Question

Hi, I need help with my comp sci assignment.

The parameters are listed below, but I am having trouble generating the number of occurrences of each word. Please use a standard library.

Read in the clean text you generated in part 2 (start a new cpp file). Create a list of all the unique words found in the entire text file (use cleanedTextTest.txt for testing). Your list should be in the form of an array of structs, where each struct has two members. One member contains the word, one member contains the number of occurrences of that word. The struct definition

should look like this:
struct UniqueWord
{
string word;
int numOccurrences;
};

There are two sub-parts that we want to accomplish:-
1. Sort the array in ascending order based on the number of occurrences. Display to the console the number of unique words, the 10 most frequently occurring, and 10 least frequently occurring. Again, since we have not yet covered techniques for “growing” arrays in C++, preallocate your array to some large number. To play it safe, this could mean the number of words in the entire input file (this is assuming worst case scenario, where every word in your input file is unique).
Hint: Consider the algorithm for this before starting to write code. Start by writing pseudocode. You need to think about looking at every word in the input file and comparing it against a list of unique words.

2. Write the contents of the array to 2 new files named “words.txt” and “counts.txt”. Each line of the “words.txt” file will have a unique word, i.e.
word1
word2
…
Each line of the “counts.txt” file will have the numOccurrences/counts for the corresponding words, i.e.
count of word1
count of word2
…
Note that the words will be in the ascending order based on the the number of occurrences since your array is already sorted in this fashion.

Answer 1

#include<iostream> //for cout
#include<fstream> //for ifstream and ofstream
using namespace std;

//structure declaration
struct UniqueWord
{
string word;
int numOccurrences;
};

//present_index function returns -1 if the word is not present in Uniquewords array
//returns the index of the array if the word is present.
int present_index(UniqueWord uw[],string word,int n){
for(int i=0;i<n;i++){
if(uw[i].word==word)
return i;
}
return -1;
}

//sorts the uniqueword array based on numOccurrences in ascending order.
void sort(UniqueWord uw[],int n)
{
for(int i=0;i<n-1;i++){
for(int j=0;j<n-i-1;j++){
if(uw[j].numOccurrences>uw[j+1].numOccurrences){
UniqueWord temp = uw[j];
uw[j] = uw[j+1];
uw[j+1] = temp;
}
}
}
}

//main function
int main()
{
ifstream in; //ifstream to read files.
in.open("cleanedTextTest.txt"); //opens file
if(in==NULL){ //if file opening fails then
cout<<"Unable to open input file"; //prints message and
return -1; //terminates the program.
}

UniqueWord uw[1000]; //declared array of struct of size 1000
int n = 0; //to keep track of number of words stored in array
string word; //to store the read string from file
while(in>>word){ //reads words until end of file gets reached
int index = present_index(uw,word,n); //calls present_index function
if(index==-1){ //if index is -1 then word is not present
uw[n].word = word; //stores the word into array
uw[n].numOccurrences = 1; //assingns the numOccurrences to 1.
n += 1; //increases n value by 1.
}
else uw[index].numOccurrences += 1; //if the word is present then just increases the numOccurrences.
}
in.close(); //closes in stream.

sort(uw,n); //calls sort function

//prints the data about words.
cout<<"Unique Words: "<<n<<endl;
cout<<"\n10 most frequently occurring words\n";
for(int i=n-1;i>=n-10;i--){
cout<<uw[i].word<<" "<<uw[i].numOccurrences<<endl;
}
cout<<"\n10 least frequently occurring words\n";
for(int i=0;i<10;i++){
cout<<uw[i].word<<" "<<uw[i].numOccurrences<<endl;
}

ofstream out1, out2; //declares two ofstreams
out1.open("words.txt"); //opens words.txt file
out2.open("counts.txt"); //opens counts.txt file
if(out1==NULL&&out2==NULL){ //if any file falls to open then
cout<<"Error occurred while opening output files";
return -1; //terminates the program
}
//loops through array and writes into them
for(int i=0;i<n;i++){
out1<<uw[i].word<<"\n";
out2<<uw[i].numOccurrences<<"\n";
}
out1.close(); //closes out1 stream
out2.close(); //closes out2 stream

return 0;
}

//cleanedTextTest.txt file screenshot

deanedTetlest Notepad File Edit Format View Help Nory was a Catholic because her mother was a Catholic and Nory mother was a Catholic because her father was a Catholic and her father was a Catholic because his mother was a Catholic or had been I felt happy because I saw the others were happy and because I knew I should feel happy but I was not really happy

//console ouput screenshot

CAC&C+withlbin\Debuglwith.exe Unique Words: 26 10 most frequently occurring words as Catholic 6 because 5 happy 4 and 3 mother 3 her 3 father 2 10 least frequently occurring words his 1 or 1 had 1 been 1 felt 1 saw 1 the 1 others 1 ere 1 knew 1 Process returned (8x0) execution time : 0.042 s Press any key to continue.

//words.txt screenshot

words - Notepad File Edit Format View Help hi 1s or been felt saw the others Were knew should feel but not really Nory father her mother and happy because Catholic WaS

//counts.txt screenshot

counts Note File Edit Forma

//any query, post in the comment section

Answer 2

C++ Code:

#include <iostream>
#include <fstream>
#include <string>
using namespace std;

   struct UniqueWords{
       string word;
       int numOccurrences;
   };

   UniqueWords List[100];
   int uniqueWordCount = 0;

   void nextWord(string next)
   {
       int wordFound = 0;
       for (int i = 0; i < uniqueWordCount; i++)
       {
           if (List[i].word == next)
           {
               wordFound = 1;
               List[i].numOccurrences++;
               break;
           }
       }
       if (wordFound == 0)
       {
           List[uniqueWordCount].word = next;
           List[uniqueWordCount].numOccurrences = 1;
           uniqueWordCount++;
       }
   }

   void swap(UniqueWords *a, UniqueWords *b)
   {
     UniqueWords temp = *a;
     *a=*b;
     *b=temp;
   }

   void sortWords()
   {
     int i,j;
       for (i = 0; i < uniqueWordCount - 1; i++)
       {
         for (j = 0; j < uniqueWordCount-i-1; j++)
         if (List[j].numOccurrences > List[j+1].numOccurrences)
            swap(&List[j], &List[j+1]);
       }
   }

   int main()
   {
       ifstream ifs;
       string word;
       int count = 0;
       ifs.open("uniqueword.txt");
       if (!ifs)
       {
           cout << "Unable to Open File";
           exit(1);
       }
       while (!ifs.eof())
       {
           ifs >> word;
           nextWord(word);
       }

       sortWords();
       if (uniqueWordCount > 10)
       {
           cout << "\n10 Most frequently Occurring List"<<endl;
           for (int i = uniqueWordCount - 1, count = 1; count <= 10; i--, count++)
           {
               cout << List[i].word << endl;
           }
           cout << "\n10 least frequently Occurring List" << endl;
           for (int i = 0, count = 1; count <= 10; i++, count++)
           {
               cout << List[i].word << endl;
           }
       }
       else
       {
           cout << "Most frequently Occurring List" << endl;
           for (int i = uniqueWordCount - 1; i>=0; i--)
           {
               cout << List[i].word << endl;
           }
           cout << "least frequently Occurring List" << endl;
           for (int i = 0; i < uniqueWordCount; i++)
           {
               cout << List[i].word << endl;
           }
       }
       // writing files
       ofstream wordFile("uniquewordList.txt");
       ofstream countFile("uniquewordcounts.txt");
       if (wordFile.is_open() && countFile.is_open())
       {
           for (int i = 0; i < uniqueWordCount; i++)
           {
               wordFile << List[i].word << "\n";
               countFile << List[i].numOccurrences << "\n";
           }
       }
       wordFile.close();
       countFile.close();
       system("pause");
   }

Input Text file:

Output:

Output text file words:

Output text file count: