You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
85 lines
2.9 KiB
Java
85 lines
2.9 KiB
Java
|
|
|
|
import edu.princeton.cs.introcs.StdIn;
|
|
import edu.princeton.cs.introcs.StdOut;
|
|
|
|
/*************************************************************************
|
|
* Compilation: javac FrequencyCounter.java
|
|
* Execution: java FrequencyCounter L < input.txt
|
|
* Dependencies: ST.java StdIn.java StdOut.java
|
|
* Data files: http://algs4.cs.princeton.edu/31elementary/tnyTale.txt
|
|
* http://algs4.cs.princeton.edu/31elementary/tale.txt
|
|
* http://algs4.cs.princeton.edu/31elementary/leipzig100K.txt
|
|
* http://algs4.cs.princeton.edu/31elementary/leipzig300K.txt
|
|
* http://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
|
|
*
|
|
*
|
|
*************************************************************************/
|
|
|
|
/**
|
|
* The 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 <a href="http://algs4.cs.princeton.edu/31elementary">Section 3.1</a> of
|
|
* Algorithms, 4th Edition by Robert Sedgewick and Kevin Wayne.
|
|
*
|
|
* @author Robert Sedgewick
|
|
* @author Kevin Wayne
|
|
*/
|
|
public class 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.
|
|
*/
|
|
public static void main(String[] args) {
|
|
int distinct = 0, words = 0;
|
|
int minlen = Integer.parseInt(args[0]);
|
|
ST<String, Integer> st = new ST<String, Integer>();
|
|
|
|
// 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);
|
|
}
|
|
}
|