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
}
});
}
