public void ReviewersThatHaveReviewedUniqueTitlesShouldNotBeSimilar()
{
var r1 = ReviewerBuilder.BuildReviewer1();
var r2 = ReviewerBuilder.BuildAReviewerThatReviewedSomethingUnique();
pearsonCorrelationScore = new PearsonCorrelation(r1, r2);
Assert.AreEqual(0, pearsonCorrelationScore.Score());
}
private static void RunPearsonCorrelationWithLowScore()
{
var r1 = ReviewerBuilder.BuildReviewer1();
var r2 = ReviewerBuilder.BuildReviewer2();
var pearsonCorrelation = new PearsonCorrelation(r1, r2);
Console.WriteLine("The Pearson Correlation between {0} and {1} is: {2}", r1.Name, r2.Name, pearsonCorrelation.Score());
}
public void TestFile()
{
UserCorrelation userCorrelation = new PearsonCorrelation(model);
UserNeighborhood neighborhood = new NearestNUserNeighborhood(2, userCorrelation, model);
Recommender recommender = new GenericUserBasedRecommender(model, neighborhood, userCorrelation);
Assert.AreEqual(2, recommender.Recommend("A123", 3).Count);
Assert.AreEqual(2, recommender.Recommend("B234", 3).Count);
Assert.AreEqual(1, recommender.Recommend("C345", 3).Count);
// Make sure this doesn't throw an exception
model.Refresh();
}
public void TestBestRating()
{
List <User> users = new List <User>(4);
users.Add(GetUser("test1", 0.1, 0.3));
users.Add(GetUser("test2", 0.2, 0.3, 0.3));
users.Add(GetUser("test3", 0.4, 0.3, 0.5));
users.Add(GetUser("test4", 0.7, 0.3, 0.8));
DataModel dataModel = new GenericDataModel(users);
UserCorrelation correlation = new PearsonCorrelation(dataModel);
ClusterSimilarity similarity = new FarthestNeighborClusterSimilarity(correlation);
Recommender recommender = new TreeClusteringRecommender(dataModel, similarity, 2);
IList <RecommendedItem> recommended = recommender.Recommend("test1", 1);
Assert.IsNotNull(recommended);
Assert.AreEqual(1, recommended.Count);
RecommendedItem firstRecommended = recommended[0];
// item one should be recommended because it has a greater rating/score
Assert.AreEqual(new GenericItem <String>("2"), firstRecommended.Item);
Assert.AreEqual(0.3, firstRecommended.Value, EPSILON);
}
public void TwoReviewersWithSomeSimilarReviewsShouldHaveTheSameScoreRegardlessOfOrder()
{
pearsonCorrelationScore = new PearsonCorrelation(ReviewerBuilder.BuildReviewer7(), ReviewerBuilder.BuildReviewer6());
Assert.AreEqual(0.396, pearsonCorrelationScore.Score());
}
public void SetUp()
{
pearsonCorrelationScore = new PearsonCorrelation(ReviewerBuilder.BuildReviewer1(), ReviewerBuilder.BuildReviewer2());
}
public void ReviewersThatHaveTheSameTasteShouldHaveAPerfectScore()
{
var r1 = ReviewerBuilder.BuildReviewer1();
pearsonCorrelationScore = new PearsonCorrelation(r1, r1);
Assert.AreEqual(1.0, pearsonCorrelationScore.Score());
}
static void Main(string[] args)
{
// Specify which files to use.
var projectDir = Directory.GetParent(Directory.GetCurrentDirectory()).Parent.Parent.FullName;
var pathFiles = Directory.EnumerateFiles(projectDir + @"\DocumentClusteringExample\Samples").ToList();
// Hyper parameters.
// This option prevent overfitting on missing words.
var replaceMissingValueWithRandomValue = false;
var usePCA = false;
var numberOfOutputPCA = 100;
var distanceFunction = new PearsonCorrelation();
var strategy = ValueStrategy.Freq;
var minVectorElements = 2;
var freqMin = 2;
var minWordCount = 1;
var maxWordCount = 3;
var minGroupOfWordsLength = 3;
var minWordLength = 1;
var firstWordMinLength = 1;
var lastWordMinLength = 1;
var maxComposition = int.MaxValue;
var badWords = File.ReadLines(projectDir + @"\DocumentClusteringExample\stop-words-english.txt")
.Where(m => !string.IsNullOrWhiteSpace(m))
.ToArray();
var badPatternList = new string[]
{
};
// Files -> List of expressions (Our dictionary based on files)
var expressions = ExtractExpressionFromTextFiles.ExtractExpressions(
pathFiles,
new ExtractExpressionFromTextFilesOption
{
BadPatternList = badPatternList,
BadWords = badWords,
FirstWordMinLength = firstWordMinLength,
LastWordMinLength = lastWordMinLength,
MaxExpressionComposition = maxComposition,
MaxWordCount = maxWordCount,
MinGroupOfWordsLength = minGroupOfWordsLength,
MinWordCount = minWordCount,
MinWordFrequency = freqMin,
MinWordLength = minWordLength
});
Console.WriteLine("Expressions: " + expressions.Count);
// Files -> Vectors
var expressionVectorOption = new TextFileToExpressionVectorOption
{
MinVectorElements = minVectorElements,
BadPatternList = badPatternList,
MaxWordCount = maxWordCount,
MinWordCount = minWordCount,
Strategy = strategy,
ReplaceMissingValueWithRandomValue = replaceMissingValueWithRandomValue
};
List <Tuple <string, double[]> > filesToVector = new List <Tuple <string, double[]> >();
foreach (var pathFile in pathFiles)
{
filesToVector.Add(
new Tuple <string, double[]>(
pathFile,
TextFileToExpressionVector.GenerateExpressionVector(
expressions,
pathFile,
expressionVectorOption)
)
);
}
var vectors = filesToVector
.Select(m => m.Item2)
.ToList();
Console.WriteLine("vectors count: " + vectors.Count);
// Remove non-representative vectors
for (int i = 0; i < vectors.Count; i++)
{
var vector = vectors[i];
if (vector.Sum() < minVectorElements)
{
vectors.RemoveAt(i);
pathFiles.RemoveAt(i);
i--;
}
}
Console.WriteLine("vectors count (after removing non-representative vectors): " + vectors.Count);
// Reduce the vector size with PCA.
if (usePCA)
{
Console.WriteLine("Reducing vector size with PCA");
Stopwatch stopwatch = new Stopwatch();
stopwatch.Start();
PrincipalComponentAnalysis pca = new PrincipalComponentAnalysis();
pca.NumberOfOutputs = numberOfOutputPCA;
var trainingVector = vectors.ToArray();
Shuffle(trainingVector);
trainingVector = trainingVector.Take(600).ToArray();
var pcaResult = pca.Learn(trainingVector);
var reducedVectorsWithPCA = pcaResult.Transform(vectors.ToArray());
stopwatch.Stop();
Console.WriteLine("PCA duration: " + stopwatch.Elapsed.ToString());
vectors = reducedVectorsWithPCA.ToList();
}
// Run HDBSCAN algo.
Console.WriteLine("HDBSCAN starting...");
var contraintsList = new List <HdbscanConstraint>();
if (usePCA)
{
for (int i = 1; i < numberOfOutputPCA; i++)
{
contraintsList.Add(new HdbscanConstraint(i - 1, i, HdbscanConstraintType.CannotLink));
}
}
var watch = Stopwatch.StartNew();
var result = HdbscanRunner.Run(new HdbscanParameters
{
DataSet = vectors.ToArray(),
MinPoints = 5,
MinClusterSize = 5,
DistanceFunction = distanceFunction,
Constraints = contraintsList,
UseMultipleThread = true
});
watch.Stop();
Console.WriteLine("HDBSCAN done " + watch.Elapsed);
// Read results.
var labels = result.Labels;
int n = labels.Max();
Console.WriteLine("\n\n");
int clusterId = 0;
for (int iCluster = 1; iCluster <= n; iCluster++)
{
Dictionary <string, int> categories = new Dictionary <string, int>();
bool anyFound = false;
for (int i = 0; i < labels.Length; i++)
{
if (labels[i] == iCluster)
{
var fileName = Path.GetFileNameWithoutExtension(pathFiles[i]);
var category = fileName.Split('-')[0].Trim();
if (categories.ContainsKey(category))
{
var count = categories[category];
categories.Remove(category);
categories.Add(category, count + 1);
}
else
{
categories.Add(category, 1);
}
anyFound = true;
}
}
if (anyFound)
{
clusterId++;
Console.WriteLine("Cluster #" + clusterId);
Console.WriteLine();
foreach (var category in categories)
{
Console.WriteLine(category.Key + ": " + category.Value);
}
Console.ReadLine();
}
}
Console.WriteLine("Press any key to continue...");
Console.ReadLine();
}
static void Main(string[] args)
{
DataTable meta_table = createMetaTable();
DataTable distractors_video_table = createDistractorVideoTable();
DataTable distractors_game_table = createDistractorGameTable();
DataTable deaths_table = createDeathsTable();
var QuestionnaireScores = new List <double>();
var video_sound_distractor_percentages = new List <double>();
var video_image_distractor_percentages = new List <double>();
var sound_distractor_percentages = new List <double>();
var image_distractor_percentages = new List <double>();
var avgdistractors = new List <double>();
var aps = new List <double>();
var summs = new List <double>();
var exptype = new List <double>();
var skill_lvl = new List <double>();
var death_remembered_percentages = new List <double>();
var underskill_scores = new List <double>();
var overskill_scores = new List <double>();
var matched_scores = new List <double>();
var focused_scores = new List <double>();
var average_scores = new List <double>();
var detached_scores = new List <double>();
var bronze_scores = new List <double>();
var goldplus_scores = new List <double>();
var bps = new List <double[]>();
int participantID = 0;
foreach (String uname in usernames)
{
participantID++;
Experiment exp1 = new Experiment(uname);
Console.Out.WriteLine("User: "******"Skill Level: " + exp1.skill_level);
Console.Out.WriteLine("Play Style: " + exp1.style);
Console.Out.WriteLine("Experiment Type: " + exp1.exp_type);
Console.Out.WriteLine("Questionnaire Score: " + exp1.questionnaire_score);
Console.Out.WriteLine("number of distractors: ");
Console.Out.WriteLine(exp1.video_image_distractor_no + " " + exp1.video_sound_distractor_no + " " + exp1.game_sound_distractor_no + " " + exp1.game_image_distractor_no);
Console.Out.WriteLine("distractor remembering percentages:");
Console.Out.WriteLine("video sound distractors: " + exp1.video_sound_distractor_proc);
Console.Out.WriteLine("video image distractors: " + exp1.video_image_distractor_proc);
Console.Out.WriteLine("game sound distractors: " + exp1.game_sound_distractor_proc);
Console.Out.WriteLine("game image distractors: " + exp1.game_image_distractor_proc);
Console.Out.WriteLine("");
Console.Out.WriteLine("");
QuestionnaireScores.Add(exp1.questionnaire_score);
video_sound_distractor_percentages.Add(exp1.video_sound_distractor_proc);
video_image_distractor_percentages.Add(exp1.video_image_distractor_proc);
sound_distractor_percentages.Add(exp1.game_sound_distractor_proc);
image_distractor_percentages.Add(exp1.game_image_distractor_proc);
death_remembered_percentages.Add(exp1.death_remember_proc);
double video_avg_proc = (exp1.video_sound_distractor_proc + exp1.video_image_distractor_proc) / 2;
double avg_proc = (exp1.game_sound_distractor_proc + exp1.game_image_distractor_proc) / 2;
avgdistractors.Add(avg_proc);
aps.Add(exp1.moves_per_sec);
summs.Add(exp1.summ_no);
exptype.Add((int)exp1.exp_type);
skill_lvl.Add((int)exp1.skill_level);
if (exp1.exp_type == Experiment_Types.UnderSkill)
{
underskill_scores.Add(exp1.questionnaire_score);
}
else if (exp1.exp_type == Experiment_Types.Matched)
{
matched_scores.Add(exp1.questionnaire_score);
}
else if (exp1.exp_type == Experiment_Types.OverSkill)
{
overskill_scores.Add(exp1.questionnaire_score);
}
if (exp1.style == PlayStyle.Focused)
{
focused_scores.Add(exp1.questionnaire_score);
}
else if (exp1.style == PlayStyle.Average)
{
average_scores.Add(exp1.questionnaire_score);
}
else if (exp1.style == PlayStyle.Detached)
{
detached_scores.Add(exp1.questionnaire_score);
}
if (exp1.skill_level == Ranks.Bronze)
{
bronze_scores.Add(exp1.questionnaire_score);
}
else
{
goldplus_scores.Add(exp1.questionnaire_score);
}
foreach (var item in exp1.game_bandpower)
{
bps.Add(item);
}
foreach (var item in exp1.video_bandpower)
{
bps.Add(item);
}
// KMeans tr = new KMeans(4);
// tr.Learn(exp1.game_bandpower);
// Console.Write(tr.ToString());
// Console.ReadKey();
meta_table.Rows.Add(participantID, exp1.skill_level, exp1.style, exp1.exp_type, exp1.questionnaire_score);
deaths_table.Rows.Add(participantID, exp1.death_no, exp1.actual_death_no, exp1.death_remember_proc);
distractors_video_table.Rows.Add(participantID, exp1.video_sound_distractor_proc, exp1.video_image_distractor_proc, video_avg_proc);
distractors_game_table.Rows.Add(participantID, exp1.game_sound_distractor_proc, exp1.game_image_distractor_proc, avg_proc);
}
var test = new PearsonCorrelation();
test.Similarity(QuestionnaireScores.ToArray(), sound_distractor_percentages.ToArray());
Console.Out.WriteLine("accord.net similarity value: ");
Console.Out.WriteLine(test.Similarity(QuestionnaireScores.ToArray(), sound_distractor_percentages.ToArray()));
Console.Out.WriteLine("");
Console.Out.WriteLine("correlation questionnaire - sound distractor rememberabce");
Console.Out.WriteLine(Correlation.Pearson(QuestionnaireScores, sound_distractor_percentages));
Console.Out.WriteLine("");
Console.Out.WriteLine("correlation questionnaire - image distractor rememberabce");
Console.Out.WriteLine(Correlation.Pearson(QuestionnaireScores, image_distractor_percentages));
Console.Out.WriteLine("");
Console.Out.WriteLine("correlation questionnaire - overall distractor rememberabce");
Console.Out.WriteLine(Correlation.Pearson(QuestionnaireScores, avgdistractors));
Console.Out.WriteLine("");
Console.Out.WriteLine("correlation questionnaire - moves per second");
Console.Out.WriteLine(Correlation.Pearson(QuestionnaireScores, aps));
Console.Out.WriteLine("");
Console.Out.WriteLine("correlation questionnaire - number of summ spells");
Console.Out.WriteLine(Correlation.Pearson(QuestionnaireScores, summs));
Console.Out.WriteLine("");
Console.Out.WriteLine("");
Console.Out.WriteLine("correlation questionnaire - skill");
Console.Out.WriteLine(Correlation.Pearson(QuestionnaireScores, skill_lvl));
Console.Out.WriteLine("");
Console.Out.WriteLine("correlation questionnaire - death rememberabce");
Console.Out.WriteLine(Correlation.Pearson(QuestionnaireScores, death_remembered_percentages));
Console.Out.WriteLine("");
var scatter_values = new List <double>();
scatter_values.AddRange(video_sound_distractor_percentages);
scatter_values.AddRange(sound_distractor_percentages);
double[][] samples = { underskill_scores.ToArray(),
matched_scores.ToArray(),
overskill_scores.ToArray() };
OneWayAnova anova = new OneWayAnova(samples);
// DataGridBox.Show(anova.Table);
//Console.ReadKey();
double[][] style_samples = { focused_scores.ToArray(),
detached_scores.ToArray(),
average_scores.ToArray() };
OneWayAnova style_anova = new OneWayAnova(style_samples);
// DataGridBox.Show(style_anova.Table);
// Console.ReadKey();
double[][] skill_samples = { bronze_scores.ToArray(),
goldplus_scores.ToArray() };
OneWayAnova skill_anova = new OneWayAnova(skill_samples);
//DataGridBox.Show(skill_anova.Table);
//Console.ReadKey();
String meta_table_file = "D:\\Projects\\Conference Paper\\Tables\\meta_table.xml";
String distractors_video_table_file = "D:\\Projects\\Conference Paper\\Tables\\distractors_video_table.xml";
String distractors_game_table_file = "D:\\Projects\\Conference Paper\\Tables\\distractors_game_table.xml";
String deaths_table_file = "D:\\Projects\\Conference Paper\\Tables\\deaths_table.xml";
StreamWriter metaStreamWriter = new StreamWriter(meta_table_file);
StreamWriter distractorsVideoStreamWriter = new StreamWriter(distractors_video_table_file);
StreamWriter distractorsGameStreamWriter = new StreamWriter(distractors_game_table_file);
StreamWriter deathsStreamWriter = new StreamWriter(deaths_table_file);
meta_table.WriteXml(metaStreamWriter);
distractors_video_table.WriteXml(distractorsVideoStreamWriter);
distractors_game_table.WriteXml(distractorsGameStreamWriter);
deaths_table.WriteXml(deathsStreamWriter);
Console.ReadKey();
}
protected override void WriteData(ExcelWorksheet worksheet)
{
Class[] classes = _classStore.Classes.ToArray();
List <double> smellsCountList = new List <double>();
List <double> commentsCountList = new List <double>();
List <double> nonDocCommentsCountList = new List <double>();
List <double> docCommentsCountList = new List <double>();
List <double> badCommentsCountList = new List <double>();
List <double> badNonDocCommentsCountList = new List <double>();
List <double> badDocCommentsCountList = new List <double>();
int rowNumber = 2;
foreach (var @class in classes)
{
worksheet.Cells[rowNumber, 1].Value = @class.FileName;
worksheet.Cells[rowNumber, 2].Value = @class.Namespace;
worksheet.Cells[rowNumber, 3].Value = @class.Name;
worksheet.Cells[rowNumber, 4].Value = @class.SmellsCount;
worksheet.Cells[rowNumber, 5].Value = @class.Comments.Count();
worksheet.Cells[rowNumber, 6].Value = @class.Comments.Count(c => c.Type == CommentType.SingleLine);
worksheet.Cells[rowNumber, 7].Value = @class.Comments.Count(c => c.Type == CommentType.MultiLine);
worksheet.Cells[rowNumber, 8].Value = @class.Comments.Count(c => c.Type == CommentType.SingleLine || c.Type == CommentType.MultiLine);
worksheet.Cells[rowNumber, 9].Value = @class.Comments.Count(c => c.Type == CommentType.Doc);
worksheet.Cells[rowNumber, 10].Value = @class.Comments.Count(c => c.LocationRelativeToMethod == LocationRelativeToMethod.MethodDescription);
worksheet.Cells[rowNumber, 11].Value = @class.Comments.Count(c => c.LocationRelativeToMethod == LocationRelativeToMethod.MethodStart);
worksheet.Cells[rowNumber, 12].Value = @class.Comments.Count(c => c.LocationRelativeToMethod == LocationRelativeToMethod.MethodInner);
worksheet.Cells[rowNumber, 13].Value = @class.Comments.Count(c => c.LocationRelativeToMethod == LocationRelativeToMethod.MethodEnd);
worksheet.Cells[rowNumber, 14].Value = @class.AbstractionSmellsCount;
worksheet.Cells[rowNumber, 15].Value = @class.EncapsulationSmellsCount;
worksheet.Cells[rowNumber, 16].Value = @class.ModularizationSmellsCount;
worksheet.Cells[rowNumber, 17].Value = @class.HierarchySmellsCount;
smellsCountList.Add(@class.SmellsCount);
commentsCountList.Add(@class.Comments.Count());
nonDocCommentsCountList.Add(@class.Comments.Count(c => c.Type == CommentType.SingleLine || c.Type == CommentType.MultiLine));
docCommentsCountList.Add(@class.Comments.Count(c => c.Type == CommentType.Doc));
badCommentsCountList.Add(@class.Comments.Count(c => c.IsBad() == true));
badNonDocCommentsCountList.Add(@class.Comments.Count(c => c.IsBad() == true && (c.Type == CommentType.SingleLine || c.Type == CommentType.MultiLine)));
badDocCommentsCountList.Add(@class.Comments.Count(c => c.IsBad() == true && c.Type == CommentType.Doc));
rowNumber++;
}
worksheet.Cells["T4"].Value = Math.Round(PearsonCorrelation.Compute(smellsCountList, commentsCountList), 3);
worksheet.Cells["U4"].Value = Math.Round(PearsonCorrelation.Compute(smellsCountList, nonDocCommentsCountList), 3);
worksheet.Cells["V4"].Value = Math.Round(PearsonCorrelation.Compute(smellsCountList, docCommentsCountList), 3);
worksheet.Cells["T8"].Value = Math.Round(PearsonCorrelation.Compute(commentsCountList, classes.Select(c => (double)c.AbstractionSmellsCount).ToList()), 3);
worksheet.Cells["U8"].Value = Math.Round(PearsonCorrelation.Compute(commentsCountList, classes.Select(c => (double)c.EncapsulationSmellsCount).ToList()), 3);
worksheet.Cells["V8"].Value = Math.Round(PearsonCorrelation.Compute(commentsCountList, classes.Select(c => (double)c.ModularizationSmellsCount).ToList()), 3);
worksheet.Cells["W8"].Value = Math.Round(PearsonCorrelation.Compute(commentsCountList, classes.Select(c => (double)c.HierarchySmellsCount).ToList()), 3);
worksheet.Cells["T12"].Value = Math.Round(PearsonCorrelation.Compute(smellsCountList, badCommentsCountList), 3);
worksheet.Cells["U12"].Value = Math.Round(PearsonCorrelation.Compute(smellsCountList, badNonDocCommentsCountList), 3);
worksheet.Cells["V12"].Value = Math.Round(PearsonCorrelation.Compute(smellsCountList, badDocCommentsCountList), 3);
worksheet.Cells["T16"].Value = Math.Round(PearsonCorrelation.Compute(badCommentsCountList, classes.Select(c => (double)c.AbstractionSmellsCount).ToList()), 3);
worksheet.Cells["U16"].Value = Math.Round(PearsonCorrelation.Compute(badCommentsCountList, classes.Select(c => (double)c.EncapsulationSmellsCount).ToList()), 3);
worksheet.Cells["V16"].Value = Math.Round(PearsonCorrelation.Compute(badCommentsCountList, classes.Select(c => (double)c.ModularizationSmellsCount).ToList()), 3);
worksheet.Cells["W16"].Value = Math.Round(PearsonCorrelation.Compute(badCommentsCountList, classes.Select(c => (double)c.HierarchySmellsCount).ToList()), 3);
}