我编写了Java代码来计算事件的总和。它使用2个.txt
文件作为输入,并给出单词和频率作为输出。
我也想打印,哪个文件包含多少次给定的单词。你知道怎么做吗?
public class JavaApplication2
{
public static void main(String[] args) throws IOException
{
Path filePath1 = Paths.get("test.txt");
Path filePath2 = Paths.get("test2.txt");
Scanner readerL = new Scanner(filePath1);
Scanner readerR = new Scanner(filePath2);
String line1 = readerL.nextLine();
String line2 = readerR.nextLine();
String text = new String();
text=text.concat(line1).concat(line2);
String[] keys = text.split("[!.?:;\\s]");
String[] uniqueKeys;
int count = 0;
System.out.println(text);
uniqueKeys = getUniqueKeys(keys);
for(String key: uniqueKeys)
{
if(null == key)
{
break;
}
for(String s : keys)
{
if(key.equals(s))
{
count++;
}
}
System.out.println("["+key+"] frequency : "+count);
count=0;
}
}
private static String[] getUniqueKeys(String[] keys)
{
String[] uniqueKeys = new String[keys.length];
uniqueKeys[0] = keys[0];
int uniqueKeyIndex = 1;
boolean keyAlreadyExists = false;
for(int i=1; i<keys.length ; i++)
{
for(int j=0; j<=uniqueKeyIndex; j++)
{
if(keys[i].equals(uniqueKeys[j]))
{
keyAlreadyExists = true;
}
}
if(!keyAlreadyExists)
{
uniqueKeys[uniqueKeyIndex] = keys[i];
uniqueKeyIndex++;
}
keyAlreadyExists = false;
}
return uniqueKeys;
}
发布于 2015-05-05 08:07:49
首先,不要使用数组作为唯一的键,而是使用HashMap<String, Integer>
。效率要高很多。
最好的选择是在每一行/文件上分别运行处理,并分别存储这些计数。然后合并这两个计数,以获得总频率。
更多细节:
String[] keys = text.split("[!.?:;\\s]");
HashMap<String,Integer> uniqueKeys = new HashMap<>();
for(String key : keys){
if(uniqueKeys.containsKey(key)){
// if your keys is already in map, increment count of it
uniqueKeys.put(key, uniqueKeys.get(map) + 1);
}else{
// if it isn't in it, add it
uniqueKeys.put(key, 1);
}
}
// You now have the count of all unique keys in a given text
// To print them to console
for(Entry<String, Integer> keyCount : uniqueKeys.getEntrySet()){
System.out.println(keyCount.getKey() + ": " + keyCount.getValue());
}
// To merge, if you're using Java 8
for(Entry<String, Integer> keyEntry : uniqueKeys1.getEntrySet()){
uniqueKeys2.merge(keyEntry.getKey(), keyEntry.getValue(), Integer::add);
}
// To merge, otherwise
for(Entry<String, Integer> keyEntry : uniqueKeys1.getEntrySet()){
if(uniqueKeys2.containsKey()){
uniqueKeys2.put(keyEntry.getKey(),
uniqueKeys2.get(keyEntry.getKey()) + keyEntry.getValue());
}else{
uniqueKeys2.put(keyEntry.getKey(), keyEntry.getValue());
}
}
发布于 2015-05-06 02:03:29
更新:word出现的代码(谢谢@George)
此示例用于文件,您可以将其用于多个文件:
public class MyTest {
Map<String,Integer> mapTable;
public MyTest(List<String> wordList){
//initialize map
makeMap(wordList);
}
public void makeMap(List<String> wordList){
mapTable = new HashMap();
for(int i = 0; i < wordList.size(); i++){
//fill the map up
mapTable.put(wordList.get(i), 0);
}
}
//update occurences in a map
public void updateMap(String [] _words){
for(int i = 0; i < _words.length; i++){
updateWordCount(_words[i]);
}
}
public void updateWordCount(String _word){
int value = 0;
//check if a word present
if(mapTable.containsKey(_word)){
value = mapTable.get(_word);
value++;
mapTable.put(_word, value);
}
}
public void DisplayCounts(){
for( String key : mapTable.keySet()){
System.out.println("Word : "+key+"\t Occurrence(s) :"+mapTable.get(key));
}
}
public void getWordCount(){
String filePath = "C:\\Users\\Jyo\\Desktop\\help.txt";
String line = "";
try {
// FileReader reads text files in the default encoding.
FileReader fileReader = new FileReader(filePath);
// Always wrap FileReader in BufferedReader.
BufferedReader bufferedReader = new BufferedReader(fileReader);
String _words[] = null;
while((line = bufferedReader.readLine()) != null) {
System.out.println(line);
_words = line.split(" ");
updateMap(_words);
}
// Always close files.
bufferedReader.close();
} catch (Exception e) {
System.out.println("Error :"+e.getMessage());
}
}
/**
* @param args the command line arguments
*/
public static void main(String[] args) {
// TODO code application logic here
List<String> wordList = new ArrayList<>();
wordList.add("data");
wordList.add("select");
MyTest mt = new MyTest(wordList);
mt.getWordCount();
mt.DisplayCounts();
}
}
发布于 2017-01-29 11:08:13
进口java.io.;进口java.util.
public class file1{
public static void main(String[] args) throws Exception{
HashMap<String,Integer> words_fre = new HashMap<String,Integer>();
HashSet<String> words = new HashSet<String>();
try{
File folder = new File("/home/jsrathore/Dropbox/Semester 6th/IR_Lab/lab_01/one");
File[] listOfFiles = folder.listFiles();
BufferedReader bufferedReader=null;
FileInputStream inputfilename=null;
BufferedWriter out= new BufferedWriter(new OutputStreamWriter(new FileOutputStream("outfilename.txt",false), "UTF-8"));
for(File file : listOfFiles){
inputfilename= new FileInputStream(file);
/*System.out.println(file); */
bufferedReader= new BufferedReader(new InputStreamReader(inputfilename, "UTF-8"));
String s;
while((s = bufferedReader.readLine()) != null){
/*System.out.println(line);*/
s = s.replaceAll("\\<.*?>"," ");
if(s.contains("॥") || s.contains(":")|| s.contains("।")||
s.contains(",")|| s.contains("!")|| s.contains("?")){
s=s.replace("॥"," ");
s=s.replace(":"," ");
s=s.replace("।"," ");
s=s.replace(","," ");
s=s.replace("!"," ");
s=s.replace("?"," ");
}
StringTokenizer st = new StringTokenizer(s," ");
while (st.hasMoreTokens()) {
/*out.write(st.nextToken()+"\n");*/
String str=(st.nextToken()).toString();
words.add(str);
}
for(String str : words){
if(words_fre.containsKey(str)){
int a = words_fre.get(str);
words_fre.put(str,a+1);
}else{
words_fre.put(str,1);/*uwords++;//unique words count */
}
}
words.clear();
/*out.write("\n");
out.close();*/
}
Object[] key = words_fre.keySet().toArray();
Arrays.sort(key);
for (int i = 0; i < key.length; i++) {
//System.out.println(key[i]+"= "+words_fre.get(key[i]));
out.write(key[i]+" : "+words_fre.get(key[i]) +"\n");
}
}
out.close();
bufferedReader.close();
}catch(FileNotFoundException ex){
System.out.println("Error in reading line");
}catch(IOException ex){
/*System.out.println("Error in reading line"+fileReader );*/
ex.printStackTrace();
}
}}
https://stackoverflow.com/questions/30057864
复制相似问题