Added FamScore function, added remove_edges function in network graph

main_package/classes/fam_score_calculator.py

@@ -9,7 +9,7 @@ from networkx.readwrite import json_graph
 
 from math import log
 
-from scipy.special import gamma
+from scipy.special import loggamma
 from random import choice
 
 import set_of_cims as soCims
@@ -19,30 +19,115 @@ import conditional_intensity_matrix as cim_class
 
 '''
 TODO: Parlare dell'idea di ciclare sulle cim senza filtrare
-TODO: Parlare di gamma in scipy e math(overflow) 
-TODO: Problema warning overflow
+TODO: Parlare del problema con gamma in scipy e math(overflow)
+TODO: Problema warning overflow durante l'esecuzione
 '''
 
+
 class FamScoreCalculator:
     """
-    Has the task of calculate the FamScore of a node
+    Has the task of calculating the FamScore of a node
     """
 
     def __init__(self):
+        np.seterr('raise')
         pass
 
+    # region theta
+
     def marginal_likelihood_theta(self,
-                            node_id: str, 
-                            set_of_cims: soCims.SetOfCims,
-                            graph:net_graph.NetworkGraph):
+                        cims: cim_class.ConditionalIntensityMatrix,
+                        alpha_xu: float = 1,
+                        alpha_xxu: float = 1):
+        """
+        calculate the FamScore value of the node identified by the label node_id
+        Parameters:
+            cims: np.array with all the node's cims,
+            alpha_xu: hyperparameter over the CTBN’s q parameters
+            alpha_xxu: hyperparameter over the CTBN’s theta parameters
+        Returns:
+            the value of the marginal likelihood over theta
+        """
+        return np.sum(
+                        [self.variable_cim_xu_marginal_likelihood_theta(cim,
+                                                                    alpha_xu,
+                                                                    alpha_xxu)
+                        for cim in cims])
+
+    def variable_cim_xu_marginal_likelihood_theta(self,
+                        cim: cim_class.ConditionalIntensityMatrix,
+                        alpha_xu: float = 1,
+                        alpha_xxu: float = 1):
         """
-       calculate the value of the marginal likelihood over theta of the node identified by the label node_id
+        calculate the value of the marginal likelihood over theta given a cim
         Parameters:
-            node_id: the label of the node
+            cim: A conditional_intensity_matrix object with the sufficient statistics,
+            alpha_xu: hyperparameter over the CTBN’s q parameters
+            alpha_xxu: hyperparameter over the CTBN’s theta parameters
         Returns:
             the value of the marginal likelihood over theta
         """
-        return 2
+
+        'get cim length'
+        values = len(cim.state_residence_times)
+
+        print(f"transition time: {cim.state_transition_matrix}")
+        'compute the marginal likelihood for the current cim'
+        return np.sum([
+                    self.single_cim_xu_marginal_likelihood_theta(
+                                                index,
+                                                cim,
+                                                alpha_xu,
+                                                alpha_xxu)
+                    for index in range(values)])
+
+    def single_cim_xu_marginal_likelihood_theta(self,
+                    index: int,
+                    cim: cim_class.ConditionalIntensityMatrix,
+                    alpha_xu: float = 1,
+                    alpha_xxu: float = 1):
+        """
+        calculate the marginal likelihood on q of the node when assumes a specif value
+        and a specif parents's assignment
+        Parameters:
+            index: current x instance's index
+            cim: A conditional_intensity_matrix object with the sufficient statistics,
+            alpha_xu: hyperparameter over the CTBN’s q parameters
+            alpha_xxu: hyperparameter over the CTBN’s theta parameters
+        Returns:
+            the marginal likelihood of the node when assumes a specif value
+        """
+
+        values = list(range(len(cim.state_residence_times)))
+
+        values.remove(index)
+
+        print(values)
+
+        return (loggamma(alpha_xu) - loggamma(alpha_xu + cim.state_transition_matrix[index, index])) \
+                + \
+                np.sum([self.single_internal_cim_xxu_marginal_likelihood_theta(
+                                                                        cim.state_transition_matrix[index,index_x_first],
+                                                                        alpha_xxu)
+                for index_x_first in values])
+
+
+    def single_internal_cim_xxu_marginal_likelihood_theta(self,
+                                                M_xxu_suff_stats: float,
+                                                alpha_xxu: float=1):
+        """
+        calculate the second part of the marginal likelihood over theta formula
+        Parameters:
+            M_xxu_suff_stats: value of the suffucient statistic M[xx'|u]
+            alpha_xxu: hyperparameter over the CTBN’s theta parameters
+        Returns:
+            the marginal likelihood of the node when assumes a specif value
+        """
+        return loggamma(alpha_xxu+M_xxu_suff_stats) - loggamma(alpha_xxu)
+
+    # endregion
+
+    # region q
 
     def marginal_likelihood_q(self,
                         cims: np.array,
@@ -57,17 +142,27 @@ class FamScoreCalculator:
         Returns:
             the value of the marginal likelihood over q
         """
-        return np.prod([self.variable_cim_xu_marginal_likelihood_q(cim,tau_xu,alpha_xu) for cim in cims])
+        return np.sum([self.variable_cim_xu_marginal_likelihood_q(cim, tau_xu, alpha_xu) for cim in cims])
 
     def variable_cim_xu_marginal_likelihood_q(self,
                         cim: cim_class.ConditionalIntensityMatrix,
                         tau_xu: float=1,
                         alpha_xu: float=1):
+        """
+        calculate the value of the marginal likelihood over q given a cim
+        Parameters:
+            cim: A conditional_intensity_matrix object with the sufficient statistics,
+            tau_xu: hyperparameter over the CTBN’s q parameters
+            alpha_xu: hyperparameter over the CTBN’s q parameters
+        Returns:
+            the value of the marginal likelihood over q
+        """
+
         'get cim length'
         values=len(cim.state_residence_times)
 
         'compute the marginal likelihood for the current cim'
-        return np.prod([
+        return np.sum([
                     self.single_cim_xu_marginal_likelihood_q(
                                                 cim.state_transition_matrix[index, index],
                                                 cim.state_residence_times[index],
@@ -77,25 +172,36 @@ class FamScoreCalculator:
 
 
     def single_cim_xu_marginal_likelihood_q(self,
-                        M_suff_stats:float,
-                        T_suff_stats:float,
+                        M_xu_suff_stats: float,
+                        T_xu_suff_stats: float,
                         tau_xu: float=1,
                         alpha_xu: float=1):
         """
-        calculate the marginal likelihood of the node when assumes a specif value
+        calculate the marginal likelihood on q of the node when assumes a specif value
         and a specif parents's assignment
         Parameters:
-            cims: np.array with all the node's cims,
+            M_xu_suff_stats: value of the suffucient statistic M[x|u]
+            T_xu_suff_stats: value of the suffucient statistic T[x|u]
             tau_xu: hyperparameter over the CTBN’s q parameters
             alpha_xu: hyperparameter over the CTBN’s q parameters
         Returns:
             the marginal likelihood of the node when assumes a specif value
         """
-        print(M_suff_stats)
-        return  (gamma(alpha_xu + M_suff_stats + 1)* (tau_xu**(alpha_xu+1))) \
-                / \
-                (gamma(alpha_xu + 1)*((tau_xu + T_suff_stats)**(alpha_xu + M_suff_stats + 1)))
+        print(f"M[x|u]: {M_xu_suff_stats} T[x|u]: {T_xu_suff_stats}")
+        return (
+                loggamma(alpha_xu + M_xu_suff_stats + 1) + 
+                                                        (log(tau_xu)
+                                                        *
+                                                        (alpha_xu+1))
+                ) \
+                - \
+                (loggamma(alpha_xu + 1)+(
+                                    log(tau_xu + T_xu_suff_stats) 
+                                    *
+                                    (alpha_xu + M_xu_suff_stats + 1))
+                )
 
+    # end region
 
     def get_fam_score(self,
                 cims: np.array,
@@ -112,10 +218,10 @@ class FamScoreCalculator:
         Returns:
             the FamScore value of the node
         """
-        return log(
-                    self.marginal_likelihood_q(cims,tau_xu,alpha_xu)
-                ) \
+        return self.marginal_likelihood_q(cims,
+                                    tau_xu,
+                                    alpha_xu) \
                + \
-                log(
-                    self.marginal_likelihood_theta(cims,tau_xu,alpha_xu,alpha_xxu)
-                    )
+               self.marginal_likelihood_theta(cims, 
+                                        alpha_xu,
+                                        alpha_xxu)

main_package/classes/network_graph.py

@@ -100,6 +100,17 @@ class NetworkGraph:
         """
         self.graph.add_edges_from(list_of_edges)
 
+    def remove_edges(self, list_of_edges: typing.List):
+        """
+        Remove the edges to the graph contained in the list list_of_edges.
+
+        Parameters:
+            list_of_edges
+        Returns:
+            void
+        """
+        self.graph.remove_edges_from(list_of_edges)
+
     def get_ordered_by_indx_set_of_parents(self, node: str):
         """
         Builds the aggregated structure that holds all the infos relative to the parent set of the node, namely

main_package/classes/structure_score_based_estimator.py

@@ -80,16 +80,24 @@ class StructureScoreBasedEstimator:
     def estimate_parents(self,node_id:str):
         """
         Use the FamScore of a node in order to find the best parent nodes
-
         Parameters:
             void
         Returns:
             void
-
         """
         'Create the graph for the single node'
         graph = ng.NetworkGraph(self.sample_path.structure)
         'inizialize the graph for a single node'
+
+        graph.graph_struct._edges_list=[]
+
+        graph.fast_init(node_id) 
+
+        #graph.graph.remove_edge('Z','X')
+
+        graph.add_edges([['Z','X']])
+        #graph.add_edges([['X','Z']])
+
         graph.fast_init(node_id) 
     
         params_estimation = pe.ParametersEstimator(self.sample_path, graph)
@@ -98,17 +106,16 @@ class StructureScoreBasedEstimator:
         params_estimation.fast_init(node_id)
         SoCims = params_estimation.compute_parameters_for_node(node_id)
 
-        'Get the node\'s parents list'
-        parents = graph.get_parents_by_id(node_id)
-
-        values = graph.get_states_number(parents[0])
-
-        print(f" actual_cims {len(SoCims.actual_cims)} padri {len(parents)} ")
+        print(f"il numero di cims è : {len(SoCims.actual_cims)}")
 
+        'calculate the FamScore for the node'
         fam_score_obj = fam_score.FamScoreCalculator()
 
         score = fam_score_obj.get_fam_score(SoCims.actual_cims)
         
+        print(f" lo score per {node_id} risulta: {score} ")
+        return score 
+        
         '''mask = np.array([True,True])
 
         cims = SoCims.filter_cims_with_mask(mask,[1,1])

main_package/tests/test_structure_score_based_estimator.py

@@ -29,7 +29,6 @@ class TestStructureScoreBasedEstimator(unittest.TestCase):
 
 
 
-
     def test_esecuzione(self):
         se1 = se.StructureScoreBasedEstimator(self.s1)
         se1.estimate_structure()