将两列数据帧转换为Quanteda字典格式

library(quanteda)

data_frame <- data.frame(column1 = c("This is the first document.", "This document is the second document."), 
                         column2 = c("This document is the first document.", "And this is the second one."))

dfm_obj <- dfm(data_frame, 
               tolower = TRUE,   # 将文本转换为小写（可选）
               remove_punct = TRUE,   # 移除标点符号（可选）
               remove = c(stopwords("english"), "document"),   # 移除常见词汇和特定词汇（可选）
               remove_numbers = TRUE)   # 移除数字（可选）