pipeline components added, readme, docs

firefly-cpp · Dec 12, 2020 · 85bd0c0 · 85bd0c0
1 parent f00230a
commit 85bd0c0
Show file tree

Hide file tree

Showing 9 changed files with 289 additions and 11 deletions.
diff --git a/COMPONENTS.md b/COMPONENTS.md
@@ -5,7 +5,12 @@
 * Extremely Randomized Trees (ExtremelyRandomizedTrees),
 * Linear SVC (LinearSVC),
 * Multi Layer Perceptron (MultiLayerPerceptron),
-* Random Forest Classifier (RandomForestClassifier).
+* Random Forest Classifier (RandomForest),
+* Decision Tree Classifier (DecisionTree),
+* K-Neighbors Classifier (KNeighbors),
+* Gaussian Process Classifier (GaussianProcess),
+* Gaussian Naive Bayes (GaussianNB),
+* Quadratic Discriminant Analysis (QuadraticDiscriminantAnalysis).
 
 ### Feature Selection Algorithms
 
@@ -24,7 +29,10 @@
 ### Feature Transformation Algorithms
 
 * Normalizer (Normalizer),
-* Standard Scaler (StandardScaler).
+* Standard Scaler (StandardScaler),
+* Maximum Absolute Scaler (MaxAbsScaler),
+* Quantile Transformer (QuantileTransformer),
+* Robust Scaler (RobustScaler).
 
 ### Fitness Functions based on
 

diff --git a/README.rst b/README.rst
@@ -108,7 +108,12 @@ Classifiers
 -  Extremely Randomized Trees (ExtremelyRandomizedTrees),
 -  Linear SVC (LinearSVC),
 -  Multi Layer Perceptron (MultiLayerPerceptron),
--  Random Forest Classifier (RandomForestClassifier).
+-  Random Forest Classifier (RandomForest),
+-  Decision Tree Classifier (DecisionTree),
+-  K-Neighbors Classifier (KNeighbors),
+-  Gaussian Process Classifier (GaussianProcess),
+-  Gaussian Naive Bayes (GaussianNB),
+-  Quadratic Discriminant Analysis (QuadraticDiscriminantAnalysis).
 
 Feature Selection Algorithms
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~
@@ -130,10 +135,13 @@ Feature Transformation Algorithms
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 -  Normalizer (Normalizer),
--  Standard Scaler (StandardScaler).
+-  Standard Scaler (StandardScaler),
+-  Maximum Absolute Scaler (MaxAbsScaler),
+-  Quantile Transformer (QuantileTransformer),
+-  Robust Scaler (RobustScaler).
 
-Fitness Functions
-~~~~~~~~~~~~~~~~~
+Fitness Functions based on
+~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 -  Accuracy (Accuracy),
 -  Cohen's kappa (CohenKappa),

diff --git a/docs/getting_started.rst b/docs/getting_started.rst
@@ -71,7 +71,12 @@ Classifiers
 * Extremely Randomized Trees (ExtremelyRandomizedTrees),
 * Linear SVC (LinearSVC),
 * Multi Layer Perceptron (MultiLayerPerceptron),
-* Random Forest Classifier (RandomForestClassifier).
+* Random Forest Classifier (RandomForest),
+* Decision Tree Classifier (DecisionTree),
+* K-Neighbors Classifier (KNeighbors),
+* Gaussian Process Classifier (GaussianProcess),
+* Gaussian Naive Bayes (GaussianNB),
+* Quadratic Discriminant Analysis (QuadraticDiscriminantAnalysis).
 
 Feature Selection Algorithms
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
@@ -93,16 +98,29 @@ Feature Transformation Algorithms
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
 * Normalizer (Normalizer),
-* Standard Scaler (StandardScaler).
+* Standard Scaler (StandardScaler),
+* Maximum Absolute Scaler (MaxAbsScaler),
+* Quantile Transformer (QuantileTransformer),
+* Robust Scaler (RobustScaler).
 
-Fitness Functions
-^^^^^^^^^^^^^^^^^
+Fitness Functions based on
+^^^^^^^^^^^^^^^^^^^^^^^^^^
 
 * Accuracy (Accuracy),
 * Cohen's kappa (CohenKappa),
 * F1-Score (F1),
 * Precision (Precision).
 
+Categorical Feature Encoders
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+* One-Hot Encoder (OneHotEncoder).
+
+Feature Imputers
+^^^^^^^^^^^^^^^^
+
+* Simple Imputer (SimpleImputer).
+
 Optimization Algorithms
 ^^^^^^^^^^^^^^^^^^^^^^^
 

diff --git a/niaaml/classifiers/__init__.py b/niaaml/classifiers/__init__.py
@@ -7,6 +7,9 @@
 from niaaml.classifiers.bagging import Bagging
 from niaaml.classifiers.decision_tree import DecisionTree
 from niaaml.classifiers.k_neighbors import KNeighbors
+from niaaml.classifiers.gaussian_process import GaussianProcess
+from niaaml.classifiers.gaussian_naive_bayes import GaussianNB
+from niaaml.classifiers.quadratic_driscriminant_analysis import QuadraticDiscriminantAnalysis
 from niaaml.classifiers.utility import ClassifierFactory
 
 __all__ = [
@@ -19,5 +22,8 @@
     'ExtremelyRandomizedTrees',
     'DecisionTree',
     'KNeighbors',
+    'GaussianProcess',
+    'GaussianNB',
+    'QuadraticDiscriminantAnalysis',
     'ClassifierFactory'
 ]
diff --git a/niaaml/classifiers/gaussian_naive_bayes.py b/niaaml/classifiers/gaussian_naive_bayes.py
@@ -0,0 +1,66 @@
+from niaaml.classifiers.classifier import Classifier
+from niaaml.utilities import MinMax
+from niaaml.utilities import ParameterDefinition
+from sklearn.naive_bayes import GaussianNB as GNB
+import numpy as np
+
+__all__ = ['GaussianNB']
+
+class GaussianNB(Classifier):
+    r"""Implementation of gaussian Naive Bayes classifier.
+    
+    Date:
+        2020
+
+    Author:
+        Luka Pečnik
+
+    License:
+        MIT
+
+    See Also:
+        * :class:`niaaml.classifiers.Classifier`
+    """
+    Name = 'Gaussian Naive Bayes'
+
+    def __init__(self, **kwargs):
+        r"""Initialize GaussianNB instance.
+        """
+        self.__gaussian_nb = GNB()
+        super(GaussianNB, self).__init__()
+
+    def set_parameters(self, **kwargs):
+        r"""Set the parameters/arguments of the algorithm.
+        """
+        self.__gaussian_nb.set_params(**kwargs)
+
+    def fit(self, x, y, **kwargs):
+        r"""Fit GaussianNB.
+
+        Arguments:
+            x (pandas.core.frame.DataFrame): n samples to classify.
+            y (pandas.core.series.Series): n classes of the samples in the x array.
+
+        Returns:
+            None
+        """
+        self.__gaussian_nb.fit(x, y)
+
+    def predict(self, x, **kwargs):
+        r"""Predict class for each sample (row) in x.
+
+        Arguments:
+            x (pandas.core.frame.DataFrame): n samples to classify.
+
+        Returns:
+            pandas.core.series.Series: n predicted classes.
+        """
+        return self.__gaussian_nb.predict(x)
+
+    def to_string(self):
+        r"""User friendly representation of the object.
+
+        Returns:
+            str: User friendly representation of the object.
+        """
+        return Classifier.to_string(self).format(name=self.Name, args=self._parameters_to_string(self.__gaussian_nb.get_params()))
diff --git a/niaaml/classifiers/gaussian_process.py b/niaaml/classifiers/gaussian_process.py
@@ -0,0 +1,70 @@
+from niaaml.classifiers.classifier import Classifier
+from niaaml.utilities import MinMax
+from niaaml.utilities import ParameterDefinition
+from sklearn.gaussian_process import GaussianProcessClassifier as GPC
+import numpy as np
+
+__all__ = ['GaussianProcess']
+
+class GaussianProcess(Classifier):
+    r"""Implementation of gaussian process classifier.
+    
+    Date:
+        2020
+
+    Author:
+        Luka Pečnik
+
+    License:
+        MIT
+
+    See Also:
+        * :class:`niaaml.classifiers.Classifier`
+    """
+    Name = 'Gaussian Process Classifier'
+
+    def __init__(self, **kwargs):
+        r"""Initialize GaussianProcess instance.
+        """
+        self._params = dict(
+            max_iter_predict = ParameterDefinition(MinMax(50, 200), np.uint),
+            warm_start = ParameterDefinition([True, False]),
+            multi_class = ParameterDefinition(['one_vs_rest', 'one_vs_one'])
+        )
+        self.__gaussian_process = GPC()
+
+    def set_parameters(self, **kwargs):
+        r"""Set the parameters/arguments of the algorithm.
+        """
+        self.__gaussian_process.set_params(**kwargs)
+
+    def fit(self, x, y, **kwargs):
+        r"""Fit GaussianProcess.
+
+        Arguments:
+            x (pandas.core.frame.DataFrame): n samples to classify.
+            y (pandas.core.series.Series): n classes of the samples in the x array.
+
+        Returns:
+            None
+        """
+        self.__gaussian_process.fit(x, y)
+
+    def predict(self, x, **kwargs):
+        r"""Predict class for each sample (row) in x.
+
+        Arguments:
+            x (pandas.core.frame.DataFrame): n samples to classify.
+
+        Returns:
+            pandas.core.series.Series: n predicted classes.
+        """
+        return self.__gaussian_process.predict(x)
+
+    def to_string(self):
+        r"""User friendly representation of the object.
+
+        Returns:
+            str: User friendly representation of the object.
+        """
+        return Classifier.to_string(self).format(name=self.Name, args=self._parameters_to_string(self.__gaussian_process.get_params()))
diff --git a/niaaml/classifiers/quadratic_driscriminant_analysis.py b/niaaml/classifiers/quadratic_driscriminant_analysis.py
@@ -0,0 +1,66 @@
+from niaaml.classifiers.classifier import Classifier
+from niaaml.utilities import MinMax
+from niaaml.utilities import ParameterDefinition
+from sklearn.discriminant_analysis import QuadraticDiscriminantAnalysis as QDA
+import numpy as np
+
+__all__ = ['QuadraticDiscriminantAnalysis']
+
+class QuadraticDiscriminantAnalysis(Classifier):
+    r"""Implementation of quadratic discriminant analysis classifier.
+    
+    Date:
+        2020
+
+    Author:
+        Luka Pečnik
+
+    License:
+        MIT
+
+    See Also:
+        * :class:`niaaml.classifiers.Classifier`
+    """
+    Name = 'Quadratic Discriminant Analysis'
+
+    def __init__(self, **kwargs):
+        r"""Initialize QuadraticDiscriminantAnalysis instance.
+        """
+        self.__qda = QDA()
+        super(QuadraticDiscriminantAnalysis, self).__init__()
+
+    def set_parameters(self, **kwargs):
+        r"""Set the parameters/arguments of the algorithm.
+        """
+        self.__qda.set_params(**kwargs)
+
+    def fit(self, x, y, **kwargs):
+        r"""Fit QuadraticDiscriminantAnalysis.
+
+        Arguments:
+            x (pandas.core.frame.DataFrame): n samples to classify.
+            y (pandas.core.series.Series): n classes of the samples in the x array.
+
+        Returns:
+            None
+        """
+        self.__qda.fit(x, y)
+
+    def predict(self, x, **kwargs):
+        r"""Predict class for each sample (row) in x.
+
+        Arguments:
+            x (pandas.core.frame.DataFrame): n samples to classify.
+
+        Returns:
+            pandas.core.series.Series: n predicted classes.
+        """
+        return self.__qda.predict(x)
+
+    def to_string(self):
+        r"""User friendly representation of the object.
+
+        Returns:
+            str: User friendly representation of the object.
+        """
+        return Classifier.to_string(self).format(name=self.Name, args=self._parameters_to_string(self.__qda.get_params()))
diff --git a/niaaml/classifiers/utility.py b/niaaml/classifiers/utility.py
@@ -7,6 +7,9 @@
 from niaaml.classifiers.random_forest import RandomForest
 from niaaml.classifiers.decision_tree import DecisionTree
 from niaaml.classifiers.k_neighbors import KNeighbors
+from niaaml.classifiers.gaussian_process import GaussianProcess
+from niaaml.classifiers.gaussian_naive_bayes import GaussianNB
+from niaaml.classifiers.quadratic_driscriminant_analysis import QuadraticDiscriminantAnalysis
 
 __all__ = [
     'ClassifierFactory'
@@ -42,5 +45,8 @@ def _set_parameters(self, **kwargs):
             'MultiLayerPerceptron': MultiLayerPerceptron,
             'RandomForest': RandomForest,
             'DecisionTree': DecisionTree,
-            'KNeighbors': KNeighbors
+            'KNeighbors': KNeighbors,
+            'GaussianProcess': GaussianProcess,
+            'GaussianNB': GaussianNB,
+            'QuadraticDiscriminantAnalysis': QuadraticDiscriminantAnalysis
         }
diff --git a/niaaml/tests/test_classifiers.py b/niaaml/tests/test_classifiers.py
@@ -43,4 +43,34 @@ def test_rf_works_fine(self):
         algo = c.RandomForest()
         algo.fit(self.__x_train, self.__y_train)
         predictions = algo.predict(self.__x_test)
+        self.assertEqual(predictions.shape, self.__y_test.shape)
+
+    def test_dt_works_fine(self):
+        algo = c.DecisionTree()
+        algo.fit(self.__x_train, self.__y_train)
+        predictions = algo.predict(self.__x_test)
+        self.assertEqual(predictions.shape, self.__y_test.shape)
+
+    def test_kn_works_fine(self):
+        algo = c.KNeighbors()
+        algo.fit(self.__x_train, self.__y_train)
+        predictions = algo.predict(self.__x_test)
+        self.assertEqual(predictions.shape, self.__y_test.shape)
+
+    def test_gp_works_fine(self):
+        algo = c.GaussianProcess()
+        algo.fit(self.__x_train, self.__y_train)
+        predictions = algo.predict(self.__x_test)
+        self.assertEqual(predictions.shape, self.__y_test.shape)
+
+    def test_gnb_works_fine(self):
+        algo = c.GaussianNB()
+        algo.fit(self.__x_train, self.__y_train)
+        predictions = algo.predict(self.__x_test)
+        self.assertEqual(predictions.shape, self.__y_test.shape)
+
+    def test_qda_works_fine(self):
+        algo = c.QuadraticDiscriminantAnalysis()
+        algo.fit(self.__x_train, self.__y_train)
+        predictions = algo.predict(self.__x_test)
         self.assertEqual(predictions.shape, self.__y_test.shape)