/// <summary>
/// Used to compute the difference between the two files
/// </summary>
/// <param name="queue">Queue containing the frequencies of the words used in the files</param>
/// <returns>The difference percentage between the two authors</returns>
public static float GetDifference(MinPriorityQueue<float, WordFrequency> queue)
{
float percentageDifference = 0;
while (queue.Count > 0)
{
WordFrequency x = queue.RemoveMinimumPriority();
percentageDifference += ((x[0] - x[1]) * (x[0] - x[1]));
} //END OF WHILE LOOP
return (100 * ((float)Math.Sqrt(percentageDifference)));
} //END OF GerDifference METHOD
/// <summary>
/// Returns a float giving the difference measure.
/// </summary>
/// <param name="data">MinPriorirtyQueue contain a float(priority) and a Word frequency object</param>
/// <returns></returns>
public static float GetDifference(MinPriorityQueue <float, WordFrequency> data)
{
float accumulator = 0;
while (data.Count > 0)
{
WordFrequency x = data.RemoveMinimumPriority();
accumulator += ((x[0] - x[1]) * (x[0] - x[1]));
}
return(100 * ((float)Math.Sqrt(accumulator)));
}
/// <summary>
/// returns a float giving the difference measure using the elements of the min-priority queue
/// </summary>
/// <param name="queue">queue to use</param>
/// <returns>the difference measure</returns>
public static float GetDifference(MinPriorityQueue <float, WordFrequency> queue)
{
// d = 100 * sqrt( (x1 - y1)^2 + ... + (xn - yn)^2 )
float d = 0;
while (queue.Count > 0)
{
WordFrequency f = queue.RemoveMinimumPriority();
d += ((f[0] - f[1]) * (f[0] - f[1]));
}
return(100 * (float)Math.Sqrt(d));
}
} // end GetMostCommonWords
/// <summary>
/// This method finds the difference measure between the frequency of the words to use
/// </summary>
/// <param name="frequency">frequency of the word in MinPriorityQueue</param>
/// <returns>Returns the difference between the frequencies</returns>
public static float GetDifference(MinPriorityQueue <float, WordFrequency> frequency)
{
float diffMeasured = 0;
while (frequency.Count > 0)
{
WordFrequency wordFrequency = frequency.RemoveMinimumPriority();
diffMeasured += (wordFrequency[0] - wordFrequency[1]) * (wordFrequency[0] - wordFrequency[1]);
}
float squareRoot = 100 * (float)Math.Sqrt(diffMeasured);
return(squareRoot);
}//end GetDifference
/// <summary>
/// A method to compute the difference measure
/// </summary>
/// <param name="p">contains the frequencies of the words to use in computing the difference measure</param>
/// <returns>a float giving the difference measure</returns>
public static float GetDifference(MinPriorityQueue <float, WordFrequency> freq)
{
float diff = 0;
while (freq.Count > 0)
{
WordFrequency wordFreq = freq.RemoveMinimumPriority();
diff += (wordFreq[0] - wordFreq[1]) * (wordFreq[0] - wordFreq[1]);
}
float sqrt = 100 * (float)Math.Sqrt(diff);
return(sqrt);
}
} //END OF GerDifference METHOD
/// <summary>
/// Method used to find the highest frequencies of words in each file
/// </summary>
/// <param name="dictionary">Gives the number of occurrences of each word in each file</param>
/// <param name="numberOfWords">Gives the number of words in each file</param>
/// <param name="num">number of words to get</param>
/// <returns></returns>
public static MinPriorityQueue<float, WordFrequency> GetMostCommonWord(Dictionary<string, WordCount> dictionary, int[] numberOfWords, int number)
{
MinPriorityQueue<float, WordFrequency> queue = new MinPriorityQueue<float, WordFrequency>();
foreach (KeyValuePair<string, WordCount> pair in dictionary)
{
WordFrequency temp = new WordFrequency(pair.Value, numberOfWords);
queue.Add(temp[0] + temp[1], temp);
if (queue.Count > number)
{
queue.RemoveMinimumPriority();
} //END OF IF STATEMENT
} //END OF FOREACH LOOP
return queue;
} //END OF GetMostCommonWord METHOD
/// <summary>
/// Returns a MinPriorityQueue whose elements contain the frequencies in each file of the most common words.
/// </summary>
/// <param name="input">Dictionary containing a string and a WordCount object</param>
/// <param name="words">int array storing words</param>
/// <param name="num">int for comparing against count</param>
/// <returns></returns>
public static MinPriorityQueue <float, WordFrequency> GetMostCommonWord(Dictionary <string, WordCount> input, int[] words, int num)
{
MinPriorityQueue <float, WordFrequency> queue = new MinPriorityQueue <float, WordFrequency>();
foreach (KeyValuePair <string, WordCount> pair in input)
{
WordFrequency temp = new WordFrequency(pair.Value, words);
queue.Add(temp[0] + temp[1], temp);
if (queue.Count > num)
{
queue.RemoveMinimumPriority();
}
}
return(queue);
}
} //end ProcessFile
/// <summary>
/// This method removes the minimum priority object in the queue
/// </summary>
/// <param name="wordDictionary">This dictionary holds words and WordCounts</param>
/// <param name="wordCount">The count of words</param>
/// <param name="wordsToGet">The number of words to get</param>
/// <returns>Returns the frequencies in each file of the most common words</returns>
public static MinPriorityQueue <float, WordFrequency> GetMostCommonWords(Dictionary <string, WordCount> wordDictionary, int[] wordCount, int wordsToGet)
{
MinPriorityQueue <float, WordFrequency> minimumQueue = new MinPriorityQueue <float, WordFrequency>();
foreach (WordCount w in wordDictionary.Values)
{
WordFrequency frequency = new WordFrequency(w, wordCount);
minimumQueue.Add(frequency[0] + frequency[1], frequency);
if (minimumQueue.Count > wordsToGet)
{
minimumQueue.RemoveMinimumPriority();
} //end if
} // foreach
return(minimumQueue);
} // end GetMostCommonWords
/// <summary>
/// A method to get the words with highest combined frequencies
/// </summary>
/// <param name="d">A Dictionary<string, WordCount> giving the number of occurrences of each word in each file.</param>
/// <param name="numWords">An int[ ] of size 2 giving the number of words in each file.</param>
/// <param name="getNum">An int giving the number of words to get.</param>
/// <returns>a MinPriorityQueue<float, WordFrequency> whose elements contain the frequencies in each file of the most common words, and whose priorities are the combined frequencies of each of these words</returns>
public static MinPriorityQueue <float, WordFrequency> GetMostCommonWords(Dictionary <string, WordCount> d, int[] wordCount, int getNum)
{
MinPriorityQueue <float, WordFrequency> minQueue = new MinPriorityQueue <float, WordFrequency>();
foreach (WordCount w in d.Values)
{
WordFrequency freq = new WordFrequency(w, wordCount);
minQueue.Add(freq[0] + freq[1], freq);
if (minQueue.Count > getNum)
{
minQueue.RemoveMinimumPriority();
}
}
return(minQueue);
}
/// <summary>
/// returns a MinPriorityQueue whose elements contain the frequencies in each file of the most common words,
/// and whose priorities are the combined frequencies of each of these words
/// </summary>
/// <param name="dictionary">dictionary to take words from</param>
/// <param name="words">total number of words</param>
/// <param name="number">number of words needed to get</param>
/// <returns>min priority queue holding the frequencies</returns>
public static MinPriorityQueue <float, WordFrequency> GetMostCommonWords(Dictionary <string, WordCount> dictionary, int[] words, int number)
{
MinPriorityQueue <float, WordFrequency> queue = new MinPriorityQueue <float, WordFrequency>();
foreach (WordCount value in dictionary.Values)
{
WordFrequency wordFrequency = new WordFrequency(value, words);
queue.Add(wordFrequency[0] + wordFrequency[1], wordFrequency);
if (queue.Count > number)
{
queue.RemoveMinimumPriority();
}
}
return(queue);
}
