理解文本分析中的元数据
了解 tm 包在自然语言处理过程中如何使用元数据。
library(tm) docDir <- DirSource(directory = "data") newSimpleCorpus <- SimpleCorpus(docDir)
meta(newSimpleCorpus[[2]])
library(tm) docDir <- DirSource(directory = "data") newSimpleCorpus <- SimpleCorpus(docDir)
meta(newSimpleCorpus, type = "corpus")
library(tm, quietly = TRUE)
docDir <- DirSource(directory = "data", pattern = ".*.txt")
newVCorpus <- VCorpus(docDir)
列出 newVCorpus 的语料库元数据
meta(newVCorpus, type = "corpus")
列出 newVCorpus 的文档元数据
meta(newVCorpus, type = "local")
library(tm, quietly = TRUE)
创建名为 "newVCorpus" 的语料库
docDir <- DirSource(directory = "data", pattern = "mws_.+txt")
newVCorpus <- VCorpus(docDir)
创建语料库级别的元数据
meta(newVCorpus, tag = 'mnrMeta') <- "I did this" meta(newVCorpus, tag = 'dueDate') <- c("Monday", "Wednesday") meta(newVCorpus)
创建文档级别的元数据
meta(newVCorpus[[1]], tag = 'comment') <- "great writing" meta(newVCorpus, type = "local")