public void CreateSimpleStatsAndVerifyAlphabetIsReturned()
{
ISequence sequence = new Sequence(Alphabets.DNA, "A");
SequenceStatistics stats = new SequenceStatistics(sequence);
Assert.AreEqual(Alphabets.DNA, stats.Alphabet);
}
static void DumpStatsForOneSequence()
{
ISequence oneSequence = null;
var parser = SequenceParsers.FindParserByFileName(Filename);
if (parser != null)
{
oneSequence = parser.Parse().First();
parser.Close();
}
if (oneSequence == null)
{
Console.WriteLine("Could not load sequence.");
return;
}
SequenceStatistics stats =
new SequenceStatistics(oneSequence);
foreach (var symbol in oneSequence.Alphabet)
{
Console.WriteLine("{0} = Count={1}, Fraction={2}",
(char)symbol, stats.GetCount(symbol),
stats.GetFraction(symbol));
}
}
public void CreateSimpleStatsAndVerifyCount()
{
ISequence sequence = new Sequence(Alphabets.DNA, "ACGT--ACGT--ACGT--");
SequenceStatistics stats = new SequenceStatistics(sequence);
Assert.AreEqual(18, stats.TotalCount);
}
public void CreateSimpleStatsAndVerifyAlphabetIsReturned()
{
ISequence sequence = new Sequence(Alphabets.DNA, "A");
SequenceStatistics stats = new SequenceStatistics(sequence);
Assert.AreEqual(Alphabets.DNA, stats.Alphabet);
}
/// <summary>
/// Iterate through each sequence and calculate the symbol content.
/// </summary>
public override void ContentBySequence()
{
if (this.Sequences == null)
{
throw new ArgumentNullException("Sequences");
}
//int i = 0;
//foreach (var seqObj in this.sequences)
Parallel.ForEach(this.Sequences, (seqObj, state, i) =>
{
if (Worker != null && WorkerArgs != null && Worker.CancellationPending)
{
WorkerArgs.Cancel = true;
state.Stop();
}
// Instead of storing all SequenceStatistics objects, just calculate the required GC content values here.
SequenceStatistics seqStats = new SequenceStatistics(seqObj);
double gcPercent = GCContentBySequence(seqStats, seqObj.Count);
GCContentBySequenceArray[(int)i] = gcPercent;
//i++;
}
);
HasRunContentBySequence = true;
}
public void ValidateDnaSparseSequenceConstAlpIndexByteList()
{
byte[] byteArrayObj = encodingObj.GetBytes("AGCT");
IEnumerable <byte> seqItems =
new List <Byte>()
{
byteArrayObj[0], byteArrayObj[1], byteArrayObj[2], byteArrayObj[3]
};
SparseSequence sparseSeq = new SparseSequence(Alphabets.DNA, 4, seqItems);
Assert.IsNotNull(sparseSeq);
Assert.IsNotNull(sparseSeq.Statistics);
Assert.AreEqual(8, sparseSeq.Count);
SequenceStatistics seqStatObj = sparseSeq.Statistics;
Assert.AreEqual(1, seqStatObj.GetCount('A'));
Assert.AreEqual(1, seqStatObj.GetCount('G'));
Assert.AreEqual(1, seqStatObj.GetCount('C'));
Assert.AreEqual(1, seqStatObj.GetCount('T'));
Console.WriteLine("SparseSequence BVT: Validation of SparseSequence(alp, index, seq items) constructor is completed");
ApplicationLog.WriteLine("SparseSequence BVT: Validation of SparseSequence(alp, index, seq items) constructor is completed");
}
public void CreateSimpleStatsAndVerifyCount()
{
ISequence sequence = new Sequence(Alphabets.DNA, "ACGT--ACGT--ACGT--");
SequenceStatistics stats = new SequenceStatistics(sequence);
Assert.AreEqual(18, stats.TotalCount);
}
public void ValidateSequenceStatisticsToString()
{
ISequence seq = new Sequence(Alphabets.DNA, "ATCGATCG");
var seqStats = new SequenceStatistics(seq);
string actualString = seqStats.ToString();
string expectedString = "A - 2\r\nC - 2\r\nG - 2\r\nT - 2\r\n".Replace("\r\n", System.Environment.NewLine);
Assert.AreEqual(actualString, expectedString);
// Gets the expected sequence from the Xml
List <ISequence> seqsList;
IEnumerable <ISequence> sequences = null;
string filePath = this.utilityObj.xmlUtil.GetTextValue(Constants.SimpleFastaNodeName,
Constants.FilePathNode);
using (var reader = File.OpenRead(filePath))
{
var parser = new FastAParser();
{
parser.Alphabet = Alphabets.Protein;
sequences = parser.Parse(reader);
//Create a list of sequences.
seqsList = sequences.ToList();
}
}
foreach (ISequence Sequence in seqsList)
{
seqStats = new SequenceStatistics(Sequence);
string seqStatStr = seqStats.ToString();
Assert.IsTrue(seqStatStr.Contains(" - "));
}
}
/// <summary>
/// Calculate GC content for a read
/// </summary>
/// <param name="seqStats">SequenceStatistics object</param>
/// <param name="length">The length of the read</param>
/// <returns>GC percentage of a read</returns>
public double GCContentBySequence(SequenceStatistics seqStats, long length)
{
if (seqStats == null)
{
throw new ArgumentNullException("seqStats");
}
return(100 * (double)(seqStats.GetCount('G') + seqStats.GetCount('C') + seqStats.GetCount('S')) / length);
}
/// <summary>
/// The execution method for the activity.
/// </summary>
/// <param name="executionContext">The execution context.</param>
/// <returns>The execution status.</returns>
protected override ActivityExecutionStatus Execute(ActivityExecutionContext executionContext)
{
SequenceData = new string(Sequence.ToArray().Select(a => (char)a).ToArray());
ID = Sequence.ID;
DisplayID = Sequence.ID;
Statistics = new SequenceStatistics(Sequence);
return(ActivityExecutionStatus.Closed);
}
/// <summary>
/// Main method
/// </summary>
public static void Main()
{
var array = new double[] { 3, 5, 2.12, 4, 23.1, 12, 3.32, 32, 14 };
SequenceStatistics stat = new SequenceStatistics(array);
stat.PrintAverageValue();
stat.PrintMaxElement();
stat.PrintMinElement();
}
protected override ActivityExecutionStatus Execute(ActivityExecutionContext executionContext)
{
SequenceData = Sequence.ToString();
ID = Sequence.ID;
DisplayID = Sequence.DisplayID;
Statistics = Sequence.Statistics;
return(ActivityExecutionStatus.Closed);
}
public void TestSequenceStatisticsToString()
{
ISequence seq = new Sequence(Alphabets.DNA, "ATCGATCG");
SequenceStatistics seqStats = new SequenceStatistics(seq);
string actualString = seqStats.ToString();
string expectedString = "A - 2\r\nC - 2\r\nG - 2\r\nT - 2\r\n".Replace("\r\n", Environment.NewLine);
Assert.AreEqual(actualString, expectedString);
}
public ListSequence(IEnumerable <T> enumerable, T endSentinel)
{
Assert.ArgumentNotNull(enumerable, nameof(enumerable));
_list = enumerable is IReadOnlyList <T> list ? list : enumerable.ToList();
_endSentinelValue = endSentinel;
_index = 0;
_stats = default;
}
public void CreateStatsAndCheckToString()
{
ISequence sequence = new Sequence(Alphabets.DNA, "ACGT--ACGT--ACGT--");
SequenceStatistics stats = new SequenceStatistics(sequence);
string expectedValue = "- - 6\r\nA - 3\r\nC - 3\r\nG - 3\r\nT - 3\r\n".Replace("\r\n", Environment.NewLine);
string actualValue = stats.ToString();
Assert.AreEqual(expectedValue, actualValue);
}
public ListSequence(IReadOnlyList <T> list, T endSentinel)
{
Assert.ArgumentNotNull(list, nameof(list));
_list = list;
_endSentinelValue = endSentinel;
_index = 0;
_stats = default;
}
private IEnumerable <TItem> BaseStatistics <TItem>(string fileName, string content,
Func <SequenceStatistics, TItem> selector)
{
var sequences = _sequenceProvider.Provide(fileName, content);
return(sequences.ToList().Select(x =>
{
var stats = new SequenceStatistics(x);
return selector(stats);
}));
}
/// <summary>
/// When implemented in a derived class, performs the execution of the activity.
/// </summary>
/// <param name="context">The execution context under which the activity executes.</param>
protected override string Execute(CodeActivityContext context)
{
var sequence = Sequence.Get(context);
StringBuilder buff = new StringBuilder();
buff.AppendLine(sequence.ID);
buff.Append("Statistics: ");
buff.Append(sequence.Count);
buff.Append(" Total");
var statistics = new SequenceStatistics(sequence);
foreach (var symbol in sequence.Alphabet)
{
buff.AppendFormat(" - {0}:", (char)symbol);
buff.Append(statistics.GetCount(symbol));
}
buff.AppendLine();
buff.AppendLine();
for (int i = 0; i < sequence.Count; i++)
{
if ((i % 50) == 0)
{
string num = (i + 1).ToString(CultureInfo.InvariantCulture);
int pad = 5 - num.Length;
StringBuilder buff2 = new StringBuilder();
for (int j = 0; j < pad; j++)
{
buff2.Append(' ');
}
buff2.Append(num);
buff.Append(buff2);
}
if ((i % 10) == 0)
{
buff.Append(' ');
}
buff.Append((char)sequence[i]);
if ((i % 50) == 49)
{
buff.AppendLine();
}
}
buff.AppendLine();
return(buff.ToString());
}
public void ValidateDnaSparseSequenceConstAlpIndexByte()
{
byte[] byteArrayObj = Encoding.ASCII.GetBytes("AGCT");
var sparseSeq = new SparseSequence(Alphabets.DNA, 1, byteArrayObj[0]);
Assert.IsNotNull(sparseSeq);
Assert.IsNotNull(sparseSeq.Statistics);
SequenceStatistics seqStatObj = sparseSeq.Statistics;
Assert.AreEqual(1, seqStatObj.GetCount('A'));
ApplicationLog.WriteLine("SparseSequence BVT: Validation of SparseSequence(alp, index, byte) constructor is completed");
}
public void CreateStatsWithMixedcaseLetterSequence()
{
ISequence sequence = new Sequence(Alphabets.DNA, "aAaAaAaA");
SequenceStatistics stats = new SequenceStatistics(sequence);
Assert.AreEqual(8, stats.GetCount('A'));
Assert.AreEqual(8, stats.GetCount(65));
Assert.AreEqual(8, stats.GetCount('a'));
Assert.AreEqual(1.0, stats.GetFraction('A'));
Assert.AreEqual(1.0, stats.GetFraction(65));
Assert.AreEqual(1.0, stats.GetFraction('a'));
}
static void Main(string[] args)
{
var parser = SequenceParsers.FindParserByFileName(Filename);
if (parser == null)
{
Console.WriteLine("No parser found.");
return;
}
List <ISequence> allSequences = parser
.Parse()
.ToList();
IAlphabet alphabet = allSequences[0].Alphabet;
long totalColums = allSequences.Min(s => s.Count);
//byte[] data = new byte[allSequences.Count];
for (int column = 0; column < totalColums; column++)
{
// for (int row = 0; row < allSequences.Count; row++)
// data[row] = allSequences[row][column];
//ISequence newSequence = new Sequence(alphabet, data);
ISequence newSequence = new Sequence(AmbiguousRnaAlphabet.Instance,
allSequences
.Select(s => s[column]).ToArray());
SequenceStatistics stats =
new SequenceStatistics(newSequence);
var TopCount =
alphabet
.Where(symbol => !alphabet.CheckIsGap(symbol))
.Select(symbol =>
new
{
Symbol = (char)symbol,
Count = stats.GetCount(symbol),
Frequency = stats.GetFraction(symbol)
})
.Where(tc => tc.Count > 0)
.OrderByDescending(c => c.Count)
.FirstOrDefault();
if (TopCount != null)
{
Console.WriteLine("{0}: {1} = {2} of {3}",
column, TopCount.Symbol, TopCount.Count, totalColums);
}
}
}
public void ValidateProteinSparseSequenceConstAlpIndexByte()
{
byte[] byteArrayObj = encodingObj.GetBytes("KIEG");
SparseSequence sparseSeq = new SparseSequence(Alphabets.Protein, 1, byteArrayObj[0]);
Assert.IsNotNull(sparseSeq);
Assert.IsNotNull(sparseSeq.Statistics);
SequenceStatistics seqStatObj = sparseSeq.Statistics;
Assert.AreEqual(1, seqStatObj.GetCount('K'));
Console.WriteLine("SparseSequence P1: Validation of SparseSequence(alp, index, byte) constructor is completed");
ApplicationLog.WriteLine("SparseSequence P1: Validation of SparseSequence(alp, index, byte) constructor is completed");
}
public void CreateSimpleStatsWithSingleLetterSequence()
{
ISequence sequence = new Sequence(Alphabets.DNA, "A");
SequenceStatistics stats = new SequenceStatistics(sequence);
Assert.AreEqual(1, stats.GetCount('A'));
Assert.AreEqual(1, stats.GetCount(65));
Assert.AreEqual(0, stats.GetCount('C'));
Assert.AreEqual(0, stats.GetCount('G'));
Assert.AreEqual(0, stats.GetCount('T'));
Assert.AreEqual(1.0, stats.GetFraction('A'));
Assert.AreEqual(1.0, stats.GetFraction(65));
}
public void CreateSimpleStatsWithSingleLetterSequence()
{
ISequence sequence = new Sequence(Alphabets.DNA, "A");
SequenceStatistics stats = new SequenceStatistics(sequence);
Assert.AreEqual(1, stats.GetCount('A'));
Assert.AreEqual(1, stats.GetCount(65));
Assert.AreEqual(0, stats.GetCount('C'));
Assert.AreEqual(0, stats.GetCount('G'));
Assert.AreEqual(0, stats.GetCount('T'));
Assert.AreEqual(1.0, stats.GetFraction('A'));
Assert.AreEqual(1.0, stats.GetFraction(65));
}
public void CreateStatsAndConsumeEnumerable()
{
ISequence sequence = new Sequence(Alphabets.DNA, "ACGT--ACGT--ACGT--");
SequenceStatistics stats = new SequenceStatistics(sequence);
int loopCounts = 0;
foreach (var value in stats.SymbolCounts)
{
Assert.AreEqual(value.Item2, stats.GetCount(value.Item1));
loopCounts++;
}
Assert.AreEqual(5, loopCounts);
}
public void CreateStatsWithSeveralMixedcaseLetterSequence()
{
ISequence sequence = new Sequence(Alphabets.DNA, "a-c-g-t-A-C-G-T-");
SequenceStatistics stats = new SequenceStatistics(sequence);
Assert.AreEqual(2, stats.GetCount('A'));
Assert.AreEqual(2, stats.GetCount('a'));
Assert.AreEqual(2, stats.GetCount('C'));
Assert.AreEqual(2, stats.GetCount('c'));
Assert.AreEqual(2, stats.GetCount('G'));
Assert.AreEqual(2, stats.GetCount('g'));
Assert.AreEqual(2, stats.GetCount('T'));
Assert.AreEqual(2, stats.GetCount('t'));
Assert.AreEqual(8, stats.GetCount('-'));
Assert.AreEqual(2.0 / 16.0, stats.GetFraction('A'));
Assert.AreEqual(2.0 / 16.0, stats.GetFraction('C'));
Assert.AreEqual(2.0 / 16.0, stats.GetFraction('G'));
Assert.AreEqual(2.0 / 16.0, stats.GetFraction('T'));
Assert.AreEqual(.5, stats.GetFraction('-'));
Assert.AreEqual(.5, stats.GetFraction(45));
}
public void ValidateProteinSparseSequenceConstAlpIndexByteList()
{
byte[] byteArrayObj = Encoding.ASCII.GetBytes("KIEG");
IEnumerable <byte> seqItems =
new List <Byte> {
byteArrayObj[0], byteArrayObj[1], byteArrayObj[2], byteArrayObj[3]
};
var sparseSeq = new SparseSequence(Alphabets.Protein, 4, seqItems);
Assert.IsNotNull(sparseSeq);
Assert.IsNotNull(sparseSeq.Statistics);
Assert.AreEqual(8, sparseSeq.Count);
SequenceStatistics seqStatObj = sparseSeq.Statistics;
Assert.AreEqual(1, seqStatObj.GetCount('K'));
Assert.AreEqual(1, seqStatObj.GetCount('I'));
Assert.AreEqual(1, seqStatObj.GetCount('E'));
Assert.AreEqual(1, seqStatObj.GetCount('G'));
ApplicationLog.WriteLine("SparseSequence P1: Validation of SparseSequence(alp, index, seq items) constructor is completed");
}
public void testSobol()
{
//("Testing Sobol sequences up to dimension "
// + PPMT_MAX_DIM + "...");
List<double> point;
double tolerance = 1.0e-15;
// testing max dimensionality
int dimensionality =(int)SobolRsg.PPMT_MAX_DIM;
ulong seed = 123456;
SobolRsg rsg=new SobolRsg(dimensionality, seed);
int points = 100, i;
for (i=0; i<points; i++)
{
point = rsg.nextSequence().value;
if (point.Count!=dimensionality) {
Assert.Fail("Sobol sequence generator returns "+
" a sequence of wrong dimensionality: " + point.Count
+ " instead of " + dimensionality);
}
}
// testing homogeneity properties
dimensionality = 33;
seed = 123456;
rsg = new SobolRsg(dimensionality, seed);
SequenceStatistics stat=new SequenceStatistics(dimensionality);
List<double> mean;
int k = 0;
for (int j=1; j<5; j++) { // five cycle
points = (int)(Utils.Pow(2.0, j)-1); // base 2
for (; k<points; k++) {
point = rsg.nextSequence().value;
stat.add(point);
}
mean = stat.mean();
for (i=0; i<dimensionality; i++) {
double error = Math.Abs(mean[i]-0.5);
if (error > tolerance) {
Assert.Fail(i+1 + " dimension: "
// + QL_FIXED
+ "mean (" + mean[i]
+ ") at the end of the " + j+1
+ " cycle in Sobol sequence is not " + 0.5
//+ QL_SCIENTIFIC
+ " (error = " + error + ")");
}
}
}
// testing first dimension (van der Corput sequence)
double[] vanderCorputSequenceModuloTwo= {
// first cycle (zero excluded)
0.50000,
// second cycle
0.75000, 0.25000,
// third cycle
0.37500, 0.87500, 0.62500, 0.12500,
// fourth cycle
0.18750, 0.68750, 0.93750, 0.43750, 0.31250, 0.81250, 0.56250, 0.06250,
// fifth cycle
0.09375, 0.59375, 0.84375, 0.34375, 0.46875, 0.96875, 0.71875, 0.21875,
0.15625, 0.65625, 0.90625, 0.40625, 0.28125, 0.78125, 0.53125, 0.03125
};
dimensionality = 1;
rsg = new SobolRsg(dimensionality);
points = (int)(Utils.Pow(2.0, 5))-1; // five cycles
for (i=0; i<points; i++) {
point = rsg.nextSequence().value;
double error =Math.Abs(point[0]-vanderCorputSequenceModuloTwo[i]);
if (error > tolerance) {
Assert.Fail(i+1 + " draw ("
//+ QL_FIXED
+ point[0]
+ ") in 1-D Sobol sequence is not in the "
+ "van der Corput sequence modulo two: "
+ "it should have been "
+ vanderCorputSequenceModuloTwo[i]
//+ QL_SCIENTIFIC
+ " (error = " + error + ")");
}
}
}
public void testHalton()
{
//("Testing Halton sequences...");
List<double> point;
double tolerance = 1.0e-15;
// testing "high" dimensionality
int dimensionality = (int)SobolRsg.PPMT_MAX_DIM;
HaltonRsg rsg = new HaltonRsg(dimensionality, 0, false, false);
int points = 100, i, k;
for (i = 0; i < points; i++)
{
point = rsg.nextSequence().value;
if (point.Count != dimensionality)
{
Assert.Fail("Halton sequence generator returns "+
" a sequence of wrong dimensionality: " + point.Count
+ " instead of " + dimensionality)
;
}
}
// testing first and second dimension (van der Corput sequence)
double[] vanderCorputSequenceModuloTwo = {
// first cycle (zero excluded)
0.50000,
// second cycle
0.25000, 0.75000,
// third cycle
0.12500, 0.62500, 0.37500, 0.87500,
// fourth cycle
0.06250, 0.56250, 0.31250, 0.81250, 0.18750, 0.68750, 0.43750,
0.93750,
// fifth cycle
0.03125, 0.53125, 0.28125, 0.78125, 0.15625, 0.65625, 0.40625,
0.90625,
0.09375, 0.59375, 0.34375, 0.84375, 0.21875, 0.71875, 0.46875,
0.96875,
};
dimensionality = 1;
rsg = new HaltonRsg(dimensionality, 0, false, false);
points = (int) (Math.Pow(2.0, 5)) - 1; // five cycles
for (i = 0; i < points; i++)
{
point = rsg.nextSequence().value;
double error = Math.Abs(point[0] - vanderCorputSequenceModuloTwo[i]);
if (error > tolerance)
{
Assert.Fail(i + 1 + " draw ("
+ /*QL_FIXED*/ + point[0]
+ ") in 1-D Halton sequence is not in the "
+ "van der Corput sequence modulo two: "
+ "it should have been "
+ vanderCorputSequenceModuloTwo[i]
//+ QL_SCIENTIFIC
+ " (error = " + error + ")");
}
}
double[] vanderCorputSequenceModuloThree = {
// first cycle (zero excluded)
1.0/3, 2.0/3,
// second cycle
1.0/9, 4.0/9, 7.0/9, 2.0/9, 5.0/9, 8.0/9,
// third cycle
1.0/27, 10.0/27, 19.0/27, 4.0/27, 13.0/27, 22.0/27,
7.0/27, 16.0/27, 25.0/27, 2.0/27, 11.0/27, 20.0/27,
5.0/27, 14.0/27, 23.0/27, 8.0/27, 17.0/27, 26.0/27
};
dimensionality = 2;
rsg = new HaltonRsg(dimensionality, 0, false, false);
points = (int) (Math.Pow(3.0, 3)) - 1; // three cycles of the higher dimension
for (i = 0; i < points; i++)
{
point = rsg.nextSequence().value;
double error = Math.Abs(point[0] - vanderCorputSequenceModuloTwo[i]);
if (error > tolerance)
{
Assert.Fail("First component of " + i + 1
+ " draw (" + /*QL_FIXED*/ + point[0]
+ ") in 2-D Halton sequence is not in the "
+ "van der Corput sequence modulo two: "
+ "it should have been "
+ vanderCorputSequenceModuloTwo[i]
//+ QL_SCIENTIFIC
+ " (error = " + error + ")");
}
error = Math.Abs(point[1] - vanderCorputSequenceModuloThree[i]);
if (error > tolerance)
{
Assert.Fail("Second component of " + i + 1
+ " draw (" + /*QL_FIXED*/ + point[1]
+ ") in 2-D Halton sequence is not in the "
+ "van der Corput sequence modulo three: "
+ "it should have been "
+ vanderCorputSequenceModuloThree[i]
//+ QL_SCIENTIFIC
+ " (error = " + error + ")");
}
}
// testing homogeneity properties
dimensionality = 33;
rsg = new HaltonRsg(dimensionality, 0, false, false);
SequenceStatistics stat = new SequenceStatistics(dimensionality);
List<double> mean; //, stdev, variance, skewness, kurtosis;
k = 0;
int j;
for (j = 1; j < 5; j++)
{
// five cycle
points = (int) (Math.Pow(2.0, j)) - 1; // base 2
for (; k < points; k++)
{
point = rsg.nextSequence().value;
stat.add(point);
}
mean = stat.mean();
double error = Math.Abs(mean[0] - 0.5);
if (error > tolerance)
{
Assert.Fail("First dimension mean (" + /*QL_FIXED*/ + mean[0]
+ ") at the end of the " + j + 1
+ " cycle in Halton sequence is not " + 0.5
//+ QL_SCIENTIFIC
+ " (error = " + error + ")");
}
}
// reset generator and gaussianstatistics
rsg = new HaltonRsg(dimensionality, 0, false, false);
stat.reset(dimensionality);
k = 0;
for (j = 1; j < 3; j++)
{
// three cycle
points = (int) (Math.Pow(3.0, j)) - 1; // base 3
for (; k < points; k++)
{
point = rsg.nextSequence().value;
stat.add(point);
}
mean = stat.mean();
double error = Math.Abs(mean[1] - 0.5);
if (error > tolerance)
{
Assert.Fail("Second dimension mean (" + /*QL_FIXED*/ + mean[1]
+ ") at the end of the " + j + 1
+ " cycle in Halton sequence is not " + 0.5
//+ QL_SCIENTIFIC
+ " (error = " + error + ")");
}
}
}
/// <summary>
/// The execution method for the activity.
/// </summary>
/// <param name="executionContext">The execution context.</param>
/// <returns>The execution status.</returns>
protected override ActivityExecutionStatus Execute(ActivityExecutionContext executionContext)
{
StringBuilder buff = new StringBuilder();
buff.AppendLine(Sequence.ID);
buff.Append("Statistics: ");
buff.Append(Sequence.Count);
buff.Append(" Total");
var statistics = new SequenceStatistics(Sequence);
if (Sequence.Alphabet == Alphabets.DNA)
{
buff.Append(" - G: ");
buff.Append(statistics.GetCount(Alphabets.DNA.G));
buff.Append(" - A: ");
buff.Append(statistics.GetCount(Alphabets.DNA.A));
buff.Append(" - T: ");
buff.Append(statistics.GetCount(Alphabets.DNA.T));
buff.Append(" - C: ");
buff.Append(statistics.GetCount(Alphabets.DNA.C));
}
else if (Sequence.Alphabet == Alphabets.RNA)
{
buff.Append(" - G: ");
buff.Append(statistics.GetCount(Alphabets.RNA.G));
buff.Append(" - A: ");
buff.Append(statistics.GetCount(Alphabets.RNA.A));
buff.Append(" - U: ");
buff.Append(statistics.GetCount(Alphabets.RNA.U));
buff.Append(" - C: ");
buff.Append(statistics.GetCount(Alphabets.RNA.C));
}
buff.AppendLine();
buff.AppendLine();
for (int i = 0; i < Sequence.Count; i++)
{
if ((i % 50) == 0)
{
string num = (i + 1).ToString();
int pad = 5 - num.Length;
StringBuilder buff2 = new StringBuilder();
for (int j = 0; j < pad; j++)
{
buff2.Append(' ');
}
buff2.Append(num);
buff.Append(buff2.ToString());
}
if ((i % 10) == 0)
{
buff.Append(' ');
}
buff.Append((char)Sequence[i]);
if ((i % 50) == 49)
{
buff.AppendLine();
}
}
buff.AppendLine();
Data = buff.ToString();
return(ActivityExecutionStatus.Closed);
}
public void CreateStatsWithSeveralMixedcaseLetterSequence()
{
ISequence sequence = new Sequence(Alphabets.DNA, "a-c-g-t-A-C-G-T-");
SequenceStatistics stats = new SequenceStatistics(sequence);
Assert.AreEqual(2, stats.GetCount('A'));
Assert.AreEqual(2, stats.GetCount('a'));
Assert.AreEqual(2, stats.GetCount('C'));
Assert.AreEqual(2, stats.GetCount('c'));
Assert.AreEqual(2, stats.GetCount('G'));
Assert.AreEqual(2, stats.GetCount('g'));
Assert.AreEqual(2, stats.GetCount('T'));
Assert.AreEqual(2, stats.GetCount('t'));
Assert.AreEqual(8, stats.GetCount('-'));
Assert.AreEqual(2.0 / 16.0, stats.GetFraction('A'));
Assert.AreEqual(2.0 / 16.0, stats.GetFraction('C'));
Assert.AreEqual(2.0 / 16.0, stats.GetFraction('G'));
Assert.AreEqual(2.0 / 16.0, stats.GetFraction('T'));
Assert.AreEqual(.5, stats.GetFraction('-'));
Assert.AreEqual(.5, stats.GetFraction(45));
}
public void CreateStatsAndConsumeEnumerable()
{
ISequence sequence = new Sequence(Alphabets.DNA, "ACGT--ACGT--ACGT--");
SequenceStatistics stats = new SequenceStatistics(sequence);
int loopCounts = 0;
foreach (var value in stats.SymbolCounts)
{
Assert.AreEqual(value.Item2, stats.GetCount(value.Item1));
loopCounts++;
}
Assert.AreEqual(5,loopCounts);
}
public void CreateStatsWithNullSequence()
{
var stats = new SequenceStatistics(null);
Assert.IsNotNull(stats);
}
public void CreateStatsWithMixedcaseLetterSequence()
{
ISequence sequence = new Sequence(Alphabets.DNA, "aAaAaAaA");
SequenceStatistics stats = new SequenceStatistics(sequence);
Assert.AreEqual(8, stats.GetCount('A'));
Assert.AreEqual(8, stats.GetCount(65));
Assert.AreEqual(8, stats.GetCount('a'));
Assert.AreEqual(1.0, stats.GetFraction('A'));
Assert.AreEqual(1.0, stats.GetFraction(65));
Assert.AreEqual(1.0, stats.GetFraction('a'));
}
internal static global::System.Runtime.InteropServices.HandleRef getCPtr(SequenceStatistics obj)
{
return((obj == null) ? new global::System.Runtime.InteropServices.HandleRef(null, global::System.IntPtr.Zero) : obj.swigCPtr);
}
public void ValidateSequenceStatisticsToString()
{
ISequence seq = new Sequence(Alphabets.DNA, "ATCGATCG");
var seqStats = new SequenceStatistics(seq);
string actualString = seqStats.ToString();
string expectedString = "A - 2\r\nC - 2\r\nG - 2\r\nT - 2\r\n".Replace("\r\n", System.Environment.NewLine);
Assert.AreEqual(actualString, expectedString);
// Gets the expected sequence from the Xml
List<ISequence> seqsList;
IEnumerable<ISequence> sequences = null;
string filePath = this.utilityObj.xmlUtil.GetTextValue(Constants.SimpleFastaNodeName,
Constants.FilePathNode);
using (var reader = File.OpenRead(filePath))
{
var parser = new FastAParser();
{
parser.Alphabet = Alphabets.Protein;
sequences = parser.Parse(reader);
//Create a list of sequences.
seqsList = sequences.ToList();
}
}
foreach (ISequence Sequence in seqsList)
{
seqStats = new SequenceStatistics(Sequence);
string seqStatStr = seqStats.ToString();
Assert.IsTrue(seqStatStr.Contains(" - "));
}
}
public void testSobol()
{
//("Testing Sobol sequences up to dimension "
// + PPMT_MAX_DIM + "...");
List <double> point;
double tolerance = 1.0e-15;
// testing max dimensionality
int dimensionality = (int)SobolRsg.PPMT_MAX_DIM;
ulong seed = 123456;
SobolRsg rsg = new SobolRsg(dimensionality, seed);
int points = 100, i;
for (i = 0; i < points; i++)
{
point = rsg.nextSequence().value;
if (point.Count != dimensionality)
{
Assert.Fail("Sobol sequence generator returns " +
" a sequence of wrong dimensionality: " + point.Count
+ " instead of " + dimensionality);
}
}
// testing homogeneity properties
dimensionality = 33;
seed = 123456;
rsg = new SobolRsg(dimensionality, seed);
SequenceStatistics stat = new SequenceStatistics(dimensionality);
List <double> mean;
int k = 0;
for (int j = 1; j < 5; j++) // five cycle
{
points = (int)(Utils.Pow(2.0, j) - 1); // base 2
for (; k < points; k++)
{
point = rsg.nextSequence().value;
stat.add(point);
}
mean = stat.mean();
for (i = 0; i < dimensionality; i++)
{
double error = Math.Abs(mean[i] - 0.5);
if (error > tolerance)
{
Assert.Fail(i + 1 + " dimension: "
// + QL_FIXED
+ "mean (" + mean[i]
+ ") at the end of the " + j + 1
+ " cycle in Sobol sequence is not " + 0.5
//+ QL_SCIENTIFIC
+ " (error = " + error + ")");
}
}
}
// testing first dimension (van der Corput sequence)
double[] vanderCorputSequenceModuloTwo =
{
// first cycle (zero excluded)
0.50000,
// second cycle
0.75000, 0.25000,
// third cycle
0.37500, 0.87500, 0.62500, 0.12500,
// fourth cycle
0.18750, 0.68750, 0.93750, 0.43750, 0.31250, 0.81250, 0.56250, 0.06250,
// fifth cycle
0.09375, 0.59375, 0.84375, 0.34375, 0.46875, 0.96875, 0.71875, 0.21875,
0.15625, 0.65625, 0.90625, 0.40625, 0.28125, 0.78125, 0.53125, 0.03125
};
dimensionality = 1;
rsg = new SobolRsg(dimensionality);
points = (int)(Utils.Pow(2.0, 5)) - 1; // five cycles
for (i = 0; i < points; i++)
{
point = rsg.nextSequence().value;
double error = Math.Abs(point[0] - vanderCorputSequenceModuloTwo[i]);
if (error > tolerance)
{
Assert.Fail(i + 1 + " draw ("
//+ QL_FIXED
+ point[0]
+ ") in 1-D Sobol sequence is not in the "
+ "van der Corput sequence modulo two: "
+ "it should have been "
+ vanderCorputSequenceModuloTwo[i]
//+ QL_SCIENTIFIC
+ " (error = " + error + ")");
}
}
}
public void testHalton()
{
//("Testing Halton sequences...");
List <double> point;
double tolerance = 1.0e-15;
// testing "high" dimensionality
int dimensionality = (int)SobolRsg.PPMT_MAX_DIM;
HaltonRsg rsg = new HaltonRsg(dimensionality, 0, false, false);
int points = 100, i, k;
for (i = 0; i < points; i++)
{
point = rsg.nextSequence().value;
if (point.Count != dimensionality)
{
Assert.Fail("Halton sequence generator returns " +
" a sequence of wrong dimensionality: " + point.Count
+ " instead of " + dimensionality)
;
}
}
// testing first and second dimension (van der Corput sequence)
double[] vanderCorputSequenceModuloTwo =
{
// first cycle (zero excluded)
0.50000,
// second cycle
0.25000, 0.75000,
// third cycle
0.12500, 0.62500, 0.37500, 0.87500,
// fourth cycle
0.06250, 0.56250, 0.31250, 0.81250, 0.18750, 0.68750, 0.43750,
0.93750,
// fifth cycle
0.03125, 0.53125, 0.28125, 0.78125, 0.15625, 0.65625, 0.40625,
0.90625,
0.09375, 0.59375, 0.34375, 0.84375, 0.21875, 0.71875, 0.46875,
0.96875,
};
dimensionality = 1;
rsg = new HaltonRsg(dimensionality, 0, false, false);
points = (int)(Math.Pow(2.0, 5)) - 1; // five cycles
for (i = 0; i < points; i++)
{
point = rsg.nextSequence().value;
double error = Math.Abs(point[0] - vanderCorputSequenceModuloTwo[i]);
if (error > tolerance)
{
Assert.Fail(i + 1 + " draw ("
+ /*QL_FIXED*/ +point[0]
+ ") in 1-D Halton sequence is not in the "
+ "van der Corput sequence modulo two: "
+ "it should have been "
+ vanderCorputSequenceModuloTwo[i]
//+ QL_SCIENTIFIC
+ " (error = " + error + ")");
}
}
double[] vanderCorputSequenceModuloThree =
{
// first cycle (zero excluded)
1.0 / 3, 2.0 / 3,
// second cycle
1.0 / 9, 4.0 / 9, 7.0 / 9, 2.0 / 9, 5.0 / 9, 8.0 / 9,
// third cycle
1.0 / 27, 10.0 / 27, 19.0 / 27, 4.0 / 27, 13.0 / 27, 22.0 / 27,
7.0 / 27, 16.0 / 27, 25.0 / 27, 2.0 / 27, 11.0 / 27, 20.0 / 27,
5.0 / 27, 14.0 / 27, 23.0 / 27, 8.0 / 27, 17.0 / 27, 26.0 / 27
};
dimensionality = 2;
rsg = new HaltonRsg(dimensionality, 0, false, false);
points = (int)(Math.Pow(3.0, 3)) - 1; // three cycles of the higher dimension
for (i = 0; i < points; i++)
{
point = rsg.nextSequence().value;
double error = Math.Abs(point[0] - vanderCorputSequenceModuloTwo[i]);
if (error > tolerance)
{
Assert.Fail("First component of " + i + 1
+ " draw (" + /*QL_FIXED*/ +point[0]
+ ") in 2-D Halton sequence is not in the "
+ "van der Corput sequence modulo two: "
+ "it should have been "
+ vanderCorputSequenceModuloTwo[i]
//+ QL_SCIENTIFIC
+ " (error = " + error + ")");
}
error = Math.Abs(point[1] - vanderCorputSequenceModuloThree[i]);
if (error > tolerance)
{
Assert.Fail("Second component of " + i + 1
+ " draw (" + /*QL_FIXED*/ +point[1]
+ ") in 2-D Halton sequence is not in the "
+ "van der Corput sequence modulo three: "
+ "it should have been "
+ vanderCorputSequenceModuloThree[i]
//+ QL_SCIENTIFIC
+ " (error = " + error + ")");
}
}
// testing homogeneity properties
dimensionality = 33;
rsg = new HaltonRsg(dimensionality, 0, false, false);
SequenceStatistics stat = new SequenceStatistics(dimensionality);
List <double> mean; //, stdev, variance, skewness, kurtosis;
k = 0;
int j;
for (j = 1; j < 5; j++)
{
// five cycle
points = (int)(Math.Pow(2.0, j)) - 1; // base 2
for (; k < points; k++)
{
point = rsg.nextSequence().value;
stat.add(point);
}
mean = stat.mean();
double error = Math.Abs(mean[0] - 0.5);
if (error > tolerance)
{
Assert.Fail("First dimension mean (" + /*QL_FIXED*/ +mean[0]
+ ") at the end of the " + j + 1
+ " cycle in Halton sequence is not " + 0.5
//+ QL_SCIENTIFIC
+ " (error = " + error + ")");
}
}
// reset generator and gaussianstatistics
rsg = new HaltonRsg(dimensionality, 0, false, false);
stat.reset(dimensionality);
k = 0;
for (j = 1; j < 3; j++)
{
// three cycle
points = (int)(Math.Pow(3.0, j)) - 1; // base 3
for (; k < points; k++)
{
point = rsg.nextSequence().value;
stat.add(point);
}
mean = stat.mean();
double error = Math.Abs(mean[1] - 0.5);
if (error > tolerance)
{
Assert.Fail("Second dimension mean (" + /*QL_FIXED*/ +mean[1]
+ ") at the end of the " + j + 1
+ " cycle in Halton sequence is not " + 0.5
//+ QL_SCIENTIFIC
+ " (error = " + error + ")");
}
}
}
public void CreateStatsAndCheckToString()
{
ISequence sequence = new Sequence(Alphabets.DNA, "ACGT--ACGT--ACGT--");
SequenceStatistics stats = new SequenceStatistics(sequence);
string expectedValue = "- - 6\r\nA - 3\r\nC - 3\r\nG - 3\r\nT - 3\r\n".Replace("\r\n", Environment.NewLine);
string actualValue = stats.ToString();
Assert.AreEqual(expectedValue, actualValue);
}
public void TestSequenceStatisticsToString()
{
ISequence seq = new Sequence(Alphabets.DNA, "ATCGATCG");
SequenceStatistics seqStats = new SequenceStatistics(seq);
string actualString = seqStats.ToString();
string expectedString = "A - 2\r\nC - 2\r\nG - 2\r\nT - 2\r\n".Replace("\r\n", Environment.NewLine);
Assert.AreEqual(actualString, expectedString);
}
internal static global::System.Runtime.InteropServices.HandleRef getCPtr(SequenceStatistics obj) {
return (obj == null) ? new global::System.Runtime.InteropServices.HandleRef(null, global::System.IntPtr.Zero) : obj.swigCPtr;
}
