Getting data on your government

 1 # install_github('govdat', 'schamberlain')
 2 library(govdat)
 3 library(reshape2)
 4 library(ggplot2)
 5 
 6 dems <- sll_cw_dates(phrase = "science", start_date = "1996-01-20", end_date = "2012-09-01", 
 7     granularity = "year", party = "D", printdf = TRUE)
 8 repubs <- sll_cw_dates(phrase = "science", start_date = "1996-01-20", end_date = "2012-09-01", 
 9     granularity = "year", party = "R", printdf = TRUE)
10 df <- melt(rbind(data.frame(party = rep("D", nrow(dems)), dems), data.frame(party = rep("R", 
11     nrow(repubs)), repubs)))
12 df$count <- as.numeric(df$count)
13 
14 ggplot(df, aes(yearmonth, count, colour = party, group = party)) + geom_line() + 
15     scale_colour_manual(values = c("blue", "red")) + labs(y = "use of the word 'Science'") + 
16     theme_bw(base_size = 18) + opts(axis.text.x = theme_text(size = 10), panel.grid.major = theme_blank(), 
17     panel.grid.minor = theme_blank(), legend.position = c(0.2, 0.8))

1 library(plyr)
2 
3 # Let's get Nancy Pelosi's entity ID
4 sll_ts_aggregatesearch("Nancy Pelosi")[[1]]

$name
[1] "Nancy Pelosi (D)"

$count_given
[1] 0

$firm_income
[1] 0

$count_lobbied
[1] 0

$seat
[1] "federal:house"

$total_received
[1] 13769274

$state
[1] "CA"

$lobbying_firm
NULL

$count_received
[1] 9852

$party
[1] "D"

$total_given
[1] 0

$type
[1] "politician"

$id
[1] "85ab2e74589a414495d18cc7a9233981"

$non_firm_spending
[1] 0

$is_superpac
NULL

1 # Her entity ID
2 sll_ts_aggregatesearch("Nancy Pelosi")[[1]]$id

[1] "85ab2e74589a414495d18cc7a9233981"

1 # And search for her top donors by sector
2 nancy <- ldply(sll_ts_aggregatetopsectors(sll_ts_aggregatesearch("Nancy Pelosi")[[1]]$id))
3 nancy  # but just abbreviations for sectors

   sector count     amount
1       F  1847 2698672.00
2       P   981 2243050.00
3       H   829 1412700.00
4       K  1345 1409836.00
5       Q  1223 1393154.00
6       N   829 1166187.00
7       B   537  932044.00
8       W   724  760800.00
9       Y   820  664926.00
10      E   201  283575.00

1 data(sll_ts_sectors)  # load sectors abbrevations data
2 nancy2 <- merge(nancy, sll_ts_sectors, by = "sector")  # attach full sector names
3 nancy2_melt <- melt(nancy2[, -1], id.vars = 3)
4 nancy2_melt$value <- as.numeric(nancy2_melt$value)
5 
6 # and lets plot some results
7 ggplot(nancy2_melt, aes(sector_name, value)) + geom_bar() + coord_flip() + facet_wrap(~variable, 
8     scales = "free", ncol = 1)

1 ## It looks like a lot of individual donations (the count facet) by
2 ## finance/insurance/realestate, but by amount, the most (by slim margin)
3 ## is from labor organizations.

1 out <- nyt_cg_memberbioroles("A000358")  # cool, lots of info, output cutoff for brevity
2 out[[3]][[1]][1:2]

$member_id
[1] "A000358"

$first_name
[1] "Todd"

1 # we can get her twitter id from this bio, and search twitter using
2 # twitteR package
3 akintwitter <- out[[3]][[1]]$twitter_id
4 
5 # install.packages('twitteR')
6 library(twitteR)
7 tweets <- userTimeline(akintwitter, n = 100)
8 tweets[1:5]  # there's some gems in there no doubt

[[1]]
[1] "RepToddAkin: Do you receive my Akin Alert e-newsletter?  Pick the issues you’d like to get updates on and sign up here!\nhttp://t.co/nZfiRjTF"

[[2]]
[1] "RepToddAkin: If the 2001 & 2003 tax policies expire, taxes will increase over $4 trillion in the next 10 years. America can't afford it. #stopthetaxhike"

[[3]]
[1] "RepToddAkin: A govt agency's order shouldn't defy constitutional rights. I'm still working for #religiousfreedom and repealing the HHS mandate. #prolife"

[[4]]
[1] "RepToddAkin: I am a cosponsor of the bill being considered today to limit abortions in DC. RT if you agree! #prolife http://t.co/Mesrjl0w"

[[5]]
[1] "RepToddAkin: We need to #StopTheTaxHike. Raising taxes like the President wants would destroy more than 700,000 jobs. #4jobs http://t.co/KUTd0M7U"