# Random name generation

(Difference between revisions)

Markov-Chains are usually used in the field of thermodynamics, but I will be using a fudged version of Markov-Chains to generate some random names. The basic premise of Markov-Chains is that if we have a big enough data set we should be able to predict the next event in a series of seemingly random events. So using this we need to create a dataset of names that we want to generate, lucky for you I have already done this. Here is the List of Names.

This list is every male and gender-neutral name from babynames.com. Now we need to create a program to parse this list for it's statistics. To make this interesting I have split the statistics up, 1. Letter combinations that begin names, 2. Letter combinations that end names, and 3. Letter combinations that are in betwee the beginning and end. This should give us slightly better names. The following is my code samples in C++, after compilation this program will output some randomly generated names.

```// CWordFrequncy.h
#ifndef CWORDFREQUENCY_H_
#define CWORDFREQUENCY_H_

class CWordFrequency
{

private:
int countBeginning;
int countEnd;
int countWithin;

public:
CWordFrequency();
~CWordFrequency();
void incrementCountBeginning();
void incrementCountEnd();
void incrementCountWithin();
int returnCountBeginning();
int returnCountEnd();
int returnCountWithin();

};

#endif

```

```//CWordFrequency.cpp
#include "CWordFrequency.h"

CWordFrequency::CWordFrequency() : countBeginning(0), countEnd(0),
countWithin(0)
{

}

CWordFrequency::~CWordFrequency()
{

}

void CWordFrequency::incrementCountBeginning()
{

++countBeginning;

}

void CWordFrequency::incrementCountEnd()
{

++countEnd;

}

void CWordFrequency::incrementCountWithin()
{

++countWithin;

}

int CWordFrequency::returnCountBeginning()
{

return countBeginning;

}

int CWordFrequency::returnCountEnd()
{

return countEnd;

}

int CWordFrequency::returnCountWithin()
{

return countWithin;

}
```

```//CRandomName.h
#include <fstream>
#include <map>
#include <string>
#include <cstdlib>
#include <ctime>
#include <vector>
#include <algorithm>

#include "CWordFrequency.h"

#ifndef CRANDOMNAME_H_
#define CRANDOMNAME_H_

class CRandomName
{

private:

std::string errorMessage;
std::ifstream *fileStreamIn;
std::ofstream *fileStreamOut;
std::map<char, std::map<char, CWordFrequency> > baseMap;
std::map<char, CWordFrequency> sequenceFrequencyMap;
CWordFrequency tempFrequency;

public:

CRandomName();
~CRandomName();
void inputFile(std::ifstream &streamHandle);
void processFile();
void outputList(std::ofstream &streamHandle);
std::string outputName(double minLength, double maxLength);

};

#endif
```

```//CRandomName.cpp
#include <iostream>
#include "CRandomName.h"

CRandomName::CRandomName()
{
srand(time(NULL));
}

CRandomName::~CRandomName()
{
fileStreamOut->close();
fileStreamIn->close();
}

void CRandomName::inputFile(std::ifstream &streamHandle)
{

fileStreamIn = &streamHandle;

}

void CRandomName::processFile()
{

std::string word;
char base;
char sequence;
int wordPosition;

while(!fileStreamIn->eof())
{
*fileStreamIn >> word;
for (wordPosition = 0; (wordPosition + 1) < (word.length()); wordPosition++)
{
base = word[wordPosition];
sequence = word[wordPosition + 1];

CWordFrequency &wf = baseMap[base][sequence];

if (wordPosition == 0) {wf.incrementCountBeginning();}
else if ((wordPosition + 1) >= (word.length() - 1)) {wf.incrementCountEnd();}
else if ((wordPosition > 0) && ((wordPosition + 1) < (word.length() - 1))) {wf.incrementCountWithin();}
}
}
}

void CRandomName::outputList(std::ofstream &streamHandle)
{
fileStreamOut = &streamHandle;

std::map<char, std::map<char, CWordFrequency> >::iterator itr;

std::map<char, CWordFrequency>::iterator itr2;

for (itr = baseMap.begin(); itr != baseMap.end(); itr++)
{
sequenceFrequencyMap = itr->second;
for (itr2 = sequenceFrequencyMap.begin(); itr2 != sequenceFrequencyMap.end(); itr2++)
{
tempFrequency = itr2->second;
*fileStreamOut << itr->first << " " << itr2->first << " " << tempFrequency.returnCountBeginning() << " " << tempFrequency.returnCountWithin() << " " << tempFrequency.returnCountEnd() << std::endl;
}
}
}

std::string CRandomName::outputName(double minLength, double maxLength)
{
std::string name;
std::vector<char> freqVector;
double range = static_cast<double>((maxLength - minLength) + 1);
int rangeLength = static_cast<int>(minLength + (range * ((double)rand() / (double)(RAND_MAX + 1))));
char a = static_cast<char> (65 + (26 * rand() / ( RAND_MAX + 1.0 )));
//I made this only go to
//'Z' because I haven't finished compiling my list of names

name += a;

for(int counter = 1; counter < rangeLength; counter++)
{
int cdc = 0;
if(baseMap.find(a) != baseMap.end())
{
for (char b = 'A'; b <= 'Z'; b++)
{
if(baseMap[a].find(b) != baseMap[a].end())
{
if(counter == 1)
{
for(int cc = 0; cc < (baseMap[a][b].returnCountBeginning()); cc++)
{
freqVector.push_back(b);
cdc++;
}
}
else if((counter + 1) >= (rangeLength - 1))
{
for(int cc = 0; cc < baseMap[a][b].returnCountEnd();cc++)
{
freqVector.push_back(b);
cdc++;
}
}
else
{
for(int cc = 0; cc < baseMap[a][b].returnCountWithin();cc++)
{
freqVector.push_back(b);
cdc++;
}
}
}
}
}
std::random_shuffle(freqVector.begin(), freqVector.end());
std::random_shuffle(freqVector.begin(), freqVector.end());
std::random_shuffle(freqVector.begin(), freqVector.end());
int c = (int)(((cdc) * rand() / ( RAND_MAX + 1.0 )));
name += freqVector.at(c);
a = freqVector.at(c);
}
return name;
}
```

```//main.cpp
#include <iostream>
#include "CRandomName.h"
int main()
{
CRandomName name;

std::ifstream inFile("NameList.txt");
std::ofstream outFile("Stats.txt", std::ios_base::trunc);

name.inputFile(inFile);
name.processFile();
name.outputList(outFile);

std::cout << name.outputName(3, 9) << '\n' << name.outputName(3, 9) << '\n' << name.outputName(3, 9) << '\n' << name.outputName(3, 9) << '\n' << name.outputName(3, 9);
}
```

And here is some sample output:

```ONMY
TERLEMDA
ZENEEVML
CHIA
SAWH
SPTKIVCDE
ILAN
COONR
VIAN
XAIIN
URRIRERON
FRTOKRR
YONNAN
IDANSZEDS
CAALLSTF
FLVAHE
XHAM
DUSEXNCST