static public IEnumerable <Pair <string, Dictionary <string, SufficientStatistics> > > LoadSparseFileEnumeration(string sparseFileName) //where T1:ISufficientStatistics
{
Set <string> variablesAlreadySeenSet = new Set <string>();
Pair <string, Dictionary <string, SufficientStatistics> > variableAndCaseIdToNonMissingValue = null;
foreach (Dictionary <string, string> row in SpecialFunctions.TabFileTable(sparseFileName, "var\tcid\tval", false))
{
string variable = row["var"];
if (variableAndCaseIdToNonMissingValue != null && variableAndCaseIdToNonMissingValue.First != variable)
{
yield return(variableAndCaseIdToNonMissingValue);
variableAndCaseIdToNonMissingValue = null;
}
if (variableAndCaseIdToNonMissingValue == null)
{
SpecialFunctions.CheckCondition(!variablesAlreadySeenSet.Contains(variable), string.Format("Input file ({0}) is not grouped by variable. Variable {1} appears in multiple places", sparseFileName, variable));
variablesAlreadySeenSet.AddNew(variable);
variableAndCaseIdToNonMissingValue =
new Pair <string, Dictionary <string, SufficientStatistics> >(variable, new Dictionary <string, SufficientStatistics>());
}
string caseId = row["cid"];
SufficientStatistics val = SufficientStatistics.Parse(row["val"]);
SpecialFunctions.CheckCondition(!variableAndCaseIdToNonMissingValue.Second.ContainsKey(caseId), string.Format("Input file ({0}) for var {1} contains multiple entries for caseId {2}", sparseFileName, variable, caseId));
variableAndCaseIdToNonMissingValue.Second.Add(caseId, val);
}
if (variableAndCaseIdToNonMissingValue != null)
{
yield return(variableAndCaseIdToNonMissingValue);
}
}
static public Dictionary <string, Dictionary <string, SufficientStatistics> > LoadSparseFileInMemory(string sparseFileName) //where TStat:ISufficientStatistics
{
Dictionary <string, Dictionary <string, SufficientStatistics> > variableToCaseIdToNonMissingValue =
new Dictionary <string, Dictionary <string, SufficientStatistics> >();
foreach (Dictionary <string, string> row in SpecialFunctions.TabFileTable(sparseFileName, "var\tcid\tval", false))
{
string variable = row["var"];
string caseId = row["cid"];
SufficientStatistics val = SufficientStatistics.Parse(row["val"]);
Dictionary <string, SufficientStatistics> caseIdToNonMissingValue = SpecialFunctions.GetValueOrDefault(variableToCaseIdToNonMissingValue, variable);
SpecialFunctions.CheckCondition(!caseIdToNonMissingValue.ContainsKey(caseId), string.Format("Input file ({0}) for var {1} contains multiple entries for caseId {2}", sparseFileName, variable, caseId));
caseIdToNonMissingValue.Add(caseId, val);
}
return(variableToCaseIdToNonMissingValue);
}