R Stats script used to process NYPD Stop & Frisk Data for map at http://project.wnyc.org/stop-frisk-delta/embed.html

stop-frisk-process.r

# load foreign package
library("foreign", lib.loc="/Library/Frameworks/R.framework/Versions/2.15/Resources/library")

# set working directory
setwd("/Volumes/JK-Spinner/Dropbox/Coding/r/stop-frisk-delta")

## To get the .por file into R, I turned on the "foreign" package
data2011<-read.spss("2011.por")

#check to see field names
names(data2011)

# change to data frame
# found here: http://www.statmethods.net/management/typeconversion.html
data2011<-as.data.frame(data2011)

# check to see dimension of data
dim(data2011)

# Selecting just the varibles we need
picvars <- c("SER_NUM", "XCOORD", "YCOORD")

csvdata <- data2011[picvars]
dim(csvdata)
names(csvdata)

# save as csv
# but don't quote out the values, so they're not considered strings
write.csv(csvdata,file="stop-frisk-2011-all-points.csv", quote = FALSE)

# --------------

### do again for 2012 data 
meddata2012<-read.spss("2012.por")

#check to see field names
names(data2012)

# change to data frame
# found here: http://www.statmethods.net/management/typeconversion.html
data2012<-as.data.frame(data2012)

# check to see dimension of data
dim(data2012)

# Selecting just the varibles we need
picvars <- c("SER_NUM", "XCOORD", "YCOORD")

csvdata <- data2012[picvars]
dim(csvdata)
names(csvdata)

# save as csv
# but don't quote out the values, so they're not considered strings
write.csv(csvdata,file="stop-frisk-2012-all-points.csv", quote = FALSE)