::install_github("hafen/trelliscopejs")

library(gdeltr2)
library(dplyr)

asb_ocr <- "Brooklyn Nets"
gkg_codes <-
  get_codes_gkg_themes()
imageweb_codes <- get_gdelt_codebook_ft_api(code_book = "imageweb")

## rent control

# Read the data
sf <- read.csv("sf_tenants.csv")

# Recode
sf$market_rates <- gsub("%", "", sapply(strsplit(sf$market_rate, " / "), "[", 2)) # market_rate
sf$rent_control_rates <- gsub("%", "", sapply(strsplit(sf$rent_control, " / "), "[", 2)) # market_rate

# Ratio of rent_control vs. rent_control
sf$ratio <- as.numeric(sf$rent_control_rates)/as.numeric(sf$market_rates)

## Liberal Regex Pattern for All URLs
The regex patterns in this gist are intended to match any URLs,
including "mailto:foo@example.com", "x-whatever://foo", etc. For a
pattern that attempts only to match web URLs (http, https), see:
https://gist.github.com/gruber/8891611


# Single-line version of pattern:

(?i)\b((?:[a-z][\w-]+:(?:/{1,3}|[a-z0-9%])|www\d{0,3}[.]|[a-z0-9.\-]+[.][a-z]{2,4}/)(?:[^\s()<>]+|\(([^\s()<>]+|(\([^\s()<>]+\)))*\))+(?:\(([^\s()<>]+|(\([^\s()<>]+\)))*\)|[^\s`!()\[\]{};:'".,<>?«»“”‘’]))
	#
	# Get All Unique Domain Names from comScore
	#
	# INPUT: comScore browsing data file
	#
	# OUTPUT: a text file containing a list of unique domains
	#
	# PAREMETERS:
	# + INTERNET_USAGE_FILE: path to the comScore browsing data
	# + FINAL_OUTPUT_FILE: path to intended output file

	library(readr)
	library(dplyr)
	a_string <- read_file("nielsen_2016")
	split_lines <- strsplit(a_string, "\r\n")[[1]]
	split_cols <- strsplit(split_lines, "--")
	dat_frame <- ldply(split_cols)
	names(dat_frame) <- c("dma", "counties")
	write.csv(dat_frame, file = "dma_counties_2016.csv", row.names = F)
State	Position	Name	@Twitter Handle	Part Affiliation	Boris Shor's Score
AZ	Senator	David Bradley	@Bradley4AZ	Democrat	-1.253
AZ	Senator	Katie Hobbs	@katiehobbs	Democrat	-1.684
AZ	Senator	Ed Ableser	@SenatorAbleser	Democrat	-1.606
AZ	Senator	Barbara McGuire	@SenBarbMcGuire	Democrat	-0.672
AZ	Senator	Steve Farley	@SteveFarleyAZ	Democrat	-1.413
AZ	Senator	Adam Driggs	@AdamDriggs	Republican	0.738
AZ	Senator	Bob Worsley	@bob_worsley	Republican	0.46
AZ	Senator	Kelli Ward	@kelliwardaz	Republican	1.144
AZ	Senator	Nancy Barto	@NancyBarto	Republican	0.996

	# Output = http://gbytes.gsood.com/2013/11/02/the-fairest-of-them-all/

	# Uses cces_recode.R here: https://github.com/soodoku/in-n-out/scripts/cces_recode.R

	# Plotting the fairest of all media
	library(lattice)
	png("fairmedia.png")
	dotplot(t(t(table(droplevels(cces06$fairmedia[cces06$fairmedia != "Don't know"]), cces06$pid3[cces06$fairmedia != "Don't know"]))/colSums(table(droplevels(cces06$v2112[cces06$fairmedia != "Don't know"]), cces06$pid3[cces06$fairmedia != "Don't know"]))),
	main = "Which network do you think provides the \n fairest coverage of national news?",
	Last,First,N,Mode,Date Start,Date End,TotApp,TotDis,TotDK,DemApp,DemDis,DemDK,RepApp,RepDis,RepDK,IndApp,IndDis,IndDK,LibApp,LibDis,LibDK,ModApp,ModDis,ModDK,ConApp,ConDis,ConDK,Source,Link,,,,,,,,,
	Bachmann,Michelle,928,Phone,07/15/11,07/17/11,29,45,26,16,58,26,45,27,28,28,47,24,15,64,21,17,53,30,50,24,26,PPP,http://www.publicpolicypolling.com/pdf/2011/PPP_Release_National_720925.pdf,,,,,,,,,
	Bachmann,Michelle,700,Phone,10/07/11,10/10/11,27,56,17,15,68,17,43,36,21,23,64,13,11,77,12,14,62,23,49,34,17,PPP,http://www.publicpolicypolling.com/pdf/2011/PPP_Release_US_1011513.pdf,,,,,,,,,
	Bachmann,Michelle,700,Phone,12/16/11,12/18/11,30,54,16,22,65,13,41,39,19,26,59,16,21,71,8,20,67,12,42,34,23,PPP,http://www.publicpolicypolling.com/pdf/2011/PPP_Release_National_1220925.pdf,,,,,,,,,
	Bloomberg,Michael,707,Phone,11/19/10,11/21/10,19,38,44,24,30,46,12,48,40,19,37,44,28,29,43,24,28,48,9,53,39,PPP,http://publicpolicypolling.blogspot.com/2010/11/americans-not-impressed-with-bloomberg.html,,,,,,,,,
	Bloomberg,Michael,700,P
	devtools::install_github("abresler/gdeltr2")
	devtools::install_github("hafen/trelliscopejs")

	library(gdeltr2)
	library(dplyr)

	asb_ocr <- "Brooklyn Nets"
	gkg_codes <-
	get_codes_gkg_themes()
	imageweb_codes <- get_gdelt_codebook_ft_api(code_book = "imageweb")

	# Read the data
	sf <- read.csv("sf_tenants.csv")

	# Recode
	sf$market_rates <- gsub("%", "", sapply(strsplit(sf$market_rate, " / "), "[", 2)) # market_rate
	sf$rent_control_rates <- gsub("%", "", sapply(strsplit(sf$rent_control, " / "), "[", 2)) # market_rate

	# Ratio of rent_control vs. rent_control
	sf$ratio <- as.numeric(sf$rent_control_rates)/as.numeric(sf$market_rates)
	The regex patterns in this gist are intended to match any URLs,
	including "mailto:foo@example.com", "x-whatever://foo", etc. For a
	pattern that attempts only to match web URLs (http, https), see:
	https://gist.github.com/gruber/8891611


	# Single-line version of pattern:

	(?i)\b((?:[a-z][\w-]+:(?:/{1,3}\|[a-z0-9%])\|www\d{0,3}[.]\|[a-z0-9.\-]+[.][a-z]{2,4}/)(?:[^\s()<>]+\|\(([^\s()<>]+\|(\([^\s()<>]+\)))\))+(?:\(([^\s()<>]+\|(\([^\s()<>]+\)))\)\|[^\s`!()\[\]{};:'".,<>?«»“”‘’]))