public IList<ISplittedData> SplitData(IDataFrame dataToSplit, IBinarySplittingParams splttingParams)
{
var queries = BuildQueries(splttingParams.SplitOnFeature, splttingParams.SplitOnValue);
var splitResults = new List<ISplittedData>();
var totalRowsCount = (double)dataToSplit.RowCount;
foreach (var boolAndQuery in queries)
{
var resultDataFrame = dataToSplit.GetSubsetByQuery(boolAndQuery.Value);
splitResults.Add(new SplittedData(GetSubsetLink(resultDataFrame, totalRowsCount, boolAndQuery.Key), resultDataFrame));
}
return splitResults;
}
public IList <ISplittedData> SplitData(IDataFrame dataToSplit, IBinarySplittingParams splttingParams)
{
var queries = BuildQueries(splttingParams.SplitOnFeature, splttingParams.SplitOnValue);
var splitResults = new List <ISplittedData>();
var totalRowsCount = (double)dataToSplit.RowCount;
foreach (var boolAndQuery in queries)
{
var resultDataFrame = dataToSplit.GetSubsetByQuery(boolAndQuery.Value);
splitResults.Add(new SplittedData(GetSubsetLink(resultDataFrame, totalRowsCount, boolAndQuery.Key), resultDataFrame));
}
return(splitResults);
}
public IList<ISplittedData> SplitData(IDataFrame dataToSplit, ISplittingParams splttingParams)
{
var splitFeature = splttingParams.SplitOnFeature;
var totalRowsCount = dataToSplit.RowCount;
var uniqueValues = dataToSplit.GetColumnVector(splitFeature).Distinct();
var splittedData = new List<ISplittedData>();
//TODO: AAA emarassingly parallel - test it for performance
foreach (var uniqueValue in uniqueValues)
{
var query = BuildQuery(splitFeature, uniqueValue);
var splitResult = dataToSplit.GetSubsetByQuery(query);
var subsetCount = splitResult.RowCount;
var link = new DecisionLink(
CalcInstancesPercentage(totalRowsCount, subsetCount),
subsetCount,
uniqueValue);
splittedData.Add(new SplittedData(link, splitResult));
}
return splittedData;
}
public IList <ISplittedData> SplitData(IDataFrame dataToSplit, ISplittingParams splttingParams)
{
var splitFeature = splttingParams.SplitOnFeature;
var totalRowsCount = dataToSplit.RowCount;
var uniqueValues = dataToSplit.GetColumnVector(splitFeature).Distinct();
var splittedData = new List <ISplittedData>();
//TODO: AAA emarassingly parallel - test it for performance
foreach (var uniqueValue in uniqueValues)
{
var query = BuildQuery(splitFeature, uniqueValue);
var splitResult = dataToSplit.GetSubsetByQuery(query);
var subsetCount = splitResult.RowCount;
var link = new DecisionLink(
CalcInstancesPercentage(totalRowsCount, subsetCount),
subsetCount,
uniqueValue);
splittedData.Add(new SplittedData(link, splitResult));
}
return(splittedData);
}