ImputeEmotionalContentFromFile(string filename, uint column, uint repeats, string imputesave)
{
MemorySource <string, ThreeTuple <ContinuousDistribution, ContinuousDistribution, ContinuousDistribution> > imputed = new MemorySource <string, ThreeTuple <ContinuousDistribution, ContinuousDistribution, ContinuousDistribution> >();
ComboSource <string, ThreeTuple <ContinuousDistribution, ContinuousDistribution, ContinuousDistribution> > combo = new ComboSource <string, ThreeTuple <ContinuousDistribution, ContinuousDistribution, ContinuousDistribution> >(source, imputed);
// Check for existing imputed file
DataReader imputereader = new DataReader(imputesave);
uint kk = 0;
for (string[] row = imputereader.ReadRow(); row != null; row = imputereader.ReadRow())
{
kk++;
if (kk % 1000 == 0)
{
Console.WriteLine("#" + kk);
}
double meanv = double.Parse(row[1]), varv = double.Parse(row[2]), meana = double.Parse(row[3]), vara = double.Parse(row[4]), meand = double.Parse(row[5]), vard = double.Parse(row[6]);
ContinuousDistribution valence = new ClippedGaussianDistribution(meanv, varv, 0, 1);
ContinuousDistribution arousal = new ClippedGaussianDistribution(meana, vara, 0, 1);
ContinuousDistribution dominance = new ClippedGaussianDistribution(meand, vard, 0, 1);
imputed[row[0]] = new ThreeTuple <ContinuousDistribution, ContinuousDistribution, ContinuousDistribution>(valence, arousal, dominance);
}
imputereader.Close();
for (uint ii = 0; ii < repeats; ii++)
{
Dictionary <string, List <KeyValuePair <double, double> > >
sentencesV = new Dictionary <string, List <KeyValuePair <double, double> > >(),
sentencesA = new Dictionary <string, List <KeyValuePair <double, double> > >(),
sentencesD = new Dictionary <string, List <KeyValuePair <double, double> > >();
DataReader reader = new DataReader(filename);
uint jj = 0;
for (string[] row = reader.ReadRow(); row != null; row = reader.ReadRow())
{
jj++;
if (jj % 1000 == 0)
{
Console.WriteLine("#" + jj + ": " + sentencesV.Count + ", " + imputed.Count);
}
List <string> words = TwitterUtilities.SplitWords(row[column].ToLower());
AnalyzeWords(words, combo, sentencesV, sentencesA, sentencesD);
}
reader.Close();
AnalyzeSentences(imputed, sentencesV, sentencesA, sentencesD, imputesave);
}
source = combo;
return(imputed);
}
public void AnalyzeSentences(MemorySource <string, ThreeTuple <ContinuousDistribution, ContinuousDistribution, ContinuousDistribution> > inputed,
Dictionary <string, List <KeyValuePair <double, double> > > sentencesV,
Dictionary <string, List <KeyValuePair <double, double> > > sentencesA,
Dictionary <string, List <KeyValuePair <double, double> > > sentencesD, string imputesave)
{
using (var stream = File.CreateText(imputesave)) {
foreach (string stem in sentencesV.Keys)
{
double vmean = WeightedStatistics.Mean(sentencesV[stem]), amean = WeightedStatistics.Mean(sentencesA[stem]), dmean = WeightedStatistics.Mean(sentencesD[stem]);
ClippedGaussianDistribution valence = new ClippedGaussianDistribution(vmean, WeightedStatistics.Variance(sentencesV[stem], vmean, true), 0, 1);
ClippedGaussianDistribution arousal = new ClippedGaussianDistribution(amean, WeightedStatistics.Variance(sentencesA[stem], amean, true), 0, 1);
ClippedGaussianDistribution dominance = new ClippedGaussianDistribution(dmean, WeightedStatistics.Variance(sentencesD[stem], dmean, true), 0, 1);
inputed[stem] = new ThreeTuple <ContinuousDistribution, ContinuousDistribution, ContinuousDistribution>(valence, arousal, dominance);
stream.WriteLine(stem + "," + valence.InternalMean + "," + valence.InternalVariance + "," + arousal.InternalMean + "," + arousal.InternalVariance + "," + dominance.InternalMean + "," + dominance.InternalVariance);
}
}
}
