gaurav soodoku

## state_abbrev_fips.txt
1 AL
2 AK
4 AZ
5 AR
6 CA
8 CO
9 CT
10 DE
11 DC
12 FL

## state_various.csv

          
            state
            code
            num
            census
            icpsr
            icpsr2

            
              Alabama
              AL
              1
              South
              41
              41 AL ALABAMA

            
              Alaska
              AK
              2
              West
              81
              81 AK ALASKA

            
              Arizona
              AZ
              3
              West
              61
              61 AZ ARIZONA

            
              Arkansas
              AR
              4
              South
              42
              42 AR ARKANSAS

            
              California
              CA
              5
              West
              71
              71 CA CALIFORNIA

            
              Colorado
              CO
              6
              West
              62
              62 CO COLORADO

            
              Connecticut
              CT
              7
              Northeast
              1
              01 CT CONNECTICUT

            
              Delaware
              DE
              8
              South
              11
              11 DE DELAWARE

            
              District of Columbia
              DC
              9
              Northeast
              55
              55 DC DISTRICT OF COLUMBIA

## missing.R


# Load libs
library(ggplot2)


# Simulate correlated data
R = matrix(cbind(1,.80, .80,1), nrow=2)
U = t(chol(R))

## scrape_wisconsin_ads.py
'''
Text from Searchable pdfs
Scrape Text off Wisconsin Ads pdfs

Uses pyPdf to get text from searchable pdfs. The script is for tailored for getting data
from Wisconsin Political Ads Database: http://wiscadproject.wisc.edu/Storyboards.

@author: Gaurav Sood

Created on November 02, 2011

## 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)

## text_classifier.R
"
Basic Text Classifier
	- Takes a csv with a text column, and column of labels
	- Splits into train and test
	- Preprocesses text using tm/bag-of-words, 1/2-order Markov
	- Uses SVM and Lasso

@author: Gaurav Sood

"

## median.R
> median(FALSE)
[1] FALSE

> median(c(TRUE, FALSE))
[1] 0.5

> median(c(TRUE, FALSE, TRUE))
[1] TRUE

> f <- factor(c('a', 'b', 'c'), levels = c('a', 'b', 'c'), ordered = TRUE)

## mturk.ipynb

      
              1 file
            
          
              0 forks
            
          
              0 comments
            
          
              1 star
            
          
                soodoku
                / mturk.ipynb
            
            
              Created
              August 31, 2018 17:40
            
          
      Sorry, something went wrong. Reload?
      Sorry, we cannot display this file.
      Sorry, this file is invalid so it cannot be displayed.
      
          Viewer requires iframe.
      
    
## classify.R
#' Manual classification of observations
#'
#' \code{classify} launches a Shiny app to manually classify a subset of observations.
#'
#' @param x A character vector.
#' @param btn_labels A character vector of length 2 corresponding to 0 and 1.
#' @return A vector of 0/1 for each element in \code{x}.
#' @export
#' @examples \dontrun{
#'  foo <- sprintf('%s (%.2f miles per gallon)', rownames(mtcars), mtcars$mpg)

## a_pandas_on_ray_blogpost_01.ipynb

      
              6 files
            
          
              3 forks
            
          
              1 comment
            
          
              6 stars
            
          
                devin-petersohn
                / a_pandas_on_ray_blogpost_01.ipynb
            
            
              Last active
              October 14, 2018 19:14
            
              
                Pandas on Ray - Lessons learned Blog Post. Also introduces Modin, a project for unifying the APIs of computing engines.
              
          
      Sorry, something went wrong. Reload?
      Sorry, we cannot display this file.
      Sorry, this file is invalid so it cannot be displayed.
      
          Viewer requires iframe.
state	code	num	census	icpsr	icpsr2
Alabama	AL	1	South	41	41 AL ALABAMA
Alaska	AK	2	West	81	81 AK ALASKA
Arizona	AZ	3	West	61	61 AZ ARIZONA
Arkansas	AR	4	South	42	42 AR ARKANSAS
California	CA	5	West	71	71 CA CALIFORNIA
Colorado	CO	6	West	62	62 CO COLORADO
Connecticut	CT	7	Northeast	1	01 CT CONNECTICUT
Delaware	DE	8	South	11	11 DE DELAWARE
District of Columbia	DC	9	Northeast	55	55 DC DISTRICT OF COLUMBIA



	# Load libs
	library(ggplot2)


	# Simulate correlated data
	R = matrix(cbind(1,.80, .80,1), nrow=2)
	U = t(chol(R))
	'''
	Text from Searchable pdfs
	Scrape Text off Wisconsin Ads pdfs

	Uses pyPdf to get text from searchable pdfs. The script is for tailored for getting data
	from Wisconsin Political Ads Database: http://wiscadproject.wisc.edu/Storyboards.

	@author: Gaurav Sood

	Created on November 02, 2011

	# 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)
	"
	Basic Text Classifier
	- Takes a csv with a text column, and column of labels
	- Splits into train and test
	- Preprocesses text using tm/bag-of-words, 1/2-order Markov
	- Uses SVM and Lasso

	@author: Gaurav Sood

	"
	> median(FALSE)
	[1] FALSE

	> median(c(TRUE, FALSE))
	[1] 0.5

	> median(c(TRUE, FALSE, TRUE))
	[1] TRUE

	> f <- factor(c('a', 'b', 'c'), levels = c('a', 'b', 'c'), ordered = TRUE)
	#' Manual classification of observations
	#'
	#' \code{classify} launches a Shiny app to manually classify a subset of observations.
	#'
	#' @param x A character vector.
	#' @param btn_labels A character vector of length 2 corresponding to 0 and 1.
	#' @return A vector of 0/1 for each element in \code{x}.
	#' @export
	#' @examples \dontrun{
	#' foo <- sprintf('%s (%.2f miles per gallon)', rownames(mtcars), mtcars$mpg)