static void CheckFeatureReordering(string dataPath)
{
var model = GetModel(dataPath, null);
ModelSummary(model);
Console.WriteLine("\nReordered");
var reorderMapping = GetReorderMapping("reorder.csv");
var reorderedModel = FeatureReorderer.ReorderXGBoost(model, reorderMapping);
ModelSummary(reorderedModel);
}
private static XGBoost GetModel(string dataPath, short[] reorderMapping)
{
var filename = Path.Combine(dataPath, @"model_xbg_trees.txt");
var treesString = File.ReadAllText(filename);
var model = XGBoost.Create(treesString);
if (reorderMapping != null)
{
model = FeatureReorderer.ReorderXGBoost(model, reorderMapping);
}
return(model);
}
static void DoFeatureReordering(string dataPath)
{
var model = GetModel(dataPath, null);
int numTrees = model.Trees.Length;
var timer = new Timer(SaveBestFeatures, dataPath, 60_000, 60_000);
var greedyReorderMap = FeatureReorderer.Greedy(model, numTrees);
timer.Dispose();
SaveBestFeatures(null);
var allFeatureIndices = new HashSet <short>(greedyReorderMap);
for (short i = 0; i < greedyReorderMap.Length; i++)
{
if (!allFeatureIndices.Contains(i))
{
Console.WriteLine("The reorder mapping is not valid: not found index " + i);
break;
}
}
}
public void TestXGBoostEvaluateTimingReordered()
{
var filename1 = @"../../../../datasets/xgboost/reorder.csv";
var reorderMapping = File.ReadAllLines(filename1)
.Select(m => short.Parse(m))
.ToArray();
var filename = @"../../../../datasets/xgboost/model_xbg_trees.txt";
var treesString = File.ReadAllText(filename);
var model = XGBoost.Create(treesString);
model = FeatureReorderer.ReorderXGBoost(model, reorderMapping);
var filename2 = @"../../../../datasets/xgboost/xgboost_test_cases_no_feature_names.txt";
var samplesString = File.ReadLines(filename2);
var samples = new Dictionary <string, float[]>();
foreach (var line in samplesString.Skip(1))
{
var parts = line.Split(',');
var sample = parts[0];
var featureIndex = int.Parse(parts[1]);
if (featureIndex >= 0 && featureIndex < reorderMapping.Length)
{
featureIndex = reorderMapping[featureIndex];
}
var value = float.Parse(parts[2]);
if (!samples.ContainsKey(sample))
{
samples.Add(sample, new float[1000]);
}
samples[sample][featureIndex] = value;
}
DoXGBoostEvaluateTimingFlat(model, samples);
}
