刮刮資料以構建 N-gram Word 雲

以下示例利用 tm 文字挖掘包來從 Web 中挖掘和挖掘文字資料，以構建具有符號著色和排序的文字雲。

require(RWeka)
require(tau)
require(tm)
require(tm.plugin.webmining)
require(wordcloud)

# Scrape Google Finance ---------------------------------------------------
googlefinance <- WebCorpus(GoogleFinanceSource("NASDAQ:LFVN"))
 
# Scrape Google News ------------------------------------------------------
lv.googlenews <- WebCorpus(GoogleNewsSource("LifeVantage"))
p.googlenews  <- WebCorpus(GoogleNewsSource("Protandim"))
ts.googlenews <- WebCorpus(GoogleNewsSource("TrueScience"))
 
# Scrape NYTimes ----------------------------------------------------------
lv.nytimes <- WebCorpus(NYTimesSource(query = "LifeVantage", appid = nytimes_appid))
p.nytimes  <- WebCorpus(NYTimesSource("Protandim", appid = nytimes_appid))
ts.nytimes <- WebCorpus(NYTimesSource("TrueScience", appid = nytimes_appid))
 
# Scrape Reuters ----------------------------------------------------------
lv.reutersnews <- WebCorpus(ReutersNewsSource("LifeVantage"))
p.reutersnews  <- WebCorpus(ReutersNewsSource("Protandim"))
ts.reutersnews <- WebCorpus(ReutersNewsSource("TrueScience"))
 
# Scrape Yahoo! Finance ---------------------------------------------------
lv.yahoofinance <- WebCorpus(YahooFinanceSource("LFVN"))
 
# Scrape Yahoo! News ------------------------------------------------------
lv.yahoonews <- WebCorpus(YahooNewsSource("LifeVantage"))
p.yahoonews  <- WebCorpus(YahooNewsSource("Protandim"))
ts.yahoonews <- WebCorpus(YahooNewsSource("TrueScience"))
 
# Scrape Yahoo! Inplay ----------------------------------------------------
lv.yahooinplay <- WebCorpus(YahooInplaySource("LifeVantage"))

# Text Mining the Results -------------------------------------------------
corpus <- c(googlefinance, lv.googlenews, p.googlenews, ts.googlenews, lv.yahoofinance, lv.yahoonews, p.yahoonews,
ts.yahoonews, lv.yahooinplay) #lv.nytimes, p.nytimes, ts.nytimes,lv.reutersnews, p.reutersnews, ts.reutersnews,
 
inspect(corpus)
wordlist <- c("lfvn", "lifevantage", "protandim", "truescience", "company", "fiscal", "nasdaq")
 
ds0.1g <- tm_map(corpus, content_transformer(tolower))
ds1.1g <- tm_map(ds0.1g, content_transformer(removeWords), wordlist)
ds1.1g <- tm_map(ds1.1g, content_transformer(removeWords), stopwords("english"))
ds2.1g <- tm_map(ds1.1g, stripWhitespace)
ds3.1g <- tm_map(ds2.1g, removePunctuation)
ds4.1g <- tm_map(ds3.1g, stemDocument)
 
tdm.1g <- TermDocumentMatrix(ds4.1g)
dtm.1g <- DocumentTermMatrix(ds4.1g)

findFreqTerms(tdm.1g, 40)
findFreqTerms(tdm.1g, 60)
findFreqTerms(tdm.1g, 80)
findFreqTerms(tdm.1g, 100)
 
findAssocs(dtm.1g, "skin", .75)
findAssocs(dtm.1g, "scienc", .5)
findAssocs(dtm.1g, "product", .75) 
 
tdm89.1g <- removeSparseTerms(tdm.1g, 0.89)
tdm9.1g  <- removeSparseTerms(tdm.1g, 0.9)
tdm91.1g <- removeSparseTerms(tdm.1g, 0.91)
tdm92.1g <- removeSparseTerms(tdm.1g, 0.92)
 
tdm2.1g <- tdm92.1g
 
# Creates a Boolean matrix (counts # docs w/terms, not raw # terms)
tdm3.1g <- inspect(tdm2.1g)
tdm3.1g[tdm3.1g>=1] <- 1 
 
# Transform into a term-term adjacency matrix
termMatrix.1gram <- tdm3.1g %*% t(tdm3.1g)
 
# inspect terms numbered 5 to 10
termMatrix.1gram[5:10,5:10]
termMatrix.1gram[1:10,1:10]
 
# Create a WordCloud to Visualize the Text Data ---------------------------
notsparse <- tdm2.1g
m = as.matrix(notsparse)
v = sort(rowSums(m),decreasing=TRUE)
d = data.frame(word = names(v),freq=v)
 
# Create the word cloud
pal = brewer.pal(9,"BuPu")
wordcloud(words = d$word,
          freq = d$freq,
          scale = c(3,.8),
          random.order = F,
          colors = pal)

請注意使用 random.order 和來自 RColorBrewer 的順序托盤，它允許程式設計師通過為術語的順序和著色分配含義來捕獲雲中的更多資訊。

以上是 1 克的情況。

我們可以對 n-gram 詞雲做出重大突破，在這樣做的過程中，我們將看到如何通過改變我們的 TDM 來使幾乎任何文字挖掘分析足夠靈活地處理 n-gram。

你在 R 中使用 n-gram 遇到的最初困難是 tm，這是最受歡迎的文字挖掘包，並不固有地支援 bi-gram 或 n-gram 的標記化。標記化是將單詞，單詞的一部分或單片語（或符號）表示為稱為標記的單個資料元素的過程。

幸運的是，我們有一些黑客可以讓我們繼續使用 tm 和升級的標記器。實現這一目標的方法不止一種。我們可以使用 tau 的 textcnt() 函式編寫自己的簡單標記器：

tokenize_ngrams <- function(x, n=3) return(rownames(as.data.frame(unclass(textcnt(x,method="string",n=n)))))

或者我們可以在 tm 中呼叫 RWeka 的 tokenizer：

# BigramTokenize
BigramTokenizer <- function(x) NGramTokenizer(x, Weka_control(min = 2, max = 2))

從這一點開始，你可以像在 1 克的情況下那樣進行：

# Create an n-gram Word Cloud ----------------------------------------------
tdm.ng <- TermDocumentMatrix(ds5.1g, control = list(tokenize = BigramTokenizer))
dtm.ng <- DocumentTermMatrix(ds5.1g, control = list(tokenize = BigramTokenizer))
 
# Try removing sparse terms at a few different levels
tdm89.ng <- removeSparseTerms(tdm.ng, 0.89)
tdm9.ng  <- removeSparseTerms(tdm.ng, 0.9)
tdm91.ng <- removeSparseTerms(tdm.ng, 0.91)
tdm92.ng <- removeSparseTerms(tdm.ng, 0.92)

notsparse <- tdm91.ng
m = as.matrix(notsparse)
v = sort(rowSums(m),decreasing=TRUE)
d = data.frame(word = names(v),freq=v)
 
# Create the word cloud
pal = brewer.pal(9,"BuPu")
wordcloud(words = d$word,
          freq = d$freq,
          scale = c(3,.8),
          random.order = F,
          colors = pal)

上面的例子是在 Hack-R 的資料科學部落格的許可下複製的。其他評論可以在原始文章中找到。