static void IndexMode()
{
if (File.Exists(strInputFile) == false ||
File.Exists(strTemplateFile) == false)
{
UsageIndex();
return;
}
//Load feature set from given file
List <string> features = new List <string>();
StreamReader sr = new StreamReader(strInputFile);
string strLine = null;
while ((strLine = sr.ReadLine()) != null)
{
string[] items = strLine.Split('\t');
features.Add(items[0]);
}
sr.Close();
//Build indexed feature set
templateFeaturizer = new TemplateFeaturizer();
templateFeaturizer.LoadTemplateFromFile(strTemplateFile);
templateFeaturizer.BuildIndexedFeatureIntoFile(strFeatureFile, features);
}
private static void IndexMode()
{
if (File.Exists(inputFilePath) == false ||
File.Exists(templateFilePath) == false)
{
UsageIndex();
return;
}
//Load feature set from given file
var features = new List <string>();
var sr = new StreamReader(inputFilePath);
string strLine;
while ((strLine = sr.ReadLine()) != null)
{
var items = strLine.Split('\t');
features.Add(items[0]);
}
sr.Close();
//Build indexed feature set
templateFeaturizer = new TemplateFeaturizer();
templateFeaturizer.LoadTemplateFromFile(templateFilePath);
templateFeaturizer.BuildIndexedFeatureIntoFile(featureFilePath, features);
}
static IDictionary <string, int> ExtractFeatureSetFromFile()
{
//Load templates from given file
Logger.WriteLine("Loading feature template from {0}...", strTemplateFile);
templateFeaturizer = new TemplateFeaturizer();
templateFeaturizer.LoadTemplateFromFile(strTemplateFile);
Logger.WriteLine("Generate feature set...");
BigDictionary <string, int> feature2freq = new BigDictionary <string, int>();
List <string[]> tokenList = new List <string[]>();
string strLine = null;
Sentence sentence = null;
using (StreamReader srCorpus = new StreamReader(strInputFile, Encoding.UTF8))
{
while ((strLine = srCorpus.ReadLine()) != null)
{
strLine = strLine.Trim();
if (strLine.Length == 0)
{
//The end of current record
sentence = new Sentence(tokenList);
for (int i = 0; i < sentence.TokensList.Count; i++)
{
//Get feature of i-th token
List <string> featureList = templateFeaturizer.GenerateFeature(sentence.TokensList, i);
foreach (string strFeature in featureList)
{
if (feature2freq.ContainsKey(strFeature) == false)
{
feature2freq.Add(strFeature, 0);
}
feature2freq[strFeature]++;
}
}
tokenList.Clear();
}
else
{
tokenList.Add(strLine.Split('\t'));
}
}
//The end of current record
sentence = new Sentence(tokenList);
for (int i = 0; i < sentence.TokensList.Count; i++)
{
//Get feature of i-th token
List <string> featureList = templateFeaturizer.GenerateFeature(sentence.TokensList, i);
foreach (string strFeature in featureList)
{
if (feature2freq.ContainsKey(strFeature) == false)
{
feature2freq.Add(strFeature, 0);
}
feature2freq[strFeature]++;
}
}
}
//Only save the feature whose frequency is not less than minfreq
Logger.WriteLine("Filter out features whose frequency is less than {0}", minfreq);
SortedDictionary <string, int> features = new SortedDictionary <string, int>(StringComparer.Ordinal);
foreach (KeyValuePair <string, int> pair in feature2freq)
{
if (pair.Value >= minfreq)
{
features.Add(pair.Key, pair.Value);
}
}
return(features);
}
