import java.util.*;
public class Test {
static List<Map.Entry<String, Integer>> getWordInDescendingFreqOrder(Map<String, Integer> wordCount) {
// Convert map to list of <String,Integer> entries
List<Map.Entry<String, Integer>> list =
new ArrayList<>(wordCount.entrySet());
// Sort list by integer values
Collections.sort(list, new Comparator<Map.Entry<String, Integer>>() {
public int compare(Map.Entry<String, Integer> o1, Map.Entry<String, Integer> o2) {
// compare o2 to o1, instead of o1 to o2, to get descending freq. order
return (o2.getValue()).compareTo(o1.getValue());
}
});
return list;
}
public static void main(String[] args) {
// format article to simple words
String article = Test.article
.replace("'", "")
.replace("’", "")
.replace("?", " ")
.replace("!", " ")
.replace("“"," ")
.replace("”"," ")
.replace(";", " ")
.replace(",", " ")
.replace(".", " ")
.replace("\n", " ");
System.out.println("words to be sorted:\n" + article + "\n");
//tree map sort by alphabet
String[] words = article.split("\\s+");
TreeMap<String, Integer> wordCount = new TreeMap<>();
for (String word : words) {
Integer count = wordCount.get(word);
if (count == null) {
wordCount.put(word, 1);
} else {
wordCount.put(word, count + 1);
}
}
System.out.println("word count alphabet sort:");
for (String key : wordCount.keySet()) {
System.out.println(key + "-" + wordCount.get(key));
}
System.out.println("\nword count descend sort:");
List<Map.Entry<String, Integer>> wordCountDescend = Test.getWordInDescendingFreqOrder(wordCount);
for (Map.Entry<String, Integer> one : wordCountDescend) {
System.out.println(one.getKey() + "-" + one.getValue());
}
}
public static String article = "It is no mean feat to be one of the top-ten trending hashtags on Weibo, China’s equivalent of Twitter, for 20 consecutive days and counting. “All is Well”, a show on provincial television which premiered on March 1st, has done just that. The show tells the story of a fictional Chinese family torn by internal conflict. The female protagonist, Su Mingyu, is barely on speaking terms with her widowed father and one of her two brothers. The father is a nagging crank who expects his two adult sons to bankroll his lavish tastes. This leads to constant bickering between the brothers, neither of whom wants to be called unfilial.";
}
java使用treemap做词频统计wordcount(字母排序alphabet和词频排序descending freq.)
最新推荐文章于 2021-02-24 20:26:43 发布