public static TheoryData TokenMatchingTestData(int testDataPoints = 1)
{
// prepare dataset and storage options
var dataset = DatasetReader.ReadDatasetFromCSV(Constants.CompanyNamesDatasetLocation);
// preparing datapoints for testing
var sentencesToMatchList = new List <string>();
var expectedMatches = new List <MatchResult>();
for (int i = 0; i < testDataPoints; i++)
{
//random datapoint
var randomSentenceIndex = RandomGenerator.GetRandomIndex(dataset.Count);
var sentenceToMatch = dataset[randomSentenceIndex];
//constructing more complicated sentence that includes entity name
var sentenceIncludingEntity = "Sentence that includes " + sentenceToMatch + " as an entity name";
//expected outcome
var expected = new MatchResult
{
DatabaseMatchInfo = new DatabaseMatchInfo()
{
MatchText = dataset[randomSentenceIndex],
MatchIndex = randomSentenceIndex
}
};
//adding to lists
sentencesToMatchList.Add(sentenceIncludingEntity);
expectedMatches.Add(expected);
}
//returning TheoryData Objects
if (testDataPoints == 1)
{
return(new TheoryData <List <string>, string, MatchResult>
{
{
dataset,
sentencesToMatchList[0],
expectedMatches[0]
}
});
}
else
{
return(new TheoryData <List <string>, List <string>, List <MatchResult> >
{
{
dataset,
sentencesToMatchList,
expectedMatches
}
});
}
}
public static TheoryData FuzzyMatchingClientPerfomanceTestData()
{
var dataset = DatasetReader.ReadDatasetFromCSV(Constants.NewsHeadlinesDatasetLocation);
int[] testDataSizes = new int[6] {
10, 100, 1000, 10000, 25000, 50000
};
var sentenceToMatch = "take record";
return(new TheoryData <List <string>, int[], string>
{
{
dataset,
testDataSizes,
sentenceToMatch
}
});
}
public static TheoryData MultipleMatchTestData()
{
var dataset = DatasetReader.ReadDatasetFromCSV(Constants.NewsHeadlinesDatasetLocation);
var testDataPoints = 9;
var testSentencesList = new List <string>();
var expectedMatches = new List <MatchResult>();
for (int i = 0; i < testDataPoints; i++)
{
// random datapoint
var randomSentenceIndex = RandomGenerator.GetRandomIndex(dataset.Count);
var sentenceToMatch = dataset[randomSentenceIndex];
// expected outcome
var expected = new MatchResult
{
DatabaseMatchInfo = new DatabaseMatchInfo()
{
MatchText = dataset[randomSentenceIndex],
MatchIndex = randomSentenceIndex
}
};
// adding to lists
testSentencesList.Add(sentenceToMatch);
expectedMatches.Add(expected);
}
return(new TheoryData <List <string>, List <string>, List <MatchResult> >
{
{
dataset,
testSentencesList,
expectedMatches
}
});
}
public static TheoryData SingleMatchTestData()
{
var dataset = DatasetReader.ReadDatasetFromCSV(Constants.NewsHeadlinesDatasetLocation);
var randomSentenceIndex = RandomGenerator.GetRandomIndex(dataset.Count);
var sentenceToMatch = dataset[randomSentenceIndex];
var expected = new MatchResult
{
DatabaseMatchInfo = new DatabaseMatchInfo()
{
MatchText = sentenceToMatch,
MatchIndex = randomSentenceIndex
}
};
return(new TheoryData <List <string>, string, MatchResult>
{
{
dataset,
sentenceToMatch,
expected
}
});
}
//[TestMethod, DeploymentItem("Resources/DataSets/OCR/characters/cmr_all.xml")]
public void TestVisionBench()
{
// Set some training paths
string trainingDataset = "cmr_all.xml";
string testingDataset = "Resources/DataSets/OCR/characters/cmr_all.xml";
double minAccuracy = 100.0; // force max training cycles
int maxTrainingCycles = 5;
// Create spatial parameters
Parameters p = Parameters.Empty();
p.SetParameterByKey(Parameters.KEY.INPUT_DIMENSIONS, new[] { 32, 32 }); // Size of image patch
p.SetParameterByKey(Parameters.KEY.COLUMN_DIMENSIONS, new[] { 32, 32 });
p.SetParameterByKey(Parameters.KEY.POTENTIAL_RADIUS, 10000); // Ensures 100% potential pool
p.SetParameterByKey(Parameters.KEY.POTENTIAL_PCT, 0.8);
p.SetParameterByKey(Parameters.KEY.GLOBAL_INHIBITION, true);
p.SetParameterByKey(Parameters.KEY.LOCAL_AREA_DENSITY, -1.0); // Using numActiveColumnsPerInhArea
p.SetParameterByKey(Parameters.KEY.NUM_ACTIVE_COLUMNS_PER_INH_AREA, 64.0);
// All input activity can contribute to feature output
p.SetParameterByKey(Parameters.KEY.STIMULUS_THRESHOLD, 0.0);
p.SetParameterByKey(Parameters.KEY.SYN_PERM_INACTIVE_DEC, 0.001);
p.SetParameterByKey(Parameters.KEY.SYN_PERM_ACTIVE_INC, 0.001);
p.SetParameterByKey(Parameters.KEY.SYN_PERM_CONNECTED, 0.3);
p.SetParameterByKey(Parameters.KEY.MIN_PCT_OVERLAP_DUTY_CYCLES, 0.001);
p.SetParameterByKey(Parameters.KEY.MIN_PCT_ACTIVE_DUTY_CYCLES, 0.001);
p.SetParameterByKey(Parameters.KEY.DUTY_CYCLE_PERIOD, 1000);
p.SetParameterByKey(Parameters.KEY.MAX_BOOST, 1.0);
p.SetParameterByKey(Parameters.KEY.SEED, 1956); // The seed that Grok uses
p.SetParameterByKey(Parameters.KEY.RANDOM, new XorshiftRandom(1956)); // The seed that Grok uses
p.SetParameterByKey(Parameters.KEY.SP_VERBOSITY, 1);
p.SetParameterByKey(Parameters.KEY.SP_PARALLELMODE, true);
Connections cn = new Connections();
p.Apply(cn);
// Instantiate our spatial pooler
SpatialPooler sp = new SpatialPooler();
sp.Init(cn);
// Instantiate the spatial pooler test bench.
VisionTestBench tb = new VisionTestBench(cn, sp);
// Instantiate the classifier
KNNClassifier clf = KNNClassifier.GetBuilder().Apply(p);
// Get testing images and convert them to vectors.
var tupleTraining = DatasetReader.GetImagesAndTags(trainingDataset);
var trainingImages = (List <Bitmap>)tupleTraining.Get(0);
var trainingTags = tupleTraining.Get(1) as List <string>;
var trainingVectors = trainingImages.Select((i, index) => new { index, vector = i.ToVector() })
.ToDictionary(k => k.index, v => v.vector);
// Train the spatial pooler on trainingVectors.
int numcycles = tb.Train(trainingVectors, trainingTags, clf, maxTrainingCycles, minAccuracy);
// Get testing images and convert them to vectors.
var tupleTesting = DatasetReader.GetImagesAndTags(trainingDataset);
var testingImages = (List <System.Drawing.Bitmap>)tupleTesting.Get(0);
var testingTags = tupleTesting.Get(1) as List <string>;
var testingVectors = testingImages.Select((i, index) => new { index, vector = i.ToVector() })
.ToDictionary(k => k.index, v => v.vector);
// Reverse the order of the vectors and tags for testing
testingTags.Reverse();
testingVectors.Reverse();
// Test the spatial pooler on testingVectors.
var accurancy = tb.Test(testingVectors, testingTags, clf, learn: true);
Debug.WriteLine("Number of training cycles : " + numcycles);
Debug.WriteLine("Accurancy : " + accurancy);
tb.SavePermsAndConns("C:\\temp\\permsAndConns.jpg");
}
