An R package for managing and analyzing text, by Ken Benoit and Paul Nulty.[thanks]
[thanks]: This research was supported by the European Research Council grant ERC-2011-StG 283794-QUANTESS. Code contributors to the project include Ben Lauderdale, Pablo Barberà, and Kohei Watanabe.
quanteda makes it easy to manage texts in the form of a corpus, defined as a collection of texts that includes document-level variables specific to each text, as well as meta-data for documents and for the collection as a whole. quanteda includes tools to make it easy and fast to manuipulate the texts in a corpus, by performing the most common natural language processing tasks simply and quickly, such as tokenizing, stemming, or forming ngrams. quanteda's functions for tokenizing texts and forming multiple tokenized documents into a document-feature matrix are both extremely fast and extremely simple to use. quanteda can segment texts easily by words, paragraphs, sentences, or even user-supplied delimiters and tags.
Built on the text processing functions in the stringi package, which is in turn built on C++ implementation of the ICU libraries for Unicode text handling, quanteda pays special attention to fast and correct implementation of Unicode and the handling of text in any character set, following conversion internally to UTF-8.
quanteda is built for efficiency and speed, through its design around three infrastructures: the string package for text processing, the data.table package for indexing large documents efficiently, and the Matrix package for sparse matrix objects. If you can fit it into memory, quanteda will handle it quickly. (And eventually, we will make it possible to process objects even larger than available memory.)
quanteda is principally designed to allow users a fast and convenient method to go from a corpus of texts to a selected matrix of documents by features, after defining what the documents and features. The package makes it easy to redefine documents, for instance by splitting them into sentences or paragraphs, or by tags, as well as to group them into larger documents by document variables, or to subset them based on logical conditions or combinations of document variables. The package also implements common NLP feature selection functions, such as removing stopwords and stemming in numerous languages, selecting words found in dictionaries, treating words as equivalent based on a user-defined “thesaurus”, and trimming and weighting features based on document frequency, feature frequency, and related measures such as tf-idf.
The tools for getting texts into a corpus object include:
The tools for working with a corpus include:
For extracting features from a corpus, quanteda provides the following tools:
For analyzing the resulting document-feature matrix created
when features are abstracted from a corpus, quanteda provides:
Additional features of quanteda include:
the ability to explore texts using key-words-in-context;
fast computation of a variety of readability indexes;
fast computation of a variety of lexical diversity measures;
quick computation of word or document association measures, for clustering or to compute similarity scores for other purposes; and
a comprehensive suite of descriptive statistics on text such as the number of sentences, words, characters, or syllables per document.
Planned features coming soon to quanteda are:
bootstrapping methods for texts that makes it easy to resample texts from pre-defined units, to facilitate computation of confidence intervals on textual statistics using techniques of non-parametric bootstrapping, but applied to the original texts as data.
expansion of the document-feature matrix structure through a standard interface called textmodel(). (As of version 0.8.0, textmodel works in a basic fashion only for the "Wordscores” and “wordfish” scaling models.)
## Working with other text analysis packages
quanteda is hardly unique in providing facilities for working with
text – the excellent tm package already provides many of the
features we have described. quanteda is designed to complement those
packages, as well to simplify the implementation of the
text-to-analysis workflow. quanteda corpus structures are simpler
objects than in tm*s, as are the document-feature matrix
objects from quanteda, compared to the sparse matrix implementation
found in *tm. However, there is no need to choose only one
package, since we provide translator functions from one matrix or
corpus object to the other in quanteda.
Once constructed, a quanteda “dfm”“ can be easily passed to other text-analysis packages for additional analysis of topic models or scaling, such as:
topic models (including converters for direct use with the topicmodels, LDA, and stm packages)
document scaling (using quanteda's own functions for the "wordfish” and “Wordscores” models, direct use with the ca package for correspondence analysis, or scaling with the austin package)
document classification methods, using (for example) Naive Bayes, k-nearest neighbour, or Support Vector Machines
more sophisticated machine learning through a variety of other packages that take matrix or matrix-like inputs.
graphical analysis, including word clouds and strip plots for selected themes or words.
As of version 0.8.0, the GitHub master repository will always contain the development version of quanteda, while the CRAN version will contain the latest “stable” version. You therefore have two options for installing the package:
From CRAN, using your R package installer, or simply
install.packages("quanteda")
(For the development version) From GitHub, using
devtools::install_github("kbenoit/quanteda")
Because this compiles some C++ source code, you will need a compiler installed. If you are using a Windows platform, this means you will need also to install the Rtools software available from CRAN. If you are using OS X, you will probably need to install XCode, available for free from the App Store.
(Optional) You can install some additional corpus data from quantedaData using
## devtools required to install quanteda from Github
devtools::install_github("kbenoit/quantedaData")
require(quanteda)
quanteda has a simple and powerful tool for loading texts: textfile(). This function takes a file or fileset from disk or a URL, and loads it as a special class of pre-corpus object, known as a corpusSource object, from which a corpus can be constructed using a second command, corpus().
textfile() works on:
.txt) files;.csv) files;The corpus constructor command corpus() works directly on:
corpusSource object created using textfile(); andVCorpus corpus object from the tm package.The simplest case is to create a corpus from a vector of texts already in memory in R. This gives the advanced R user complete flexbility with his or her choice of text inputs, as there are almost endless ways to get a vector of texts into R.
If we already have the texts in this form, we can call the corpus constructor function directly. We can demonstrate this on the built-in character vector of 57 US president inaugural speeches called inaugTexts.
str(inaugTexts) # this gives us some information about the object
#> Named chr [1:57] "Fellow-Citizens of the Senate and of the House of Representatives:\n\nAmong the vicissitudes incident to life no event could ha"| __truncated__ ...
#> - attr(*, "names")= chr [1:57] "1789-Washington" "1793-Washington" "1797-Adams" "1801-Jefferson" ...
myCorpus <- corpus(inaugTexts) # build the corpus
summary(myCorpus, n=5)
#> Corpus consisting of 57 documents, showing 5 documents.
#>
#> Text Types Tokens Sentences
#> 1789-Washington 595 1430 24
#> 1793-Washington 90 135 4
#> 1797-Adams 794 2318 37
#> 1801-Jefferson 681 1726 42
#> 1805-Jefferson 776 2166 45
#>
#> Source: /private/var/folders/46/zfn6gwj15d3_n6dhyy1cvwc00000gp/T/Rtmp0zgvBy/Rbuild549f7ed34f2a/quanteda/vignettes/* on x86_64 by kbenoit
#> Created: Mon Jan 11 10:19:30 2016
#> Notes:
If we wanted, we could add some document-level variables – what quanteda calls docvars – to this corpus.
We can do this using the R's substring() function to extract characters from a name – in this case, the
name of the character vector inaugTexts. This works using our fixed starting and ending positions with
substring() because these names are a very regular format of YYYY-PresidentName.
docvars(myCorpus, "President") <- substring(names(inaugTexts), 6)
docvars(myCorpus, "Year") <- as.integer(substring(names(inaugTexts), 1, 4))
summary(myCorpus, n=5)
#> Corpus consisting of 57 documents, showing 5 documents.
#>
#> Text Types Tokens Sentences President Year
#> 1789-Washington 595 1430 24 Washington 1789
#> 1793-Washington 90 135 4 Washington 1793
#> 1797-Adams 794 2318 37 Adams 1797
#> 1801-Jefferson 681 1726 42 Jefferson 1801
#> 1805-Jefferson 776 2166 45 Jefferson 1805
#>
#> Source: /private/var/folders/46/zfn6gwj15d3_n6dhyy1cvwc00000gp/T/Rtmp0zgvBy/Rbuild549f7ed34f2a/quanteda/vignettes/* on x86_64 by kbenoit
#> Created: Mon Jan 11 10:19:30 2016
#> Notes:
If we wanted to tag each document with additional meta-data not considered a document variable of interest for analysis, but rather something that we need to know as an attribute of the document, we could also add those to our corpus.
metadoc(myCorpus, "language") <- "english"
metadoc(myCorpus, "docsource") <- paste("inaugTexts", 1:ndoc(myCorpus), sep="_")
summary(myCorpus, n=5, showmeta=TRUE)
#> Corpus consisting of 57 documents, showing 5 documents.
#>
#> Text Types Tokens Sentences President Year _language
#> 1789-Washington 595 1430 24 Washington 1789 english
#> 1793-Washington 90 135 4 Washington 1793 english
#> 1797-Adams 794 2318 37 Adams 1797 english
#> 1801-Jefferson 681 1726 42 Jefferson 1801 english
#> 1805-Jefferson 776 2166 45 Jefferson 1805 english
#> _docsource
#> inaugTexts_1
#> inaugTexts_2
#> inaugTexts_3
#> inaugTexts_4
#> inaugTexts_5
#>
#> Source: /private/var/folders/46/zfn6gwj15d3_n6dhyy1cvwc00000gp/T/Rtmp0zgvBy/Rbuild549f7ed34f2a/quanteda/vignettes/* on x86_64 by kbenoit
#> Created: Mon Jan 11 10:19:30 2016
#> Notes:
The last command, metadoc, allows you to define your own document meta-data fields. Note that in assiging just the single value of "english", R has recycled the value until it matches the number of documents in the corpus. In creating
a simple tag for our custom metadoc field docsource, we used the quanteda function ndoc() to retrieve
the number of documents in our corpus. This function is deliberately designed to work in a way similar to
functions you may already use in R, such as nrow() and ncol().
textfile()# Twitter json
mytf1 <- textfile("~/Dropbox/QUANTESS/social media/zombies/tweets.json")
myCorpusTwitter <- corpus(mytf1)
summary(myCorpusTwitter, 5)
# generic json - needs a textField specifier
mytf2 <- textfile("~/Dropbox/QUANTESS/Manuscripts/collocations/Corpora/sotu/sotu.json",
textField = "text")
summary(corpus(mytf2), 5)
# text file
mytf3 <- textfile("~/Dropbox/QUANTESS/corpora/project_gutenberg/pg2701.txt", cache = FALSE)
summary(corpus(mytf3), 5)
# multiple text files
mytf4 <- textfile("~/Dropbox/QUANTESS/corpora/inaugural/*.txt", cache = FALSE)
summary(corpus(mytf4), 5)
# multiple text files with docvars from filenames
mytf5 <- textfile("~/Dropbox/QUANTESS/corpora/inaugural/*.txt",
docvarsfrom="filenames", sep="-", docvarnames=c("Year", "President"))
summary(corpus(mytf5), 5)
# XML data
mytf6 <- textfile("~/Dropbox/QUANTESS/quanteda_working_files/xmlData/plant_catalog.xml",
textField = "COMMON")
summary(corpus(mytf6), 5)
# csv file
write.csv(data.frame(inaugSpeech = texts(inaugCorpus), docvars(inaugCorpus)),
file = "/tmp/inaugTexts.csv", row.names = FALSE)
mytf7 <- textfile("/tmp/inaugTexts.csv", textField = "inaugSpeech")
summary(corpus(mytf7), 5)
quanteda provides an interface to retrieve and store data from a twitter search as a corpus object. The REST API query uses the twitteR package, and an API authorization from twitter is required. The process of obtaining this authorization is described in detail here: https://openhatch.org/wiki/Community_Data_Science_Workshops/Twitter_authentication_setup, correct as of October 2014. The twitter API is a commercial service, and rate limits and the data returned are determined by twitter.
Four keys are required, to be passed to quanteda's getTweets source function, in addition to the search query term and the number of results required. The maximum number of results that can be obtained is not exactly identified in the API documentation, but experimentation indicates an upper bound of around 1500 results from a single query, with a frequency limit of one query per minute.
The code below performs authentication and runs a search for the string 'quantitative'. Many other functions for working with the API are available from the twitteR package. An R interface to the streaming API is also available link.
# These keys are examples and may not work! Get your own key at dev.twitter.com
consumer_key="vRLy03ef6OFAZB7oCL4jA"
consumer_secret="wWF35Lr1raBrPerVHSDyRftv8qB1H7ltV0T3Srb3s"
access_token="1577780816-wVbOZEED8KZs70PwJ2q5ld2w9CcvcZ2kC6gPnAo"
token_secret="IeC6iYlgUK9csWiP524Jb4UNM8RtQmHyetLi9NZrkJA"
tw <- getTweets('quantitative', numResults=20, consumer_key, consumer_secret, access_token, token_secret)
The return value from the above query is a source object which can be passed to quanteda's corpus constructor, and the document variables are set to correspond with tweet metadata returned by the API.
twCorpus <- corpus(tw)
names(docvars(twCorpus))
A corpus is designed to be a “library” of original documents that have been converted to plain, UTF-8 encoded text, and stored along with meta-data at the corpus level and at the document-level. We have a special name for document-level meta-data: docvars. These are variables or features that describe attributes of each document.
A corpus is designed to be a more or less static container of texts with respect to processing and analysis. This means that the texts in corpus are not designed to be changed internally through (for example) cleaning or pre-processing steps, such as stemming or removing punctuation. Rather, texts can be extracted from the corpus as part of processing, and assigned to new objects, but the idea is that the corpus will remain as an original reference copy so that other analyses – for instance those in which stems and punctuation were required, such as analyzing a reading ease index – can be performed on the same corpus.
To extract texts from a a corpus, we use an extractor, called texts().
texts(inaugCorpus)[2]
#> 1793-Washington
#> "Fellow citizens, I am again called upon by the voice of my country to execute the functions of its Chief Magistrate. When the occasion proper for it shall arrive, I shall endeavor to express the high sense I entertain of this distinguished honor, and of the confidence which has been reposed in me by the people of united America.\n\nPrevious to the execution of any official act of the President the Constitution requires an oath of office. This oath I am now about to take, and in your presence: That if it shall be found during my administration of the Government I have in any instance violated willingly or knowingly the injunctions thereof, I may (besides incurring constitutional punishment) be subject to the upbraidings of all who are now witnesses of the present solemn ceremony.\n\n "
To summarize the texts from a corpus, we can call a summary() method defined for a corpus.
summary(ie2010Corpus)
#> Corpus consisting of 14 documents.
#>
#> Text Types Tokens Sentences year debate
#> 2010_BUDGET_01_Brian_Lenihan_FF 1754 7916 404 2010 BUDGET
#> 2010_BUDGET_02_Richard_Bruton_FG 995 4086 217 2010 BUDGET
#> 2010_BUDGET_03_Joan_Burton_LAB 1521 5790 309 2010 BUDGET
#> 2010_BUDGET_04_Arthur_Morgan_SF 1499 6510 345 2010 BUDGET
#> 2010_BUDGET_05_Brian_Cowen_FF 1544 5964 252 2010 BUDGET
#> 2010_BUDGET_06_Enda_Kenny_FG 1087 3896 155 2010 BUDGET
#> 2010_BUDGET_07_Kieran_ODonnell_FG 638 2086 133 2010 BUDGET
#> 2010_BUDGET_08_Eamon_Gilmore_LAB 1123 3807 202 2010 BUDGET
#> 2010_BUDGET_09_Michael_Higgins_LAB 457 1149 44 2010 BUDGET
#> 2010_BUDGET_10_Ruairi_Quinn_LAB 415 1181 60 2010 BUDGET
#> 2010_BUDGET_11_John_Gormley_Green 381 939 50 2010 BUDGET
#> 2010_BUDGET_12_Eamon_Ryan_Green 486 1519 90 2010 BUDGET
#> 2010_BUDGET_13_Ciaran_Cuffe_Green 426 1144 45 2010 BUDGET
#> 2010_BUDGET_14_Caoimhghin_OCaolain_SF 1110 3699 177 2010 BUDGET
#> number foren name party
#> 01 Brian Lenihan FF
#> 02 Richard Bruton FG
#> 03 Joan Burton LAB
#> 04 Arthur Morgan SF
#> 05 Brian Cowen FF
#> 06 Enda Kenny FG
#> 07 Kieran ODonnell FG
#> 08 Eamon Gilmore LAB
#> 09 Michael Higgins LAB
#> 10 Ruairi Quinn LAB
#> 11 John Gormley Green
#> 12 Eamon Ryan Green
#> 13 Ciaran Cuffe Green
#> 14 Caoimhghin OCaolain SF
#>
#> Source: /home/paul/Dropbox/code/quantedaData/* on x86_64 by paul
#> Created: Tue Sep 16 15:58:21 2014
#> Notes:
We can save the output from the summary command as a data frame, and plot some basic descriptive statistics with this information:
tokenInfo <- summary(inaugCorpus)
#> Corpus consisting of 57 documents.
#>
#> Text Types Tokens Sentences Year President
#> 1789-Washington 595 1430 24 1789 Washington
#> 1793-Washington 90 135 4 1793 Washington
#> 1797-Adams 794 2318 37 1797 Adams
#> 1801-Jefferson 681 1726 42 1801 Jefferson
#> 1805-Jefferson 776 2166 45 1805 Jefferson
#> 1809-Madison 520 1175 21 1809 Madison
#> 1813-Madison 518 1210 33 1813 Madison
#> 1817-Monroe 980 3370 121 1817 Monroe
#> 1821-Monroe 1200 4470 131 1821 Monroe
#> 1825-Adams 962 2915 74 1825 Adams
#> 1829-Jackson 500 1128 25 1829 Jackson
#> 1833-Jackson 474 1176 30 1833 Jackson
#> 1837-VanBuren 1252 3839 95 1837 VanBuren
#> 1841-Harrison 1806 8446 210 1841 Harrison
#> 1845-Polk 1262 4803 153 1845 Polk
#> 1849-Taylor 480 1088 22 1849 Taylor
#> 1853-Pierce 1115 3333 104 1853 Pierce
#> 1857-Buchanan 892 2824 89 1857 Buchanan
#> 1861-Lincoln 1011 3634 138 1861 Lincoln
#> 1865-Lincoln 336 699 27 1865 Lincoln
#> 1869-Grant 464 1127 41 1869 Grant
#> 1873-Grant 522 1338 44 1873 Grant
#> 1877-Hayes 803 2484 59 1877 Hayes
#> 1881-Garfield 973 2975 112 1881 Garfield
#> 1885-Cleveland 645 1683 44 1885 Cleveland
#> 1889-Harrison 1300 4386 157 1889 Harrison
#> 1893-Cleveland 797 2014 58 1893 Cleveland
#> 1897-McKinley 1187 3965 130 1897 McKinley
#> 1901-McKinley 815 2212 100 1901 McKinley
#> 1905-Roosevelt 384 984 33 1905 Roosevelt
#> 1909-Taft 1376 5429 159 1909 Taft
#> 1913-Wilson 627 1699 68 1913 Wilson
#> 1917-Wilson 524 1529 60 1917 Wilson
#> 1921-Harding 1120 3327 149 1921 Harding
#> 1925-Coolidge 1160 4056 197 1925 Coolidge
#> 1929-Hoover 997 3558 171 1929 Hoover
#> 1933-Roosevelt 708 1880 85 1933 Roosevelt
#> 1937-Roosevelt 683 1808 96 1937 Roosevelt
#> 1941-Roosevelt 495 1341 68 1941 Roosevelt
#> 1945-Roosevelt 259 557 26 1945 Roosevelt
#> 1949-Truman 742 2272 116 1949 Truman
#> 1953-Eisenhower 857 2454 123 1953 Eisenhower
#> 1957-Eisenhower 586 1659 93 1957 Eisenhower
#> 1961-Kennedy 535 1366 52 1961 Kennedy
#> 1965-Johnson 528 1489 98 1965 Johnson
#> 1969-Nixon 708 2124 106 1969 Nixon
#> 1973-Nixon 508 1802 69 1973 Nixon
#> 1977-Carter 493 1224 53 1977 Carter
#> 1981-Reagan 844 2433 128 1981 Reagan
#> 1985-Reagan 866 2564 125 1985 Reagan
#> 1989-Bush 749 2317 143 1989 Bush
#> 1993-Clinton 600 1598 81 1993 Clinton
#> 1997-Clinton 719 2157 112 1997 Clinton
#> 2001-Bush 585 1584 97 2001 Bush
#> 2005-Bush 725 2071 101 2005 Bush
#> 2009-Obama 893 2390 112 2009 Obama
#> 2013-Obama 781 2097 90 2013 Obama
#>
#> Source: /home/paul/Dropbox/code/quanteda/* on x86_64 by paul
#> Created: Fri Sep 12 12:41:17 2014
#> Notes:
if (require(ggplot2))
ggplot(data=tokenInfo, aes(x=Year, y=Tokens, group=1)) + geom_line() + geom_point() +
scale_x_discrete(labels=c(seq(1789,2012,12)), breaks=seq(1789,2012,12) )
#> Loading required package: ggplot2
# Longest inaugural address: William Henry Harrison
tokenInfo[which.max(tokenInfo$Tokens),]
#> Text Types Tokens Sentences Year President
#> 1841-Harrison 1841-Harrison 1806 8446 210 1841 Harrison
The + operator provides a simple method for concatenating two corpus objects. If they contain
different sets of document-level variables, these will be stitched together in a fashion that guarantees
that no information is lost. Corpus-level medata data is also concatenated.
library(quanteda)
mycorpus1 <- corpus(inaugTexts[1:5], note="First five inaug speeches.")
mycorpus2 <- corpus(inaugTexts[53:57], note="Last five inaug speeches.")
mycorpus3 <- mycorpus1 + mycorpus2
summary(mycorpus3)
#> Corpus consisting of 10 documents.
#>
#> Text Types Tokens Sentences
#> 1789-Washington 595 1430 24
#> 1793-Washington 90 135 4
#> 1797-Adams 794 2318 37
#> 1801-Jefferson 681 1726 42
#> 1805-Jefferson 776 2166 45
#> 1997-Clinton 719 2157 112
#> 2001-Bush 585 1584 97
#> 2005-Bush 725 2071 101
#> 2009-Obama 893 2390 112
#> 2013-Obama 781 2097 90
#>
#> Source: Combination of corpuses mycorpus1 and mycorpus2
#> Created: Mon Jan 11 10:19:30 2016
#> Notes: First five inaug speeches. Last five inaug speeches.
There is a method of the subset() function defined for corpus objects, where a new corpus can
be extracted based on logical conditions applied to docvars:
summary(subset(inaugCorpus, Year > 1990))
#> Corpus consisting of 6 documents.
#>
#> Text Types Tokens Sentences Year President
#> 1993-Clinton 600 1598 81 1993 Clinton
#> 1997-Clinton 719 2157 112 1997 Clinton
#> 2001-Bush 585 1584 97 2001 Bush
#> 2005-Bush 725 2071 101 2005 Bush
#> 2009-Obama 893 2390 112 2009 Obama
#> 2013-Obama 781 2097 90 2013 Obama
#>
#> Source: /home/paul/Dropbox/code/quanteda/* on x86_64 by paul
#> Created: Fri Sep 12 12:41:17 2014
#> Notes:
summary(subset(inaugCorpus, President == "Adams"))
#> Corpus consisting of 2 documents.
#>
#> Text Types Tokens Sentences Year President
#> 1797-Adams 794 2318 37 1797 Adams
#> 1825-Adams 962 2915 74 1825 Adams
#>
#> Source: /home/paul/Dropbox/code/quanteda/* on x86_64 by paul
#> Created: Fri Sep 12 12:41:17 2014
#> Notes:
The kwic function (KeyWord In Context) performs a search for a word and allows us to view the contexts in which it occurs:
options(width = 200)
kwic(inaugCorpus, "terror")
#> contextPre keyword contextPost
#> [1797-Adams, 1327] fraud or violence, by [ terror ] , intrigue, or venality
#> [1933-Roosevelt, 112] nameless, unreasoning, unjustified [ terror ] which paralyzes needed efforts to
#> [1941-Roosevelt, 289] seemed frozen by a fatalistic [ terror ] , we proved that this
#> [1961-Kennedy, 868] alter that uncertain balance of [ terror ] that stays the hand of
#> [1981-Reagan, 821] freeing all Americans from the [ terror ] of runaway living costs.
#> [1997-Clinton, 1055] They fuel the fanaticism of [ terror ] . And they torment the
#> [1997-Clinton, 1655] maintain a strong defense against [ terror ] and destruction. Our children
#> [2009-Obama, 1646] advance their aims by inducing [ terror ] and slaughtering innocents, we
kwic(inaugCorpus, "terror", wholeword = TRUE)
#> Warning in tokenize.character(x, ...): Argument wholeword not used.
#> contextPre keyword contextPost
#> [1797-Adams, 1327] fraud or violence, by [ terror ] , intrigue, or venality
#> [1933-Roosevelt, 112] nameless, unreasoning, unjustified [ terror ] which paralyzes needed efforts to
#> [1941-Roosevelt, 289] seemed frozen by a fatalistic [ terror ] , we proved that this
#> [1961-Kennedy, 868] alter that uncertain balance of [ terror ] that stays the hand of
#> [1981-Reagan, 821] freeing all Americans from the [ terror ] of runaway living costs.
#> [1997-Clinton, 1055] They fuel the fanaticism of [ terror ] . And they torment the
#> [1997-Clinton, 1655] maintain a strong defense against [ terror ] and destruction. Our children
#> [2009-Obama, 1646] advance their aims by inducing [ terror ] and slaughtering innocents, we
kwic(inaugCorpus, "communist")
#> contextPre keyword contextPost
#> [1949-Truman, 838] the actions resulting from the [ Communist ] philosophy are a threat to
In the above summary, Year and President are variables associated with each document. We can access such variables with the docvars() function.
# inspect the document-level variables
head(docvars(inaugCorpus))
#> Year President
#> 1789-Washington 1789 Washington
#> 1793-Washington 1793 Washington
#> 1797-Adams 1797 Adams
#> 1801-Jefferson 1801 Jefferson
#> 1805-Jefferson 1805 Jefferson
#> 1809-Madison 1809 Madison
# inspect the corpus-level metadata
metacorpus(inaugCorpus)
#> $source
#> [1] "/home/paul/Dropbox/code/quanteda/* on x86_64 by paul"
#>
#> $created
#> [1] "Fri Sep 12 12:41:17 2014"
#>
#> $notes
#> NULL
#>
#> $citation
#> NULL
More corpora are available from the quantedaData package.
In order to perform statistical analysis such as document scaling, we
must extract a matrix associating values for certain features with each
document. In quanteda, we use the dfm function to produce such a matrix. “dfm” is short for document-feature matrix, and always refers to documents
in rows and “features” as columns. We fix this dimensional orientation because is is
standard in data analysis to have a unit of analysis as a row, and features or variables
pertaining to each unit as columns. We call them “features” rather than terms, because
features are more general than terms: they can be defined as raw terms, stemmed terms, the parts of speech of terms, terms after stopwords have been removed,
or a dictionary class to which a term belongs. Features can be entirely general, such as ngrams or syntactic dependencies, and we leave this open-ended.
To simply tokenize a text, quanteda provides a powerful command called tokenize(). This produces an
intermediate object, consisting of a list of tokens in the form of character vectors, where each element
of the list corresponds to an input document.
tokenize() is deliberately conservative, meaning that it does not remove anything from the text unless
told to do so.
txt <- c(text1 = "This is $10 in 999 different ways,\n up and down; left and right!",
text2 = "@kenbenoit working: on #quanteda 2day\t4ever, http://textasdata.com?page=123.")
tokenize(txt)
#> tokenizedText object from 2 documents.
#> text1 :
#> [1] "This" "is" "$" "10" "in" "999" "different" "ways" "," "up" "and" "down" ";" "left" "and" "right"
#> [17] "!"
#>
#> text2 :
#> [1] "@kenbenoit" "working" ":" "on" "#quanteda" "2day" "4ever" "," "http" ":" "/"
#> [12] "/" "textasdata.com" "?" "page" "=" "123" "."
tokenize(txt, removeNumbers=TRUE, removePunct=TRUE)
#> tokenizedText object from 2 documents.
#> text1 :
#> [1] "This" "is" "in" "different" "ways" "up" "and" "down" "left" "and" "right"
#>
#> text2 :
#> [1] "@kenbenoit" "working" "on" "#quanteda" "2day" "4ever" "http" "textasdata.com" "page"
tokenize(txt, removeNumbers=FALSE, removePunct=TRUE)
#> tokenizedText object from 2 documents.
#> text1 :
#> [1] "This" "is" "10" "in" "999" "different" "ways" "up" "and" "down" "left" "and" "right"
#>
#> text2 :
#> [1] "@kenbenoit" "working" "on" "#quanteda" "2day" "4ever" "http" "textasdata.com" "page" "123"
tokenize(txt, removeNumbers=TRUE, removePunct=FALSE)
#> tokenizedText object from 2 documents.
#> text1 :
#> [1] "This" "is" "$" "in" "different" "ways" "," "up" "and" "down" ";" "left" "and" "right" "!"
#>
#> text2 :
#> [1] "@kenbenoit" "working" ":" "on" "#quanteda" "2day" "4ever" "," "http" ":" "/"
#> [12] "/" "textasdata.com" "?" "page" "=" "."
tokenize(txt, removeNumbers=FALSE, removePunct=FALSE)
#> tokenizedText object from 2 documents.
#> text1 :
#> [1] "This" "is" "$" "10" "in" "999" "different" "ways" "," "up" "and" "down" ";" "left" "and" "right"
#> [17] "!"
#>
#> text2 :
#> [1] "@kenbenoit" "working" ":" "on" "#quanteda" "2day" "4ever" "," "http" ":" "/"
#> [12] "/" "textasdata.com" "?" "page" "=" "123" "."
tokenize(txt, removeNumbers=FALSE, removePunct=FALSE, removeSeparators=FALSE)
#> tokenizedText object from 2 documents.
#> text1 :
#> [1] "This" " " "is" " " "$" "10" " " "in" " " "999" " " "different" " " "ways" "," "\n"
#> [17] " " "up" " " "and" " " "down" ";" " " "left" " " "and" " " "right" "!"
#>
#> text2 :
#> [1] "@kenbenoit" " " "working" ":" " " "on" " " "#quanteda" " " "2day" "\t"
#> [12] "4ever" "," " " "http" ":" "/" "/" "textasdata.com" "?" "page" "="
#> [23] "123" "."
We also have the option to tokenize characters:
tokenize("Great website: http://textasdata.com?page=123.", what="character")
#> tokenizedText object from 1 document.
#> Component 1 :
#> [1] "G" "r" "e" "a" "t" "w" "e" "b" "s" "i" "t" "e" ":" "h" "t" "t" "p" ":" "/" "/" "t" "e" "x" "t" "a" "s" "d" "a" "t" "a" "." "c" "o" "m" "?" "p" "a" "g" "e" "=" "1" "2" "3" "."
tokenize("Great website: http://textasdata.com?page=123.", what="character",
removeSeparators=FALSE)
#> tokenizedText object from 1 document.
#> Component 1 :
#> [1] "G" "r" "e" "a" "t" " " "w" "e" "b" "s" "i" "t" "e" ":" " " "h" "t" "t" "p" ":" "/" "/" "t" "e" "x" "t" "a" "s" "d" "a" "t" "a" "." "c" "o" "m" "?" "p" "a" "g" "e" "=" "1" "2" "3" "."
and sentences:
# sentence level
tokenize(c("Kurt Vongeut said; only assholes use semi-colons.",
"Today is Thursday in Canberra: It is yesterday in London.",
"En el caso de que no puedas ir con ellos, ¿quieres ir con nosotros?"),
what = "sentence")
#> tokenizedText object from 3 documents.
#> Component 1 :
#> [1] "Kurt Vongeut said; only assholes use semi-colons."
#>
#> Component 2 :
#> [1] "Today is Thursday in Canberra: It is yesterday in London."
#>
#> Component 3 :
#> [1] "En el caso de que no puedas ir con ellos, ¿quieres ir con nosotros?"
Tokenizing texts is an intermediate option, and most users will want to skip straight to constructing
a document-feature matrix. For this, we have a Swiss-army knife function, called dfm(), which performs
tokenization and tabulates the extracted features into a matrix of documents by features. Unlike
the conservative approach taken by tokenize(), the dfm() function applies certain options by default,
such as toLower() – a separate function for lower-casing texts – and removes punctuation. All of the options to tokenize() can be passed to dfm(), however.
myCorpus <- subset(inaugCorpus, Year > 1990)
# make a dfm
myDfm <- dfm(myCorpus)
#> Creating a dfm from a corpus ...
#> ... lowercasing
#> ... tokenizing
#> ... indexing documents: 6 documents
#> ... indexing features: 2,303 feature types
#> ... created a 6 x 2303 sparse dfm
#> ... complete.
#> Elapsed time: 0.024 seconds.
myDfm[, 1:5]
#> Document-feature matrix of: 6 documents, 5 features.
#> 6 x 5 sparse Matrix of class "dfmSparse"
#> features
#> docs my fellow citizens today we
#> 1993-Clinton 7 5 2 10 52
#> 1997-Clinton 6 7 7 5 42
#> 2001-Bush 3 1 9 2 47
#> 2005-Bush 2 3 6 3 37
#> 2009-Obama 2 1 1 6 62
#> 2013-Obama 3 3 6 4 68
Other options for a dfm() include removing stopwords, and stemming the tokens.
# make a dfm, removing stopwords and applying stemming
myStemMat <- dfm(myCorpus, ignoredFeatures = stopwords("english"), stem=TRUE)
#> Creating a dfm from a corpus ...
#> ... lowercasing
#> ... tokenizing
#> ... indexing documents: 6 documents
#> ... indexing features: 2,303 feature types
#> ... removed 115 features, from 174 supplied (glob) feature types
#> ... stemming features (English), trimmed 504 feature variants
#> ... created a 6 x 1684 sparse dfm
#> ... complete.
#> Elapsed time: 0.033 seconds.
myStemMat[, 1:5]
#> Document-feature matrix of: 6 documents, 5 features.
#> 6 x 5 sparse Matrix of class "dfmSparse"
#> features
#> docs fellow citizen today celebr mysteri
#> 1993-Clinton 5 2 10 4 1
#> 1997-Clinton 7 8 6 1 0
#> 2001-Bush 1 10 2 0 0
#> 2005-Bush 3 7 3 2 0
#> 2009-Obama 1 1 6 2 0
#> 2013-Obama 3 8 6 1 0
The option ignoredFeatures provides a list of tokens to be ignored. Most users will
supply a list of pre-defined “stop words”, defined for numerous languages, accessed through
the stopwords() function:
head(stopwords("english"), 20)
#> [1] "i" "me" "my" "myself" "we" "our" "ours" "ourselves" "you" "your" "yours" "yourself" "yourselves" "he" "him"
#> [16] "his" "himself" "she" "her" "hers"
head(stopwords("russian"), 10)
#> [1] "и" "в" "во" "не" "что" "он" "на" "я" "с" "со"
head(stopwords("arabic"), 10)
#> [1] "فى" "في" "كل" "لم" "لن" "له" "من" "هو" "هي" "قوة"
The dfm can be inspected in the Enviroment pane in RStudio, or by calling R's View function. Calling plot on a dfm will display a wordcloud using the wordcloud package
mydfm <- dfm(ukimmigTexts, ignoredFeatures=c("will", stopwords("english")))
#>
#> ... lowercasing
#> ... tokenizing
#> ... indexing documents: 9 documents
#> ... indexing features: 1,586 feature types
#> ... removed 97 features, from 175 supplied (glob) feature types
#> ... created a 9 x 1489 sparse dfm
#> ... complete.
#> Elapsed time: 0.016 seconds.
mydfm
#> Document-feature matrix of: 9 documents, 1,489 features.
To access a list of the most frequently occurring features, we can use topfeatures():
topfeatures(mydfm, 20) # 20 top words
#> immigration british people asylum britain uk system population country new immigrants ensure shall citizenship social national
#> 66 37 35 29 28 27 27 21 20 19 17 17 17 16 14 14
#> bnp illegal work percent
#> 13 13 13 12
Plotting a word cloud is very simple, since this is the default plot() method for a dfm class object:
plot(mydfm)
The plot.dfm() method passes arguments through to wordcloud() from the wordcloud package, and can prettify the plot using the same arguments:
if (require(RColorBrewer))
plot(mydfm, max.words=100, colors = brewer.pal(6, "Dark2"), scale=c(8, .5))
#> Loading required package: RColorBrewer
Often, we are interested in analysing how texts differ according to substantive factors which may be encoded in the document variables, rather than simply by the boundaries of the document files. We can group documents which share the same value for a document variable when creating a dfm:
byPartyDfm <- dfm(ie2010Corpus, groups = "party", ignoredFeatures = stopwords("english"))
#> Creating a dfm from a corpus ...
#> ... grouping texts by variable: party
#> ... lowercasing
#> ... tokenizing
#> ... indexing documents: 5 documents
#> ... indexing features: 4,881 feature types
#> ... removed 117 features, from 174 supplied (glob) feature types
#> ... created a 5 x 4764 sparse dfm
#> ... complete.
#> Elapsed time: 0.06 seconds.
We can sort this dfm, and inspect it:
sort(byPartyDfm)[, 1:10]
#> Document-feature matrix of: 5 documents, 10 features.
#> 5 x 10 sparse Matrix of class "dfmSparse"
#> features
#> docs will people budget government public minister tax economy pay jobs
#> FF 212 23 44 47 65 11 60 37 41 41
#> FG 93 78 71 61 47 62 11 20 29 17
#> Green 59 15 26 19 4 4 11 16 4 15
#> LAB 89 69 66 36 32 54 47 37 24 20
#> SF 104 81 53 73 31 39 34 50 24 27
Note that the most frequently occurring feature is “will”, a word usually on English stop lists, but one that is not included in quanteda's built-in English stopword list.
For some applications we have prior knowledge of sets of words that are indicative of traits we would like to measure from the text. For example, a general list of positive words might indicate positive sentiment in a movie review, or we might have a dictionary of political terms which are associated with a particular ideological stance. In these cases, it is sometimes useful to treat these groups of words as equivalent for the purposes of analysis, and sum their counts into classes.
For example, let's look at how words associated with terrorism and words associated with the economy vary by President in the inaugural speeches corpus. From the original corpus, we select Presidents since Clinton:
recentCorpus <- subset(inaugCorpus, Year > 1991)
Now we define a demonstration dictionary:
myDict <- dictionary(list(terror = c("terrorism", "terrorists", "threat"),
economy = c("jobs", "business", "grow", "work")))
We can use the dictionary when making the dfm:
byPresMat <- dfm(recentCorpus, dictionary = myDict)
#> Creating a dfm from a corpus ...
#> ... lowercasing
#> ... tokenizing
#> ... indexing documents: 6 documents
#> ... indexing features: 2,303 feature types
#> ... applying a dictionary consisting of 2 keys
#> ... created a 6 x 2 sparse dfm
#> ... complete.
#> Elapsed time: 0.033 seconds.
byPresMat
#> Document-feature matrix of: 6 documents, 2 features.
#> 6 x 2 sparse Matrix of class "dfmSparse"
#> features
#> docs terror economy
#> 1993-Clinton 0 8
#> 1997-Clinton 1 8
#> 2001-Bush 0 4
#> 2005-Bush 1 6
#> 2009-Obama 1 10
#> 2013-Obama 1 6
The constructor function dictionary() also works with two common “foreign” dictionary formats: the
LIWC and Provalis Research's Wordstat format. For instance, we can load the LIWC and apply this to the Presidential inaugural speech corpus:
liwcdict <- dictionary(file = "~/Dropbox/QUANTESS/dictionaries/LIWC/LIWC2001_English.dic",
format = "LIWC")
liwcdfm <- dfm(inaugTexts[52:57], dictionary = liwcdict, verbose = FALSE)
liwcdfm[, 1:10]
presDfm <- dfm(subset(inaugCorpus, Year>1980),
ignoredFeatures = stopwords("english"),
stem=TRUE, verbose=FALSE)
obamaSimil <- similarity(presDfm, c("2009-Obama" , "2013-Obama"), n = NULL,
margin = "documents", method = "cosine", normalize = FALSE)
dotchart(obamaSimil$`2009-Obama`, xlab = "Cosine similarity")
We can use these distances to plot a dendrogram, clustering presidents:
data(SOTUCorpus, package="quantedaData")
presDfm <- dfm(subset(SOTUCorpus, year > 1960), verbose = FALSE, stem = TRUE,
ignoredFeatures = stopwords("english"))
presDfm <- trim(presDfm, minCount=5, minDoc=3)
# hierarchical clustering - get distances on normalized dfm
presDistMat <- dist(as.matrix(weight(presDfm, "relFreq")))
# hiarchical clustering the distance object
presCluster <- hclust(presDistMat)
# label with document names
presCluster$labels <- docnames(presDfm)
# plot as a dendrogram
plot(presCluster)
We can also look at term similarities:
similarity(presDfm, c("fair", "health", "terror"), method = "cosine", normalize = FALSE)
#> similarity Matrix:
#> $fair
#> economi begin mani jefferson author howev faith god struggl call order never courag
#> 0.9080 0.9076 0.9039 0.8981 0.8944 0.8944 0.8867 0.8723 0.8660 0.8608 0.8607 0.8526 0.8391
#> best creat much pledg compass social alli believ danger continu failur full limit
#> 0.8367 0.8347 0.8316 0.8293 0.8281 0.8216 0.8216 0.8195 0.8165 0.8151 0.8083 0.8083 0.8083
#> tax well govern us now side bless opportun stand beyond cost travel vice
#> 0.8081 0.8065 0.8046 0.7963 0.7886 0.7877 0.7866 0.7807 0.7804 0.7785 0.7785 0.7785 0.7746
#> suffer size chariti hold prayer peac earth way take econom preserv meet year
#> 0.7746 0.7746 0.7746 0.7746 0.7707 0.7693 0.7686 0.7659 0.7641 0.7641 0.7641 0.7641 0.7612
#> among think weapon ever american must yet thoma almost republ sign troubl declin
#> 0.7537 0.7537 0.7532 0.7506 0.7499 0.7460 0.7459 0.7454 0.7454 0.7454 0.7454 0.7454 0.7454
#> rest histor intend agre poverti system upon carri back time lead assur fall
#> 0.7454 0.7454 0.7454 0.7454 0.7454 0.7454 0.7448 0.7419 0.7419 0.7398 0.7379 0.7379 0.7379
#> aim victori left will deficit fail threaten growth digniti o'neil occas transfer inflat
#> 0.7379 0.7379 0.7379 0.7370 0.7348 0.7348 0.7333 0.7333 0.7313 0.7303 0.7303 0.7303 0.7303
#> unemploy pace bear concern ethnic barrier core revers establish genius church prioriti import
#> 0.7303 0.7303 0.7303 0.7303 0.7303 0.7303 0.7303 0.7303 0.7303 0.7303 0.7303 0.7303 0.7303
#> unborn arsenal utmost john accomplish servant enterpris virginia wrote abus fill nation peopl
#> 0.7303 0.7303 0.7303 0.7303 0.7303 0.7303 0.7303 0.7303 0.7303 0.7303 0.7303 0.7292 0.7240
#> product small place histori feder confront program resolv interest pass work power polit
#> 0.7230 0.7230 0.7197 0.7175 0.7171 0.7161 0.7161 0.7089 0.7085 0.7085 0.7049 0.7033 0.7029
#> defens societi individu purpos strength bush decis race pay ride slow independ worthi
#> 0.7006 0.6957 0.6956 0.6956 0.6938 0.6928 0.6928 0.6928 0.6928 0.6928 0.6928 0.6928 0.6928
#> citizen trust show play restor demand famili respons return sick said find follow
#> 0.6902 0.6901 0.6885 0.6885 0.6885 0.6852 0.6847 0.6842 0.6831 0.6831 0.6831 0.6831 0.6831
#> road simpl today done reduc valu declar deep act number step told can
#> 0.6831 0.6831 0.6812 0.6803 0.6803 0.6792 0.6761 0.6708 0.6708 0.6708 0.6708 0.6708 0.6696
#> support storm presid share sacrific futur principl present born kill technolog blood let
#> 0.6694 0.6694 0.6691 0.6606 0.6583 0.6558 0.6547 0.6532 0.6532 0.6532 0.6532 0.6532 0.6516
#> away progress oath world two spend look person solemn bound strongest georg spoke
#> 0.6516 0.6508 0.6492 0.6463 0.6461 0.6460 0.6460 0.6455 0.6455 0.6455 0.6455 0.6455 0.6455
#> belong liber law poor safeti doubt earn one just live decad hear energi
#> 0.6455 0.6455 0.6455 0.6455 0.6455 0.6455 0.6445 0.6435 0.6432 0.6400 0.6390 0.6390 0.6390
#> commit strive endur life children go togeth man reach month line short fate
#> 0.6390 0.6390 0.6367 0.6367 0.6364 0.6346 0.6346 0.6331 0.6325 0.6325 0.6325 0.6325 0.6325
#> mutual west effort allow countri found young seek hero know group chanc state
#> 0.6325 0.6325 0.6325 0.6325 0.6295 0.6293 0.6293 0.6283 0.6283 0.6271 0.6262 0.6262 0.6235
#> remain last answer direct capac protect great determin goal price men tri common
#> 0.6233 0.6233 0.6228 0.6228 0.6211 0.6198 0.6120 0.6086 0.6086 0.6086 0.6051 0.6025 0.6025
#> safe servic keep reverend transit goe cast labor collect whatev manag capabl around
#> 0.6025 0.6025 0.6000 0.5963 0.5963 0.5963 0.5963 0.5963 0.5963 0.5963 0.5963 0.5963 0.5963
#> grown unleash self match aspir negoti citi shore white yield knew cut bond
#> 0.5963 0.5963 0.5963 0.5963 0.5963 0.5963 0.5963 0.5963 0.5963 0.5963 0.5963 0.5963 0.5963
#> begun bring domest conduct conquer civil uphold rage forward greater rais shall past
#> 0.5963 0.5963 0.5963 0.5963 0.5963 0.5963 0.5963 0.5963 0.5943 0.5934 0.5923 0.5923 0.5922
#> thank make america help tradit feed held destruct renew war father hope public
#> 0.5906 0.5891 0.5888 0.5885 0.5855 0.5855 0.5855 0.5855 0.5847 0.5843 0.5843 0.5822 0.5798
#> whose speak chief shown put remind depend loyalti inaugur hill kind local birthright
#> 0.5798 0.5798 0.5774 0.5774 0.5774 0.5774 0.5774 0.5774 0.5774 0.5774 0.5774 0.5774 0.5774
#> hall drive music heritag spare senat provid end moment industri open affirm still
#> 0.5774 0.5774 0.5774 0.5774 0.5774 0.5754 0.5729 0.5721 0.5715 0.5715 0.5715 0.5715 0.5678
#> everi secur build million stori noth gift though birth communiti fellow crisi human
#> 0.5618 0.5591 0.5590 0.5578 0.5543 0.5521 0.5521 0.5521 0.5521 0.5518 0.5514 0.5505 0.5500
#> women alon increas process busi worst borrow week boundari patrol except recognit reserv
#> 0.5477 0.5477 0.5477 0.5477 0.5477 0.5477 0.5477 0.5477 0.5477 0.5477 0.5477 0.5477 0.5477
#> command heroic job quiet balanc decid strengthen forbear ten magnific shoulder humil dignifi
#> 0.5477 0.5477 0.5477 0.5477 0.5477 0.5477 0.5477 0.5477 0.5477 0.5477 0.5477 0.5477 0.5477
#> river arlington paid earlier lie fame win repres bestow horseback raw aid wherev
#> 0.5477 0.5477 0.5477 0.5477 0.5477 0.5477 0.5477 0.5477 0.5477 0.5477 0.5477 0.5477 0.5477
#> took equip dramat mountain enjoy modern rebuild tide overwhelm hungri treasur debt due
#> 0.5477 0.5477 0.5477 0.5477 0.5477 0.5477 0.5477 0.5477 0.5477 0.5477 0.5477 0.5477 0.5477
#> unfortun origin awesom waver research missil nowher youth snow valley affect expect pain
#> 0.5477 0.5477 0.5477 0.5477 0.5477 0.5477 0.5477 0.5477 0.5477 0.5477 0.5477 0.5477 0.5477
#> lest conscienc knowledg grace grandest delay wind serious soil respect cynic exampl medicar
#> 0.5477 0.5477 0.5477 0.5477 0.5477 0.5477 0.5477 0.5477 0.5477 0.5477 0.5477 0.5477 0.5477
#> mistak favor substitut stranger respond lend search basic pursu subject swift turn start
#> 0.5477 0.5477 0.5477 0.5477 0.5477 0.5477 0.5477 0.5477 0.5477 0.5477 0.5477 0.5472 0.5449
#> destroy nuclear spirit long face need journey happi school arm chang dream problem
#> 0.5449 0.5445 0.5444 0.5440 0.5423 0.5422 0.5418 0.5384 0.5384 0.5333 0.5324 0.5321 0.5314
#> equal day worker els parti factori realiz adversari met reward invest ambit bad
#> 0.5289 0.5289 0.5270 0.5270 0.5270 0.5270 0.5270 0.5270 0.5270 0.5270 0.5270 0.5270 0.5270
#> stake right generat grow say might voic care rich achiev requir freedom hatfield
#> 0.5270 0.5266 0.5259 0.5217 0.5217 0.5217 0.5217 0.5217 0.5217 0.5196 0.5196 0.5167 0.5164
#> mondal baker moomaw occurr routin uniqu realli ceremoni normal gracious degre bulwark afflict
#> 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164
#> proport longest distort penal thrift crush fixed-incom alik shatter idl miseri indign burden
#> 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164
#> kept pile mortgag temporari conveni trend tremend upheav period misunderstand sever bastion tempt
#> 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164
#> complex self-rul elit superior someon equit singl special neglect section made food mine
#> 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164
#> teach heal profession industrialist shopkeep clerk cabbi truckdriv breed administr healthi vigor discrimin
#> 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164
#> runaway reviv inventori check consent intent curb distinct smother foster stifl extent avail
#> 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164
#> coincid parallel proportion intervent intrus result unnecessari excess loom creativ gate counter entrepreneur
#> 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164
#> voluntari art address makeup countrymen suffici theori unequivoc emphat paraphras winston churchil dissolut
#> 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164
#> ahead propos remov roadblock various level measur inch feet mile reawaken giant lighten
#> 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164
#> punit eve dr joseph warren massachusett despair exemplar beacon benefici sovereignti sale surrend
#> 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164
#> misunderstood misjudg prevail formid practic prey deepli vista mall shrine monument revolutionari infant
#> 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164
#> nationhood eloqu pool column whoever heroism potomac slope cemeteri row marker david tini
#> 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164
#> fraction belleau wood argonn omaha beach salerno halfway guadalcan tarawa pork chop chosin
#> 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164
#> reservoir hundr rice paddi jungl barber shop franc rainbow western battalion heavi artilleri
#> 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164
#> diari flyleaf therefor cheer treptow perform deed mathia burger presenc absent stenni gilli
#> 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164
#> louisiana silent adequ 50th stood wilder gone cri moon stress glori present-day backward
#> 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164
#> proper machin ultim rate employ vibrant robust climb restat freed grip sincer meaning
#> 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164
#> reduct develop warm sunlight pois golden gain two-parti republican boston lawyer adam planter
#> 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164
#> rival later soften anger letter reestablish anniversari die fourth juli exchang sunset beset
#> 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164
#> valuabl oar harmless rode well-intent error futil chase bloat prescript reelect vindic straight
#> 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164
#> incent entrepreneuri interfer simplifi least emancip tear distress literatur poetri dynam unbroken brought
#> 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164
#> reckon staff submit freez desir unconstitut alreadi handl fundament upgrad infirm disadvantag instal
#> 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164
#> hearten brotherhood hesit abund black utter fervent scorn militari buildup offens legitim discuss
#> 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164
#> total elimin either resort retali logic recours approv shield militar space demilitar render
#> 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164
#> obsolet rid fourfold hemispher worldwid self-determin inalien staunchest inflict allianc lightn transcend ribbon
#> 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164
#> unfurl symbol insid general knee lone darken ponder alamo encourag settler sing song
#> 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164
#> unknow big-heart tender child health rare gore contest slave-hold went fallibl grand insignific
#> 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164
#> enact halt rock sea seed root inborn hidden onward deal forgiv appear undermin
#> 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164
#> permit tactic chao inspir condemn apathi prevent recov momentum invit mass horror arrog
#> 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164
#> aggress compassion unworthi view fault prolifer diminish mentor pastor synagogu mosqu listen wound
#> 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164
#> jericho scapegoat option civic uncount unhonor anyth comfort spectat miss statesman angel whirlwind
#> 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164 0.5164
#> arriv accumul theme tire finish unit see love maintain task ago across member
#> 0.5164 0.5164 0.5164 0.5164 0.5164 0.5101 0.5101 0.5085 0.5071 0.5071 0.5064 0.5021 0.5013
#> deserv revolut soviet union greatest use ideal prosper less ill save front memori
#> 0.5013 0.5013 0.5010 0.5004 0.4969 0.4969 0.4950 0.4919 0.4903 0.4899 0.4899 0.4899 0.4899
#> everyon cultur matter patriot readi understood join final dark prejudic sinc afford embrac
#> 0.4899 0.4880 0.4880 0.4880 0.4880 0.4880 0.4880 0.4880 0.4880 0.4880 0.4880 0.4880 0.4880
#> hard duti enemi threat creed challeng come caus toward serv also rather neighbor
#> 0.4880 0.4839 0.4830 0.4830 0.4795 0.4789 0.4789 0.4747 0.4739 0.4739 0.4739 0.4671 0.4671
#> capitol light shape other understand sound even cooper guarante grant reluct conflict led
#> 0.4671 0.4671 0.4671 0.4669 0.4667 0.4667 0.4667 0.4619 0.4619 0.4619 0.4619 0.4619 0.4619
#> lincoln willing dare elect area possibl echo possess depress wrong becam generous clinton
#> 0.4619 0.4619 0.4619 0.4619 0.4619 0.4619 0.4619 0.4619 0.4619 0.4619 0.4619 0.4619 0.4619
#> risk idea tomorrow name decent era question forev sometim mean confid democraci constitut
#> 0.4619 0.4611 0.4564 0.4564 0.4564 0.4564 0.4564 0.4564 0.4557 0.4529 0.4518 0.4507 0.4472
#> eye inevit ensur throughout firm beauti flame star bodi welcom wonder rob reborn
#> 0.4472 0.4472 0.4472 0.4472 0.4472 0.4472 0.4472 0.4472 0.4472 0.4472 0.4472 0.4472 0.4472
#> presidenti hour send bold next control corner spoken instead cold forg dedic wait
#> 0.4472 0.4472 0.4472 0.4472 0.4472 0.4472 0.4472 0.4472 0.4472 0.4472 0.4472 0.4472 0.4472
#> battl easi unfold fascism wage remak persist contin temper along gave replac plan
#> 0.4472 0.4472 0.4472 0.4472 0.4472 0.4472 0.4472 0.4472 0.4472 0.4472 0.4472 0.4472 0.4472
#> claim lose petti distinguish guest vulner weak ask heart celebr old may charact
#> 0.4472 0.4472 0.4472 0.4472 0.4472 0.4472 0.4472 0.4428 0.4411 0.4392 0.4385 0.4370 0.4364
#> terror better taken alway first cross reflect four democrat lesson stronger ancient seiz
#> 0.4303 0.4290 0.4260 0.4245 0.4243 0.4216 0.4216 0.4216 0.4216 0.4216 0.4216 0.4216 0.4216
#> brave humbl immigr new justic budget guid anoth age hatr spring choos drift
#> 0.4216 0.4216 0.4216 0.4154 0.4140 0.4140 0.4140 0.4131 0.4108 0.4082 0.4082 0.4082 0.4082
#> without congress defend reform watch friend word fulfil truth yes free becom wealth
#> 0.4082 0.4051 0.4045 0.4041 0.4041 0.4041 0.4038 0.4000 0.4000 0.3975 0.3937 0.3904 0.3904
#> within action moral far anew communism planet convict vision debat deni grate invent
#> 0.3904 0.3904 0.3904 0.3904 0.3904 0.3904 0.3904 0.3904 0.3892 0.3892 0.3873 0.3873 0.3873
#> given retir march commerc vital uniti defin differ washington commonplac miracl elder racial
#> 0.3873 0.3873 0.3873 0.3873 0.3873 0.3757 0.3757 0.3727 0.3727 0.3651 0.3651 0.3651 0.3651
#> object bigotri bounti unwil get compromis impos fit abraham add town messag written
#> 0.3651 0.3651 0.3651 0.3651 0.3651 0.3651 0.3651 0.3651 0.3651 0.3651 0.3651 0.3651 0.3651
#> issu martin dole clergi brighter night amen untam mankind master consist aliv neighborhood
#> 0.3651 0.3651 0.3651 0.3651 0.3651 0.3651 0.3651 0.3651 0.3651 0.3651 0.3651 0.3651 0.3651
#> self-govern totalitarian remark difficulti repeat spiral disast tool cabinet money servitud bill older
#> 0.3651 0.3651 0.3651 0.3651 0.3651 0.3651 0.3651 0.3651 0.3651 0.3651 0.3651 0.3651 0.3651
#> custom primari target noblest hunger mighti expans lit gotten push air idealist saint
#> 0.3651 0.3651 0.3651 0.3651 0.3651 0.3651 0.3651 0.3651 0.3651 0.3651 0.3651 0.3651 0.3651
#> deeper sentiment circumst hurt flaw depth reinvent weaken ocean univers competit profound harder
#> 0.3651 0.3651 0.3651 0.3651 0.3651 0.3651 0.3651 0.3651 0.3651 0.3651 0.3651 0.3651 0.3651
#> devast crise foundat engin saw sacr toil privileg asid abroad shrink recogn scriptur
#> 0.3651 0.3651 0.3651 0.3651 0.3651 0.3651 0.3651 0.3651 0.3651 0.3651 0.3651 0.3651 0.3651
#> joy touch taught reclaim near imag background ignor prison hopeless privat etern document
#> 0.3651 0.3651 0.3651 0.3651 0.3651 0.3651 0.3651 0.3651 0.3651 0.3651 0.3651 0.3651 0.3651
#> network sap lash faction unmatch surest reject precis uncertain hardship give hand sustain
#> 0.3651 0.3651 0.3651 0.3651 0.3651 0.3651 0.3651 0.3651 0.3651 0.3651 0.3629 0.3599 0.3581
#> cours leader home divis forc rememb timeless winter pursuit imagin vote skill settl
#> 0.3581 0.3581 0.3554 0.3554 0.3544 0.3478 0.3464 0.3464 0.3464 0.3464 0.3464 0.3464 0.3464
#> scienc qualiti drawn solut thousand path fear forth success lift longer sake poster
#> 0.3464 0.3464 0.3464 0.3443 0.3443 0.3443 0.3443 0.3443 0.3266 0.3266 0.3266 0.3266 0.3266
#> true honor advanc promis high relat fight deepest mother often sworn citizenship run
#> 0.3266 0.3246 0.3230 0.3216 0.3162 0.3162 0.3162 0.3162 0.3162 0.3162 0.3162 0.3162 0.3162
#> abandon belief sourc land speaker began clear set good whether thing tie highest
#> 0.3162 0.3162 0.3162 0.3152 0.3114 0.3114 0.3114 0.3114 0.3051 0.3043 0.3039 0.2981 0.2981
#> close behalf anyon resourc tell sight cure break globe role colleg recal surviv
#> 0.2981 0.2981 0.2981 0.2981 0.2981 0.2981 0.2981 0.2981 0.2981 0.2981 0.2981 0.2981 0.2981
#> evid mind higher fortun wave necessari accept came liberti soul part choic mr
#> 0.2981 0.2962 0.2928 0.2928 0.2928 0.2928 0.2887 0.2828 0.2823 0.2752 0.2725 0.2725 0.2636
#> market parent lost har difficult sure bind mysteri oldest almighti predecessor half-centuri steadfast
#> 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582
#> shadow sunshin unrival inherit stagnant inequ news slowli boat broadcast instantan tobillion communic
#> 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582
#> mobil magic livelihood shake enrich abl compet bankrupt abid erod shaken fearsom restless
#> 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582
#> muster construct pillar envi deadlock season massiv wander revit intrigu calcul maneuv posit
#> 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582
#> worri sweat pave shout advantag franklin roosevelt experiment stabl collaps animos engulf intern
#> 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582
#> defi persian gulf somalia testament rejoic unmistak undertak compani reconnect torn inde reded
#> 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582
#> myriad infus upward disciplin well-do reap faint mountaintop guard ancestor forty-four amidst cloud
#> 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582
#> simpli midst far-reach consequ greed irrespons shed indic data statist nag lower easili
#> 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582
#> span grievanc fals recrimin worn-out dogma strangl childish nobl god-given shortcut faint-heart leisur
#> 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582
#> pleasur risk-tak doer things'som obscur rug pack sweatshop whip plow fought concord gettysburg
#> 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582
#> normandi khe sahn sacrif till undiminish pat unpleas pick dust lay electr grid
#> 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582
#> digit wield sun transform scale suggest forgotten necess shift beneath stale argument consum
#> 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582
#> appli dollar wise expand spin gross abil rout peril scarc draft charter expedi
#> 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582
#> capit villag tank sturdi entitl pleas eman restraint keeper iraq hard-earn afghanistan former
#> 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582
#> foe tireless lessen specter apolog induc slaughter innoc outlast patchwork christian muslim jew
#> 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582
#> hindus non-believ languag tast bitter swill segreg someday tribe dissolv usher sow blame
#> 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582
#> cling corrupt deceit silenc unclench alongsid flourish clean nourish starv plenti indiffer outsid
#> 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582
#> regard gratitud far-off desert fallen whisper guardian embodi leve selfless firefight stairway smoke
#> 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582
#> nurtur instrument honesti curios glad satisfi sixti restaur remembr coldest band huddl campfir
#> 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582
#> ici outcom virtu alarm current refus falter fix horizon deliv biden color skin
#> 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582
#> tenet articul self-evid endow creator unalien never-end self-execut mob entrust sword half-slav half-fre
#> 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582
#> railroad highway speed train discov hazard misfortun relinquish skeptic central fiction initi insist
#> 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582
#> fidel musket militia math teacher lab steel prove resili recoveri bare brink littl
#> 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582
#> bleakest anybodi outworn inadequ revamp code empow twilight spent disabl lucki loss sudden
#> 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582
#> swept terribl medicaid taker climat betray judgment none impact drought resist cede forest
#> 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582
#> waterway crop snow-cap peak perpetu uniform sear harm heir won naiv suspicion anchor
#> 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582
#> asia africa east compel margin describ forebear seneca selma stonewal sung unsung footprint
#> 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582
#> preacher inextric pioneer wive daughter gay brother sister student enlist workforc expel detroit
#> 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582
#> appalachia lane newtown cherish contour exact centuries-long absolut spectacl name-cal reason imperfect partial
#> 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582
#> henc confer philadelphia recit durat passion complet strong want someth toler extend gather
#> 0.2582 0.2582 0.2582 0.2582 0.2582 0.2582 0.2532 0.2505 0.2449 0.2449 0.2449 0.2449 0.2449
#> real leav offer stop influenc solv potenti vietnam head bibl point blow summon
#> 0.2449 0.2335 0.2335 0.2309 0.2309 0.2309 0.2309 0.2309 0.2309 0.2309 0.2309 0.2309 0.2309
#> rule decenc constant treat attack reaffirm pride street seem produc friendship king water
#> 0.2309 0.2309 0.2309 0.2309 0.2309 0.2309 0.2309 0.2236 0.2202 0.2108 0.2108 0.2108 0.2108
#> endless larger habit offic oblig precious bridg test move whole sens divers rise
#> 0.2108 0.2108 0.2108 0.2108 0.2108 0.2108 0.2108 0.2108 0.2108 0.1952 0.1952 0.1952 0.1952
#> fire like engag ground broken reveal sum car account honest prudent chorus discord
#> 0.1826 0.1826 0.1826 0.1826 0.1826 0.1826 0.1826 0.1826 0.1826 0.1826 0.1826 0.1826 0.1826
#> heard soon mere fist effect foreign vigil salut flag truli trumpet plagu urgent
#> 0.1826 0.1826 0.1826 0.1826 0.1826 0.1826 0.1826 0.1826 0.1826 0.1826 0.1826 0.1826 0.1826
#> fractur movement sleep dawn forget yesterday environ diplomaci whenev ennobl weari middl limitless
#> 0.1826 0.1826 0.1826 0.1826 0.1826 0.1826 0.1826 0.1826 0.1826 0.1826 0.1826 0.1826 0.1826
#> thrive smaller roll shutter fuel crippl succumb everywher broad stain legaci girl farm
#> 0.1826 0.1826 0.1826 0.1826 0.1826 0.1826 0.1826 0.1826 0.1826 0.1826 0.1826 0.1826 0.1826
#> realiti mark durabl distant violenc woman maker emerg prefer grudg dissent defeat darkest
#> 0.1826 0.1826 0.1826 0.1826 0.1826 0.1826 0.1826 0.1826 0.1826 0.1826 0.1826 0.1826 0.1826
#> allegi soldier prepar judg victim consid flow inhabit centuri succeed big founder mission
#> 0.1826 0.1826 0.1826 0.1826 0.1826 0.1826 0.1826 0.1826 0.1781 0.1721 0.1721 0.1721 0.1721
#> oppress learn page educ perman proclaim assum walk exercis base chapter global destini
#> 0.1633 0.1633 0.1633 0.1557 0.1557 0.1557 0.1491 0.1491 0.1491 0.1491 0.1491 0.1491 0.1491
#> avoid narrow enough express generos bigger execut quest bright border crime certain vow
#> 0.1491 0.1491 0.1257 0.1252 0.1155 0.1155 0.1155 0.1155 0.1155 0.1155 0.1054 0.1054 0.1054
#> built read fact edg triumph feel 21st class wit institut reli seen chosen
#> 0.1054 0.1054 0.1013 0.0976 0.0976 0.0976 0.0816 0.0816 0.0816 0.0816 0.0816 0.0806 0.0778
#> tyranni quayl mitchel wright congressman michael reagan bicentenni gladden concret stun porch talk
#> 0.0497 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> suspend bow heaven heed write lord breez refresh dictat blown lifeless tree thick
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> fog sit mist door room agit thought intellectu satisfact speech unhamp perhap late
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> form wrest crucial proud loud enthral materi appreci nobil bank loyal driven stay
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> trade quieter gold silk finer wholli unless kinder gentler homeless roam normalci enslav
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> addict drug welfar demor slum rough guidanc case fund low wallet alloc wisest
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> activ hands-on involv unus talent unfocus leadership stewardship second organ spread hous agenc
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> pitch thrash fiscal dissens harmoni statement motiv apart untrust cleav earnest quarter statut
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> sunder bipartisanship opposit major clock wish await bicker partisan unaccount assist beget treati
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> agreement marbl candor compliment subtleti relationship experi throw son hymn continuum inescap connect
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> kite neither princ pope window yearn going attitud intoler obvious cocain smuggl ship
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> dead bacteria scourg mistrust larg boundless drama book 20th millennium prospect affair 18th
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> 19th abolish aw slaveri turmoil explod onto stage mightiest unriv center split atom
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> explor comput microchip deepen wellspr african minor circl third coast conserv inform perfect
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> tragedi exhilar indispens cleaner destin bend safer record flexibl everyday preemin hire behind
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> lock gang divid curs contempt cloak pretens religi fanatic torment obsess hate impuls
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> lurk region overcom textur godsend approach outlin internet mystic provinc physicist encyclopedia schoolchildren
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> scientist decod blueprint hostil camp dictatorship surpass bloodsh resound sought prize standard ignit
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> spark boy classroom librari kitchen tabl laughter shoot sell anymor medicin hardwork chemic
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> biolog port airport innov grandpar grandchildren benefit fortifi natur majest louder din regain
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> particip armi thirty-four prophet luther ceaseless redeem extrem partisanship plain deplor repair breach
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> wisdom cardin bernardin wast acrimoni patienc wide belov height summit cheney carter non
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> prescrib consequenti half shipwreck repos sabbat simmer resent prone ideolog excus murder multipli
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> mortal reign expos tyrant event conclus matchless imper slave polici primarili aris style
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> attain concentr unlimit consider unwis clarifi ruler pretend jail dissid chain humili merci
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> bulli treatment concess appeal swiftest odd surpris eventu exist oppressor repress exil outlaw
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> regim retain counsel concert promot prelud dishonor kindl burn hardest intellig devot death
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> youngest fragil evil essenti unfinish subsist broader definit homestead gi ownership widen insur
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> agent integr edific sinai sermon mount koran vari surround unwant worth racism baggag
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> perspect includ viewpoint credit known felt fellowship unjust encount captiv wheel outrag banner
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> meant ebb visibl bell rang thereof
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#>
#> $terror
#> factori adversari commonplac miracl racial bounti martin guarante solv potenti solut whose cultur
#> 0.9526 0.9526 0.9428 0.9428 0.9428 0.9428 0.9428 0.8944 0.8944 0.8944 0.8889 0.8845 0.8819
#> maintain upon dream told polit industri open grate mall strengthen cross realiz answer
#> 0.8729 0.8700 0.8677 0.8660 0.8540 0.8433 0.8433 0.8333 0.8333 0.8250 0.8165 0.8165 0.8040
#> educ problem product land go eye street grow unleash tie match highest flame
#> 0.8040 0.8003 0.8000 0.7867 0.7803 0.7698 0.7698 0.7698 0.7698 0.7698 0.7698 0.7698 0.7698
#> greatest children enough wealth within fortun understood far full remind loyalti kind sustain
#> 0.7698 0.7607 0.7570 0.7559 0.7559 0.7559 0.7559 0.7559 0.7454 0.7454 0.7454 0.7454 0.7396
#> end chanc opportun us noth gift let price decad week patrol strength recognit
#> 0.7385 0.7276 0.7139 0.7134 0.7127 0.7127 0.7074 0.7071 0.7071 0.7071 0.7071 0.7071 0.7071
#> era balanc decid forbear magnific humil dignifi river arlington earlier lie fame smaller
#> 0.7071 0.7071 0.7071 0.7071 0.7071 0.7071 0.7071 0.7071 0.7071 0.7071 0.7071 0.7071 0.7071
#> roll shutter fuel everywher stain legaci farm yes hero pledg shall govern will
#> 0.7071 0.7071 0.7071 0.7071 0.7071 0.7071 0.7071 0.7057 0.7030 0.6882 0.6882 0.6851 0.6845
#> last assur fate offic citizenship read precious bridg back centuri labor around achiev
#> 0.6809 0.6804 0.6804 0.6804 0.6804 0.6804 0.6804 0.6804 0.6761 0.6744 0.6736 0.6736 0.6708
#> new hatfield mondal baker moomaw occurr routin uniqu realli normal gracious degre bulwark
#> 0.6703 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667
#> afflict proport longest distort penal thrift crush fixed-incom alik shatter idl miseri indign
#> 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667
#> deni burden kept pile mortgag temporari conveni trend tremend upheav period misunderstand sever
#> 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667
#> bastion tempt complex self-rul elit superior someon equit special neglect section food mine
#> 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667
#> teach profession industrialist shopkeep clerk cabbi truckdriv breed administr healthi vigor discrimin runaway
#> 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667
#> reviv play inventori check consent intent curb distinct smother foster stifl extent avail
#> 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667
#> coincid parallel proportion intervent intrus result unnecessari excess loom creativ gate counter entrepreneur
#> 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667
#> voluntari art address makeup countrymen suffici theori unequivoc emphat paraphras winston churchil dissolut
#> 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667
#> strongest ahead propos remov roadblock various level inch feet mile reawaken giant lighten
#> 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667
#> punit eve dr joseph warren massachusett despair exemplar beacon benefici sovereignti sale surrend
#> 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667
#> misunderstood misjudg prevail formid practic prey thousand deepli vista shrine monument revolutionari infant
#> 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667
#> nationhood eloqu pool column whoever heroism potomac slope cemeteri row marker david tini
#> 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667
#> fraction spoke belleau wood argonn omaha beach salerno halfway guadalcan tarawa pork chop
#> 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667
#> chosin reservoir hundr rice paddi jungl barber shop franc rainbow western tri battalion
#> 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667
#> heavi artilleri diari flyleaf therefor cheer treptow perform deed big 20th millennium prospect
#> 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667
#> affair 18th 19th abolish aw turmoil explod onto stage mightiest unriv center split
#> 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667
#> atom explor comput microchip deepen wellspr african circl third coast conserv inform perfect
#> 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667
#> tragedi exhilar indispens cleaner destin bend safer record flexibl everyday preemin hire behind
#> 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667
#> lock gang divid curs contempt cloak religi fanatic torment obsess hate impuls lurk
#> 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667
#> overcom textur godsend approach outlin internet mystic provinc physicist encyclopedia schoolchildren scientist decod
#> 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667
#> blueprint hostil camp dictatorship surpass bloodsh resound sought prize ignit spark boy classroom
#> 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667
#> librari kitchen tabl laughter shoot sell anymor medicin hardwork chemic biolog port airport
#> 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667
#> innov grandpar grandchildren benefit fortifi majest louder din regain armi thirty-four prophet luther
#> 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667
#> ceaseless redeem extrem partisanship plain deplor repair breach cardin bernardin wast acrimoni wide
#> 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667
#> belov height summit individu meet come face fellow promis side group futur ill
#> 0.6667 0.6667 0.6667 0.6586 0.6576 0.6547 0.6535 0.6499 0.6487 0.6472 0.6468 0.6350 0.6325
#> born save extend present front spread 21st class nation live return said readi
#> 0.6325 0.6325 0.6325 0.6325 0.6325 0.6325 0.6325 0.6325 0.6307 0.6306 0.6299 0.6299 0.6299
#> held convict give capac spirit demand reach away economi man beyond neighbor shape
#> 0.6299 0.6299 0.6247 0.6236 0.6202 0.6124 0.6124 0.6118 0.6063 0.6041 0.6030 0.6030 0.6030
#> small cooper pay grant ever slow depend worthi reluct conflict inaugur led lincoln
#> 0.6000 0.5963 0.5963 0.5963 0.5963 0.5963 0.5963 0.5963 0.5963 0.5963 0.5963 0.5963 0.5963
#> hill willing welfar quest bright decenc less never greater energi job work time
#> 0.5963 0.5963 0.5963 0.5963 0.5963 0.5963 0.5934 0.5927 0.5893 0.5893 0.5893 0.5861 0.5824
#> stand american can take build transit collect manag inevit declin might throughout firm
#> 0.5812 0.5808 0.5808 0.5803 0.5774 0.5774 0.5774 0.5774 0.5774 0.5774 0.5774 0.5774 0.5774
#> intend citi shore bodi presidenti next forg chapter sight globe role destini plan
#> 0.5774 0.5774 0.5774 0.5774 0.5774 0.5774 0.5774 0.5774 0.5774 0.5774 0.5774 0.5774 0.5774
#> colleg lose narrow petti one interest now believ crisi may everi among order
#> 0.5774 0.5774 0.5774 0.5774 0.5740 0.5717 0.5701 0.5697 0.5685 0.5642 0.5604 0.5560 0.5556
#> suffer confront provid cours alon today preserv long worker month parti line short
#> 0.5556 0.5547 0.5547 0.5547 0.5500 0.5496 0.5480 0.5462 0.5443 0.5443 0.5443 0.5443 0.5443
#> prosper fall produc reflect mutual west stronger certain water built humbl power creat
#> 0.5443 0.5443 0.5443 0.5443 0.5443 0.5443 0.5443 0.5443 0.5443 0.5443 0.5443 0.5391 0.5388
#> world home across famili age bless just peopl memori choos real yet struggl
#> 0.5371 0.5353 0.5303 0.5303 0.5303 0.5298 0.5284 0.5278 0.5270 0.5270 0.5270 0.5252 0.5217
#> put begin well great keep even million much use day becom higher sick
#> 0.5217 0.5208 0.5206 0.5198 0.5164 0.5164 0.5143 0.5134 0.5132 0.5066 0.5040 0.5040 0.5040
#> feed patriot whole join sens prejudic edg planet faith rather began vision set
#> 0.5040 0.5040 0.5040 0.5040 0.5040 0.5040 0.5040 0.5040 0.5037 0.5025 0.5025 0.5025 0.5025
#> size chariti invent retir alreadi parent har sure bind commerc valu happi strong
#> 0.5000 0.5000 0.5000 0.5000 0.5000 0.5000 0.5000 0.5000 0.5000 0.5000 0.4932 0.4865 0.4851
#> instead see effort taken women support o'neil occas transfer process busi worst inflat
#> 0.4811 0.4789 0.4763 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714
#> elder unemploy pace borrow tomorrow bear concern boundari ethnic object barrier bigotri core
#> 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714
#> except revers establish reserv genius unwil command heroic church get prioriti compromis import
#> 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714
#> unborn strive impos arsenal ten fit shoulder abraham add paid town messag written
#> 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714
#> win utmost issu aliv remark tool target noblest mighti air form trade drug
#> 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714
#> apart await bicker connect window scourg plagu fractur sleep dawn forget environ knowledg
#> 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714
#> slaveri middl minor limitless touch thrive taught reclaim pretens near crippl succumb region
#> 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714
#> broad girl natur particip wisdom patienc realiti must life togeth father war deserv
#> 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4670 0.4646 0.4642 0.4642 0.4642 0.4623
#> revolut america divis call sacrific earth carri system look limit bush shown decis
#> 0.4623 0.4597 0.4588 0.4576 0.4576 0.4548 0.4507 0.4491 0.4491 0.4472 0.4472 0.4472 0.4472
#> failur race possess timeless wrong vice ceremoni heal restor measur common succeed child
#> 0.4472 0.4472 0.4472 0.4472 0.4472 0.4444 0.4444 0.4444 0.4444 0.4444 0.4444 0.4444 0.4444
#> fear forth founder mission health state econom endur challeng declar year differ say
#> 0.4444 0.4444 0.4444 0.4444 0.4444 0.4391 0.4384 0.4384 0.4364 0.4364 0.4336 0.4330 0.4330
#> presid fair growth understand place share seem respons make moment success deficit danger
#> 0.4319 0.4303 0.4303 0.4303 0.4288 0.4264 0.4264 0.4240 0.4225 0.4216 0.4216 0.4216 0.4216
#> lift longer learn gather true mani progress god citizen two think past advanc
#> 0.4216 0.4216 0.4216 0.4216 0.4216 0.4201 0.4201 0.4190 0.4183 0.4170 0.4170 0.4170 0.4170
#> school old histori question feder mean high speak aim relat move young journey
#> 0.4170 0.4152 0.4144 0.4125 0.4115 0.4093 0.4082 0.4082 0.4082 0.4082 0.4082 0.4062 0.4049
#> know way cost defens choic anoth union better congress weapon reverend constitut almost
#> 0.4048 0.4045 0.4020 0.4020 0.4020 0.4000 0.3975 0.3956 0.3922 0.3890 0.3849 0.3849 0.3849
#> republ goe cast whatev capabl sign grown troubl number self rest ensur histor
#> 0.3849 0.3849 0.3849 0.3849 0.3849 0.3849 0.3849 0.3849 0.3849 0.3849 0.3849 0.3849 0.3849
#> aspir negoti beauti thoma white star howev rob bond cold close heaven assum
#> 0.3849 0.3849 0.3849 0.3849 0.3849 0.3849 0.3849 0.3849 0.3849 0.3849 0.3849 0.3849 0.3849
#> global cure contin along gave replac avoid claim equal forward alway toward help
#> 0.3849 0.3849 0.3849 0.3849 0.3849 0.3849 0.3849 0.3849 0.3841 0.3836 0.3836 0.3824 0.3799
#> seek action find dark rise courag reform remain done heart need first hope
#> 0.3785 0.3780 0.3780 0.3780 0.3780 0.3750 0.3727 0.3714 0.3698 0.3685 0.3667 0.3651 0.3637
#> democraci tax renew hand trust threat free forc human quiet act found word
#> 0.3637 0.3629 0.3594 0.3574 0.3563 0.3563 0.3558 0.3558 0.3550 0.3536 0.3528 0.3482 0.3475
#> men public care solemn person bound georg march ancestor forty-four amidst cloud simpli
#> 0.3472 0.3402 0.3368 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333
#> midst far-reach consequ greed irrespons shed indic data statist nag lower easili span
#> 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333
#> grievanc fals recrimin worn-out dogma strangl childish nobl god-given shortcut faint-heart leisur pleasur
#> 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333
#> risk-tak doer things'som obscur rug pack sweatshop whip plow fought concord gettysburg normandi
#> 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333
#> khe sahn sacrif till undiminish pat unpleas pick dust lay electr grid digit
#> 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333
#> wield sun transform scale suggest forgotten necess shift beneath stale argument consum appli
#> 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333
#> dollar wise expand spin gross abil rout peril scarc draft charter expedi capit
#> 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333
#> villag tank sturdi entitl pleas eman restraint keeper iraq hard-earn afghanistan former foe
#> 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333
#> tireless lessen specter apolog induc slaughter innoc outlast patchwork christian muslim jew hindus
#> 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333
#> non-believ languag tast bitter swill segreg someday tribe dissolv usher sow blame cling
#> 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333
#> corrupt deceit silenc unclench alongsid flourish clean nourish starv plenti indiffer outsid regard
#> 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333
#> gratitud far-off desert fallen whisper guardian embodi leve selfless firefight stairway smoke nurtur
#> 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333
#> instrument honesti curios glad satisfi sixti restaur remembr coldest band huddl campfir ici
#> 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333
#> outcom virtu alarm current refus falter fix horizon deliv other communiti ago defin
#> 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3288 0.3288 0.3269 0.3234
#> societi goal whether continu thank came part destroy oath chief stop watch influenc
#> 0.3208 0.3143 0.3143 0.3095 0.3050 0.3043 0.3015 0.3015 0.2993 0.2981 0.2981 0.2981 0.2981
#> ride independ vietnam head dare possibl echo door winter imagin becam constant generous
#> 0.2981 0.2981 0.2981 0.2981 0.2981 0.2981 0.2981 0.2981 0.2981 0.2981 0.2981 0.2981 0.2981
#> standard treat reaffirm settl qualiti made mr protect task hour bold rich ask
#> 0.2981 0.2981 0.2981 0.2981 0.2981 0.2963 0.2917 0.2910 0.2910 0.2887 0.2887 0.2887 0.2858
#> prayer peac like good els friendship victori left fight four met reward ancient
#> 0.2843 0.2838 0.2828 0.2727 0.2722 0.2722 0.2722 0.2722 0.2722 0.2722 0.2722 0.2722 0.2722
#> king crime often vow ambit bad brave immigr oblig enemi guid generat secur
#> 0.2722 0.2722 0.2722 0.2722 0.2722 0.2722 0.2722 0.2722 0.2722 0.2673 0.2673 0.2667 0.2659
#> love resolv requir threaten rememb tradit matter moral simpl celebr follow wave road
#> 0.2626 0.2615 0.2609 0.2582 0.2566 0.2520 0.2520 0.2520 0.2520 0.2520 0.2520 0.2520 0.2520
#> destruct divers afford triumph feel embrac necessari law digniti senat liberti determin storm
#> 0.2520 0.2520 0.2520 0.2520 0.2520 0.2520 0.2520 0.2500 0.2485 0.2476 0.2430 0.2357 0.2357
#> social hear alli bestow raw mountain enjoy enterpris tide name hungri waver missil
#> 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357
#> snow forev ground broken reveal sum car account prudent discord soon fist effect
#> 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357
#> depth weaken ocean univers profound foundat saw sacr toil asid conscienc scriptur grace
#> 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357
#> grandest wind serious soil respect cynic exampl favor stranger search pursu subject swift
#> 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357
#> mark distant violenc woman maker emerg prefer grudg dissent defeat darkest prepar judg
#> 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357
#> consid flow inhabit document network sap lash faction unmatch surest reject precis uncertain
#> 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357
#> hardship rais serv mind freedom idea accept show die path market unit want
#> 0.2357 0.2294 0.2294 0.2294 0.2290 0.2289 0.2236 0.2222 0.2222 0.2222 0.2222 0.2195 0.2108
#> jefferson kill fail hatr blood someth toler everyon without best lead speaker capitol
#> 0.2108 0.2108 0.2108 0.2108 0.2108 0.2108 0.2108 0.2108 0.2108 0.2057 0.2041 0.2010 0.2010
#> direct light perman travel clear debat right author deep step washington wonder voic
#> 0.2010 0.2010 0.2010 0.2010 0.2010 0.2010 0.1943 0.1925 0.1925 0.1925 0.1925 0.1925 0.1925
#> knew cut control spoken domest base resourc tell unfold fascism wage remak break
#> 0.1925 0.1925 0.1925 0.1925 0.1925 0.1925 0.1925 0.1925 0.1925 0.1925 0.1925 0.1925 0.1925
#> temper rage weak recal surviv evid spend hard creed member countri justic compass
#> 0.1925 0.1925 0.1925 0.1925 0.1925 0.1925 0.1925 0.1890 0.1857 0.1849 0.1806 0.1782 0.1782
#> budget birth pass principl charact singl given ultim confid warm poor safeti doubt
#> 0.1782 0.1782 0.1715 0.1690 0.1690 0.1667 0.1667 0.1667 0.1667 0.1667 0.1667 0.1667 0.1667
#> allianc lost difficult servic vital still nuclear chang fire also ideal thing local
#> 0.1667 0.1667 0.1667 0.1667 0.1667 0.1629 0.1622 0.1586 0.1571 0.1529 0.1521 0.1509 0.1491
#> heritag generos bigger border skill scienc drawn civil soul caus habit seiz run
#> 0.1491 0.1491 0.1491 0.1491 0.1491 0.1491 0.1491 0.1443 0.1421 0.1414 0.1361 0.1361 0.1361
#> abandon sourc test fact tyranni final communism purpos commit fill decent safe technolog
#> 0.1361 0.1361 0.1361 0.1307 0.1283 0.1260 0.1260 0.1197 0.1179 0.1179 0.1179 0.1111 0.1054
#> sake reli seen duti start leav chosen proclaim reduc earn program leader friend
#> 0.1054 0.1054 0.1041 0.1041 0.1005 0.1005 0.1005 0.1005 0.0925 0.0925 0.0925 0.0925 0.0921
#> truth uniti rule bring honor turn mathia burger dole clergi brighter presenc absent
#> 0.0861 0.0808 0.0745 0.0642 0.0599 0.0442 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> john stenni welcom repres gilli louisiana night silent amen adequ express 50th bibl
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> stood horseback untam wilder gone aid mankind wherev cri moon took stress glori
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> present-day backward accomplish master servant allow equip yield proper belong machin increas consist
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> rate dramat employ vibrant robust climb birthright neighborhood restat modern freed grip sincer
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> meaning arm reduct rebuild develop self-govern totalitarian sunlight pois golden reborn gain two-parti
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> democrat republican boston lawyer adam virginia planter hall lesson rival elect later soften
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> anger letter reestablish anniversari fourth juli exchang sunset wrote beset difficulti valuabl oar
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> overwhelm harmless rode repeat well-intent error abus send futil chase spiral bloat prescript
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> disast reelect vindic straight incent drive entrepreneuri begun invest interfer simplifi anew least
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> emancip tear liber distress area spring fulfil treasur literatur music poetri dynam unbroken
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> brought reckon point cabinet staff debt submit freez desir money servitud bill due
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> unconstitut handl fundament upgrad infirm disadvantag offer unfortun older origin instal custom stori
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> hearten brotherhood hesit abund black though corner primari utter fervent scorn soviet conduct
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> militari buildup awesom offens legitim discuss total elimin either resort retali logic recours
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> approv research shield militar space demilitar render obsolet agre rid sinc fourfold nowher
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> hemispher deepest worldwid hunger self-determin inalien staunchest conquer poverti blow inflict oppress youth
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> expans lit lightn transcend ribbon unfurl symbol gotten insid general knee valley lone
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> darken ponder alamo encourag settler push sing song unknow sound big-heart idealist tender
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> hold affect dedic wait quayl mitchel wright congressman michael reagan behalf bicentenni gladden
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> concret stun porch talk suspend bow heed write lord breez refresh dictat blown
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> lifeless tree thick fog sit mist walk room agit thought intellectu satisfact speech
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> exercis unhamp perhap late wrest summon saint crucial proud loud enthral materi appreci
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> nobil bank loyal driven anyon stay quieter deeper gold silk finer wholli unless
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> engag kinder gentler homeless roam normalci enslav addict demor slum rough mother guidanc
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> case fund low wallet alloc honest wisest activ hands-on involv unus talent unfocus
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> leadership stewardship second organ sometim hous agenc pitch execut thrash fiscal dissens harmoni
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> chorus heard statement motiv untrust cleav earnest quarter statut sunder bipartisanship opposit major
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> clock wish mere partisan foreign unaccount assist beget endless treati agreement marbl candor
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> compliment subtleti relationship experi vigil throw salut flag son battl hymn sentiment continuum
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> inescap kite circumst neither princ pope yearn easi going attitud intoler obvious cocain
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> smuggl ship dead bacteria hurt mistrust larg larger flaw truli boundless drama trumpet
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> book page mysteri oldest reinvent almighti pursuit predecessor half-centuri steadfast depress shadow sunshin
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> unrival inherit stagnant inequ sworn uphold news slowli boat broadcast instantan tobillion communic
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> mobil magic livelihood competit shake urgent enrich abl compet harder devast bankrupt abid
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> drift erod shaken fearsom restless movement muster construct crise pillar envi engin deadlock
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> season massiv poster wander expect revit intrigu calcul maneuv posit worri sweat pave
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> privileg shout advantag pain franklin roosevelt persist experiment yesterday abroad stabl collaps animos
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> shrink lest engulf intern defi diplomaci whenev persian gulf somalia testament rejoic unmistak
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> vote undertak compani reconnect torn inde recogn reded ennobl myriad infus upward disciplin
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> weari well-do reap faint joy mountaintop guard clinton distinguish guest rare affirm gore
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> contest slave-hold went defend fallibl grand insignific enact halt delay rock sea seed
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> root inborn hidden imag onward background deal forgiv stake appear undermin permit vulner
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> tactic chao inspir condemn ignor apathi medicar spare prevent recov momentum invit mass
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> horror mistak arrog aggress compassion unworthi view risk fault prolifer prison substitut diminish
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> hopeless respond mentor pastor synagogu mosqu lend listen wound jericho scapegoat option privat
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> civic basic uncount unhonor anyth comfort attack spectat belief miss statesman angel whirlwind
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> arriv accumul theme etern tire finish cheney carter non prescrib durabl consequenti wit
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> half shipwreck repos sabbat simmer resent prone ideolog excus murder multipli mortal reign
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> expos tyrant event conclus matchless imper slave polici institut primarili aris style attain
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> concentr unlimit consider unwis clarifi ruler pretend jail dissid chain humili merci bulli
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> treatment concess appeal swiftest odd surpris eventu exist oppressor repress exil outlaw regim
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> retain counsel concert promot prelud dishonor kindl burn hardest intellig devot death youngest
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> allegi soldier fragil evil essenti unfinish subsist broader definit homestead gi ownership widen
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> insur agent integr edific sinai sermon mount koran vari surround unwant worth racism
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> baggag perspect includ viewpoint credit known felt fellowship pride victim unjust encount captiv
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> complet wheel outrag banner meant ebb visibl bell rang thereof biden color skin
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> tenet articul self-evid endow creator unalien never-end self-execut mob entrust sword half-slav half-fre
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> railroad highway speed train discov hazard misfortun relinquish skeptic central fiction initi insist
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> fidel musket militia math teacher lab steel prove resili recoveri bare brink littl
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> bleakest anybodi outworn inadequ revamp code empow twilight spent disabl lucki loss sudden
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> swept terribl medicaid taker climat betray judgment none impact drought resist cede forest
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> waterway crop snow-cap peak perpetu uniform sear harm heir won naiv suspicion anchor
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> asia africa east compel margin describ forebear seneca selma stonewal sung unsung footprint
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> preacher inextric pioneer wive daughter gay brother sister student enlist workforc expel detroit
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> appalachia lane newtown cherish contour exact centuries-long absolut spectacl name-cal reason imperfect partial
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> henc confer philadelphia recit durat passion
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#>
#> $health
#> knowledg shape generat wrong defin common child fear demand planet power everi task
#> 0.9428 0.9045 0.8971 0.8944 0.8893 0.8889 0.8889 0.8889 0.8845 0.8819 0.8796 0.8736 0.8729
#> eye forc even long born danger choos extend gather true without face advanc
#> 0.8660 0.8642 0.8607 0.8583 0.8433 0.8433 0.8433 0.8433 0.8433 0.8433 0.8433 0.8402 0.8341
#> school law servic commerc vital deserv america less spirit busi across endur reform
#> 0.8341 0.8333 0.8333 0.8333 0.8333 0.8321 0.8309 0.8307 0.8269 0.8250 0.8250 0.8220 0.8199
#> ambit bad brave humbl can travel set gift interest just life nation storm
#> 0.8165 0.8165 0.8165 0.8165 0.8104 0.8040 0.8040 0.8018 0.8003 0.7926 0.7862 0.7861 0.7857
#> give end see oath play measur forth respons prosper hour build care instead
#> 0.7809 0.7796 0.7783 0.7783 0.7778 0.7778 0.7778 0.7773 0.7711 0.7698 0.7698 0.7698 0.7698
#> fascism wage sight remak break temper globe role destini plan colleg lose narrow
#> 0.7698 0.7698 0.7698 0.7698 0.7698 0.7698 0.7698 0.7698 0.7698 0.7698 0.7698 0.7698 0.7698
#> petti rage weak recal surviv evid job serv also way know wealth find
#> 0.7698 0.7698 0.7698 0.7698 0.7698 0.7698 0.7660 0.7647 0.7647 0.7641 0.7619 0.7559 0.7559
#> join communism convict understood celebr road afford choic courag confid failur race possess
#> 0.7559 0.7559 0.7559 0.7559 0.7559 0.7559 0.7559 0.7538 0.7500 0.7500 0.7454 0.7454 0.7454
#> timeless winter imagin reaffirm settl qualiti last ill hatr blood longer someth toler
#> 0.7454 0.7454 0.7454 0.7454 0.7454 0.7454 0.7428 0.7379 0.7379 0.7379 0.7379 0.7379 0.7379
#> real may small still faith carri ideal duti futur purpos today threat enemi
#> 0.7379 0.7377 0.7333 0.7330 0.7326 0.7325 0.7303 0.7288 0.7197 0.7184 0.7145 0.7127 0.7127
#> trust guid birth meet valu crisi must work whether era determin quiet question
#> 0.7127 0.7127 0.7127 0.7124 0.7124 0.7107 0.7102 0.7095 0.7071 0.7071 0.7071 0.7071 0.7071
#> depth weaken ocean univers profound foundat saw sacr toil asid conscienc scriptur smaller
#> 0.7071 0.7071 0.7071 0.7071 0.7071 0.7071 0.7071 0.7071 0.7071 0.7071 0.7071 0.7071 0.7071
#> roll shutter fuel everywher stain legaci farm grace grandest wind serious soil respect
#> 0.7071 0.7071 0.7071 0.7071 0.7071 0.7071 0.7071 0.7071 0.7071 0.7071 0.7071 0.7071 0.7071
#> cynic exampl favor stranger search pursu subject swift mark distant violenc woman maker
#> 0.7071 0.7071 0.7071 0.7071 0.7071 0.7071 0.7071 0.7071 0.7071 0.7071 0.7071 0.7071 0.7071
#> emerg prefer grudg dissent defeat darkest prepar judg consid flow inhabit document network
#> 0.7071 0.7071 0.7071 0.7071 0.7071 0.7071 0.7071 0.7071 0.7071 0.7071 0.7071 0.7071 0.7071
#> sap lash faction unmatch surest reject precis uncertain hardship rather answer defens vision
#> 0.7071 0.7071 0.7071 0.7071 0.7071 0.7071 0.7071 0.7071 0.7071 0.7035 0.7035 0.7035 0.7035
#> american promis journey war now challeng come will understand truth pledg home shall
#> 0.7031 0.7006 0.6994 0.6963 0.6923 0.6910 0.6910 0.6893 0.6885 0.6885 0.6882 0.6882 0.6882
#> mind remain worker effort met stronger often water habit seiz offic citizenship read
#> 0.6882 0.6809 0.6804 0.6804 0.6804 0.6804 0.6804 0.6804 0.6804 0.6804 0.6804 0.6804 0.6804
#> precious bridg run abandon sourc test us well charact time grow citizen depend
#> 0.6804 0.6804 0.6804 0.6804 0.6804 0.6804 0.6797 0.6768 0.6761 0.6756 0.6736 0.6728 0.6708
#> children chariti grate mall ultim warm retir alreadi poor doubt path parent lost
#> 0.6694 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667
#> har difficult sure bind big ancestor forty-four amidst cloud simpli midst far-reach consequ
#> 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667
#> greed irrespons shed indic data statist nag lower easili span grievanc fals recrimin
#> 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667
#> worn-out dogma strangl childish nobl god-given shortcut faint-heart leisur pleasur risk-tak doer things'som
#> 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667
#> obscur rug pack sweatshop whip plow fought concord gettysburg normandi khe sahn sacrif
#> 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667
#> till undiminish pat unpleas pick dust lay electr grid digit wield sun transform
#> 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667
#> scale suggest forgotten necess shift beneath stale argument consum appli dollar wise expand
#> 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667
#> spin gross abil rout peril scarc draft charter expedi capit villag tank sturdi
#> 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667
#> entitl pleas eman restraint keeper iraq hard-earn afghanistan former foe tireless lessen specter
#> 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667
#> apolog induc slaughter innoc outlast patchwork christian muslim jew hindus non-believ languag tast
#> 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667
#> bitter swill segreg someday tribe dissolv usher sow blame cling corrupt deceit silenc
#> 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667
#> unclench alongsid flourish clean nourish starv plenti indiffer outsid regard gratitud far-off desert
#> 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667
#> fallen whisper guardian embodi leve selfless firefight stairway smoke nurtur instrument honesti curios
#> 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667
#> glad satisfi sixti restaur remembr coldest band huddl campfir ici outcom virtu alarm
#> 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667
#> current refus falter fix horizon deliv women stand countri protect mani let fellow
#> 0.6667 0.6667 0.6667 0.6667 0.6667 0.6667 0.6600 0.6587 0.6547 0.6547 0.6535 0.6500 0.6499
#> seek famili greater new polit father peopl never make success fail said necessari
#> 0.6489 0.6482 0.6482 0.6435 0.6405 0.6383 0.6377 0.6350 0.6337 0.6325 0.6325 0.6299 0.6299
#> feed patriot far hard embrac pass alon noth world call bless yet public
#> 0.6299 0.6299 0.6299 0.6299 0.6299 0.6288 0.6285 0.6236 0.6234 0.6210 0.6181 0.6128 0.6124
#> lead toward live men cost light proclaim forward alway communiti anoth bush cooper
#> 0.6124 0.6118 0.6088 0.6075 0.6030 0.6030 0.6030 0.6028 0.6028 0.6028 0.6000 0.5963 0.5963
#> achiev full conflict willing possibl rule border skill scienc drawn upon move strengthen
#> 0.5963 0.5963 0.5963 0.5963 0.5963 0.5963 0.5963 0.5963 0.5963 0.5963 0.5952 0.5897 0.5893
#> age forev decent resolv unit person declar found moment civil transit labor collect
#> 0.5893 0.5893 0.5893 0.5883 0.5854 0.5833 0.5819 0.5803 0.5798 0.5774 0.5774 0.5774 0.5774
#> societi manag inevit declin might throughout firm citi shore knew cut presidenti bring
#> 0.5774 0.5774 0.5774 0.5774 0.5774 0.5774 0.5774 0.5774 0.5774 0.5774 0.5774 0.5774 0.5774
#> bold next control domest forg base resourc tell unfold chapter uphold global cure
#> 0.5774 0.5774 0.5774 0.5774 0.5774 0.5774 0.5774 0.5774 0.5774 0.5774 0.5774 0.5774 0.5774
#> persist contin along gave replac avoid claim distinguish guest vulner god peac liberti
#> 0.5774 0.5774 0.5774 0.5774 0.5774 0.5774 0.5774 0.5774 0.5774 0.5774 0.5762 0.5675 0.5670
#> economi chanc caus principl hope creed word happi order show die market founder
#> 0.5659 0.5659 0.5657 0.5634 0.5577 0.5571 0.5560 0.5560 0.5556 0.5556 0.5556 0.5556 0.5556
#> mission chang equal revolut leader right year came act month line short whose
#> 0.5556 0.5551 0.5548 0.5547 0.5547 0.5504 0.5492 0.5477 0.5453 0.5443 0.5443 0.5443 0.5443
#> reach mutual relat west reward ancient sworn built immigr oblig stake belief honor
#> 0.5443 0.5443 0.5443 0.5443 0.5443 0.5443 0.5443 0.5443 0.5443 0.5443 0.5443 0.5443 0.5388
#> histori rais justic though need secur differ old technolog lift learn sake reli
#> 0.5363 0.5353 0.5345 0.5345 0.5333 0.5318 0.5292 0.5284 0.5270 0.5270 0.5270 0.5270 0.5270
#> sacrific take defend accept watch ever requir togeth fair land ask democraci cultur
#> 0.5230 0.5222 0.5222 0.5217 0.5217 0.5217 0.5217 0.5188 0.5164 0.5154 0.5145 0.5092 0.5040
#> opportun fortun follow dark wave anew prejudic edg rise triumph feel idea began
#> 0.5040 0.5040 0.5040 0.5040 0.5040 0.5040 0.5040 0.5040 0.5040 0.5040 0.5040 0.5037 0.5025
#> chosen clear debat solemn deni bound singl size invent given liber safeti march
#> 0.5025 0.5025 0.5025 0.5000 0.5000 0.5000 0.5000 0.5000 0.5000 0.5000 0.5000 0.5000 0.5000
#> allianc hold great freedom digniti earth uniti day free author say deep voic
#> 0.5000 0.5000 0.4990 0.4978 0.4969 0.4961 0.4851 0.4846 0.4829 0.4811 0.4811 0.4811 0.4811
#> creat speak better strength like week bear patrol recognit energi decid commit forbear
#> 0.4789 0.4763 0.4747 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714
#> magnific humil dignifi river arlington earlier lie fame bestow raw mountain enjoy enterpris
#> 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714
#> tide hungri waver missil snow fill ground broken reveal sum car account prudent
#> 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714
#> discord soon fist effect reinvent plagu competit urgent harder devast fractur movement crise
#> 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714
#> engin sleep expect dawn forget privileg pain yesterday abroad environ shrink lest diplomaci
#> 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714
#> whenev recogn ennobl weari joy slaveri middl minor limitless touch thrive taught reclaim
#> 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714
#> pretens near crippl succumb region broad girl natur particip wisdom patienc realiti delay
#> 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714
#> imag background ignor medicar mistak prison substitut hopeless respond lend privat basic etern
#> 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714 0.4714
#> durabl allegi soldier victim one young million done sustain cours divis congress thank
#> 0.4714 0.4714 0.4714 0.4714 0.4682 0.4642 0.4629 0.4623 0.4623 0.4623 0.4588 0.4576 0.4575
#> good greatest tyranni yes rememb shown decis independ inaugur led pursuit depress quest
#> 0.4545 0.4491 0.4491 0.4491 0.4491 0.4472 0.4472 0.4472 0.4472 0.4472 0.4472 0.4472 0.4472
#> vote bright becam decenc constant generous standard treat clinton spare risk attack pride
#> 0.4472 0.4472 0.4472 0.4472 0.4472 0.4472 0.4472 0.4472 0.4472 0.4472 0.4472 0.4472 0.4472
#> centuri suffer terror restor tri safe succeed mean other human presid renew keep
#> 0.4445 0.4444 0.4444 0.4444 0.4444 0.4444 0.4444 0.4385 0.4384 0.4369 0.4319 0.4313 0.4303
#> fulfil soul drift poster 21st class everyon affirm wit institut els parti factori
#> 0.4303 0.4264 0.4216 0.4216 0.4216 0.4216 0.4216 0.4216 0.4216 0.4216 0.4082 0.4082 0.4082
#> fate adversari fight democrat invest deepest king certain larger state capitol direct perman
#> 0.4082 0.4082 0.4082 0.4082 0.4082 0.4082 0.4082 0.4082 0.4082 0.4025 0.4020 0.4020 0.4020
#> govern place taken fire complet constitut cast street around sign match highest intend
#> 0.3978 0.3931 0.3928 0.3928 0.3922 0.3849 0.3849 0.3849 0.3849 0.3849 0.3849 0.3849 0.3849
#> thoma flame bodi welcom wonder rob bond begun corner spoken conduct agre poverti
#> 0.3849 0.3849 0.3849 0.3849 0.3849 0.3849 0.3849 0.3849 0.3849 0.3849 0.3849 0.3849 0.3849
#> cold dedic behalf heaven assum walk exercis anyon battl easi use help enough
#> 0.3849 0.3849 0.3849 0.3849 0.3849 0.3849 0.3849 0.3849 0.3849 0.3849 0.3849 0.3799 0.3785
#> tradit return readi action held simpl whole sens final destruct divers continu side
#> 0.3780 0.3780 0.3780 0.3780 0.3780 0.3780 0.3780 0.3780 0.3780 0.3780 0.3780 0.3714 0.3698
#> earn program heart friend strong best capac seem decad social hear balanc import
#> 0.3698 0.3698 0.3685 0.3682 0.3638 0.3600 0.3563 0.3553 0.3536 0.3536 0.3536 0.3536 0.3536
#> alli strive name union begin threaten arm problem back vice ceremoni product teach
#> 0.3536 0.3536 0.3536 0.3478 0.3472 0.3443 0.3443 0.3430 0.3381 0.3333 0.3333 0.3333 0.3333
#> strongest spoke belong encourag mysteri oldest almighti predecessor half-centuri steadfast shadow sunshin unrival
#> 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333
#> inherit stagnant inequ news slowli boat broadcast instantan tobillion communic mobil magic livelihood
#> 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333
#> shake enrich abl compet bankrupt abid erod shaken fearsom restless muster construct pillar
#> 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333
#> envi deadlock season massiv wander revit intrigu calcul maneuv posit worri sweat pave
#> 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333
#> shout advantag franklin roosevelt experiment stabl collaps animos engulf intern defi persian gulf
#> 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333
#> somalia testament rejoic unmistak undertak compani reconnect torn inde reded myriad infus upward
#> 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333
#> disciplin well-do reap faint mountaintop guard 20th millennium prospect affair 18th 19th abolish
#> 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333
#> aw turmoil explod onto stage mightiest unriv center split atom explor comput microchip
#> 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333
#> deepen wellspr african circl third coast conserv inform perfect tragedi exhilar indispens cleaner
#> 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333
#> destin bend safer record flexibl everyday preemin hire behind lock gang divid curs
#> 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333
#> contempt cloak religi fanatic torment obsess hate impuls lurk overcom textur godsend approach
#> 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333
#> outlin internet mystic provinc physicist encyclopedia schoolchildren scientist decod blueprint hostil camp dictatorship
#> 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333
#> surpass bloodsh resound sought prize ignit spark boy classroom librari kitchen tabl laughter
#> 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333
#> shoot sell anymor medicin hardwork chemic biolog port airport innov grandpar grandchildren benefit
#> 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333
#> fortifi majest louder din regain armi thirty-four prophet luther ceaseless redeem extrem partisanship
#> 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333
#> plain deplor repair breach cardin bernardin wast acrimoni wide belov height summit rare
#> 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333
#> gore contest slave-hold went fallibl grand insignific enact halt rock sea seed root
#> 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333
#> inborn hidden onward deal forgiv appear undermin permit tactic chao inspir condemn apathi
#> 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333
#> prevent recov momentum invit mass horror arrog aggress compassion unworthi view fault prolifer
#> 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333
#> diminish mentor pastor synagogu mosqu listen wound jericho scapegoat option civic uncount unhonor
#> 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333
#> anyth comfort spectat miss statesman angel whirlwind arriv accumul theme tire finish cheney
#> 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333
#> carter non prescrib consequenti half shipwreck repos sabbat simmer resent prone ideolog excus
#> 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333
#> murder multipli mortal reign expos tyrant event conclus matchless imper slave polici primarili
#> 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333
#> aris style attain concentr unlimit consider unwis clarifi ruler pretend jail dissid chain
#> 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333
#> humili merci bulli treatment concess appeal swiftest odd surpris eventu exist oppressor repress
#> 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333
#> exil outlaw regim retain counsel concert promot prelud dishonor kindl burn hardest intellig
#> 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333
#> devot death youngest fragil evil essenti unfinish subsist broader definit homestead gi ownership
#> 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333
#> widen insur agent integr edific sinai sermon mount koran vari surround unwant worth
#> 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333
#> racism baggag perspect includ viewpoint credit known felt fellowship unjust encount captiv wheel
#> 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333
#> outrag banner meant ebb visibl bell rang thereof biden color skin tenet articul
#> 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333
#> self-evid endow creator unalien never-end self-execut mob entrust sword half-slav half-fre railroad highway
#> 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333
#> speed train discov hazard misfortun relinquish skeptic central fiction initi insist fidel musket
#> 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333
#> militia math teacher lab steel prove resili recoveri bare brink littl bleakest anybodi
#> 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333
#> outworn inadequ revamp code empow twilight spent disabl lucki loss sudden swept terribl
#> 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333
#> medicaid taker climat betray judgment none impact drought resist cede forest waterway crop
#> 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333
#> snow-cap peak perpetu uniform sear harm heir won naiv suspicion anchor asia africa
#> 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333
#> east compel margin describ forebear seneca selma stonewal sung unsung footprint preacher inextric
#> 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333
#> pioneer wive daughter gay brother sister student enlist workforc expel detroit appalachia lane
#> 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333
#> newtown cherish contour exact centuries-long absolut spectacl name-cal reason imperfect partial henc confer
#> 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333 0.3333
#> philadelphia recit durat passion thing preserv ago sometim much progress believ dream stori
#> 0.3333 0.3333 0.3333 0.3333 0.3320 0.3288 0.3269 0.3269 0.3267 0.3267 0.3255 0.3254 0.3253
#> want industri open memori jefferson save spring oppress spread goal seen educ part
#> 0.3162 0.3162 0.3162 0.3162 0.3162 0.3162 0.3162 0.3162 0.3162 0.3143 0.3123 0.3015 0.3015
#> neighbor start destroy chief put influenc remind ride solv loyalti potenti kind local
#> 0.3015 0.3015 0.3015 0.2981 0.2981 0.2981 0.2981 0.2981 0.2981 0.2981 0.2981 0.2981 0.2981
#> heritag summon generos bigger welfar told rich hand man two member cross assur
#> 0.2981 0.2981 0.2981 0.2981 0.2981 0.2887 0.2887 0.2859 0.2843 0.2780 0.2774 0.2722 0.2722
#> high realiz aim four lesson crime mother vow endless compass turn made growth
#> 0.2722 0.2722 0.2722 0.2722 0.2722 0.2722 0.2722 0.2722 0.2722 0.2673 0.2649 0.2593 0.2582
#> look higher within sinc beyond first individu price support commonplac transfer miracl process
#> 0.2566 0.2520 0.2520 0.2520 0.2513 0.2434 0.2395 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357
#> worst borrow tomorrow concern boundari racial object bigotri bounti except reserv unwil command
#> 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357
#> heroic church prioriti impos ten fit shoulder abraham add paid messag win issu
#> 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357
#> martin clergi john repres horseback untam aid mankind wherev took accomplish master servant
#> 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357
#> equip dramat aliv modern rebuild self-govern virginia remark wrote difficulti overwhelm abus disast
#> 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357
#> treasur tool debt servitud bill due unfortun origin custom primari awesom research target
#> 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357
#> nowher noblest hunger mighti youth expans lit valley air idealist affect dictat form
#> 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357
#> saint trade deeper drug honest second chorus heard motiv apart await bicker mere
#> 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357
#> foreign vigil salut flag sentiment connect circumst window hurt scourg flaw truli trumpet
#> 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357 0.2357
#> struggl solut heal love maintain share past among leav go reverend almost republ
#> 0.2236 0.2222 0.2222 0.2188 0.2182 0.2132 0.2085 0.2085 0.2010 0.1951 0.1925 0.1925 0.1925
#> goe whatev unleash troubl number self rest ensur histor tie aspir beauti star
#> 0.1925 0.1925 0.1925 0.1925 0.1925 0.1925 0.1925 0.1925 0.1925 0.1925 0.1925 0.1925 0.1925
#> howev yield reborn send conquer close wait confront provid sound ahead georg econom
#> 0.1925 0.1925 0.1925 0.1925 0.1925 0.1925 0.1925 0.1849 0.1849 0.1721 0.1667 0.1667 0.1644
#> nuclear increas engag guarante grant lincoln hill birthright hall dare drive music echo
#> 0.1622 0.1571 0.1571 0.1491 0.1491 0.1491 0.1491 0.1491 0.1491 0.1491 0.1491 0.1491 0.1491
#> door execut fall produc reflect friendship victori left allow system spend becom sick
#> 0.1491 0.1491 0.1361 0.1361 0.1361 0.1361 0.1361 0.1361 0.1361 0.1283 0.1283 0.1260 0.1260
#> matter moral thousand hero deficit present page offer mr weapon step washington reduc
#> 0.1260 0.1260 0.1111 0.1081 0.1054 0.1054 0.1054 0.1005 0.0972 0.0972 0.0962 0.0962 0.0925
#> tax budget away limit prayer think senat hatfield mondal baker speaker o'neil moomaw
#> 0.0907 0.0891 0.0765 0.0745 0.0711 0.0695 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> occas occurr routin stop uniqu realli normal gracious degre bulwark afflict proport longest
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> inflat distort penal thrift crush fixed-incom elder alik shatter idl unemploy miseri indign
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> burden kept pace pile mortgag temporari conveni trend tremend upheav period misunderstand sever
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> bastion tempt complex self-rul elit group superior capabl someon equit pay special neglect
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> section ethnic food mine profession industrialist shopkeep clerk cabbi truckdriv breed administr healthi
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> vigor barrier discrimin runaway reviv core inventori check revers grown consent intent curb
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> feder establish distinct smother foster stifl genius extent avail coincid parallel proportion intervent
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> intrus result unnecessari excess loom creativ gate counter entrepreneur voluntari art address makeup
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> countrymen suffici fact theori unequivoc emphat paraphras winston churchil dissolut propos remov roadblock
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> slow various level inch feet mile reawaken giant get lighten punit compromis eve
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> dr joseph warren massachusett despair unborn worthi exemplar beacon benefici sovereignti sale negoti
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> surrend misunderstood reluct misjudg prevail arsenal formid practic prey deepli front vista shrine
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> monument revolutionari infant nationhood eloqu pool column whoever heroism potomac slope cemeteri row
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> white marker david tini fraction belleau wood argonn omaha beach salerno halfway guadalcan
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> tarawa pork chop chosin reservoir hundr rice paddi jungl vietnam town barber shop
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> franc rainbow western kill battalion heavi artilleri diari flyleaf head written therefor cheer
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> utmost treptow perform deed mathia burger dole brighter presenc absent stenni gilli louisiana
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> night silent amen adequ express 50th bibl stood wilder gone cri moon stress
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> glori present-day backward proper machin consist rate employ vibrant robust climb neighborhood restat
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> freed grip sincer meaning reduct develop totalitarian sunlight pois golden gain two-parti republican
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> boston lawyer adam planter rival elect later soften anger letter reestablish anniversari fourth
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> juli exchang sunset beset valuabl oar harmless rode repeat well-intent error futil chase
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> spiral bloat prescript reelect vindic straight incent entrepreneuri interfer simplifi least emancip tear
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> distress area literatur poetri dynam unbroken brought reckon point cabinet staff submit freez
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> desir money unconstitut handl fundament upgrad infirm disadvantag older instal hearten brotherhood hesit
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> abund black utter fervent scorn soviet militari buildup offens legitim discuss total elimin
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> either resort retali logic recours approv shield militar space demilitar render obsolet rid
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> fourfold hemispher worldwid self-determin inalien staunchest blow inflict lightn transcend ribbon unfurl symbol
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> gotten insid general knee lone darken ponder alamo settler push sing song unknow
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> big-heart tender quayl mitchel wright congressman michael reagan bicentenni gladden concret stun porch
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> talk suspend bow heed write lord breez refresh blown lifeless tree thick fog
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> sit mist room agit thought intellectu satisfact speech unhamp perhap late wrest crucial
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> proud loud enthral materi appreci nobil bank loyal driven stay quieter gold silk
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> finer wholli unless kinder gentler homeless roam normalci enslav addict demor slum rough
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> guidanc case fund low wallet alloc wisest activ hands-on involv unus talent unfocus
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> leadership stewardship organ hous agenc pitch thrash fiscal dissens harmoni statement untrust cleav
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> earnest quarter statut sunder bipartisanship opposit major clock wish partisan unaccount assist beget
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> treati agreement marbl candor compliment subtleti relationship experi throw son hymn continuum inescap
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> kite neither princ pope yearn going attitud intoler obvious cocain smuggl ship dead
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
#> bacteria mistrust larg boundless drama book
#> 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
We have a lot of development work to do on the textmodel() function, but here is a demonstration of unsupervised document scaling comparing the “wordfish” model to scaling from correspondence analysis:
# make prettier document names
docnames(ie2010Corpus) <-
paste(docvars(ie2010Corpus, "name"), docvars(ie2010Corpus, "party"))
ieDfm <- dfm(ie2010Corpus, verbose = FALSE)
wf <- textmodel(ieDfm, model = "wordfish", dir=c(2,1))
#> Warning in if (dispersion == "poisson" & dispersionFloor != 0) warning("dispersionFloor argument ignored for poisson"): the condition has length > 1 and only the first element will be used
wca <- textmodel(ieDfm, model = "ca")
# plot the results
plot(wf@theta, -1*wca$rowcoord[,1],
xlab="Wordfish theta-hat", ylab="CA dim 1 coordinate", pch=19)
text(wf@theta, -1*wca$rowcoord[,1], docnames(ieDfm), cex=.8, pos=1)
abline(lm(-1*wca$rowcoord[,1] ~ wf@theta), col="grey50", lty="dotted")
quantdfm <- dfm(ie2010Corpus, verbose = FALSE,
ignoredFeatures = c("will", stopwords("english")))
if (require(topicmodels)) {
myLDAfit20 <- LDA(convert(quantdfm, to = "topicmodels"), k = 20)
get_terms(myLDAfit20, 5)
topics(myLDAfit20, 3)
}
#> Loading required package: topicmodels
#> Lenihan FF Bruton FG Burton LAB Morgan SF Cowen FF Kenny FG ODonnell FG Gilmore LAB Higgins LAB Quinn LAB Gormley Green Ryan Green Cuffe Green OCaolain SF
#> [1,] 4 19 2 7 17 13 6 16 14 18 5 8 12 9
#> [2,] 3 12 18 18 20 11 15 10 7 20 1 14 20 15
#> [3,] 1 15 14 14 18 15 5 12 3 7 20 12 3 5