public void WeirdColumnTest()
{
Stream weirdStream = TestUtils.RetrieveResource(weirdColumnResource);
var weirdConfig = GetWeirdConfig();
CCRecordSet recordSet = CCRecordSet.FromStream(weirdStream, weirdConfig);
var nbc = ClassifierFactory.GetClassifierByName <string>("NaiveBayesClassifier");
nbc.Train(recordSet.Select(rec => new KeyValuePair <string, string>(rec.Description, rec.PredictedValues["Fish"])).ToList());
Assert.AreEqual(nbc.Categorize("Seattle Lounge").Category, "Trout");
}
public void NaiveBayesClassifierSimpleTest()
{
var records = KeyValuePairFromTsv(bookExample);
var classifier = ClassifierFactory.GetClassifierByName <Genre>("NaiveBayesClassifier");
classifier.Train(records);
Assert.AreEqual(classifier.Categorize("Curtains and Drapes").Category, Genre.INTERIORDECORATING);
Assert.AreEqual(classifier.Categorize("The Ventilation of Bridges").Category, Genre.ENGINEERING);
Assert.AreEqual(classifier.Categorize("Tax Accounting").Category, Genre.ACCOUNTING);
}
public void NaiveBayesClassificationIntegrationTest()
{
Stream oldRecordsStream = TestUtils.RetrieveResource(fullChargeList);
CCRecordSet records = CCRecordSet.FromStream(oldRecordsStream, config);
var nbc = ClassifierFactory.GetClassifierByName <string>("NaiveBayesClassifier");
var trainingData = records
.Select(rec => new KeyValuePair <string, string>(rec.Description, rec.PredictedValues["Category"]))
.ToList();
nbc.Train(trainingData);
Assert.AreEqual(nbc.Categorize("Trader Joe's").Category, "GROC");
Assert.AreEqual(nbc.Categorize("Shell Oil 27440482209 Seattle Wa").Category, "TRANS");
trainingData = records
.Select(rec => new KeyValuePair <string, string>(rec.Description, rec.PredictedValues["Owner"]))
.ToList();
nbc = ClassifierFactory.GetClassifierByName <string>("NaiveBayesClassifier");
nbc.Train(trainingData);
Assert.AreEqual(nbc.Categorize("Radio Shack 00133652 Knoxville").Category, "Bob");
}
internal static CCRecordSet ClassifyAndUpdate(CCRecordSet oldRecordSet, List <CCRecord> newRecords,
IRecordReader reader, C3Configuration config)
{
var classifers = new Dictionary <C3PredictedColumn, IClassifier <string> >();
foreach (C3PredictedColumn predictedColumn in config.columns)
{
var trainingData = oldRecordSet
.Select(rec => new KeyValuePair <string, string>(rec.Description, rec.PredictedValues[predictedColumn.columnName]))
.ToList();
var classifier = ClassifierFactory.GetClassifierByName <string>(predictedColumn.classifierName);
Utils.Log(LoggingSeverity.DEBUG,
$"Training {predictedColumn.classifierName} on column '{predictedColumn.columnName}' with {trainingData.Count} records");
classifier.Train(trainingData);
classifers.Add(predictedColumn, classifier);
}
AppendRecords(oldRecordSet, newRecords, classifers);
return(oldRecordSet);
}