private List <List <Double> > rawExamplesFromDataSet(DataSet ds,
Numerizer numerizer)
{
// assumes all values for inout and target are doubles
List <List <Double> > rds = new List <List <Double> >();
for (int i = 0; i < ds.size(); i++)
{
List <Double> rexample = new List <Double>();
Example e = ds.getExample(i);
Pair <List <Double>, List <Double> > p = numerizer.numerize(e);
List <Double> attributes = p.getFirst();
foreach (Double d in attributes)
{
rexample.Add(d);
}
List <Double> targets = p.getSecond();
foreach (Double d in targets)
{
rexample.Add(d);
}
rds.Add(rexample);
}
return(rds);
}
/*
* create a normalized data "table" from the DataSet using numerizer. At
* this stage, the data isnot split into input pattern and targets TODO
* remove redundancy of recreating the target columns. the numerizer has
* already isolated the targets
*/
public void createNormalizedDataFromDataSet(DataSet ds, Numerizer numerizer)
{
List <List <Double> > rds = rawExamplesFromDataSet(ds, numerizer);
// normalize raw dataset
nds = normalize(rds);
}
/*
* create a normalized data "table" from the DataSet using numerizer. At
* this stage, the data isnot split into input pattern and targets TODO
* remove redundancy of recreating the target columns. the numerizer has
* already isolated the targets
*/
public void createNormalizedDataFromDataSet(DataSet ds, Numerizer numerizer)
{
List<List<Double>> rds = rawExamplesFromDataSet(ds, numerizer);
// normalize raw dataset
nds = normalize(rds);
}
static string NumerizeLongScale(long r, string s)
{
string numerizedInput = null;
try
{
numerizedInput = Numerizer.Numerize(s, true);
}
catch (Exception ex)
{
throw new Exception(
String.Format(
"Test case: {0} => {1} :: {2}", s, r, ex.Message),
ex);
}
return(numerizedInput);
}
static string Numerize(int r, string s, string culture = "en")
{
Thread.CurrentThread.CurrentCulture = new System.Globalization.CultureInfo(culture);
string numerizedInput = null;
try
{
numerizedInput = Numerizer.Numerize(s);
}
catch (Exception ex)
{
throw new Exception(
String.Format(
"Test case: {0} => {1} :: {2}", s, r, ex.Message),
ex);
}
return(numerizedInput);
}
private static string Numerize(int r, string s)
{
string numerizedInput = null;
try
{
numerizedInput = Numerizer.Numerize(s);
}
catch (Exception ex)
{
throw new Exception(
string.Format(
"Test case: {0} => {1} :: {2}",
s,
r,
ex.Message),
ex);
}
return(numerizedInput);
}
public void test_edges_in_french()
{
Assert.Equal(
"27 Oct 2006 7h30", Numerizer.Numerize("27 Oct 2006 7h30"));
}
public void test_edges()
{
Assert.Equal(
"27 Oct 2006 7:30am", Numerizer.Numerize("27 Oct 2006 7:30am"));
}
/*
* method called by clients to set up data set and make it ready for
* processing
*/
public void createExamplesFromDataSet(DataSet ds, Numerizer numerizer)
{
createNormalizedDataFromDataSet(ds, numerizer);
setTargetColumns();
createExamples();
}
public static string Numerize(this string @this, bool intendingTime)
{
return(Numerizer.Numerize(@this, intendingTime));
}
public static string Numerize(this string @this)
{
return(Numerizer.Numerize(@this));
}
private List<List<Double>> rawExamplesFromDataSet(DataSet ds,
Numerizer numerizer) {
// assumes all values for inout and target are doubles
List<List<Double>> rds = new List<List<Double>>();
for (int i = 0; i < ds.size(); i++) {
List<Double> rexample = new List<Double>();
Example e = ds.getExample(i);
Pair<List<Double>, List<Double>> p = numerizer.numerize(e);
List<Double> attributes = p.getFirst();
foreach (Double d in attributes) {
rexample.Add(d);
}
List<Double> targets = p.getSecond();
foreach (Double d in targets) {
rexample.Add(d);
}
rds.Add(rexample);
}
return rds;
}
/*
* method called by clients to set up data set and make it ready for
* processing
*/
public void createExamplesFromDataSet(DataSet ds, Numerizer numerizer)
{
createNormalizedDataFromDataSet(ds, numerizer);
setTargetColumns();
createExamples();
}
