文本的R特征提取
我的问题是关于文本挖掘和文本处理 我想从我的文本构建一个数据框架 我的数据是：文本的R特征提取,r,text,nlp,text-mining,feature-extraction,R,Text,Nlp,Text Mining,Feature Extraction,我的问题是关于文本挖掘和文本处理 我想从我的文本构建一个数据框架 我的数据是： text <- c("#*TeX: The Program, #@Donald E. Knuth, #t1986, #c, #index68, "" #*Foundations of Databases., #@Serge Abiteboul,Richard Hull,Victor Vianu, #t1995, #c, #index69, #%1118192, #%189, #%1088975, #%97127
text <- c("#*TeX: The Program,
#@Donald E. Knuth,
#t1986,
#c,
#index68,
""
#*Foundations of Databases.,
#@Serge Abiteboul,Richard Hull,Victor Vianu,
#t1995,
#c,
#index69,
#%1118192,
#%189,
#%1088975,
#%971271,
#%832272,
#!From the Book: This book will teach you how to write specifications of computer systems, using the language TLA+.")
text新的和改进的
text.n <- strsplit(text, "\n(?=#\\*)", perl=TRUE)[[1]]; text.n
text.s <- lapply(text.n, function(x) strsplit(x, "\n")[[1]])
patterns <- list(title="^#\\*",
autors="^#@",
year="^#t",
revue="^#c",
id_paper="^#index",
id_ref="^#%",
abstract="^#!")
tex.l <- lapply(text.s, function(x)
lapply(patterns, function(y)
paste(sub(y, "", grep(y, x, value=TRUE)), collapse=",")
)
)
tex.m <- matrix(unlist(tex.l), ncol=length(tex.l[[1]]), byrow=TRUE)
tex.df <- as.data.frame(tex.m, stringsAsFactors=FALSE)
colnames(tex.df) <- names(patterns)
str(tex.df)
# 'data.frame': 2 obs. of 7 variables:
# $ title : chr "TeX: The Program" "Foundations of Databases."
# $ autors : chr "Donald E. Knuth" "Serge Abiteboul,Richard Hull,Victor Vianu"
# $ year : chr "1986" "1995"
# $ revue : chr "" ""
# $ id_paper: chr "68" "69"
# $ id_ref : chr "" "1118192,189,1088975,971271,832272"
# $ abstract: chr "" "From the Book: This book will teach you how to write
# specifications of computer systems, using the language TLA+."
text.n这里有一个基于@AkselA答案的解决方案。我不能仅在评论中处理这一点，因此，还有一个额外的答案（我知道我可以把它格式化得更漂亮…）
到目前为止，您尝试了什么？我尝试了使用grep进行提取，但无法将id_ref连接到唯一的行中。请参阅下面的回答…您可以使用list（）
或paste0（…，collapse=“，”）
连接多个元素并将它们存储为单个条目。数据框的大小将是标题的大小。因为每篇文章都必须有一个标题。@ManuelBickel:但我们最终只会得到一个向量。@Cincinatus:id\u ref
会与之冲突。@ManuelBickel:没问题，只是停下来重新看一下。谢谢你的regex模式，我得到的不是最理想的。非常感谢你，你的答案是正确的。但我只能给出一个解决方案。谢谢你，你是个天才。
coln <- c("title", "authors", "year", "revue","id_paper", "id_ref", "abstract")
title_index <- grep("^#[*]", text)
authors_index <- grep("#@", text)
year_index <- grep("#t", text)
revue_index <- grep("#c", text)
id_paper_index <- grep("#index", text)
id_refindex <- grep("#%", text)
abstract_index <- grep("#!", text)
df <- matrix(NA, nrow=length(title_index), ncol=length(coln))
colnames(df) <- coln
stoc_index <- grep("#cSTOC", text)
sigir_index <- grep("#cSIGIR", text)}
########## titre
{der_pos <- length(title_index)
tit_position <- c(title_index , der_pos)
for(i in 1:length(title_position)){
if(i != length(title_position)){
df[i, "title"] <- text[title_position[i]]
}
}
}
########## author
{der_pos <- length(authors_index)
authors_position <- c(authors_index )
for(i in 1:length(auteur_position)){
if(i != length(auteur_position)){
df[i, "auteur"] <- text[auteur_position[i]]
}
}
}
########## year
{der_pos <- length(year_index)
year_position <- c(year_index , der_pos)
for(i in 1:length(year_position)){
if(i != length(year_position)){
df[i, "année"] <- text[year_position[i]]
}
}
}
##########??? revue
{der_pos <- length(revue_index)
revue_position <- c(revue_index )
for(i in 1:length(revue_position)){
if(i != length(revue_position)){
df[i, "revue"] <- text[revue_position[i]]
}
}
}
########## id_paper
{der_pos <- length(id_paper_index)
id_paper_position <- c(id_paper_index , dern_pos)
for(i in 1:length(id_paper_position)){
if(i != length(id_paper_position)){
df[i, "id_paper"] <- text[id_paper_position[i]]
}
}
}
########## id_ref
{der_pos <- length(id_ref_index)
id_ref_position <- c(id_ref_index , der_pos)
for(i in 1:length(id_ref_position)){
if(i != length(id_ref_position)){
df[i, "id_ref"] <- text[id_ref_position[i]]
}
}
}
########## abstract
{der_pos <- length(abstract_index)
abstract_position <- c(abstract_index , der_pos)
for(i in 1:length(abstract_position)){
if(i != length(abstract_position)){
df[i, "abstract"] <- text[abstract_position[i]]
}
}
}
text.n <- strsplit(text, "\n(?=#\\*)", perl=TRUE)[[1]]; text.n
text.s <- lapply(text.n, function(x) strsplit(x, "\n")[[1]])
patterns <- list(title="^#\\*",
autors="^#@",
year="^#t",
revue="^#c",
id_paper="^#index",
id_ref="^#%",
abstract="^#!")
tex.l <- lapply(text.s, function(x)
lapply(patterns, function(y)
paste(sub(y, "", grep(y, x, value=TRUE)), collapse=",")
)
)
tex.m <- matrix(unlist(tex.l), ncol=length(tex.l[[1]]), byrow=TRUE)
tex.df <- as.data.frame(tex.m, stringsAsFactors=FALSE)
colnames(tex.df) <- names(patterns)
str(tex.df)
# 'data.frame': 2 obs. of 7 variables:
# $ title : chr "TeX: The Program" "Foundations of Databases."
# $ autors : chr "Donald E. Knuth" "Serge Abiteboul,Richard Hull,Victor Vianu"
# $ year : chr "1986" "1995"
# $ revue : chr "" ""
# $ id_paper: chr "68" "69"
# $ id_ref : chr "" "1118192,189,1088975,971271,832272"
# $ abstract: chr "" "From the Book: This book will teach you how to write
# specifications of computer systems, using the language TLA+."
#split into individual docs
text.s = strsplit(text, "\n(?=#\\*)", perl = T)[[1]]
# function to extract information from individual docs
extract_info = function(x, patterns = list(title="^*#\\*",
autors="^*#@",
year="^*#t",
revue="^*#c",
id_paper="^*#index",
id_ref="^*#%",
abstract="^*#!")) {
lapply(patterns, function(p) {
extract = grep(p, x, value = T)
# here you check the length of the potential output
# and modify the type according to your needs
if (length(extract) > 1) {
extract = list(extract)
} else if (length(extract) == 0) {
extract = NA
}
return(extract)
})
}
# apply the function to the data
# and rbind it into a data.frame
do.call(rbind,
lapply(text.s, function(x) {
x = strsplit(x, "\\n")[[1]]
extract_info(x)
})
)
# title autors year revue id_paper id_ref
# [1,] "#*TeX: The Program" "#@Donald E. Knuth" "#t1986" "#c" "#index68" NA
# [2,] "#*Foundations of Databases." "#@Serge Abiteboul,Richard Hull,Victor Vianu" "#t1995" "#c" "#index69" List,1
# abstract
# [1,] NA
# [2,] "#!From the Book: This book will teach you how to write specifications of computer systems, using th" [truncated]