public void TestCountVectorizer()
{
DataFrame input = _spark.Sql("SELECT array('hello', 'I', 'AM', 'a', 'string', 'TO', " +
"'TOKENIZE') as input from range(100)");
const string inputColumn = "input";
const string outputColumn = "output";
const double minDf = 1;
const double minTf = 10;
const int vocabSize = 10000;
const bool binary = false;
var countVectorizer = new CountVectorizer();
countVectorizer
.SetInputCol(inputColumn)
.SetOutputCol(outputColumn)
.SetMinDF(minDf)
.SetMinTF(minTf)
.SetVocabSize(vocabSize);
Assert.IsType <CountVectorizerModel>(countVectorizer.Fit(input));
Assert.Equal(inputColumn, countVectorizer.GetInputCol());
Assert.Equal(outputColumn, countVectorizer.GetOutputCol());
Assert.Equal(minDf, countVectorizer.GetMinDF());
Assert.Equal(minTf, countVectorizer.GetMinTF());
Assert.Equal(vocabSize, countVectorizer.GetVocabSize());
Assert.Equal(binary, countVectorizer.GetBinary());
using (var tempDirectory = new TemporaryDirectory())
{
string savePath = Path.Join(tempDirectory.Path, "countVectorizer");
countVectorizer.Save(savePath);
CountVectorizer loadedVectorizer = CountVectorizer.Load(savePath);
Assert.Equal(countVectorizer.Uid(), loadedVectorizer.Uid());
}
Assert.NotEmpty(countVectorizer.ExplainParams());
Assert.NotEmpty(countVectorizer.ToString());
}
