Converted library to snake_case and made small improvements.

Author: Olcay Taner YILDIZ

Classification/Attribute/DiscreteIndexedAttribute.py

@@ -6,7 +6,10 @@ class DiscreteIndexedAttribute(DiscreteAttribute):
     __index: int
     __maxIndex: int
 
-    def __init__(self, value: str, index: int, maxIndex: int):
+    def __init__(self,
+                 value: str,
+                 index: int,
+                 maxIndex: int):
         """
         Constructor for a discrete attribute.
 

Classification/Classifier/AutoEncoder.py

@@ -8,7 +8,9 @@
 
 class AutoEncoder(Classifier):
 
-    def train(self, trainSet: InstanceList, parameters: MultiLayerPerceptronParameter):
+    def train(self,
+              trainSet: InstanceList,
+              parameters: MultiLayerPerceptronParameter):
         """
         Training algorithm for auto encoders. An auto encoder is a neural network which attempts to replicate its input
         at its output.
@@ -20,8 +22,13 @@ def train(self, trainSet: InstanceList, parameters: MultiLayerPerceptronParamete
         parameters : MultiLayerPerceptronParameter
             Parameters of the auto encoder.
         """
-        partition = Partition(trainSet, 0.2, parameters.getSeed(), True)
-        self.model = AutoEncoderModel(partition.get(1), partition.get(0), parameters)
+        partition = Partition(instanceList=trainSet,
+                              ratio=0.2,
+                              seed=parameters.getSeed(),
+                              stratified=True)
+        self.model = AutoEncoderModel(trainSet=partition.get(1),
+                                      validationSet=partition.get(0),
+                                      parameters=parameters)
 
     def test(self, testSet: InstanceList) -> Performance:
         """

Classification/Classifier/Bagging.py

@@ -9,7 +9,9 @@
 
 class Bagging(Classifier):
 
-    def train(self, trainSet: InstanceList, parameters: BaggingParameter):
+    def train(self,
+              trainSet: InstanceList,
+              parameters: BaggingParameter):
         """
         Bagging bootstrap ensemble method that creates individuals for its ensemble by training each classifier on a
         random redistribution of the training set.
@@ -24,9 +26,9 @@ def train(self, trainSet: InstanceList, parameters: BaggingParameter):
         parameters : Parameter
             Parameters of the bagging trees algorithm. ensembleSize returns the number of trees in the bagged forest.
         """
-        forestSize = parameters.getEnsembleSize()
+        forest_size = parameters.getEnsembleSize()
         forest = []
-        for i in range(forestSize):
+        for i in range(forest_size):
             bootstrap = trainSet.bootstrap(i)
             tree = DecisionTree(DecisionNode(InstanceList(bootstrap.getSample())))
             forest.append(tree)

Classification/Classifier/C45.py

@@ -8,7 +8,9 @@
 
 class C45(Classifier):
 
-    def train(self, trainSet: InstanceList, parameters: C45Parameter):
+    def train(self,
+              trainSet: InstanceList,
+              parameters: C45Parameter):
         """
         Training algorithm for C4.5 univariate decision tree classifier. 20 percent of the data are left aside for
         pruning 80 percent of the data is used for constructing the tree.
@@ -21,7 +23,10 @@ def train(self, trainSet: InstanceList, parameters: C45Parameter):
             Parameter of the C45 algorithm.
         """
         if parameters.isPrune():
-            partition = Partition(trainSet, parameters.getCrossValidationRatio(), parameters.getSeed(), True)
+            partition = Partition(instanceList=trainSet,
+                                  ratio=parameters.getCrossValidationRatio(),
+                                  seed=parameters.getSeed(),
+                                  stratified=True)
             tree = DecisionTree(DecisionNode(partition.get(1)))
             tree.prune(partition.get(0))
         else:

Classification/Classifier/C45Stump.py

@@ -7,7 +7,9 @@
 
 class C45Stump(Classifier):
 
-    def train(self, trainSet: InstanceList, parameters: Parameter):
+    def train(self,
+              trainSet: InstanceList,
+              parameters: Parameter):
         """
         Training algorithm for C4.5 Stump univariate decision tree classifier.
 
@@ -18,4 +20,5 @@ def train(self, trainSet: InstanceList, parameters: Parameter):
         parameters: Parameter
             Parameter of the C45Stump algorithm.
         """
-        self.model = DecisionTree(DecisionNode(trainSet, None, None, True))
+        self.model = DecisionTree(DecisionNode(data=trainSet,
+                                               isStump=True))

Classification/Classifier/Classifier.py

@@ -16,7 +16,9 @@ class Classifier(object):
     model: Model
 
     @abstractmethod
-    def train(self, trainSet: InstanceList, parameters: Parameter):
+    def train(self,
+              trainSet: InstanceList,
+              parameters: Parameter):
         pass
 
     def discreteCheck(self, instance: Instance) -> bool:
@@ -52,14 +54,17 @@ def test(self, testSet: InstanceList) -> Performance:
         Performance
             The accuracy (and error) of the model as an instance of Performance class.
         """
-        classLabels = testSet.getUnionOfPossibleClassLabels()
-        confusion = ConfusionMatrix(classLabels)
+        class_labels = testSet.getUnionOfPossibleClassLabels()
+        confusion = ConfusionMatrix(class_labels)
         for i in range(testSet.size()):
             instance = testSet.get(i)
             confusion.classify(instance.getClassLabel(), self.model.predict(instance))
         return DetailedClassificationPerformance(confusion)
 
-    def singleRun(self, parameter: Parameter, trainSet: InstanceList, testSet: InstanceList) -> Performance:
+    def singleRun(self,
+                  parameter: Parameter,
+                  trainSet: InstanceList,
+                  testSet: InstanceList) -> Performance:
         """
         Runs current classifier with the given train and test data.
 

Classification/Classifier/DeepNetwork.py

@@ -7,7 +7,9 @@
 
 class DeepNetwork(Classifier):
 
-    def train(self, trainSet: InstanceList, parameters: DeepNetworkParameter):
+    def train(self,
+              trainSet: InstanceList,
+              parameters: DeepNetworkParameter):
         """
         Training algorithm for deep network classifier.
 
@@ -18,5 +20,10 @@ def train(self, trainSet: InstanceList, parameters: DeepNetworkParameter):
         parameters : DeepNetworkParameter
             Parameters of the deep network algorithm. crossValidationRatio and seed are used as parameters.
         """
-        partition = Partition(trainSet, parameters.getCrossValidationRatio(), parameters.getSeed(), True)
-        self.model = DeepNetworkModel(partition.get(1), partition.get(0), parameters)
+        partition = Partition(instanceList=trainSet,
+                              ratio=parameters.getCrossValidationRatio(),
+                              seed=parameters.getSeed(),
+                              stratified=True)
+        self.model = DeepNetworkModel(trainSet=partition.get(1),
+                                      validationSet=partition.get(0),
+                                      parameters=parameters)

Classification/Classifier/Dummy.py

@@ -6,7 +6,9 @@
 
 class Dummy(Classifier):
 
-    def train(self, trainSet: InstanceList, parameters: Parameter):
+    def train(self,
+              trainSet: InstanceList,
+              parameters: Parameter):
         """
         Training algorithm for the dummy classifier. Actually dummy classifier returns the maximum occurring class in
         the training data, there is no training.

Classification/Classifier/KMeans.py

@@ -7,10 +7,14 @@
 
 class KMeans(Classifier):
 
-    def train(self, trainSet: InstanceList, parameters: KMeansParameter):
-        priorDistribution = trainSet.classDistribution()
-        classMeans = InstanceList()
-        classLists = Partition(trainSet)
-        for i in range(classLists.size()):
-            classMeans.add(classLists.get(i).average())
-        self.model = KMeansModel(priorDistribution, classMeans, parameters.getDistanceMetric())
+    def train(self,
+              trainSet: InstanceList,
+              parameters: KMeansParameter):
+        prior_distribution = trainSet.classDistribution()
+        class_means = InstanceList()
+        class_lists = Partition(trainSet)
+        for i in range(class_lists.size()):
+            class_means.add(class_lists.get(i).average())
+        self.model = KMeansModel(priorDistribution=prior_distribution,
+                                 classMeans=class_means,
+                                 distanceMetric=parameters.getDistanceMetric())

Classification/Classifier/Knn.py

@@ -6,7 +6,9 @@
 
 class Knn(Classifier):
 
-    def train(self, trainSet: InstanceList, parameters: KnnParameter):
+    def train(self,
+              trainSet: InstanceList,
+              parameters: KnnParameter):
         """
         Training algorithm for K-nearest neighbor classifier.
 
@@ -17,4 +19,6 @@ def train(self, trainSet: InstanceList, parameters: KnnParameter):
         parameters : KnnParameter
             Parameters of the Knn algorithm.
         """
-        self.model = KnnModel(trainSet, parameters.getK(), parameters.getDistanceMetric())
+        self.model = KnnModel(data=trainSet,
+                              k=parameters.getK(),
+                              distanceMetric=parameters.getDistanceMetric())