public DomainNameAddOnFeaturesGenerator(FeaturesConfig featuresConfig) : base(featuresConfig)
{
if (!this.FeaturesConfig.UseDomainAsFeature)
{
FeatureDefaults = new Features();
FeatureDefaultsValueTypes = new FeatureValueTypes();
FeatureGranularities = new FeatureGranularities();
return;
}
if (this.FeaturesConfig.NullDefaultsAllowed)
{
FeatureDefaults = new Features()
{
{ CityFeatureType.Domain, (int?)null }
};
}
else
{
FeatureDefaults = new Features()
{
{ CityFeatureType.Domain, int.MaxValue }
};
}
FeatureDefaultsValueTypes = new FeatureValueTypes()
{
{ CityFeatureType.Domain, typeof(int?) }
};
FeatureGranularities = new FeatureGranularities()
{
{ CityFeatureType.Domain, FeatureGranularity.Discrete }
};
}
public FirstLettersAdmin1AddOnFeaturesGenerator(FeaturesConfig featuresConfig) : base(featuresConfig)
{
if (this.FeaturesConfig.NullDefaultsAllowed)
{
FeatureDefaults = new Features()
{
{ CityFeatureType.FirstLettersAdmin1NameMatch, false },
{ CityFeatureType.FirstLettersAdmin1Letters, (byte?)null },
{ CityFeatureType.FirstLettersAdmin1LettersRatio, (float?)null }
};
if (this.FeaturesConfig.UseSlotIndex)
{
FeatureDefaults[CityFeatureType.FirstLettersAdmin1RTLSlotIndex] = (byte?)null;
FeatureDefaults[CityFeatureType.FirstLettersAdmin1LTRSlotIndex] = (byte?)null;
}
}
else
{
FeatureDefaults = new Features()
{
{ CityFeatureType.FirstLettersAdmin1NameMatch, false },
{ CityFeatureType.FirstLettersAdmin1Letters, (byte?)0 },
{ CityFeatureType.FirstLettersAdmin1LettersRatio, (float?)0 },
};
if (this.FeaturesConfig.UseSlotIndex)
{
FeatureDefaults[CityFeatureType.FirstLettersAdmin1RTLSlotIndex] = (byte?)byte.MaxValue;
FeatureDefaults[CityFeatureType.FirstLettersAdmin1LTRSlotIndex] = (byte?)byte.MaxValue;
}
}
FeatureDefaultsValueTypes = new FeatureValueTypes()
{
{ CityFeatureType.FirstLettersAdmin1NameMatch, typeof(bool) },
{ CityFeatureType.FirstLettersAdmin1Letters, typeof(byte?) },
{ CityFeatureType.FirstLettersAdmin1LettersRatio, typeof(float?) }
};
if (this.FeaturesConfig.UseSlotIndex)
{
FeatureDefaultsValueTypes[CityFeatureType.FirstLettersAdmin1RTLSlotIndex] = typeof(byte?);
FeatureDefaultsValueTypes[CityFeatureType.FirstLettersAdmin1LTRSlotIndex] = typeof(byte?);
}
FeatureGranularities = new FeatureGranularities()
{
{ CityFeatureType.FirstLettersAdmin1NameMatch, FeatureGranularity.Discrete },
{ CityFeatureType.FirstLettersAdmin1Letters, FeatureGranularity.Continuous },
{ CityFeatureType.FirstLettersAdmin1LettersRatio, FeatureGranularity.Continuous }
};
if (this.FeaturesConfig.UseSlotIndex)
{
FeatureGranularities[CityFeatureType.FirstLettersAdmin1RTLSlotIndex] = FeatureGranularity.Discrete;
FeatureGranularities[CityFeatureType.FirstLettersAdmin1LTRSlotIndex] = FeatureGranularity.Discrete;
}
}
public ExactCountryAddOnFeaturesGenerator(FeaturesConfig featuresConfig) : base(featuresConfig)
{
if (this.FeaturesConfig.NullDefaultsAllowed)
{
FeatureDefaults = new Features()
{
{ CityFeatureType.ExactCountryNameMatch, false },
{ CityFeatureType.ExactCountryLetters, (byte?)null }
};
if (this.FeaturesConfig.UseSlotIndex)
{
FeatureDefaults[CityFeatureType.ExactCountryRTLSlotIndex] = (byte?)null;
FeatureDefaults[CityFeatureType.ExactCountryLTRSlotIndex] = (byte?)null;
}
}
else
{
FeatureDefaults = new Features()
{
{ CityFeatureType.ExactCountryNameMatch, false },
{ CityFeatureType.ExactCountryLetters, (byte?)0 }
};
if (this.FeaturesConfig.UseSlotIndex)
{
FeatureDefaults[CityFeatureType.ExactCountryRTLSlotIndex] = (byte?)byte.MaxValue;
FeatureDefaults[CityFeatureType.ExactCountryLTRSlotIndex] = (byte?)byte.MaxValue;
}
}
FeatureDefaultsValueTypes = new FeatureValueTypes()
{
{ CityFeatureType.ExactCountryNameMatch, typeof(bool) },
{ CityFeatureType.ExactCountryLetters, typeof(byte?) }
};
if (this.FeaturesConfig.UseSlotIndex)
{
FeatureDefaultsValueTypes[CityFeatureType.ExactCountryRTLSlotIndex] = typeof(byte?);
FeatureDefaultsValueTypes[CityFeatureType.ExactCountryLTRSlotIndex] = typeof(byte?);
}
FeatureGranularities = new FeatureGranularities()
{
{ CityFeatureType.ExactCountryNameMatch, FeatureGranularity.Discrete },
{ CityFeatureType.ExactCountryLetters, FeatureGranularity.Continuous }
};
if (this.FeaturesConfig.UseSlotIndex)
{
FeatureGranularities[CityFeatureType.ExactCountryRTLSlotIndex] = FeatureGranularity.Discrete;
FeatureGranularities[CityFeatureType.ExactCountryLTRSlotIndex] = FeatureGranularity.Discrete;
}
}
public SVMClassifier(FeatureValueTypes featureDefaultsValueTypes, FeatureGranularities featureGranularities, string serializedClassifierPath = null)
{
Teacher = new SequentialMinimalOptimization <Gaussian>()
{
UseComplexityHeuristic = true,
UseKernelEstimation = true // Estimate the kernel from the data
};
if (serializedClassifierPath != null)
{
this.Svm = Serializer.Load <SupportVectorMachine <Gaussian> >(serializedClassifierPath);
}
}
public RandomForestClassifier(FeatureValueTypes featureDefaultsValueTypes, FeatureGranularities featureGranularities, string serializedClassifierPath = null)
{
var featureKinds = new List <DecisionVariable>();
foreach (var entry in featureDefaultsValueTypes)
{
var featureName = entry.Key.ToString();
var featureType = entry.Value;
var featureGranularity = featureGranularities[entry.Key];
if (featureGranularity == FeatureGranularity.Continuous)
{
featureKinds.Add(new DecisionVariable(featureName, DecisionVariableKind.Continuous));
}
else if (featureGranularity == FeatureGranularity.Discrete)
{
var decisionVar = new DecisionVariable(featureName, DecisionVariableKind.Discrete);
// TODO: Fix uint, there is no Accord.UIntRange
if (featureType == (typeof(int)) || featureType == (typeof(int?)) || featureType == (typeof(uint)) || featureType == (typeof(uint?)))
{
decisionVar.Range = new Accord.IntRange(min: int.MinValue, max: int.MaxValue);
}
else if (featureType == (typeof(byte)) || featureType == (typeof(byte?)))
{
decisionVar.Range = new Accord.IntRange(min: byte.MinValue, max: byte.MaxValue);
}
featureKinds.Add(decisionVar);
}
else
{
throw new ArgumentException("Unknown feature granularity");
}
}
var featureKindsArr = featureKinds.ToArray <DecisionVariable>();
this.RandomForestLearner = new RandomForestLearning(featureKindsArr)
{
NumberOfTrees = 10
};
if (serializedClassifierPath != null)
{
this.RandomForest = Serializer.Load <RandomForest>(serializedClassifierPath);
}
}
public TLDAddOnFeaturesGenerator(FeaturesConfig featuresConfig) : base(featuresConfig)
{
FeatureDefaults = new Features()
{
{ CityFeatureType.TLDMatch, false },
};
FeatureDefaultsValueTypes = new FeatureValueTypes()
{
{ CityFeatureType.TLDMatch, typeof(bool) },
};
FeatureGranularities = new FeatureGranularities()
{
{ CityFeatureType.TLDMatch, FeatureGranularity.Discrete }
};
}
public HostnamePatternsAddOnFeaturesGenerator(FeaturesConfig featuresConfig,
HostnamePatternMiner miner,
Dictionary <string, Dictionary <PatternRule, PatternMiningCoordinates> > hostnamePatternRules) : base(featuresConfig)
{
this.miner = miner;
this.hostnamePatternRules = hostnamePatternRules;
FeatureDefaults = new Features()
{
{ CityFeatureType.HostnamePatternMatch, false },
};
FeatureDefaultsValueTypes = new FeatureValueTypes()
{
{ CityFeatureType.HostnamePatternMatch, typeof(bool) },
};
FeatureGranularities = new FeatureGranularities()
{
{ CityFeatureType.HostnamePatternMatch, FeatureGranularity.Discrete }
};
}
public HostnamePatternsFeaturesGenerator(
FeaturesConfig featuresConfig,
HostnamePatternMiner miner,
Dictionary <string, Dictionary <PatternRule, PatternMiningCoordinates> > hostnamePatternRules) : base(featuresConfig)
{
this.miner = miner;
this.hostnamePatternRules = hostnamePatternRules;
if (this.FeaturesConfig.NullDefaultsAllowed)
{
FeatureDefaults = new Features()
{
{ CityFeatureType.HostnamePatternMatch, false },
{ CityFeatureType.HostnamePatternConfidence, (float?)null }
};
}
else
{
FeatureDefaults = new Features()
{
{ CityFeatureType.HostnamePatternMatch, false },
{ CityFeatureType.HostnamePatternConfidence, (float?)0 }
};
}
FeatureDefaultsValueTypes = new FeatureValueTypes()
{
{ CityFeatureType.HostnamePatternMatch, typeof(bool) },
{ CityFeatureType.HostnamePatternConfidence, typeof(float?) }
};
FeatureGranularities = new FeatureGranularities()
{
{ CityFeatureType.HostnamePatternMatch, FeatureGranularity.Discrete },
{ CityFeatureType.HostnamePatternConfidence, FeatureGranularity.Continuous }
};
}
public IClassifier CreateInstance(FeatureValueTypes featureDefaultsValueTypes, FeatureGranularities featureGranularities, string serializedClassifierPath = null)
{
return(new RandomForestClassifier(featureDefaultsValueTypes, featureGranularities, serializedClassifierPath));
}
public LogisticRegressionClassifier(FeatureValueTypes featureDefaultsValueTypes, FeatureGranularities featureGranularities, string serializedClassifierPath = null)
{
Learner = new IterativeReweightedLeastSquares <LogisticRegression>()
{
Tolerance = 1e-4, // Convergence parameters
Iterations = 500, // Maximum number of iterations to perform
Regularization = 0
};
if (serializedClassifierPath != null)
{
this.Regression = Serializer.Load <LogisticRegression>(serializedClassifierPath);
}
}
public IClassifier CreateInstance(FeatureValueTypes featureDefaultsValueTypes, FeatureGranularities featureGranularities, string serializedClassifierPath = null)
{
return(new LogisticRegressionClassifier(featureDefaultsValueTypes, featureGranularities, serializedClassifierPath));
}