public string ToGainSummary(FeaturesToContentMap fmap, Dictionary <int, int> featureToID, int prefix, bool includeZeroGainFeatures, bool normalize, int startingCommentNumber)
{
if (_trees.Count == 0)
{
return(string.Empty);
}
StringBuilder output = new StringBuilder();
// use only first prefix trees
if (prefix > _trees.Count || prefix < 0)
{
prefix = _trees.Count;
}
FeatureToGainMap gainMap = new FeatureToGainMap(_trees.Take(prefix).ToList(), normalize);
if (includeZeroGainFeatures)
{
for (int ifeat = 0; ifeat < fmap.Count; ++ifeat)
{
gainMap[ifeat++] += 0.0;
}
}
var sortedByGain = gainMap.OrderByDescending(pair => pair.Value).AsEnumerable();
var maxValue = sortedByGain.First().Value;
double normalizingFactor = normalize && maxValue != 0 ? Math.Sqrt(maxValue) : 1.0;
double power = normalize ? 0.5 : 1.0;
foreach (var pair in sortedByGain)
{
int outputInputId = featureToID.ContainsKey(pair.Key) ? featureToID[pair.Key] : 0;
output.Append(string.Format("C:{0}=FG:I{1}:{2}:{3}\n", startingCommentNumber++, outputInputId,
fmap.GetName(pair.Key), Math.Pow(pair.Value, power) / normalizingFactor));
}
return(output.ToString());
}
