Merge pull request #420 from aayushKumarJarvis/master

Stop Words - A Text Mining Problem

Factorial/Java/aayushKumarJarvis/Factorial.java

@@ -0,0 +1,20 @@
+import java.util.Scanner;
+
+public class Factorial {
+
+   public static void main(String[] args) {
+       Scanner scanner = new Scanner(System.in);
+       System.out.print("Enter the number whose factorial is to be found: ");
+       int n = scanner.nextInt();
+       int result = factorial(n);
+       System.out.println("The factorial of " + n + " is " + result);
+   }
+
+   public static int factorial(int n) {
+       int result = 1;
+       for (int i = 1; i <= n; i++) {
+           result = result * i;
+       }
+       return result;
+   }
+}

README.md

@@ -2,6 +2,9 @@
 
 (Note: there is a backstory on my motivation for starting this at the bottom of this README)
 
+<<<<<<< HEAD
+Website coming soon!.
+=======
 **Update 06/09/14**
 I have released a native Android app for viewing the algorithms! It's a wrapper around the web app with some native functionality. Check it out on Google Play here
 [Algorithm Implementations Android App](https://play.google.com/store/apps/details?id=com.kennyledet.algorithms.app.grmeb)
@@ -13,6 +16,7 @@ You can see a preview here!
 [Algorithms Implementations Website](http://dry-sea-7022.herokuapp.com/algorithms)
 
 Please offer up your suggestions in the Issues section of the Github repository
+>>>>>>> upstream/master
 
 **Update 12/30/13:** I have given the 3 top committers (jcla1, PatrickYevsukov, dalleng) collaborator access. This was very well earned, as they have managed to contribute much more to this repo than I have had the time to.
 

Stop_Words/aayushKumarJarvis/StopWords.java

@@ -0,0 +1,88 @@
+import java.util.*;
+import java.io.*;
+
+public class StopWords {
+
+    private static String OUTPUT_FILE = "YOUR_FILE_LOCATION";
+
+    public static Boolean searchForStopWord(String word, List<String> textForCheck) {
+
+        int indexOfWord = Collections.binarySearch(textForCheck,word);
+
+        if(indexOfWord < 0)
+            return false;
+        else
+            return true;
+    }
+
+    public static List<String> readStopWords(String stopWordsFilename) throws Exception {
+
+            FileInputStream fStream = new FileInputStream(stopWordsFilename);
+
+            DataInputStream dataStreamObject = new DataInputStream(fStream);
+            BufferedReader objectForBuffer = new BufferedReader(new InputStreamReader(dataStreamObject));
+
+            String strLine;
+            String oneLinerString = "";
+
+            while ((strLine = objectForBuffer.readLine()) != null) {
+                strLine.trim();
+                oneLinerString = oneLinerString + "," + strLine;
+            }
+
+            List<String> tokenizedList = Arrays.asList(oneLinerString.split(","));
+            fStream.close();
+
+            return tokenizedList;
+     }
+
+    public static void removeStopWords(String textFilename, List<String> stopWords)  {
+
+        try {
+            FileOutputStream outputStream = new FileOutputStream(OUTPUT_FILE);
+            PrintStream outputFileWriter = new PrintStream(outputStream);
+
+            FileInputStream fStream = new FileInputStream(textFilename);
+            DataInputStream dataStreamObject = new DataInputStream(fStream);
+            BufferedReader objectForBuffer = new BufferedReader(new InputStreamReader(dataStreamObject));
+
+            String strLine;
+
+            while ((strLine = objectForBuffer.readLine()) != null) {
+
+                boolean flag = false;
+
+                List<String> tokenizedList = Arrays.asList(strLine.split("([^a-zA-z0-9])"));
+
+                for(int i=0;i<tokenizedList.size();i++) {
+
+                    flag = searchForStopWord(tokenizedList.get(i), stopWords);
+
+                    if (!flag)
+                        outputFileWriter.print(tokenizedList.get(i)+" ");
+
+                    flag = false;
+                }
+
+                outputFileWriter.print("\n");
+            }
+        }
+
+        catch(Exception e){
+            System.err.println(e.getMessage());
+         }
+    }
+
+    public static void main(String[] arg) throws Exception {
+
+        Scanner keyboard = new Scanner(System.in);
+
+        System.out.print("Please type stop words file name: ");
+        List<String> stopWords = readStopWords(keyboard.next());
+
+        System.out.print("Please type text file name: ");
+        removeStopWords(keyboard.next(), stopWords);
+
+    }
+}
+

Stop_Words/aayushKumarJarvis/TestStopWords.java

@@ -0,0 +1,43 @@
+mport org.junit.Test;
+import java.util.Arrays;
+import java.util.List;
+
+import static org.junit.Assert.*;
+
+public class TestStopWords {
+
+    @Test
+    public void testSearchForStopWord() {
+
+        String testWord1 = "Aayush";
+        String testWord2 = "Kumar";
+        String testWord3 = "Srivastava";
+        String testWord4 = "Random Text";
+        String testWord5 = "Text";
+
+        String[] listOfNames = {"Aayush","Kumar","Srivastava"};
+        List<String> testString = Arrays.asList(listOfNames); // Converting Array into List of String
+
+        assertEquals(StopWords.searchForStopWord(testWord1, testString), true);
+        assertEquals(StopWords.searchForStopWord(testWord2,testString),true);
+        assertEquals(StopWords.searchForStopWord(testWord3,testString),true);
+        assertEquals(StopWords.searchForStopWord(testWord4,testString),false);
+        assertEquals(StopWords.searchForStopWord(testWord5,testString),false);
+    }
+
+   @Test
+    public void testReadStopWords() throws Exception {
+
+       List<String> tokenizedText = StopWords.readStopWords("FILE_NAME");
+       System.out.println(tokenizedText);
+   }
+
+   @Test
+   public void testForRemoveStopWords() throws Exception {
+
+       List<String> tokenizedText = StopWords.readStopWords("FILE_NAME");
+       StopWords.removeStopWords("FILE_NAME",tokenizedText);
+   }
+
+}
+