private IArffDataRow AddData(string id, DateTime?date, ExtractTextVectorBase extractTextVector, PositivityType positivity)
{
var cells = extractTextVector.GetCells();
if (cells.Count == 0)
{
return(null);
}
lock (DataSet)
{
IArffDataRow review = string.IsNullOrEmpty(id) ? DataSet.AddDocument() : DataSet.GetOrCreateDocument(id);
review.Class.Value = positivity;
review.Date = date ?? DateTime.Today;
foreach (var cell in cells)
{
var name = cell.Name;
var data = review.AddRecord(name);
if (data != null)
{
data.Header.Source = cell.Item;
data.Value = cell.Value;
}
}
return(review);
}
}
public static void ProcessLine(this IArffDataRow row, DataLine line)
{
var indexes = new Dictionary <int, double>();
foreach (var wordsData in row.GetRecords().Where(item => !(item.Header is DateHeader)))
{
int index = row.Owner.Header.GetIndex(wordsData.Header);
double value = 1;
if (wordsData.Value != null)
{
value = Convert.ToDouble(wordsData.Value);
}
indexes[index] = value;
}
foreach (var index in indexes.OrderBy(item => item.Key))
{
line.SetValue(index.Key, index.Value);
}
}
public void Save(string path)
{
if (string.IsNullOrWhiteSpace(path))
{
throw new ArgumentException("Value cannot be null or whitespace.", nameof(path));
}
log.LogInformation("Saving {0}...", path);
var fileName = $"{Word.Text.CreatePureLetterText()}.arff";
path = Path.Combine(path, fileName);
IArffDataSet arff = ArffDataSet.Create <PositivityType>(Word.Text);
arff.UseTotal = true;
foreach (WordsContext vector in Vectors)
{
IArffDataRow review = arff.AddDocument();
review.Class.Value = vector.SentimentValue > 0
? PositivityType.Positive
: PositivityType.Negative;
foreach (WordEx wordItem in vector.Words)
{
if (!wordItem.IsAspect &&
wordItem.Value == 0)
{
continue;
}
DataRecord addedWord = review.AddRecord(wordItem.Text);
addedWord.Value = addedWord.Total;
}
}
arff.Save(path);
log.LogInformation("Saving {0} Completed.", path);
}