无法在 R 中绘制 Zipf 定律

Question

我从一个文本文件中加载了大量术语及其频率，并将其转换为 table:

myTbl = read.table("word_count.txt")  # read text file 

colnames(myTbl)<-c("term", "frequency")
head(myTbl, n = 10)

> head(myTbl, n = 10)
    term frequency
1     de     35945
2      i     34850
3  \xe3n     19936
4      s     15348
5     cu     13722
6     la     13505
7     se     13364
8     pe     13361
9     nu     12693
10     o     11995

我应该添加一个包含单词排名的列，然后根据频率绘制排名，但我该怎么做？

Answer 1

与其滚动自己的计算，不如使用 tm 包更容易。将 myTbl 转换为术语文档矩阵 (tdm)

library(tm)
tdm <- TermDocumentMatrix(myTbl) # there are many more clean up steps, but I am simplifying

那么您不仅可以显示 Zipf，还可以显示 Heaps 和 plots。

Zipf_plot(tdm) 
Heaps_plot(tdm) # how vocabulary grows as size of text grows

或者，您可以使用 qdap 包及其排名频率图。这是小插图中的引述：

Rank Frequency Plots are a way of visualizing word rank versus frequencies as related to Zipf's law which states that the rank of a word is inversely related to its frequency. The rank_freq_mplot and rank_freq_plot provide the means to plot the ranks and frequencies of words (with rank_freq_mplot plotting by grouping variable(s)).
Rank_freq_mplot utilizes the ggplot2 package, whereas, rank_freq_plot employs base graphics.

无法在 R 中绘制 Zipf 定律

Can't plot Zipf's law in R

r

distribution

tm

qdap