edu.princeton.cs.algs4.FrequencyCounter Maven / Gradle / Ivy
Show all versions of algorithm Show documentation
/******************************************************************************
* Compilation: javac FrequencyCounter.java
* Execution: java FrequencyCounter L < input.txt
* Dependencies: ST.java StdIn.java StdOut.java
* Data files: https://algs4.cs.princeton.edu/31elementary/tnyTale.txt
* https://algs4.cs.princeton.edu/31elementary/tale.txt
* https://algs4.cs.princeton.edu/31elementary/leipzig100K.txt
* https://algs4.cs.princeton.edu/31elementary/leipzig300K.txt
* https://algs4.cs.princeton.edu/31elementary/leipzig1M.txt
*
* Read in a list of words from standard input and print out
* the most frequently occurring word that has length greater than
* a given threshold.
*
* % java FrequencyCounter 1 < tinyTale.txt
* it 10
*
* % java FrequencyCounter 8 < tale.txt
* business 122
*
* % java FrequencyCounter 10 < leipzig1M.txt
* government 24763
*
*
******************************************************************************/
package edu.princeton.cs.algs4;
/**
* The {@code FrequencyCounter} class provides a client for
* reading in a sequence of words and printing a word (exceeding
* a given length) that occurs most frequently. It is useful as
* a test client for various symbol table implementations.
*
* For additional documentation, see Section 3.1 of
* Algorithms, 4th Edition by Robert Sedgewick and Kevin Wayne.
*
* @author Robert Sedgewick
* @author Kevin Wayne
*/
public class FrequencyCounter {
// Do not instantiate.
private FrequencyCounter() { }
/**
* Reads in a command-line integer and sequence of words from
* standard input and prints out a word (whose length exceeds
* the threshold) that occurs most frequently to standard output.
* It also prints out the number of words whose length exceeds
* the threshold and the number of distinct such words.
*
* @param args the command-line arguments
*/
public static void main(String[] args) {
int distinct = 0, words = 0;
int minlen = Integer.parseInt(args[0]);
ST st = new ST();
// compute frequency counts
while (!StdIn.isEmpty()) {
String key = StdIn.readString();
if (key.length() < minlen) continue;
words++;
if (st.contains(key)) {
st.put(key, st.get(key) + 1);
}
else {
st.put(key, 1);
distinct++;
}
}
// find a key with the highest frequency count
String max = "";
st.put(max, 0);
for (String word : st.keys()) {
if (st.get(word) > st.get(max))
max = word;
}
StdOut.println(max + " " + st.get(max));
StdOut.println("distinct = " + distinct);
StdOut.println("words = " + words);
}
}
/******************************************************************************
* Copyright 2002-2018, Robert Sedgewick and Kevin Wayne.
*
* This file is part of algs4.jar, which accompanies the textbook
*
* Algorithms, 4th edition by Robert Sedgewick and Kevin Wayne,
* Addison-Wesley Professional, 2011, ISBN 0-321-57351-X.
* http://algs4.cs.princeton.edu
*
*
* algs4.jar is free software: you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* algs4.jar is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with algs4.jar. If not, see http://www.gnu.org/licenses.
******************************************************************************/