Merge pull request #2 from philipMartini/Structure_Class_Optimization

Add optimizations in NetworkGraph initzialization

main_package/classes/abstract_importer.py

@@ -3,34 +3,21 @@ from abc import ABC, abstractmethod
 
 class AbstractImporter(ABC):
     """
-    Interfaccia che espone i metodi necessari all'importing delle trajectories e della struttura della CTBN
+    Interface that exposes all the necessary methods to import the trajectories and the net structure.
 
-    :files_path: il path in cui sono presenti i/il file da importare
+    :file_path: the file path
 
     """
 
-    def __init__(self, files_path):
-        self.files_path = files_path
+    def __init__(self, file_path: str):
+        self.file_path = file_path
         super().__init__()
 
     @abstractmethod
     def import_trajectories(self, raw_data):
-        """
-        Costruisce le traj partendo dal dataset raw_data
-        Parameters:
-            raw_data: il dataset da cui estrarre le traj
-        Returns:
-            void
-        """
         pass
 
     @abstractmethod
     def import_structure(self, raw_data):
-        """
-        Costruisce la struttura della rete partendo dal dataset raw_data
-        Parameters:
-            raw_data: il dataset da cui estrarre la struttura
-        Returns:
-            void
-        """
         pass
+

main_package/classes/abstract_sample_path.py

@@ -0,0 +1,37 @@
+from abc import ABC, abstractmethod
+import abstract_importer as ai
+
+
+class AbstractSamplePath(ABC):
+
+    def __init__(self, importer: ai.AbstractImporter):
+        self.importer = importer
+        self._trajectories = None
+        self._structure = None
+        super().__init__()
+
+    @abstractmethod
+    def build_trajectories(self):
+        """
+        Builds the Trajectory object that will contain all the trajectories.
+        Assigns the Trajectoriy object to the instance attribute _trajectories
+        Clears all the unused dataframes in Importer Object
+
+        Parameters:
+            void
+        Returns:
+            void
+        """
+        pass
+
+    @abstractmethod
+    def build_structure(self):
+        """
+        Builds the Structure object that aggregates all the infos about the net.
+        Assigns the Structure object to the instance attribuite _structure
+        Parameters:
+            void
+        Returns:
+            void
+        """
+        pass

main_package/classes/cache.py

@@ -1,24 +1,61 @@
 import typing
 import set_of_cims as sofc
 
+
 class Cache:
+    """
+    This class has the role of a cache for SetOfCIMS of a test node that have been already computed during the ctpc algorithm.
+
+    :list_of_sets_of_parents: a list of Sets of the parents to which the cim in cache at SAME index is related
+    :actual_cache: a list of setOfCims objects
+    """
 
     def __init__(self):
-        self.list_of_sets_of_indxs = []
+        self.list_of_sets_of_parents = []
         self.actual_cache = []
 
-    def find(self, parents_comb: typing.Set):
+    def find(self, parents_comb: typing.Set): #typing.Union[typing.Set, str]
+        """
+        Tries to find in cache given the symbolic parents combination parents_comb the SetOfCims related to that parents_comb.
+        Parameters:
+            parents_comb: the parents related to that SetOfCims
+        Returns:
+            A SetOfCims object if the parents_comb index is found in list_of_sets_of_parents.
+            None otherwise.
+
+        """
         try:
-                result = self.actual_cache[self.list_of_sets_of_indxs.index(parents_comb)]
-                print("CACHE HIT!!!!")
+            #print("Cache State:", self.list_of_sets_of_indxs)
+            #print("Look For:", parents_comb)
+            result = self.actual_cache[self.list_of_sets_of_parents.index(parents_comb)]
+            print("CACHE HIT!!!!", parents_comb)
             return result
         except ValueError:
             return None
 
-    def put(self, parents_comb: typing.Set, socim: sofc.SetOfCims):
-        self.list_of_sets_of_indxs.append(parents_comb)
+    def put(self, parents_comb: typing.Union[typing.Set, str], socim: sofc.SetOfCims):
+        """
+        Place in cache the SetOfCims object, and the related sybolyc index parents_comb in list_of_sets_of_parents
+
+        Parameters:
+            parents_comb: the symbolic set index
+            socim: the related SetOfCims object
+
+        Returns:
+            void
+        """
+        #print("Putting in cache:", parents_comb)
+        self.list_of_sets_of_parents.append(parents_comb)
         self.actual_cache.append(socim)
 
     def clear(self):
-        del self.list_of_sets_of_indxs[:]
+        """
+        Clear the contents of both caches.
+
+        Parameters:
+            void
+        Returns:
+            void
+        """
+        del self.list_of_sets_of_parents[:]
         del self.actual_cache[:]

main_package/classes/conditional_intensity_matrix.py

@@ -2,18 +2,30 @@ import numpy as np
 
 
 class ConditionalIntensityMatrix:
-
-    def __init__(self, state_residence_times, state_transition_matrix):
+    """
+    Abstracts the Conditional Intesity matrix of a node as aggregation of the state residence times vector
+    and state transition matrix and the actual CIM matrix.
+
+    :_state_residence_times: state residence times vector
+    :_state_transition_matrix: the transitions count matrix
+    :_cim: the actual cim of the node
+    """
+    def __init__(self, state_residence_times: np.array, state_transition_matrix: np.array):
         self._state_residence_times = state_residence_times
         self._state_transition_matrix = state_transition_matrix
-        #self.cim = np.zeros(shape=(dimension, dimension), dtype=float)
-        self._cim = self.state_transition_matrix.astype(np.float)
+        self._cim = self.state_transition_matrix.astype(np.float64)
 
     def compute_cim_coefficients(self):
+        """
+        Compute the coefficients of the matrix _cim by using the following equality q_xx' = M[x, x'] / T[x]
+
+        Parameters:
+            void
+        Returns:
+            void
+        """
         np.fill_diagonal(self._cim, self._cim.diagonal() * -1)
-        #print(self._cim)
         self._cim = ((self._cim.T + 1) / (self._state_residence_times + 1)).T
-        #np.fill_diagonal(self.state_transition_matrix, 0)
 
     @property
     def state_residence_times(self):

main_package/classes/json_importer.py

@@ -4,26 +4,31 @@ import pandas as pd
 import json
 import typing
 from abstract_importer import AbstractImporter
-from line_profiler import LineProfiler
 
 
 class JsonImporter(AbstractImporter):
     """
-    Implementa l'interfaccia AbstractImporter e aggiunge i metodi necessari a costruire le trajectories e la struttura della rete
-    del dataset in formato json con la seguente struttura:
+    Implements the Interface AbstractImporter and adds all the necessary methods to process and prepare the data in json ext.
+    with the following structure:
     [] 0
         |_ dyn.cims
         |_ dyn.str
         |_ samples
         |_ variabels
-
-    :df_samples_list: lista di dataframe, ogni dataframe contiene una traj
-    :df_structure: dataframe contenente la struttura della rete
-    :df_variables: dataframe contenente le infromazioni sulle variabili della rete
-
+    :file_path: the path of the file that contains tha data to be imported
+    :samples_label: the reference key for the samples in the trajectories
+    :structure_label: the reference key for the structure of the network data
+    :variables_label: the reference key for the cardinalites of the nodes data
+    :time_key: the key used to identify the timestamps in each trajectory
+    :variables_key: the key used to identify the names of the variables in the net
+    :df_samples_list: a Dataframe list in which every df contains a trajectory
+    :df_structure: Dataframe containing the structure of the network (edges)
+    :df_variables: Dataframe containing the nodes cardinalities
+    :df_concatenated_samples: the concatenation and processing of all the trajectories present in the list df_samples list
+    :sorter: the columns header(excluding the time column) of the Dataframe concatenated_samples
     """
 
-    def __init__(self, files_path: str, samples_label: str, structure_label: str, variables_label: str, time_key: str,
+    def __init__(self, file_path: str, samples_label: str, structure_label: str, variables_label: str, time_key: str,
                  variables_key: str):
         self.samples_label = samples_label
         self.structure_label = structure_label
@@ -35,80 +40,135 @@ class JsonImporter(AbstractImporter):
         self._df_variables = pd.DataFrame()
         self._concatenated_samples = None
         self.sorter = None
-        super(JsonImporter, self).__init__(files_path)
+        super(JsonImporter, self).__init__(file_path)
 
     def import_data(self):
+        """
+        Imports and prepares all data present needed for susequent computation.
+        Parameters:
+            void
+        Returns:
+            void
+        """
         raw_data = self.read_json_file()
+        #self.import_variables(raw_data)
         self.import_trajectories(raw_data)
         self.compute_row_delta_in_all_samples_frames(self.time_key)
         self.clear_data_frame_list()
         self.import_structure(raw_data)
         self.import_variables(raw_data, self.sorter)
 
-    def import_trajectories(self, raw_data: pd.DataFrame):
+    def import_trajectories(self, raw_data: typing.List):
+        """
+        Imports the trajectories in the list of dicts raw_data.
+        Parameters:
+            :raw_data: List of Dicts
+        Returns:
+            void
+        """
         self.normalize_trajectories(raw_data, 0, self.samples_label)
 
-    def import_structure(self, raw_data: pd.DataFrame):
+    def import_structure(self, raw_data: typing.List):
+        """
+        Imports in a dataframe the data in the list raw_data at the key structure_label
+
+        Parameters:
+            raw_data: the data
+        Returns:
+            void
+        """
         self._df_structure = self.one_level_normalizing(raw_data, 0, self.structure_label)
 
-    def import_variables(self, raw_data: pd.DataFrame, sorter: typing.List):
+    def import_variables(self, raw_data: typing.List, sorter: typing.List):
+        """
+        Imports the data in raw_data at the key variables_label.
+        Sorts the row of the dataframe df_variables using the list sorter.
+
+        Parameters:
+            raw_data: the data
+            sorter: the list used to sort the dataframe self.df_variables
+        Returns:
+            void
+        """
         self._df_variables = self.one_level_normalizing(raw_data, 0, self.variables_label)
+        #self.sorter = self._df_variables[self.variables_key].to_list()
+        #self.sorter.sort()
+        #print("Sorter:", self.sorter)
         self._df_variables[self.variables_key] = self._df_variables[self.variables_key].astype("category")
         self._df_variables[self.variables_key] = self._df_variables[self.variables_key].cat.set_categories(sorter)
         self._df_variables = self._df_variables.sort_values([self.variables_key])
+        self._df_variables.reset_index(inplace=True)
+        print("Var Frame", self._df_variables)
 
     def read_json_file(self) -> typing.List:
         """
-        Legge il primo file .json nel path self.filepath
+        Reads the first json file in the path self.filePath
 
         Parameters:
               void
         Returns:
-              :data: il contenuto del file json
+              data: the contents of the json file
 
         """
-        try:
-            read_files = glob.glob(os.path.join(self.files_path, "*.json"))
-            if not read_files:
-                raise ValueError('No .json file found in the entered path!')
-            with open(read_files[0]) as f:
+        #try:
+            #read_files = glob.glob(os.path.join(self.files_path, "*.json"))
+            #if not read_files:
+                #raise ValueError('No .json file found in the entered path!')
+        with open(self.file_path) as f:
             data = json.load(f)
             return data
-        except ValueError as err:
-            print(err.args)
+        #except ValueError as err:
+            #print(err.args)
 
-    def one_level_normalizing(self, raw_data: pd.DataFrame, indx: int, key: str) -> pd.DataFrame:
+    def one_level_normalizing(self, raw_data: typing.List, indx: int, key: str) -> pd.DataFrame:
         """
-        Estrae i dati innestati di un livello, presenti nel dataset raw_data,
-        presenti nel json array all'indice indx nel json object key
+        Extracts the one-level nested data in the list raw_data at the index indx at the key key
 
         Parameters:
-            :raw_data: il dataset json completo
-            :indx: l'indice del json array da cui estrarre i dati
-            :key: il json object da cui estrarre i dati
+            raw_data: List of Dicts
+            indx: The index of the array from which the data have to be extracted
+            key: the key for the Dicts from which exctract data
         Returns:
-            Il dataframe contenente i dati normalizzati
+            a normalized dataframe
 
         """
         return pd.DataFrame(raw_data[indx][key])
 
-    def normalize_trajectories(self, raw_data: pd.DataFrame, indx: int, trajectories_key: str):
+    def normalize_trajectories(self, raw_data: typing.List, indx: int, trajectories_key: str):
         """
-        Estrae le traiettorie presenti in rawdata nel json array all'indice indx, nel json object trajectories_key.
-        Aggiunge le traj estratte nella lista di dataframe self.df_samples_list
+        Extracts the traj in raw_data at the index index at the key trajectories key.
+        Adds the extracted traj in the dataframe list self._df_samples_list.
+        Initializes the list self.sorter.
 
         Parameters:
-            void
+            raw_data: the data
+            indx: the index of the array from which extract data
+            trajectories_key: the key of the trajectories objects
         Returns:
             void
         """
-        for sample_indx, sample in enumerate(raw_data[indx][trajectories_key]):
-            self.df_samples_list.append(pd.DataFrame(sample))
-        self.sorter = list(self.df_samples_list[0].columns.values)[1:]
+        dataframe = pd.DataFrame
+        smps = raw_data[indx][trajectories_key]
+        self.df_samples_list = [dataframe(sample) for sample in smps]
+        columns_header = list(self.df_samples_list[0].columns.values)
+        columns_header.remove(self.time_key)
+        self.sorter = columns_header
 
     def compute_row_delta_sigle_samples_frame(self, sample_frame: pd.DataFrame, time_header_label: str,
                                               columns_header: typing.List, shifted_cols_header: typing.List) \
             -> pd.DataFrame:
+        """
+        Computes the difference between each value present in th time column.
+        Copies and shift by one position up all the values present in the remaining columns.
+        Parameters:
+            sample_frame: the traj to be processed
+            time_header_label: the label for the times
+            columns_header: the original header of sample_frame
+            shifted_cols_header: a copy of columns_header with changed names of the contents
+        Returns:
+            sample_frame: the processed dataframe
+
+        """
         sample_frame[time_header_label] = sample_frame[time_header_label].diff().shift(-1)
         shifted_cols = sample_frame[columns_header].shift(-1).fillna(0).astype('int32')
         #print(shifted_cols)
@@ -118,31 +178,49 @@ class JsonImporter(AbstractImporter):
         return sample_frame
 
     def compute_row_delta_in_all_samples_frames(self, time_header_label: str):
-        #columns_header = list(self.df_samples_list[0].columns.values)
-        #self.sorter = columns_header[1:]
+        """
+        Calls the method compute_row_delta_sigle_samples_frame on every dataframe present in the list self.df_samples_list.
+        Concatenates the result in the dataframe concatanated_samples
+
+        Parameters:
+            time_header_label: the label of the time column
+        Returns:
+            void
+        """
+        """columns_header = list(self.df_samples_list[0].columns.values)
+        columns_header.remove('Time')
+        self.sorter = columns_header"""
         shifted_cols_header = [s + "S" for s in self.sorter]
-        for indx, sample in enumerate(self.df_samples_list):
+        compute_row_delta = self.compute_row_delta_sigle_samples_frame
+        """for indx, sample in enumerate(self.df_samples_list):
             self.df_samples_list[indx] = self.compute_row_delta_sigle_samples_frame(sample,
-                                                        time_header_label, self.sorter, shifted_cols_header)
+                                                        time_header_label, self.sorter, shifted_cols_header)"""
+        self.df_samples_list = [compute_row_delta(sample, time_header_label, self.sorter, shifted_cols_header)
+                                for sample in self.df_samples_list]
         self._concatenated_samples = pd.concat(self.df_samples_list)
+        complete_header = self.sorter[:]
+        complete_header.insert(0,'Time')
+        complete_header.extend(shifted_cols_header)
+        #print("Complete Header", complete_header)
+        self._concatenated_samples = self._concatenated_samples[complete_header]
+        #print("Concat Samples",self._concatenated_samples)
 
     def build_list_of_samples_array(self, data_frame: pd.DataFrame) -> typing.List:
         """
-        Costruisce una lista contenente le colonne presenti nel dataframe data_frame convertendole in numpy_array
+        Builds a List containing the columns of dataframe and converts them to a numpy array.
         Parameters:
-            :data_frame: il dataframe da cui estrarre e convertire le colonne
+            :data_frame: the dataframe from which the columns have to be extracted and converted
         Returns:
-            :columns_list: la lista contenente le colonne convertite in numpyarray
-
+            :columns_list: the resulting list of numpy arrays
         """
-        columns_list = []
-        for column in data_frame:
-            columns_list.append(data_frame[column].to_numpy())
+        columns_list = [data_frame[column].to_numpy() for column in data_frame]
+        #for column in data_frame:
+            #columns_list.append(data_frame[column].to_numpy())
         return columns_list
 
     def clear_concatenated_frame(self):
         """
-        Rimuove tutti i valori contenuti nei data_frames presenti in df_samples_list
+        Removes all values in the dataframe concatenated_samples
         Parameters:
             void
         Returns:
@@ -151,10 +229,13 @@ class JsonImporter(AbstractImporter):
         self._concatenated_samples = self._concatenated_samples.iloc[0:0]
 
     def clear_data_frame_list(self):
-        for indx in range(len(self.df_samples_list)):  # Le singole traj non servono più
+        """
+        Removes all values present in the dataframes in the list df_samples_list
+        """
+        for indx in range(len(self.df_samples_list)):  # Le singole traj non servono più #TODO usare list comprens
             self.df_samples_list[indx] = self.df_samples_list[indx].iloc[0:0]
 
-    def import_sampled_cims(self, raw_data: pd.DataFrame, indx: int, cims_key: str) -> typing.Dict:
+    def import_sampled_cims(self, raw_data: typing.List, indx: int, cims_key: str) -> typing.Dict:
         cims_for_all_vars = {}
         for var in raw_data[indx][cims_key]:
             sampled_cims_list = []
@@ -163,7 +244,6 @@ class JsonImporter(AbstractImporter):
                 cims_for_all_vars[var].append(pd.DataFrame(raw_data[indx][cims_key][var][p_comb]).to_numpy())
         return cims_for_all_vars
 
-
     @property
     def concatenated_samples(self):
         return self._concatenated_samples

main_package/classes/network_graph.py

@@ -1,198 +1,279 @@
 
 import networkx as nx
 import numpy as np
+import typing
 
 
-
-class NetworkGraph():
+class NetworkGraph:
     """
-    Rappresenta il grafo che contiene i nodi e gli archi presenti nell'oggetto Structure graph_struct.
-    Ogni nodo contine la label node_id, al nodo è anche associato un id numerico progressivo indx che rappresenta la posizione
-    dei sui valori nella colonna indx della traj
-
-    :graph_struct: l'oggetto Structure da cui estrarre i dati per costruire il grafo graph
-    :graph: il grafo
-
+    Abstracts the infos contained in the Structure class in the form of a directed graph.
+    Has the task of creating all the necessary filtering structures for parameters estimation
+
+    :graph_struct: the Structure object from which infos about the net will be extracted
+    :graph: directed graph
+    :nodes_labels: the symbolic names of the variables
+    :nodes_indexes: the indexes of the nodes
+    :nodes_values: the cardinalites of the nodes
+    :aggregated_info_about_nodes_parents: a structure that contains all the necessary infos about every parents of every
+    node in the net
+    :_fancy_indexing: the indexes of every parent of every node in the net
+    :_time_scalar_indexing_structure: the indexing structure for state res time estimation
+    :_transition_scalar_indexing_structure: the indexing structure for transition computation
+    :_time_filtering: the columns filtering structure used in the computation of the state res times
+    :_transition_filtering: the columns filtering structure used in the computation of the transition from one state to another
+    :self._p_combs_structure: all the possibile parents states combination for every node in the net
     """
 
     def __init__(self, graph_struct):
         self.graph_struct = graph_struct
         self.graph = nx.DiGraph()
-        self._nodes_indexes = self.graph_struct.list_of_nodes_indexes()
-        self._nodes_labels = self.graph_struct.list_of_nodes_labels()
+        self._nodes_indexes = self.graph_struct.nodes_indexes
+        self._nodes_labels = self.graph_struct.nodes_labels
+        self._nodes_values = self.graph_struct.nodes_values
         self.aggregated_info_about_nodes_parents = None
         self._fancy_indexing = None
-        self._time_scalar_indexing_structure = []
-        self._transition_scalar_indexing_structure = []
-        self._time_filtering = []
-        self._transition_filtering = []
+        self._time_scalar_indexing_structure = None
+        self._transition_scalar_indexing_structure = None
+        self._time_filtering = None
+        self._transition_filtering = None
+        self._p_combs_structure = None
 
     def init_graph(self):
-        self.add_nodes(self.graph_struct.list_of_nodes_labels())
-        self.add_edges(self.graph_struct.list_of_edges())
+        self.add_nodes(self._nodes_labels)
+        self.add_edges(self.graph_struct.edges)
         self.aggregated_info_about_nodes_parents = self.get_ord_set_of_par_of_all_nodes()
         self._fancy_indexing = self.build_fancy_indexing_structure(0)
-        self.build_time_scalar_indexing_structure()
+        self.build_scalar_indexing_structures()
         self.build_time_columns_filtering_structure()
-        self.build_transition_scalar_indexing_structure()
         self.build_transition_columns_filtering_structure()
+        self._p_combs_structure = self.build_p_combs_structure()
+
+    def fast_init(self, node_id: str):
+        """
+        Initializes all the necessary structures for parameters estimation of the node identified by the label node_id
+        Parameters:
+            node_id: the label of the node
+        Returns:
+            void
+        """
+        self.add_nodes(self._nodes_labels)
+        self.add_edges(self.graph_struct.edges)
+        self.aggregated_info_about_nodes_parents = self.get_ordered_by_indx_set_of_parents(node_id)
+        self._fancy_indexing = self.aggregated_info_about_nodes_parents[1]
+        p_indxs = self._fancy_indexing
+        p_vals = self.aggregated_info_about_nodes_parents[2]
+        self._time_scalar_indexing_structure = self.build_time_scalar_indexing_structure_for_a_node(node_id,
+                                                                                                    p_vals)
+        self._transition_scalar_indexing_structure = self.build_transition_scalar_indexing_structure_for_a_node(node_id,
+                                                                                                                p_vals)
+        node_indx = self.get_node_indx(node_id)
+        self._time_filtering = self.build_time_columns_filtering_for_a_node(node_indx, p_indxs)
+        self._transition_filtering = self.build_transition_filtering_for_a_node(node_indx, p_indxs)
+        self._p_combs_structure = self.build_p_comb_structure_for_a_node(p_vals)
 
-    def add_nodes(self, list_of_nodes):
-        #self.graph.add_nodes_from(list_of_nodes)
-        for id in list_of_nodes:
-            self.graph.add_node(id)
-            nx.set_node_attributes(self.graph, {id:self.graph_struct.get_node_indx(id)}, 'indx')
+    def add_nodes(self, list_of_nodes: typing.List):
+        """
+        Adds the nodes to the graph contained in the list of nodes list_of_nodes.
+        Sets all the properties that identify a nodes (index, positional index, cardinality)
 
-    def add_edges(self, list_of_edges):
+        Parameters:
+            list_of_nodes: the nodes to add to graph
+        Returns:
+            void
+        """
+        nodes_indxs = self._nodes_indexes
+        nodes_vals = self.graph_struct.nodes_values
+        pos = 0
+        for id, node_indx, node_val in zip(list_of_nodes, nodes_indxs, nodes_vals):
+            self.graph.add_node(id, indx=node_indx, val=node_val, pos_indx=pos)
+            pos += 1
+
+    def add_edges(self, list_of_edges: typing.List):
+        """
+        Add the edges to the graph contained in the list list_of_edges.
+
+        Parameters:
+            list_of_edges
+        Returns:
+            void
+        """
         self.graph.add_edges_from(list_of_edges)
 
-    def get_ordered_by_indx_set_of_parents(self, node):
-        #print(node)
-        #ordered_set = {}
+    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
+        (parents_labels, parents_indexes, parents_cardinalities).
+        N.B. The parent set is sorted using the list of sorted nodes nodes
+
+        Parameters:
+            node: the label of the node
+        Returns:
+            a tuple containing all the parent set infos
+
+        """
         parents = self.get_parents_by_id(node)
-        #print(parents)
-        sorted_parents = [x for _, x in sorted(zip(self.graph_struct.list_of_nodes_labels(), parents))]
-        #print(sorted_parents)
-        #print(parents)
-        p_indxes= []
-        p_values = []
-        for n in parents:
-            #indx = self.graph_struct.get_node_indx(n)
-
-            #print(indx)
-            #ordered_set[n] = indx
-            node_indx = self.get_node_indx(n)
-            p_indxes.append(node_indx)
-            #p_values.append(self.graph_struct.get_states_number(n))
-            p_values.append(self.get_states_number_by_indx(node_indx))
-        ordered_set = (sorted_parents, p_indxes, p_values)
-        #print(ordered_set)
-
-        #ordered_set = {k: v for k, v in sorted(ordered_set.items(), key=lambda item: item[1])}
-        return ordered_set
+        nodes = self._nodes_labels
+        d = {v: i for i, v in enumerate(nodes)}
+        sorted_parents = sorted(parents, key=lambda v: d[v])
+        get_node_indx = self.get_node_indx
+        p_indxes = [get_node_indx(node) for node in sorted_parents]
+        p_values = [self.get_states_number(node) for node in sorted_parents]
+        return (sorted_parents, p_indxes, p_values)
 
     def get_ord_set_of_par_of_all_nodes(self):
-        result = []
-        for node in self._nodes_labels:
-            result.append(self.get_ordered_by_indx_set_of_parents(node))
-        #print(result)
+        get_ordered_by_indx_set_of_parents = self.get_ordered_by_indx_set_of_parents
+        result = [get_ordered_by_indx_set_of_parents(node) for node in self._nodes_labels]
         return result
 
-    """def get_ordered_by_indx_parents_values(self, node):
-        parents_values = []
-        parents = self.get_ordered_by_indx_set_of_parents(node)
-        for n in parents:
-            parents_values.append(self.graph_struct.get_states_number(n))
-        return parents_values"""
-
     def get_ordered_by_indx_parents_values_for_all_nodes(self):
-        """result = []
-        for node in self._nodes_labels:
-            result.append(self.get_ordered_by_indx_parents_values(node))
-        return result"""
         pars_values = [i[2] for i in self.aggregated_info_about_nodes_parents]
         return pars_values
 
-    def get_states_number_of_all_nodes_sorted(self):
-        states_number_list = []
-        for node in self._nodes_labels:
-            states_number_list.append(self.get_states_number(node))
-        return states_number_list
-
     def build_fancy_indexing_structure(self, start_indx):
-        """list_of_parents_list = self.get_ord_set_of_par_of_all_nodes()
-        #print(list_of_parents_list)
-        index_structure = []
-        for i, list_of_parents in enumerate(list_of_parents_list):
-            indexes_for_a_node = []
-            for j, node in enumerate(list_of_parents):
-                indexes_for_a_node.append(self.get_node_indx(node) + start_indx)
-            index_structure.append(np.array(indexes_for_a_node, dtype=np.int))
-        #print(index_structure)
-        return index_structure"""
         if start_indx > 0:
             pass
         else:
             fancy_indx = [i[1] for i in self.aggregated_info_about_nodes_parents]
             return fancy_indx
 
+    def build_time_scalar_indexing_structure_for_a_node(self, node_id: str, parents_vals: typing.List) -> np.ndarray:
+        """
+        Builds an indexing structure for the computation of state residence times values.
 
-    def build_time_scalar_indexing_structure_for_a_node(self, node_indx, parents_indxs):
-        #print(node_indx)
-        #print("Parents_id", parents_indxs)
-        #T_vector = np.array([self.graph_struct.variables_frame.iloc[node_id, 1].astype(np.int)])
-        T_vector = np.array([self.get_states_number_by_indx(node_indx)])
-        #print(T_vector)
-        #print("Here ", self.graph_struct.variables_frame.iloc[parents_id[0], 1])
-        T_vector = np.append(T_vector, [self.graph_struct.get_states_number_by_indx(x) for x in parents_indxs])
-        #print(T_vector)
+        Parameters:
+            node_id: the node label
+            parents_vals: the caridinalites of the node's parents
+        Returns:
+            a numpy array.
+
+        """
+        T_vector = np.array([self.get_states_number(node_id)])
+        T_vector = np.append(T_vector, parents_vals)
         T_vector = T_vector.cumprod().astype(np.int)
         return T_vector
-        #print(T_vector)
-
-    def build_time_scalar_indexing_structure(self):
-        #parents_indexes_list = self._fancy_indexing
-        for node_indx, p_indxs in zip(self.graph_struct.list_of_nodes_indexes(), self._fancy_indexing):
-            #if not p_indxs:
-                #self._time_scalar_indexing_structure.append(np.array([self.get_states_number_by_indx(node_indx)],
-                                                                     #dtype=np.int))
-            #else:
-                self._time_scalar_indexing_structure.append(
-                    self.build_time_scalar_indexing_structure_for_a_node(node_indx, p_indxs))
-
-    def build_transition_scalar_indexing_structure_for_a_node(self, node_indx, parents_indxs):
-        #M_vector = np.array([self.graph_struct.variables_frame.iloc[node_id, 1],
-                             #self.graph_struct.variables_frame.iloc[node_id, 1].astype(np.int)])
-        M_vector = np.array([self.get_states_number_by_indx(node_indx),
-                             self.get_states_number_by_indx(node_indx)])
-        M_vector = np.append(M_vector, [self.graph_struct.get_states_number_by_indx(x) for x in parents_indxs])
+
+
+    def build_transition_scalar_indexing_structure_for_a_node(self, node_id: str, parents_vals: typing.List) -> np.ndarray:
+        """
+        Builds an indexing structure for the computation of state transitions values.
+
+        Parameters:
+            node_id: the node label
+            parents_vals: the caridinalites of the node's parents
+        Returns:
+            a numpy array.
+
+        """
+        node_states_number = self.get_states_number(node_id)
+        M_vector = np.array([node_states_number,
+                             node_states_number])
+        M_vector = np.append(M_vector, parents_vals)
         M_vector = M_vector.cumprod().astype(np.int)
         return M_vector
 
-    def build_transition_scalar_indexing_structure(self):
-        #parents_indexes_list = self._fancy_indexing
-        for node_indx, p_indxs in zip(self.graph_struct.list_of_nodes_indexes(), self._fancy_indexing):
-            self._transition_scalar_indexing_structure.append(
-                self.build_transition_scalar_indexing_structure_for_a_node(node_indx, p_indxs))
-
-    def build_time_columns_filtering_structure(self):
-        #parents_indexes_list = self._fancy_indexing
-        for node_indx, p_indxs in zip(self.graph_struct.list_of_nodes_indexes(), self._fancy_indexing):
-            #if p_indxs.size == 0:
-                #self._time_filtering.append(np.append(p_indxs, np.array([node_indx], dtype=np.int)))
-            #else:
-                self._time_filtering.append(np.append(np.array([node_indx], dtype=np.int), p_indxs).astype(np.int))
+    def build_time_columns_filtering_for_a_node(self, node_indx: int, p_indxs: typing.List) -> np.ndarray:
+        """
+        Builds the necessary structure to filter the desired columns indicated by node_indx and p_indxs in the dataset.
+        This structute will be used in the computation of the state res times.
+        Parameters:
+            node_indx: the index of the node
+            p_indxs: the indexes of the node's parents
+        Returns:
+            a numpy array
+        """
+        return np.append(np.array([node_indx], dtype=np.int), p_indxs).astype(np.int)
 
-    def build_transition_columns_filtering_structure(self):
-        #parents_indexes_list = self._fancy_indexing
+    def build_transition_filtering_for_a_node(self, node_indx, p_indxs) -> np.ndarray:
+        """
+        Builds the necessary structure to filter the desired columns indicated by node_indx and p_indxs in the dataset.
+        This structute will be used in the computation of the state transitions values.
+        Parameters:
+            node_indx: the index of the node
+            p_indxs: the indexes of the node's parents
+        Returns:
+            a numpy array
+        """
         nodes_number = self.graph_struct.total_variables_number
-        for node_indx, p_indxs in zip(self.graph_struct.list_of_nodes_indexes(), self._fancy_indexing):
-            self._transition_filtering.append(np.array([node_indx + nodes_number, node_indx, *p_indxs], dtype=np.int))
+        return np.array([node_indx + nodes_number, node_indx, *p_indxs], dtype=np.int)
 
-    def get_nodes(self):
-        return list(self.graph.nodes)
+    def build_p_comb_structure_for_a_node(self, parents_values: typing.List) -> np.ndarray:
+        """
+        Builds the combinatory structure that contains the combinations of all the values contained in parents_values.
 
-    def get_edges(self):
-        return list(self.graph.edges)
+        Parameters:
+            parents_values: the cardinalities of the nodes
+        Returns:
+            a numpy matrix containinga grid of the combinations
+        """
+        tmp = []
+        for val in parents_values:
+            tmp.append([x for x in range(val)])
+        if len(parents_values) > 0:
+            parents_comb = np.array(np.meshgrid(*tmp)).T.reshape(-1, len(parents_values))
+            if len(parents_values) > 1:
+                tmp_comb = parents_comb[:, 1].copy()
+                parents_comb[:, 1] = parents_comb[:, 0].copy()
+                parents_comb[:, 0] = tmp_comb
+        else:
+            parents_comb = np.array([[]], dtype=np.int)
+        return parents_comb
 
-    def get_nodes_sorted_by_indx(self):
-        return self.graph_struct.list_of_nodes_labels()
+    def build_time_columns_filtering_structure(self):
+        nodes_indxs = self._nodes_indexes
+        self._time_filtering = [np.append(np.array([node_indx], dtype=np.int), p_indxs).astype(np.int)
+            for node_indx, p_indxs in zip(nodes_indxs, self._fancy_indexing)]
+
+    def build_transition_columns_filtering_structure(self):
+        nodes_number = self.graph_struct.total_variables_number
+        nodes_indxs = self._nodes_indexes
+        self._transition_filtering = [np.array([node_indx + nodes_number, node_indx, *p_indxs], dtype=np.int)
+                                      for node_indx, p_indxs in zip(nodes_indxs,
+                                                                    self._fancy_indexing)]
+
+    def build_scalar_indexing_structures(self):
+        parents_values_for_all_nodes = self.get_ordered_by_indx_parents_values_for_all_nodes()
+        build_transition_scalar_indexing_structure_for_a_node = self.build_transition_scalar_indexing_structure_for_a_node
+        build_time_scalar_indexing_structure_for_a_node = self.build_time_scalar_indexing_structure_for_a_node
+        aggr = [(build_transition_scalar_indexing_structure_for_a_node(node_id, p_vals),
+                 build_time_scalar_indexing_structure_for_a_node(node_id, p_vals))
+                                                      for node_id, p_vals in
+                                                      zip(self._nodes_labels,
+                                                          parents_values_for_all_nodes)]
+        self._transition_scalar_indexing_structure = [i[0] for i in aggr]
+        self._time_scalar_indexing_structure = [i[1] for i in aggr]
+
+    def build_p_combs_structure(self):
+        parents_values_for_all_nodes = self.get_ordered_by_indx_parents_values_for_all_nodes()
+        p_combs_struct = [self.build_p_comb_structure_for_a_node(p_vals) for p_vals in parents_values_for_all_nodes]
+        return p_combs_struct
 
     def get_parents_by_id(self, node_id):
         return list(self.graph.predecessors(node_id))
 
     def get_states_number(self, node_id):
-        return self.graph_struct.get_states_number(node_id)
-
-    def get_states_number_by_indx(self, node_indx):
-        return self.graph_struct.get_states_number_by_indx(node_indx)
-
-    def get_node_by_index(self, node_indx):
-        return self.graph_struct.get_node_id(node_indx)
+        return self.graph.nodes[node_id]['val']
 
     def get_node_indx(self, node_id):
         return nx.get_node_attributes(self.graph, 'indx')[node_id]
-        #return self.graph_struct.get_node_indx(node_id)
+
+    def get_positional_node_indx(self, node_id):
+        return self.graph.nodes[node_id]['pos_indx']
+
+    @property
+    def nodes(self):
+        return self._nodes_labels
+
+    @property
+    def edges(self):
+        return list(self.graph.edges)
+
+    @property
+    def nodes_indexes(self):
+        return self._nodes_indexes
+
+    @property
+    def nodes_values(self):
+        return self._nodes_values
 
     @property
     def time_scalar_indexing_strucure(self):
@@ -210,16 +291,8 @@ class NetworkGraph():
     def transition_filtering(self):
         return self._transition_filtering
 
-    """def remove_node(self, node_id):
-        node_indx = self.get_node_indx(node_id)
-        self.graph_struct.remove_node(node_id)
-        self.graph.remove_node(node_id)
-        del self._fancy_indexing[node_indx]
-        del self._time_filtering[node_indx]
-        del self._nodes_labels[node_indx]
-        del self._transition_scalar_indexing_structure[node_indx]
-        del self._transition_filtering[node_indx]
-        del self._time_scalar_indexing_structure[node_indx]
-        del self.aggregated_info_about_nodes_parents[node_indx]
-        del self._nodes_indexes[node_indx]"""
+    @property
+    def p_combs(self):
+        return self._p_combs_structure
+
 

main_package/classes/parameters_estimator.py

@@ -1,32 +1,52 @@
-import os
 
-from line_profiler import LineProfiler
-
-import numba as nb
 import numpy as np
-import network_graph as ng
-import sample_path as sp
 import sets_of_cims_container as acims
+import set_of_cims as sofc
+import sample_path as sp
+import network_graph as ng
 
 
 class ParametersEstimator:
+    """
+    Has the task of computing the cims of particular node given the trajectories in samplepath and the net structure
+    in the graph net_graph
+
+    :sample_path: the container of the trajectories
+    :net_graph: the net structure
+    :single_srt_of_cims: the set of cims object that will hold the cims of the node
+    """
 
-    def __init__(self, sample_path, net_graph):
+    def __init__(self, sample_path: sp.SamplePath, net_graph: ng.NetworkGraph):
         self.sample_path = sample_path
         self.net_graph = net_graph
         self.sets_of_cims_struct = None
+        self.single_set_of_cims = None
 
     def init_sets_cims_container(self):
-        self.sets_of_cims_struct = acims.SetsOfCimsContainer(self.net_graph.get_nodes(),
-                                                             self.net_graph.get_states_number_of_all_nodes_sorted(),
-                                                    self.net_graph.get_ordered_by_indx_parents_values_for_all_nodes())
+        self.sets_of_cims_struct = acims.SetsOfCimsContainer(self.net_graph.nodes,
+                                                             self.net_graph.nodes_values,
+                                                    self.net_graph.get_ordered_by_indx_parents_values_for_all_nodes(),
+                                                    self.net_graph.p_combs)
+
+    def fast_init(self, node_id: str):
+        """
+        Initializes all the necessary structures for the parameters estimation.
+
+        Parameters:
+            node_id: the node label
+        Returns:
+            void
+        """
+        p_vals = self.net_graph.aggregated_info_about_nodes_parents[2]
+        node_states_number = self.net_graph.get_states_number(node_id)
+        self.single_set_of_cims = sofc.SetOfCims(node_id, p_vals, node_states_number, self.net_graph.p_combs)
 
 
     def compute_parameters(self):
         #print(self.net_graph.get_nodes())
         #print(self.amalgamated_cims_struct.sets_of_cims)
         #enumerate(zip(self.net_graph.get_nodes(), self.amalgamated_cims_struct.sets_of_cims))
-        for indx, aggr in enumerate(zip(self.net_graph.get_nodes(), self.sets_of_cims_struct.sets_of_cims)):
+        for indx, aggr in enumerate(zip(self.net_graph.nodes, self.sets_of_cims_struct.sets_of_cims)):
             #print(self.net_graph.time_filtering[indx])
             #print(self.net_graph.time_scalar_indexing_strucure[indx])
             self.compute_state_res_time_for_node(self.net_graph.get_node_indx(aggr[0]), self.sample_path.trajectories.times,
@@ -43,75 +63,79 @@ class ParametersEstimator:
                                                       aggr[1].transition_matrices)
             aggr[1].build_cims(aggr[1].state_residence_times, aggr[1].transition_matrices)
 
-    def compute_parameters_for_node(self, node_id):
-        pos_index = self.net_graph.graph_struct.get_positional_node_indx(node_id)
+    def compute_parameters_for_node(self, node_id: str) -> sofc.SetOfCims:
+        """
+        Compute the CIMS of the node identified by the label node_id
+
+        Parameters:
+            node_id: the node label
+        Returns:
+            A setOfCims object filled with the computed CIMS
+        """
         node_indx = self.net_graph.get_node_indx(node_id)
-        #print("Nodes", self.net_graph.get_nodes())
+        state_res_times = self.single_set_of_cims.state_residence_times
+        transition_matrices = self.single_set_of_cims.transition_matrices
+        trajectory = self.sample_path.trajectories.trajectory
         self.compute_state_res_time_for_node(node_indx, self.sample_path.trajectories.times,
-                                             self.sample_path.trajectories.trajectory,
-                                             self.net_graph.time_filtering[pos_index],
-                                             self.net_graph.time_scalar_indexing_strucure[pos_index],
-                                             self.sets_of_cims_struct.sets_of_cims[pos_index].state_residence_times)
-        # print(self.net_graph.transition_filtering[indx])
-        # print(self.net_graph.transition_scalar_indexing_structure[indx])
+                                             trajectory,
+                                             self.net_graph.time_filtering,
+                                             self.net_graph.time_scalar_indexing_strucure,
+                                             state_res_times)
         self.compute_state_transitions_for_a_node(node_indx,
                                                   self.sample_path.trajectories.complete_trajectory,
-                                                  self.net_graph.transition_filtering[pos_index],
-                                                  self.net_graph.transition_scalar_indexing_structure[pos_index],
-                                                  self.sets_of_cims_struct.sets_of_cims[pos_index].transition_matrices)
-        self.sets_of_cims_struct.sets_of_cims[pos_index].build_cims(
-            self.sets_of_cims_struct.sets_of_cims[pos_index].state_residence_times,
-            self.sets_of_cims_struct.sets_of_cims[pos_index].transition_matrices)
-
-
-    def compute_state_res_time_for_node(self, node_indx, times, trajectory, cols_filter, scalar_indexes_struct, T):
-        #print(times.size)
-        #print(trajectory)
-        #print(cols_filter)
-        #print(scalar_indexes_struct)
-        #print(T)
+                                                  self.net_graph.transition_filtering,
+                                                  self.net_graph.transition_scalar_indexing_structure,
+                                                  transition_matrices)
+        self.single_set_of_cims.build_cims(state_res_times, transition_matrices)
+        return self.single_set_of_cims
+
+    def compute_state_res_time_for_node(self, node_indx: int, times: np.ndarray, trajectory: np.ndarray,
+                                        cols_filter: np.ndarray, scalar_indexes_struct: np.ndarray, T: np.ndarray):
+        """
+        Compute the state residence times for a node and fill the matrix T with the results
+
+        Parameters:
+            node_indx: the index of the node
+            times: the times deltas vector
+            trajectory: the trajectory
+            cols_filter: the columns filtering structure
+            scalar_indexes_struct: the indexing structure
+            T: the state residence times vectors
+        Returns:
+            void
+        """
         T[:] = np.bincount(np.sum(trajectory[:, cols_filter] * scalar_indexes_struct / scalar_indexes_struct[0], axis=1)
                            .astype(np.int), \
                            times,
                            minlength=scalar_indexes_struct[-1]).reshape(-1, T.shape[1])
-        #print("Done This NODE", T)
-
-    def compute_state_residence_time_for_all_nodes(self):
-        for node_indx, set_of_cims in enumerate(self.amalgamated_cims_struct.sets_of_cims):
-            self.compute_state_res_time_for_node(node_indx, self.sample_path.trajectories[0].get_times(),
-                self.sample_path.trajectories[0].get_trajectory(), self.columns_filtering_structure[node_indx],
-                    self.scalar_indexes_converter[node_indx], set_of_cims.state_residence_times)
-
 
     def compute_state_transitions_for_a_node(self, node_indx, trajectory, cols_filter, scalar_indexing, M):
-        #print(node_indx)
-        #print(trajectory)
-        #print(cols_filter)
-        #print(scalar_indexing)
-        #print(M)
+        """
+        Compute the state residence times for a node and fill the matrices M with the results
+
+        Parameters:
+            node_indx: the index of the node
+            times: the times deltas vector
+            trajectory: the trajectory
+            cols_filter: the columns filtering structure
+            scalar_indexes: the indexing structure
+            M: the state transition matrices
+        Returns:
+            void
+        """
         diag_indices = np.array([x * M.shape[1] + x % M.shape[1] for x in range(M.shape[0] * M.shape[1])],
                                 dtype=np.int64)
         trj_tmp = trajectory[trajectory[:, int(trajectory.shape[1] / 2) + node_indx].astype(np.int) >= 0]
-        #print(trj_tmp)
-        #print("Summing", np.sum(trj_tmp[:, cols_filter] * scalar_indexing / scalar_indexing[0], axis=1).astype(np.int))
-        #print(M.shape[1])
-        #print(M.shape[2])
-
         M[:] = np.bincount(np.sum(trj_tmp[:, cols_filter] * scalar_indexing / scalar_indexing[0], axis=1).astype(np.int),
                            minlength=scalar_indexing[-1]).reshape(-1, M.shape[1], M.shape[2])
         M_raveled = M.ravel()
         M_raveled[diag_indices] = 0
-        #print(M_raveled)
         M_raveled[diag_indices] = np.sum(M, axis=2).ravel()
-        #print(M_raveled)
 
-        #print(M)
 
-    def compute_state_transitions_for_all_nodes(self):
-        for node_indx, set_of_cims in enumerate(self.amalgamated_cims_struct.sets_of_cims):
-            self.compute_state_transitions_for_a_node(node_indx, self.sample_path.trajectories[0].get_complete_trajectory(),
-                 self.transition_filtering[node_indx],
-                    self.transition_scalar_index_converter[node_indx], set_of_cims.transition_matrices)
+
+
+
 
 
 

main_package/classes/sample_path.py

@@ -1,29 +1,41 @@
-
+import abstract_sample_path as asam
 import json_importer as imp
 import trajectory as tr
 import structure as st
 
 
-class SamplePath:
+class SamplePath(asam.AbstractSamplePath):
     """
-    Contiene l'aggregazione di una o più traiettorie e la struttura della rete.
-    Ha il compito dato di costruire tutte gli oggetti Trajectory e l'oggetto Structure
-    a partire dai dataframe contenuti in self.importer
+    Aggregates all the informations about the trajectories, the real structure of the sampled net and variables
+    cardinalites.
+    Has the task of creating the objects that will contain the mentioned data.
+    :importer: the Importer objects that will import ad process data
 
+    :trajectories: the Trajectory object that will contain all the concatenated trajectories
+    :structure: the Structure Object that will contain all the structurral infos about the net
+    :total_variables_count: the number of variables in the net
 
-    :importer: l'oggetto Importer che ha il compito di caricare i dataset
-    :trajectories: lista di oggetti Trajectories
-    :structure: oggetto Structure
     """
 
-    def __init__(self, files_path, samples_label, structure_label, variables_label, time_key, variables_key):
-        self.importer = imp.JsonImporter(files_path, samples_label, structure_label,
-                                         variables_label, time_key, variables_key)
-        self._trajectories = None
-        self._structure = None
+    #def __init__(self, files_path: str, samples_label: str, structure_label: str, variables_label: str, time_key: str,
+                 #variables_key: str):
+    def __init__(self, importer: imp.JsonImporter):
+        #self.importer =importer
+        super().__init__(importer)
+        #self._trajectories = None
+        #self._structure = None
         self.total_variables_count = None
 
     def build_trajectories(self):
+        """
+        Builds the Trajectory object that will contain all the trajectories.
+        Clears all the unused dataframes in Importer Object
+
+        Parameters:
+            void
+        Returns:
+            void
+        """
         self.importer.import_data()
         self._trajectories = \
             tr.Trajectory(self.importer.build_list_of_samples_array(self.importer.concatenated_samples),
@@ -32,8 +44,20 @@ class SamplePath:
         self.importer.clear_concatenated_frame()
 
     def build_structure(self):
+        """
+        Builds the Structure object that aggregates all the infos about the net.
+        Parameters:
+            void
+        Returns:
+            void
+        """
         self.total_variables_count = len(self.importer.sorter)
-        self._structure = st.Structure(self.importer.structure, self.importer.variables,
+        labels = self.importer.variables[self.importer.variables_key].to_list()
+        #print("SAMPLE PATH LABELS",labels)
+        indxs = self.importer.variables.index.to_numpy()
+        vals = self.importer.variables['Value'].to_numpy()
+        edges = list(self.importer.structure.to_records(index=False))
+        self._structure = st.Structure(labels, indxs, vals, edges,
                                        self.total_variables_count)
 
     @property
@@ -47,12 +71,6 @@ class SamplePath:
     def total_variables_count(self):
         return self.total_variables_count
 
-    """def build_possible_values_variables_structure(self):
-        possible_val_list = []
-        print(self.importer.variables)
-        for cardinality in self.importer.variables['Value']:
-            possible_val_list.append(list(range(0, cardinality)))
-        self.possible_variables_values = possible_val_list"""
 
 
 

main_package/classes/set_of_cims.py

@@ -1,27 +1,41 @@
 import numpy as np
+import typing
 import conditional_intensity_matrix as cim
 
 
 class SetOfCims:
     """
-    Rappresenta la struttura che aggrega tutte le CIM per la variabile di label node_id
+    Aggregates all the CIMS of the node identified by the label node_id.
 
-    :node_id: la label della varibile a cui fanno riferimento le CIM
-    :ordered_parent_set: il set dei parent della variabile node_id ordinata secondo la property indx
-    :value: il numero massimo di stati assumibili dalla variabile
-    :actual_cims: le CIM della varibile
+    :node_id: the node label
+    :parents_states_number: the cardinalities of the parents
+    :node_states_number: the caridinality of the node
+    :p_combs: the relative p_comb structure
+
+    :state_residence_time: matrix containing all the state residence time vectors for the node
+    :transition_matrices: matrix containing all the transition matrices for the node
+    :actaul_cims: the cims of the node
     """
 
-    def __init__(self, node_id, parents_states_number, node_states_number):
+    def __init__(self, node_id: str, parents_states_number: typing.List, node_states_number: int, p_combs: np.ndarray):
         self.node_id = node_id
         self.parents_states_number = parents_states_number
         self.node_states_number = node_states_number
         self.actual_cims = []
         self.state_residence_times = None
         self.transition_matrices = None
-        self.build_actual_cims_structure()
+        self.p_combs = p_combs
+        self.build_times_and_transitions_structures()
+
+    def build_times_and_transitions_structures(self):
+        """
+        Initializes at the correct dimensions the state residence times matrix and the state transition matrices
 
-    def build_actual_cims_structure(self):
+        Parameters:
+            void
+        Returns:
+            void
+        """
         if not self.parents_states_number:
             self.state_residence_times = np.zeros((1, self.node_states_number), dtype=np.float)
             self.transition_matrices = np.zeros((1,self.node_states_number, self.node_states_number), dtype=np.int)
@@ -31,41 +45,60 @@ class SetOfCims:
             self.transition_matrices = np.zeros([np.prod(self.parents_states_number), self.node_states_number,
                                                  self.node_states_number], dtype=np.int)
 
+    def build_cims(self, state_res_times: typing.List, transition_matrices: typing.List):
+        """
+        Build the ConditionalIntensityMatrix object given the state residence times and transitions matrices.
+        Compute the cim coefficients.
 
-    def get_cims_number(self):
-        return len(self.actual_cims)
-
-    def indexes_converter(self, indexes): # Si aspetta array del tipo [2,2] dove
-        assert len(indexes) == len(self.parents_states_number)
-        vector_index = 0
-        if not indexes:
-            return vector_index
-        else:
-            for indx, value in enumerate(indexes):
-                vector_index = vector_index*self.parents_states_number[indx] + indexes[indx]
-            return vector_index
-
-    def build_cims(self, state_res_times, transition_matrices):
+        Parameters:
+            state_res_times: the state residence times matrix
+            transition_matrices: the transition matrices
+        Returns:
+            void
+        """
         for state_res_time_vector, transition_matrix in zip(state_res_times, transition_matrices):
-            #print(state_res_time_vector, transition_matrix)
             cim_to_add = cim.ConditionalIntensityMatrix(state_res_time_vector, transition_matrix)
             cim_to_add.compute_cim_coefficients()
-            #print(cim_to_add)
             self.actual_cims.append(cim_to_add)
+        self.actual_cims = np.array(self.actual_cims)
         self.transition_matrices = None
         self.state_residence_times = None
 
+    def filter_cims_with_mask(self, mask_arr: np.ndarray, comb: typing.List) -> np.ndarray:
+        """
+        Filter the cims contained in the array actual_cims given the boolean mask mask_arr and the index comb.
+        Parameters:
+            mask_arr: the boolean mask
+            comb: the indexes of the selected cims
+
+        Returns:
+            Array of ConditionalIntensityMatrix
+        """
+        if mask_arr.size <= 1:
+            return self.actual_cims
+        else:
+            tmp_parents_comb_from_ids = np.argwhere(np.all(self.p_combs[:, mask_arr] == comb, axis=1)).ravel()
+            return self.actual_cims[tmp_parents_comb_from_ids]
+
+    @property
     def get_cims(self):
         return self.actual_cims
 
+    def get_cims_number(self):
+        return len(self.actual_cims)
+"""
     def get_cim(self, index):
         flat_index = self.indexes_converter(index)
         return self.actual_cims[flat_index]
 
+    def indexes_converter(self, indexes):
+        assert len(indexes) == len(self.parents_states_number)
+        vector_index = 0
+        if not indexes:
+            return vector_index
+        else:
+            for indx, value in enumerate(indexes):
+                vector_index = vector_index*self.parents_states_number[indx] + indexes[indx]
+            return vector_index"""
+
 
-"""sofc = SetOfCims('Z', [3, 3], 3)
-sofc.build_actual_cims_structure()
-print(sofc.actual_cims)
-print(sofc.actual_cims[0,0])
-print(sofc.actual_cims[1,2])
-#print(sofc.indexes_converter([]))"""

main_package/classes/sets_of_cims_container.py

@@ -1,21 +1,21 @@
 import set_of_cims as socim
 
 
-
 class SetsOfCimsContainer:
     """
     Aggrega un insieme di oggetti SetOfCims
     """
-    # list_of_vars_orders contiene tutte le liste con i parent ordinati secondo il valore indx
-    def __init__(self, list_of_keys, states_number_per_node, list_of_parents_states_number):
-        self.sets_of_cims = []
-        self.init_cims_structure(list_of_keys, states_number_per_node, list_of_parents_states_number)
+    def __init__(self, list_of_keys, states_number_per_node, list_of_parents_states_number, p_combs_list):
+        self.sets_of_cims = None
+        self.init_cims_structure(list_of_keys, states_number_per_node, list_of_parents_states_number, p_combs_list)
         #self.states_per_variable = states_number
 
-    def init_cims_structure(self, keys, states_number_per_node, list_of_parents_states_number):
-        for indx, key in enumerate(keys):
+    def init_cims_structure(self, keys, states_number_per_node, list_of_parents_states_number, p_combs_list):
+        """for indx, key in enumerate(keys):
             self.sets_of_cims.append(
-                socim.SetOfCims(key, list_of_parents_states_number[indx], states_number_per_node[indx]))
+                socim.SetOfCims(key, list_of_parents_states_number[indx], states_number_per_node[indx]))"""
+        self.sets_of_cims = [socim.SetOfCims(pair[1], list_of_parents_states_number[pair[0]], states_number_per_node[pair[0]], p_combs_list[pair[0]])
+                             for pair in enumerate(keys)]
 
     def get_set_of_cims(self, node_indx):
         return self.sets_of_cims[node_indx]
@@ -23,13 +23,3 @@ class SetsOfCimsContainer:
     def get_cims_of_node(self, node_indx, cim_indx):
         return self.sets_of_cims[node_indx].get_cim(cim_indx)
 
-"""
-    def get_vars_order(self, node):
-        return self.actual_cims[node][1]
-
-    def update_state_transition_for_matrix(self, node, which_matrix, element_indx):
-        self.sets_of_cims[node].update_state_transition(which_matrix, element_indx)
-
-    def update_state_residence_time_for_matrix(self, which_node, which_matrix, which_element, time):
-        self.sets_of_cims[which_node].update_state_residence_time(which_matrix, which_element, time)
-"""

main_package/classes/structure.py

@@ -1,64 +1,73 @@
+import typing as ty
 import numpy as np
 
+
 class Structure:
     """
-    Contiene tutte il informazioni sulla struttura della rete (connessione dei nodi, valori assumibili dalle variabili)
+    Contains all the infos about the network structure(nodes names, nodes caridinalites, edges...)
 
-    :structure_frame: il dataframe contenente le connessioni dei nodi della rete
-    :variables_frame: il data_frame contenente i valori assumibili dalle variabili e si suppone il corretto ordinamento
-    rispetto alle colonne del dataset
+    :nodes_labels_list: the symbolic names of the variables
+    :nodes_indexes_arr: the indexes of the nodes
+    :nodes_vals_arr: the cardinalites of the nodes
+    :edges_list: the edges of the network
+    :total_variables_number: the total number of variables in the net
     """
 
-    def __init__(self, structure, variables, total_variables_number):
-        self.structure_frame = structure
-        self.variables_frame = variables
-        self.total_variables_number = total_variables_number
-        self.name_label = variables.columns.values[0]
-        self.value_label = variables.columns.values[1]
+    def __init__(self, nodes_label_list: ty.List, node_indexes_arr: np.ndarray, nodes_vals_arr: np.ndarray,
+                 edges_list: ty.List, total_variables_number: int):
+        self._nodes_labels_list = nodes_label_list
+        self._nodes_indexes_arr = node_indexes_arr
+        self._nodes_vals_arr = nodes_vals_arr
+        self._edges_list = edges_list
+        self._total_variables_number = total_variables_number
 
-    def list_of_edges(self):
-        records = self.structure_frame.to_records(index=False)
-        edges_list = list(records)
-        return edges_list
+    @property
+    def edges(self):
+        #records = self.structure_frame.to_records(index=False)
+        #edges_list = list(records)
+        return self._edges_list
 
-    def list_of_nodes_labels(self):
-        return self.variables_frame[self.name_label].values.tolist()
+    @property
+    def nodes_labels(self):
+        return self._nodes_labels_list
 
-    def list_of_nodes_indexes(self):
-        return list(self.variables_frame.index)
+    @property
+    def nodes_indexes(self) -> np.ndarray:
+        return self._nodes_indexes_arr
 
-    def get_node_id(self, node_indx):
-        return self.variables_frame[self.name_label][node_indx]
+    @property
+    def nodes_values(self) -> np.ndarray:
+        return self._nodes_vals_arr
 
-    def get_node_indx(self, node_id):
-        return self.variables_frame[self.name_label][self.variables_frame[self.name_label] == node_id].index[0]
+    @property
+    def total_variables_number(self):
+        return self._total_variables_number
 
-    def get_positional_node_indx(self, node_id):
-        return np.flatnonzero(self.variables_frame[self.name_label] == node_id)[0]
+    def get_node_id(self, node_indx: int) -> str:
+        return self._nodes_labels_list[node_indx]
 
-    def get_states_number(self, node):
-        #print("node", node)
-        return self.variables_frame[self.value_label][self.get_node_indx(node)]
+    def get_node_indx(self, node_id: str) -> int:
+        pos_indx = self._nodes_labels_list.index(node_id)
+        return self._nodes_indexes_arr[pos_indx]
 
-    def get_states_number_by_indx(self, node_indx):
-        #print(self.value_label)
-        #print("Node indx", node_indx)
-        return self.variables_frame[self.value_label][node_indx]
+    def get_positional_node_indx(self, node_id: str) -> int:
+        return self._nodes_labels_list.index(node_id)
 
-    def total_variables_number(self):
-        return self.total_variables_number
+    def get_states_number(self, node: str) -> int:
+        pos_indx = self._nodes_labels_list.index(node)
+        return self._nodes_vals_arr[pos_indx]
 
     def __repr__(self):
-        return "Variables:\n" + str(self.variables_frame) + "\nEdges: \n" + str(self.structure_frame)
+        return "Variables:\n" + str(self._nodes_labels_list) +"\nValues:\n"+ str(self._nodes_vals_arr) +\
+               "\nEdges: \n" + str(self._edges_list)
 
     def __eq__(self, other):
         """Overrides the default implementation"""
         if isinstance(other, Structure):
-            return self.structure_frame.equals(other.structure_frame) and \
-                   self.variables_frame.equals(other.variables_frame)
+            return set(self._nodes_labels_list) == set(other._nodes_labels_list) and \
+                   np.array_equal(self._nodes_vals_arr, other._nodes_vals_arr) and \
+                   np.array_equal(self._nodes_indexes_arr, other._nodes_indexes_arr) and \
+                   self._edges_list == other._edges_list
+
         return NotImplemented
 
-    """def remove_node(self, node_id):
-        self.variables_frame = self.variables_frame[self.variables_frame.Name != node_id]
-        self.structure_frame = self.structure_frame[(self.structure_frame.From != node_id) &
-                                                    (self.structure_frame.To != node_id)]"""

main_package/classes/structure_estimator.py

@@ -1,161 +1,197 @@
-import pandas as pd
+
 import numpy as np
 import itertools
 import networkx as nx
+from networkx.readwrite import json_graph
+import json
+import typing
 from scipy.stats import f as f_dist
 from scipy.stats import chi2 as chi2_dist
 
 
-
 import sample_path as sp
 import structure as st
 import network_graph as ng
+import conditional_intensity_matrix as condim
 import parameters_estimator as pe
 import cache as ch
 
 
 class StructureEstimator:
+    """
+    Has the task of estimating the network structure given the trajectories in samplepath.
+
+    :sample_path: the sample_path object containing the trajectories and the real structure
+    :exp_test_sign: the significance level for the exponential Hp test
+    :chi_test_alfa: the significance level for the chi Hp test
+
+    :nodes: the nodes labels
+    :nodes_vals: the nodes cardinalities
+    :nodes_indxs: the nodes indexes
+    :complete_graph: the complete directed graph built using the nodes labels in nodes
+    :cache: the cache object
+    """
 
-    def __init__(self, sample_path, exp_test_alfa, chi_test_alfa):
+    def __init__(self, sample_path: sp.SamplePath, exp_test_alfa: float, chi_test_alfa: float):
         self.sample_path = sample_path
-        self.complete_graph_frame = self.build_complete_graph_frame(self.sample_path.structure.list_of_nodes_labels())
-        self.complete_graph = self.build_complete_graph(self.sample_path.structure.list_of_nodes_labels())
+        self.nodes = np.array(self.sample_path.structure.nodes_labels)
+        self.nodes_vals = self.sample_path.structure.nodes_values
+        self.nodes_indxs = self.sample_path.structure.nodes_indexes
+        self.complete_graph = self.build_complete_graph(self.sample_path.structure.nodes_labels)
         self.exp_test_sign = exp_test_alfa
         self.chi_test_alfa = chi_test_alfa
         self.cache = ch.Cache()
 
-    def build_complete_graph_frame(self, node_ids):
-        complete_frame = pd.DataFrame(itertools.permutations(node_ids, 2))
-        complete_frame.columns = ['From', 'To']
-        return complete_frame
+    def build_complete_graph(self, node_ids: typing.List):
+        """
+        Builds a complete directed graph (no self loops) given the nodes labels in the list node_ids:
 
-    def build_complete_graph(self, node_ids):
+        Parameters:
+            node_ids: the list of nodes labels
+        Returns:
+            a complete Digraph Object
+        """
         complete_graph = nx.DiGraph()
         complete_graph.add_nodes_from(node_ids)
         complete_graph.add_edges_from(itertools.permutations(node_ids, 2))
         return complete_graph
 
-    def complete_test(self, test_parent, test_child, parent_set):
+    def complete_test(self, test_parent: str, test_child: str, parent_set: typing.List, child_states_numb: int,
+                      tot_vars_count: int):
+        """
+        Permorms a complete independence test on the directed graphs G1 = test_child U parent_set
+        G2 = G1 U test_parent (added as an additional parent of the test_child).
+        Generates all the necessary structures and datas to perform the tests.
+
+        Parameters:
+            test_parent: the node label of the test parent
+            test_child: the node label of the child
+            parent_set: the common parent set
+            child_states_numb: the cardinality of the test_child
+            tot_vars_count_ the total number of variables in the net
+        Returns:
+            True iff test_child and test_parent are independent given the sep_set parent_set
+            False otherwise
+        """
+        #print("Test Parent:", test_parent)
+        #print("Sep Set", parent_set)
         p_set = parent_set[:]
         complete_info = parent_set[:]
-        complete_info.append(test_parent)
-        tmp_df = self.complete_graph_frame.loc[self.complete_graph_frame['To'].isin([test_child])]
-        #tmp_df = self.complete_graph_frame.loc[np.in1d(self.complete_graph_frame['To'], test_child)]
-        d2 = tmp_df.loc[tmp_df['From'].isin(complete_info)]
         complete_info.append(test_child)
-        v2 = self.sample_path.structure.variables_frame.loc[
-                self.sample_path.structure.variables_frame['Name'].isin(complete_info)]
-
-        #print(tmp_df)
-        #d1 = tmp_df.loc[tmp_df['From'].isin(parent_set)]
-        #parent_set.append(test_child)
-        #print(parent_set)
-        """v1 = self.sample_path.structure.variables_frame.loc[self.sample_path.structure.variables_frame['Name'].isin(parent_set)]
-        s1 = st.Structure(d1, v1, self.sample_path.total_variables_count)
-        g1 = ng.NetworkGraph(s1)
-        g1.init_graph()"""
 
-        #parent_set.append(test_parent)
-        """d2 = tmp_df.loc[tmp_df['From'].isin(parent_set)]
-        v2 = self.sample_path.structure.variables_frame.loc[self.sample_path.structure.variables_frame['Name'].isin(parent_set)]
-        s2 = st.Structure(d2, v2, self.sample_path.total_variables_count)
-        g2 = ng.NetworkGraph(s2)
-        g2.init_graph()"""
-        #parent_set.append(test_child)
-        sofc1 = None
-        #if not sofc1:
-        if not p_set:
-            sofc1 = self.cache.find(test_child)
+        parents = np.array(parent_set)
+        parents = np.append(parents, test_parent)
+        #print("PARENTS", parents)
+        #parents.sort()
+        sorted_parents = self.nodes[np.isin(self.nodes, parents)]
+        #print("SORTED PARENTS", sorted_parents)
+        cims_filter = sorted_parents != test_parent
+        #print("PARENTS NO FROM MASK", cims_filter)
+        #if not p_set:
+            #print("EMPTY PSET TRYING TO FIND", test_child)
+            #sofc1 = self.cache.find(test_child)
+        #else:
+        sofc1 = self.cache.find(set(p_set))
+
         if not sofc1:
-            #d1 = tmp_df.loc[tmp_df['From'].isin(parent_set)]
-            d1 = d2[d2.From != test_parent]
-
-            #v1 = self.sample_path.structure.variables_frame.loc[
-                #self.sample_path.structure.variables_frame['Name'].isin(parent_set)]
-            v1 = v2[v2.Name != test_parent]
-            #print("D1", d1)
-            #print("V1", v1)
-            s1 = st.Structure(d1, v1, self.sample_path.total_variables_count)
+            #print("CACHE MISSS SOFC1")
+            bool_mask1 = np.isin(self.nodes,complete_info)
+            #print("Bool mask 1", bool_mask1)
+            l1 = list(self.nodes[bool_mask1])
+            #print("L1", l1)
+            indxs1 = self.nodes_indxs[bool_mask1]
+            #print("INDXS 1", indxs1)
+            vals1 = self.nodes_vals[bool_mask1]
+            eds1 = list(itertools.product(parent_set,test_child))
+            s1 = st.Structure(l1, indxs1, vals1, eds1, tot_vars_count)
             g1 = ng.NetworkGraph(s1)
-            g1.init_graph()
+            g1.fast_init(test_child)
             p1 = pe.ParametersEstimator(self.sample_path, g1)
-            p1.init_sets_cims_container()
-            #print("Computing params for",test_child, test_parent, parent_set)
-            p1.compute_parameters_for_node(test_child)
-            sofc1 = p1.sets_of_cims_struct.sets_of_cims[s1.get_positional_node_indx(test_child)]
-            self.cache.put(test_child,sofc1)
+            p1.fast_init(test_child)
+            sofc1 = p1.compute_parameters_for_node(test_child)
+            #if not p_set:
+                #self.cache.put(test_child, sofc1)
+            #else:
+            self.cache.put(set(p_set), sofc1)
         sofc2 = None
-        p_set.append(test_parent)
+        #p_set.append(test_parent)
+        p_set.insert(0, test_parent)
         if p_set:
+            #print("FULL PSET TRYING TO FIND", p_set)
             #p_set.append(test_parent)
             #print("PSET ", p_set)
-            set_p_set = set(p_set)
-            sofc2 = self.cache.find(set_p_set)
-            #print("Sofc2 ", sofc2)
+            #set_p_set = set(p_set)
+            sofc2 = self.cache.find(set(p_set))
+            #if sofc2:
+                #print("Sofc2 in CACHE ", sofc2.actual_cims)
             #print(self.cache.list_of_sets_of_indxs)
-
-        """p2 = pe.ParametersEstimator(self.sample_path, g2)
-        p2.init_sets_cims_container()
-        #p2.compute_parameters()
-        p2.compute_parameters_for_node(test_child)
-        sofc2 = p2.sets_of_cims_struct.sets_of_cims[s2.get_positional_node_indx(test_child)]"""
-        if not sofc2 or p_set:
-            print("Cache Miss SOC2")
-            #parent_set.append(test_parent)
-            #d2 = tmp_df.loc[tmp_df['From'].isin(p_set)]
-            #v2 = self.sample_path.structure.variables_frame.loc[
-                #self.sample_path.structure.variables_frame['Name'].isin(parent_set)]
-            #print("D2", d2)
-            #print("V2", v2)
-            #s2 = st.Structure(d2, v2, self.sample_path.total_variables_count)
-            s2 = st.Structure(d2, v2, self.sample_path.total_variables_count)
+        if not sofc2:
+            #print("Cache MISSS SOFC2")
+            complete_info.append(test_parent)
+            bool_mask2 = np.isin(self.nodes, complete_info)
+            #print("BOOL MASK 2",bool_mask2)
+            l2 = list(self.nodes[bool_mask2])
+            #print("L2", l2)
+            indxs2 = self.nodes_indxs[bool_mask2]
+            #print("INDXS 2", indxs2)
+            vals2 = self.nodes_vals[bool_mask2]
+            eds2 = list(itertools.product(p_set, test_child))
+            s2 = st.Structure(l2, indxs2, vals2, eds2, tot_vars_count)
             g2 = ng.NetworkGraph(s2)
-            g2.init_graph()
+            g2.fast_init(test_child)
             p2 = pe.ParametersEstimator(self.sample_path, g2)
-            p2.init_sets_cims_container()
-            # p2.compute_parameters()
-            p2.compute_parameters_for_node(test_child)
-            sofc2 = p2.sets_of_cims_struct.sets_of_cims[s2.get_positional_node_indx(test_child)]
-            if p_set:
-                #set_p_set = set(p_set)
-                self.cache.put(set_p_set, sofc2)
-        end = 0
-        increment = self.sample_path.structure.get_states_number(test_parent)
-        for cim1 in sofc1.actual_cims:
-            start = end
-            end = start + increment
-            for j in range(start, end):
+            p2.fast_init(test_child)
+            sofc2 = p2.compute_parameters_for_node(test_child)
+            self.cache.put(set(p_set), sofc2)
+        for cim1, p_comb in zip(sofc1.actual_cims, sofc1.p_combs):
+            #print("GETTING THIS P COMB", p_comb)
+            #if len(parent_set) > 1:
+            cond_cims = sofc2.filter_cims_with_mask(cims_filter, p_comb)
+            #else:
+                #cond_cims = sofc2.actual_cims
+            #print("COnd Cims", cond_cims)
+            for cim2 in cond_cims:
                 #cim2 = sofc2.actual_cims[j]
                 #print(indx)
                 #print("Run Test", i, j)
-                if not self.independence_test(test_child, cim1, sofc2.actual_cims[j]):
+                if not self.independence_test(child_states_numb, cim1, cim2):
                     return False
         return True
 
-    def independence_test(self, tested_child, cim1, cim2):
-        # Fake exp test
-        r1s = cim1.state_transition_matrix.diagonal()
-        r2s = cim2.state_transition_matrix.diagonal()
-        F_stats = cim2.cim.diagonal() / cim1.cim.diagonal()
-        child_states_numb = self.sample_path.structure.get_states_number(tested_child)
-        for val in range(0, child_states_numb):  # i possibili valori di tested child TODO QUESTO CONTO DEVE ESSERE VETTORIZZATO
-            #r1 = cim1.state_transition_matrix[val][val]
-            #r2 = cim2.state_transition_matrix[val][val]
-            #print("No Test Parent:",cim1.cim[val][val],"With Test Parent", cim2.cim[val][val])
-            #F = cim2.cim[val][val] / cim1.cim[val][val]
-
-            #print("Exponential test", F_stats[val], r1s[val], r2s[val])
-            #print(f_dist.ppf(1 - self.exp_test_sign / 2, r1, r2))
-            #print(f_dist.ppf(self.exp_test_sign / 2, r1, r2))
-            if F_stats[val] < f_dist.ppf(self.exp_test_sign / 2, r1s[val], r2s[val]) or \
-                    F_stats[val] > f_dist.ppf(1 - self.exp_test_sign / 2, r1s[val], r2s[val]):
-                print("CONDITIONALLY DEPENDENT EXP")
+    def independence_test(self, child_states_numb: int, cim1: condim.ConditionalIntensityMatrix,
+                          cim2: condim.ConditionalIntensityMatrix):
+        """
+        Compute the actual independence test using two cims.
+        It is performed first the exponential test and if the null hypothesis is not rejected,
+        it is permormed also the chi_test.
+
+        Parameters:
+            child_states_numb: the cardinality of the test child
+            cim1: a cim belonging to the graph without test parent
+            cim2: a cim belonging to the graph with test parent
+
+        Returns:
+            True iff both tests do NOT reject the null hypothesis of indipendence
+            False otherwise
+        """
+        M1 = cim1.state_transition_matrix
+        M2 = cim2.state_transition_matrix
+        r1s = M1.diagonal()
+        r2s = M2.diagonal()
+        C1 = cim1.cim
+        C2 = cim2.cim
+        F_stats = C2.diagonal() / C1.diagonal()
+        exp_alfa = self.exp_test_sign
+        for val in range(0, child_states_numb):
+            if F_stats[val] < f_dist.ppf(exp_alfa / 2, r1s[val], r2s[val]) or \
+                    F_stats[val] > f_dist.ppf(1 - exp_alfa / 2, r1s[val], r2s[val]):
+                #print("CONDITIONALLY DEPENDENT EXP")
                 return False
-        # fake chi test
-        M1_no_diag = self.remove_diagonal_elements(cim1.state_transition_matrix)
-        M2_no_diag = self.remove_diagonal_elements(cim2.state_transition_matrix)
-        #print("M1 no diag", M1_no_diag)
-        #print("M2 no diag", M2_no_diag)
+        #M1_no_diag = self.remove_diagonal_elements(cim1.state_transition_matrix)
+        #M2_no_diag = self.remove_diagonal_elements(cim2.state_transition_matrix)
+        M1_no_diag = M1[~np.eye(M1.shape[0], dtype=bool)].reshape(M1.shape[0], -1)
+        M2_no_diag = M2[~np.eye(M2.shape[0], dtype=bool)].reshape(
+            M2.shape[0], -1)
         chi_2_quantile = chi2_dist.ppf(1 - self.chi_test_alfa, child_states_numb - 1)
         """
         Ks = np.sqrt(cim1.state_transition_matrix.diagonal() / cim2.state_transition_matrix.diagonal())
@@ -174,46 +210,52 @@ class StructureEstimator:
             #print("Chi Quantile", chi_2_quantile)
             if Chi > chi_2_quantile:
         #if np.any(chi_stats > chi_2_quantile):
-                print("CONDITIONALLY DEPENDENT CHI")
+                #print("CONDITIONALLY DEPENDENT CHI")
                 return False
             #print("Chi test", Chi)
         return True
 
-    def one_iteration_of_CTPC_algorithm(self, var_id):
+    def one_iteration_of_CTPC_algorithm(self, var_id: str, tot_vars_count: int):
+        """
+        Performs an iteration of the CTPC algorithm using the node var_id as test_child.
+
+        Parameters:
+            var_id: the node label of the test child
+            tot_vars_count: the number of nodes in the net
+        Returns:
+            void
+        """
+        print("##################TESTING VAR################", var_id)
         u = list(self.complete_graph.predecessors(var_id))
-        tests_parents_numb = len(u)
-        #print(u)
+        #tests_parents_numb = len(u)
+        #complete_frame = self.complete_graph_frame
+        #test_frame = complete_frame.loc[complete_frame['To'].isin([var_id])]
+        child_states_numb = self.sample_path.structure.get_states_number(var_id)
         b = 0
-        #parent_indx = 0
         while b < len(u):
             #for parent_id in u:
             parent_indx = 0
-            while u and parent_indx < tests_parents_numb and b < len(u):
-                # list_without_test_parent = u.remove(parent_id)
+            while parent_indx < len(u):
+                #print("Parent_indx",parent_indx)
+                #print("LEN U", len(u))
+
                 removed = False
-                #print("b", b)
-                #print("Parent Indx", parent_indx)
                 #if not list(self.generate_possible_sub_sets_of_size(u, b, u[parent_indx])):
                     #break
                 S = self.generate_possible_sub_sets_of_size(u, b, u[parent_indx])
                 #print("U Set", u)
                 #print("S", S)
+                test_parent = u[parent_indx]
+                #print("Test Parent", test_parent)
                 for parents_set in S:
                     #print("Parent Set", parents_set)
-                    #print("Test Parent", u[parent_indx])
-                    if self.complete_test(u[parent_indx], var_id, parents_set):
-                        #print("Removing EDGE:", u[parent_indx], var_id)
-                        self.complete_graph.remove_edge(u[parent_indx], var_id)
-                        #print(self.complete_graph_frame)
-                        """self.complete_graph_frame = \
-                            self.complete_graph_frame.drop(
-                                self.complete_graph_frame[(self.complete_graph_frame.From ==
-                                                     u[parent_indx]) & (self.complete_graph_frame.To == var_id)].index)"""
-                        self.complete_graph_frame.drop(self.complete_graph_frame[(self.complete_graph_frame.From == u[parent_indx]) & (self.complete_graph_frame.To == var_id)].index)
-                        #print(self.complete_graph_frame)
-                        #u.remove(u[parent_indx])
-                        del u[parent_indx]
+                    #print("Test Parent", test_parent)
+                    if self.complete_test(test_parent, var_id, parents_set, child_states_numb, tot_vars_count):
+                        #print("Removing EDGE:", test_parent, var_id)
+                        self.complete_graph.remove_edge(test_parent, var_id)
+                        u.remove(test_parent)
                         removed = True
+                        break
                     #else:
                         #parent_indx += 1
                 if not removed:
@@ -221,23 +263,55 @@ class StructureEstimator:
             b += 1
         self.cache.clear()
 
-    def generate_possible_sub_sets_of_size(self, u, size, parent_id):
-        #print("Inside Generate subsets", u)
-        #print("InsideGenerate Subsets", parent_id)
+    def generate_possible_sub_sets_of_size(self, u: typing.List, size: int, parent_label: str):
+        """
+        Creates a list containing all possible subsets of the list u of size size,
+        that do not contains a the node identified by parent_label.
+
+        Parameters:
+            u: the list of nodes
+            size: the size of the subsets
+            parent_label: the nodes to exclude in the subsets generation
+        Returns:
+            a Map Object containing a list of lists
+
+        """
         list_without_test_parent = u[:]
-        list_without_test_parent.remove(parent_id)
-        # u.remove(parent_id)
-        #print(list(map(list, itertools.combinations(list_without_test_parent, size))))
+        list_without_test_parent.remove(parent_label)
         return map(list, itertools.combinations(list_without_test_parent, size))
 
+    def ctpc_algorithm(self):
+        """
+        Compute the CTPC algorithm.
+        Parameters:
+            void
+        Returns:
+            void
+        """
+        ctpc_algo = self.one_iteration_of_CTPC_algorithm
+        total_vars_numb = self.sample_path.total_variables_count
+        [ctpc_algo(n, total_vars_numb) for n in self.nodes]
+
+    def save_results(self):
+        """
+        Save the estimated Structure to a .json file
+
+        Parameters:
+            void
+        Returns:
+            void
+        """
+        res = json_graph.node_link_data(self.complete_graph)
+        name = self.sample_path.importer.file_path.rsplit('/',1)[-1]
+        #print(name)
+        name = 'results_' + name
+        with open(name, 'w') as f:
+            json.dump(res, f)
+
+
     def remove_diagonal_elements(self, matrix):
         m = matrix.shape[0]
         strided = np.lib.stride_tricks.as_strided
         s0, s1 = matrix.strides
         return strided(matrix.ravel()[1:], shape=(m - 1, m), strides=(s0 + s1, s1)).reshape(m, -1)
 
-    def ctpc_algorithm(self):
-        for node_id in self.sample_path.structure.list_of_nodes_labels():
-            print("TESTING VAR:", node_id)
-            self.one_iteration_of_CTPC_algorithm(node_id)
-

main_package/classes/trajectory.py

@@ -4,30 +4,41 @@ import numpy as np
 
 class Trajectory:
     """ 
-    Rappresenta una traiettoria come un numpy_array contenente n-ple (indx, T_k,S_i,.....,Sj)
-    Offre i metodi utili alla computazione sulla struttura stessa.
+    Abstracts the infos about a complete set of trajectories, represented as a numpy array of doubles and a numpy matrix
+    of ints.
 
-    Una Trajectory viene costruita a partire da una lista di numpyarray dove ogni elemento rappresenta una colonna
-    della traj
-
-    :actual_trajectory: il numpy_array contenente la successione di n-ple (indx, T_k,S_i,.....,Sj)
+    :list_of_columns: the list containing the times array and values matrix
+    :original_cols_numb: total number of cols in the data
+    :actual_trajectory: the trajectory containing also the duplicated and shifted values
+    :times: the array containing the time deltas
 
     """
 
     def __init__(self, list_of_columns, original_cols_number):
         if type(list_of_columns[0][0]) != np.float64:
             raise TypeError('The first array in the list has to be Times')
-        #TODO valutare se vale la pena ordinare la lista di numpy array per tipo
         self.original_cols_number = original_cols_number
         self._actual_trajectory = np.array(list_of_columns[1:], dtype=np.int).T
         self._times = np.array(list_of_columns[0], dtype=np.float)
 
     @property
-    def trajectory(self):
+    def trajectory(self) -> np.ndarray:
+        """
+        Parameters:
+            void
+        Returns:
+            a numpy matrix containing ONLY the original columns values, not the shifted ones
+        """
         return self._actual_trajectory[:, :self.original_cols_number]
 
     @property
-    def complete_trajectory(self):
+    def complete_trajectory(self) -> np.ndarray:
+        """
+                Parameters:
+                    void
+                Returns:
+                    a numpy matrix containing all the values
+                """
         return self._actual_trajectory
 
     @property

main_package/tests/test_cache.py

@@ -0,0 +1,61 @@
+import unittest
+import numpy as np
+
+import cache as ch
+import set_of_cims as soci
+
+
+class TestCache(unittest.TestCase):
+
+    def test_init(self):
+        c1 = ch.Cache()
+        self.assertFalse(c1.list_of_sets_of_parents)
+        self.assertFalse(c1.actual_cache)
+
+    def test_put(self):
+        c1 = ch.Cache()
+        pset1 = {'X', 'Y'}
+        sofc1 = soci.SetOfCims('Z', [], 3, np.array([]))
+        c1.put(pset1, sofc1)
+        self.assertEqual(1, len(c1.actual_cache))
+        self.assertEqual(1, len(c1.list_of_sets_of_parents))
+        self.assertEqual(sofc1, c1.actual_cache[0])
+        pset2 = {'X'}
+        sofc2 = soci.SetOfCims('Z', [], 3, np.array([]))
+        c1.put(pset2, sofc2)
+        self.assertEqual(2, len(c1.actual_cache))
+        self.assertEqual(2, len(c1.list_of_sets_of_parents))
+        self.assertEqual(sofc2, c1.actual_cache[1])
+
+    def test_find(self):
+        c1 = ch.Cache()
+        pset1 = {'X', 'Y'}
+        sofc1 = soci.SetOfCims('Z', [], 3, np.array([]))
+        c1.put(pset1, sofc1)
+        self.assertEqual(1, len(c1.actual_cache))
+        self.assertEqual(1, len(c1.list_of_sets_of_parents))
+        self.assertIsInstance(c1.find(pset1), soci.SetOfCims)
+        self.assertEqual(sofc1, c1.find(pset1))
+        self.assertIsInstance(c1.find({'Y', 'X'}), soci.SetOfCims)
+        self.assertEqual(sofc1, c1.find({'Y', 'X'}))
+        self.assertIsNone(c1.find({'X'}))
+
+    def test_clear(self):
+        c1 = ch.Cache()
+        pset1 = {'X', 'Y'}
+        sofc1 = soci.SetOfCims('Z', [], 3, np.array([]))
+        c1.put(pset1, sofc1)
+        self.assertEqual(1, len(c1.actual_cache))
+        self.assertEqual(1, len(c1.list_of_sets_of_parents))
+        c1.clear()
+        self.assertFalse(c1.list_of_sets_of_parents)
+        self.assertFalse(c1.actual_cache)
+
+
+
+
+
+
+
+if __name__ == '__main__':
+    unittest.main()

main_package/tests/test_json_importer.py

@@ -1,25 +1,32 @@
 import sys
 sys.path.append("/Users/Zalum/Desktop/Tesi/CTBN_Project/main_package/classes/")
 import unittest
+import os
+import glob
 import numpy as np
 import pandas as pd
 import json_importer as ji
 
+from line_profiler import LineProfiler
+
 import os
 import json
 
 
 class TestJsonImporter(unittest.TestCase):
 
+    @classmethod
+    def setUpClass(cls) -> None:
+        cls.read_files = glob.glob(os.path.join('../data', "*.json"))
+
     def test_init(self):
-        path = os.getcwd()
-        j1 = ji.JsonImporter(path, 'samples', 'dyn.str', 'variables', 'Time', 'Name')
+        j1 = ji.JsonImporter(self.read_files[0], 'samples', 'dyn.str', 'variables', 'Time', 'Name')
         self.assertEqual(j1.samples_label, 'samples')
         self.assertEqual(j1.structure_label, 'dyn.str')
         self.assertEqual(j1.variables_label, 'variables')
         self.assertEqual(j1.time_key, 'Time')
         self.assertEqual(j1.variables_key, 'Name')
-        self.assertEqual(j1.files_path, path)
+        self.assertEqual(j1.file_path, self.read_files[0])
         self.assertFalse(j1.df_samples_list)
         self.assertTrue(j1.variables.empty)
         self.assertTrue(j1.structure.empty)
@@ -31,6 +38,7 @@ class TestJsonImporter(unittest.TestCase):
         with open('data.json', 'w') as f:
             json.dump(data_set, f)
         path = os.getcwd()
+        path = path + '/data.json'
         j1 = ji.JsonImporter(path, '', '', '', '', '')
         imported_data = j1.read_json_file()
         self.assertTrue(self.ordered(data_set) == self.ordered(imported_data))
@@ -38,28 +46,30 @@ class TestJsonImporter(unittest.TestCase):
 
     def test_read_json_file_not_found(self):
         path = os.getcwd()
+        path = path + '/data.json'
         j1 = ji.JsonImporter(path, '', '', '', '', '')
-        self.assertIsNone(j1.read_json_file())
+        self.assertRaises(FileNotFoundError, j1.read_json_file)
 
     def test_normalize_trajectories(self):
-        j1 = ji.JsonImporter('../data', 'samples', 'dyn.str', 'variables', 'Time', 'Name')
+        j1 = ji.JsonImporter(self.read_files[0], 'samples', 'dyn.str', 'variables', 'Time', 'Name')
         raw_data = j1.read_json_file()
+        #print(raw_data)
         j1.normalize_trajectories(raw_data, 0, j1.samples_label)
         self.assertEqual(len(j1.df_samples_list), len(raw_data[0][j1.samples_label]))
         self.assertEqual(list(j1.df_samples_list[0].columns.values)[1:], j1.sorter)
 
     def test_normalize_trajectories_wrong_indx(self):
-        j1 = ji.JsonImporter('../data', 'samples', 'dyn.str', 'variables', 'Time', 'Name')
+        j1 = ji.JsonImporter(self.read_files[0], 'samples', 'dyn.str', 'variables', 'Time', 'Name')
         raw_data = j1.read_json_file()
-        self.assertRaises(IndexError, j1.normalize_trajectories, raw_data, 1, j1.samples_label)
+        self.assertRaises(IndexError, j1.normalize_trajectories, raw_data, 474, j1.samples_label)
 
     def test_normalize_trajectories_wrong_key(self):
-        j1 = ji.JsonImporter('../data', 'sample', 'dyn.str', 'variables', 'Time', 'Name')
+        j1 = ji.JsonImporter(self.read_files[0], 'sample', 'dyn.str', 'variables', 'Time', 'Name')
         raw_data = j1.read_json_file()
         self.assertRaises(KeyError, j1.normalize_trajectories, raw_data, 0, j1.samples_label)
 
     def test_compute_row_delta_single_samples_frame(self):
-        j1 = ji.JsonImporter('../data', 'samples', 'dyn.str', 'variables', 'Time', 'Name')
+        j1 = ji.JsonImporter(self.read_files[0], 'samples', 'dyn.str', 'variables', 'Time', 'Name')
         raw_data = j1.read_json_file()
         j1.normalize_trajectories(raw_data, 0, j1.samples_label)
         sample_frame = j1.df_samples_list[0]
@@ -72,14 +82,15 @@ class TestJsonImporter(unittest.TestCase):
         self.assertEqual(sample_frame.shape[0] - 1, new_sample_frame.shape[0])
 
     def test_compute_row_delta_in_all_frames(self):
-        j1 = ji.JsonImporter('../data', 'samples', 'dyn.str', 'variables', 'Time', 'Name')
+        j1 = ji.JsonImporter(self.read_files[0], 'samples', 'dyn.str', 'variables', 'Time', 'Name')
         raw_data = j1.read_json_file()
         j1.import_trajectories(raw_data)
         j1.compute_row_delta_in_all_samples_frames(j1.time_key)
         self.assertEqual(list(j1.df_samples_list[0].columns.values), list(j1.concatenated_samples.columns.values))
+        self.assertEqual(list(j1.concatenated_samples.columns.values)[0], j1.time_key)
 
     def test_clear_data_frame_list(self):
-        j1 = ji.JsonImporter('../data', 'samples', 'dyn.str', 'variables', 'Time', 'Name')
+        j1 = ji.JsonImporter(self.read_files[0], 'samples', 'dyn.str', 'variables', 'Time', 'Name')
         raw_data = j1.read_json_file()
         j1.import_trajectories(raw_data)
         j1.compute_row_delta_in_all_samples_frames(j1.time_key)
@@ -92,6 +103,7 @@ class TestJsonImporter(unittest.TestCase):
         with open('data.json', 'w') as f:
             json.dump(data_set, f)
         path = os.getcwd()
+        path = path + '/data.json'
         j1 = ji.JsonImporter(path, '', '', '', '', '')
         raw_data = j1.read_json_file()
         frame = pd.DataFrame(raw_data)
@@ -104,15 +116,20 @@ class TestJsonImporter(unittest.TestCase):
         os.remove('data.json')
 
     def test_import_variables(self):
-        j1 = ji.JsonImporter('../data', 'samples', 'dyn.str', 'variables', 'Time', 'Name')
+        j1 = ji.JsonImporter(self.read_files[0], 'samples', 'dyn.str', 'variables', 'Time', 'Name')
         sorter = ['X', 'Y', 'Z']
         raw_data = [{'variables':{"Name": ['Z', 'Y', 'X'], "value": [3, 3, 3]}}]
         j1.import_variables(raw_data, sorter)
         self.assertEqual(list(j1.variables[j1.variables_key]), sorter)
 
     def test_import_data(self):
-        j1 = ji.JsonImporter('../data', 'samples', 'dyn.str', 'variables', 'Time', 'Name')
-        j1.import_data()
+        j1 = ji.JsonImporter(self.read_files[0], 'samples', 'dyn.str', 'variables', 'Time', 'Name')
+        lp = LineProfiler()
+
+        lp_wrapper = lp(j1.import_data)
+        lp_wrapper()
+        lp.print_stats()
+        #j1.import_data()
         self.assertEqual(list(j1.variables[j1.variables_key]),
                          list(j1.concatenated_samples.columns.values[1:len(j1.variables[j1.variables_key]) + 1]))
         print(j1.variables)

main_package/tests/test_networkgraph.py

@@ -1,16 +1,23 @@
 import unittest
+import glob
+import os
 import networkx as nx
 import numpy as np
+import itertools
 from line_profiler import LineProfiler
 
 import sample_path as sp
 import network_graph as ng
+import json_importer as ji
+
 
 
 class TestNetworkGraph(unittest.TestCase):
     @classmethod
     def setUpClass(cls):
-        cls.s1 = sp.SamplePath('../data', 'samples', 'dyn.str', 'variables', 'Time', 'Name')
+        cls.read_files = glob.glob(os.path.join('../data', "*.json"))
+        cls.importer = ji.JsonImporter(cls.read_files[0], 'samples', 'dyn.str', 'variables', 'Time', 'Name')
+        cls.s1 = sp.SamplePath(cls.importer)
         cls.s1.build_trajectories()
         cls.s1.build_structure()
 
@@ -18,26 +25,26 @@ class TestNetworkGraph(unittest.TestCase):
         g1 = ng.NetworkGraph(self.s1.structure)
         self.assertEqual(self.s1.structure, g1.graph_struct)
         self.assertIsInstance(g1.graph, nx.DiGraph)
-        #TODO MANCANO TUTTI I TEST DI INIZIALIZZAZIONE DEI DATI PRIVATI della classe aggiungere le property necessarie
+        self.assertTrue(np.array_equal(g1._nodes_indexes, self.s1.structure.nodes_indexes))
+        self.assertListEqual(g1._nodes_labels, self.s1.structure.nodes_labels)
+        self.assertTrue(np.array_equal(g1._nodes_values, self.s1.structure.nodes_values))
+        self.assertIsNone(g1._fancy_indexing)
+        self.assertIsNone(g1.time_scalar_indexing_strucure)
+        self.assertIsNone(g1.transition_scalar_indexing_structure)
+        self.assertIsNone(g1.transition_filtering)
+        self.assertIsNone(g1.p_combs)
 
     def test_add_nodes(self):
         g1 = ng.NetworkGraph(self.s1.structure)
-        g1.add_nodes(self.s1.structure.list_of_nodes_labels())
-        for n1, n2 in zip(g1.get_nodes(), self.s1.structure.list_of_nodes_labels()):
+        g1.add_nodes(self.s1.structure.nodes_labels)
+        for n1, n2 in zip(g1.nodes, self.s1.structure.nodes_labels):
             self.assertEqual(n1, n2)
 
     def test_add_edges(self):
         g1 = ng.NetworkGraph(self.s1.structure)
-        g1.add_edges(self.s1.structure.list_of_edges())
-        for e in self.s1.structure.list_of_edges():
-            self.assertIn(tuple(e), g1.get_edges())
-
-    """def test_get_ordered_by_indx_set_of_parents(self):
-        g1 = ng.NetworkGraph(self.s1.structure)
-        g1.add_nodes(self.s1.structure.list_of_nodes_labels())
-        g1.add_edges(self.s1.structure.list_of_edges())
-        sorted_par_list_aggregated_info = g1.get_ordered_by_indx_set_of_parents(g1.get_nodes()[2])
-        self.test_aggregated_par_list_data(g1, g1.get_nodes()[2], sorted_par_list_aggregated_info)"""
+        g1.add_edges(self.s1.structure.edges)
+        for e in self.s1.structure.edges:
+            self.assertIn(tuple(e), g1.edges)
 
     def aux_aggregated_par_list_data(self, graph, node_id, sorted_par_list_aggregated_info):
         for indx, element in enumerate(sorted_par_list_aggregated_info):
@@ -55,12 +62,12 @@ class TestNetworkGraph(unittest.TestCase):
 
     def test_get_ord_set_of_par_of_all_nodes(self):
         g1 = ng.NetworkGraph(self.s1.structure)
-        g1.add_nodes(self.s1.structure.list_of_nodes_labels())
-        g1.add_edges(self.s1.structure.list_of_edges())
+        g1.add_nodes(self.s1.structure.nodes_labels)
+        g1.add_edges(self.s1.structure.edges)
         sorted_list_of_par_lists = g1.get_ord_set_of_par_of_all_nodes()
-        for node, par_list in zip(g1.get_nodes_sorted_by_indx(), sorted_list_of_par_lists):
+        for node, par_list in zip(g1.nodes, sorted_list_of_par_lists):
             self.aux_aggregated_par_list_data(g1, node, par_list)
-
+    """
     def test_get_ordered_by_indx_parents_values_for_all_nodes(self):
         g1 = ng.NetworkGraph(self.s1.structure)
         g1.add_nodes(self.s1.structure.list_of_nodes_labels())
@@ -89,67 +96,67 @@ class TestNetworkGraph(unittest.TestCase):
             self.assertEqual(par_indxs, aggr[1])
 
     def test_build_fancy_indexing_structure_offset(self):
-        pass #TODO il codice di netgraph deve gestire questo caso
+        pass #TODO il codice di netgraph deve gestire questo caso"""
 
-    def aux_build_time_scalar_indexing_structure_for_a_node(self, graph, node_indx, parents_indxs):
-        time_scalar_indexing = graph.build_time_scalar_indexing_structure_for_a_node(node_indx, parents_indxs)
+    def aux_build_time_scalar_indexing_structure_for_a_node(self, graph, node_id, parents_indxs, parents_labels, parents_vals):
+        time_scalar_indexing = graph.build_time_scalar_indexing_structure_for_a_node(node_id, parents_vals)
         self.assertEqual(len(time_scalar_indexing), len(parents_indxs) + 1)
-        merged_list = parents_indxs[:]
-        merged_list.insert(0, node_indx)
-        #print(merged_list)
+        merged_list = parents_labels[:]
+        merged_list.insert(0, node_id)
         vals_list = []
         for node in merged_list:
-            vals_list.append(graph.get_states_number_by_indx(node))
+            vals_list.append(graph.get_states_number(node))
         t_vec = np.array(vals_list)
         t_vec = t_vec.cumprod()
-        #print(t_vec)
         self.assertTrue(np.array_equal(time_scalar_indexing, t_vec))
 
-    def aux_build_transition_scalar_indexing_structure_for_a_node(self, graph, node_indx, parents_indxs):
-        transition_scalar_indexing = graph.build_transition_scalar_indexing_structure_for_a_node(node_indx,
-                                                                                                 parents_indxs)
-        print(transition_scalar_indexing)
+    def aux_build_transition_scalar_indexing_structure_for_a_node(self, graph, node_id, parents_indxs, parents_labels,
+                                                                  parents_values):
+        transition_scalar_indexing = graph.build_transition_scalar_indexing_structure_for_a_node(node_id,
+                                                                                                 parents_values)
         self.assertEqual(len(transition_scalar_indexing), len(parents_indxs) + 2)
-        merged_list = parents_indxs[:]
-        merged_list.insert(0, node_indx)
-        merged_list.insert(0, node_indx)
+        merged_list = parents_labels[:]
+        merged_list.insert(0, node_id)
+        merged_list.insert(0, node_id)
         vals_list = []
-        for node in merged_list:
-            vals_list.append(graph.get_states_number_by_indx(node))
+        for node_id in merged_list:
+            vals_list.append(graph.get_states_number(node_id))
         m_vec = np.array([vals_list])
         m_vec = m_vec.cumprod()
         self.assertTrue(np.array_equal(transition_scalar_indexing, m_vec))
 
     def test_build_transition_scalar_indexing_structure(self):
         g1 = ng.NetworkGraph(self.s1.structure)
-        g1.add_nodes(self.s1.structure.list_of_nodes_labels())
-        g1.add_edges(self.s1.structure.list_of_edges())
+        g1.add_nodes(self.s1.structure.nodes_labels)
+        g1.add_edges(self.s1.structure.edges)
         g1.aggregated_info_about_nodes_parents = g1.get_ord_set_of_par_of_all_nodes()
+        p_labels = [i[0] for i in g1.aggregated_info_about_nodes_parents]
+        p_vals = g1.get_ordered_by_indx_parents_values_for_all_nodes()
         fancy_indx = g1.build_fancy_indexing_structure(0)
-        print(fancy_indx)
-        for node_id, p_indxs in zip(g1.graph_struct.list_of_nodes_indexes(), fancy_indx):
-            self.aux_build_transition_scalar_indexing_structure_for_a_node(g1, node_id, p_indxs)
+        for node_id, p_i ,p_l, p_v in zip(g1.graph_struct.nodes_labels, fancy_indx, p_labels, p_vals):
+            self.aux_build_transition_scalar_indexing_structure_for_a_node(g1, node_id, p_i ,p_l, p_v)
 
     def test_build_time_scalar_indexing_structure(self):
         g1 = ng.NetworkGraph(self.s1.structure)
-        g1.add_nodes(self.s1.structure.list_of_nodes_labels())
-        g1.add_edges(self.s1.structure.list_of_edges())
+        g1.add_nodes(self.s1.structure.nodes_labels)
+        g1.add_edges(self.s1.structure.edges)
         g1.aggregated_info_about_nodes_parents = g1.get_ord_set_of_par_of_all_nodes()
         fancy_indx = g1.build_fancy_indexing_structure(0)
+        p_labels = [i[0] for i in g1.aggregated_info_about_nodes_parents]
+        p_vals = g1.get_ordered_by_indx_parents_values_for_all_nodes()
         #print(fancy_indx)
-        for node_id, p_indxs in zip(g1.graph_struct.list_of_nodes_indexes(), fancy_indx):
-            self.aux_build_time_scalar_indexing_structure_for_a_node(g1, node_id, p_indxs)
-
+        for node_id, p_indxs, p_labels, p_v in zip(g1.graph_struct.nodes_labels, fancy_indx, p_labels, p_vals):
+            self.aux_build_time_scalar_indexing_structure_for_a_node(g1, node_id, p_indxs, p_labels, p_v)
+#TODO Sei arrivato QUI
     def test_build_time_columns_filtering_structure(self):
         g1 = ng.NetworkGraph(self.s1.structure)
-        g1.add_nodes(self.s1.structure.list_of_nodes_labels())
-        g1.add_edges(self.s1.structure.list_of_edges())
+        g1.add_nodes(self.s1.structure.nodes_labels)
+        g1.add_edges(self.s1.structure.edges)
         g1.aggregated_info_about_nodes_parents = g1.get_ord_set_of_par_of_all_nodes()
         g1._fancy_indexing = g1.build_fancy_indexing_structure(0)
         g1.build_time_columns_filtering_structure()
-        print(g1.time_filtering)
         t_filter = []
-        for node_id, p_indxs in zip(g1.get_nodes_sorted_by_indx(), g1._fancy_indexing):
+        for node_id, p_indxs in zip(g1.nodes, g1._fancy_indexing):
             single_filter = []
             single_filter.append(g1.get_node_indx(node_id))
             single_filter.extend(p_indxs)
@@ -160,41 +167,72 @@ class TestNetworkGraph(unittest.TestCase):
 
     def test_build_transition_columns_filtering_structure(self):
         g1 = ng.NetworkGraph(self.s1.structure)
-        g1.add_nodes(self.s1.structure.list_of_nodes_labels())
-        g1.add_edges(self.s1.structure.list_of_edges())
+        g1.add_nodes(self.s1.structure.nodes_labels)
+        g1.add_edges(self.s1.structure.edges)
         g1.aggregated_info_about_nodes_parents = g1.get_ord_set_of_par_of_all_nodes()
         g1._fancy_indexing = g1.build_fancy_indexing_structure(0)
         g1.build_transition_columns_filtering_structure()
-        print(g1.transition_filtering)
         m_filter = []
-        for node_id, p_indxs in zip(g1.get_nodes_sorted_by_indx(), g1._fancy_indexing):
+        for node_id, p_indxs in zip(g1.nodes, g1._fancy_indexing):
             single_filter = []
             single_filter.append(g1.get_node_indx(node_id) + g1.graph_struct.total_variables_number)
             single_filter.append(g1.get_node_indx(node_id))
             single_filter.extend(p_indxs)
             m_filter.append(np.array(single_filter))
-        print(m_filter)
         for a1, a2 in zip(g1.transition_filtering, m_filter):
             self.assertTrue(np.array_equal(a1, a2))
 
-    def test_init_graph(self):
+    def test_build_p_combs_structure(self):
         g1 = ng.NetworkGraph(self.s1.structure)
-        lp = LineProfiler()
-        lp.add_function(g1.get_ordered_by_indx_set_of_parents)
-        lp_wrapper = lp(g1.init_graph)
-        lp_wrapper()
-        lp.print_stats()
-
-    """def test_remove_node(self):
+        g1.add_nodes(self.s1.structure.nodes_labels)
+        g1.add_edges(self.s1.structure.edges)
+        g1.aggregated_info_about_nodes_parents = g1.get_ord_set_of_par_of_all_nodes()
+        p_vals = g1.get_ordered_by_indx_parents_values_for_all_nodes()
+        p_combs = g1.build_p_combs_structure()
+
+        for matrix, p_v in zip(p_combs, p_vals):
+            p_possible_vals = []
+            for val in p_v:
+                vals = [v for v in range(val)]
+                p_possible_vals.extend(vals)
+                comb_struct = set(itertools.product(p_possible_vals,repeat=len(p_v)))
+                #print(comb_struct)
+                for comb in comb_struct:
+                    self.assertIn(np.array(comb), matrix)
+
+    def test_fast_init(self):
         g1 = ng.NetworkGraph(self.s1.structure)
+        g2 = ng.NetworkGraph(self.s1.structure)
         g1.init_graph()
-        g1.remove_node('Y')
-        print(g1.get_nodes())
-        print(g1.get_edges())"""
-
+        for indx, node in enumerate(g1.nodes):
+            g2.fast_init(node)
+            self.assertListEqual(g2._fancy_indexing, g1._fancy_indexing[indx])
+            self.assertTrue(np.array_equal(g2.time_scalar_indexing_strucure, g1.time_scalar_indexing_strucure[indx]))
+            self.assertTrue(np.array_equal(g2.transition_scalar_indexing_structure, g1.transition_scalar_indexing_structure[indx]))
+            self.assertTrue(np.array_equal(g2.time_filtering, g1.time_filtering[indx]))
+            self.assertTrue(np.array_equal(g2.transition_filtering, g1.transition_filtering[indx]))
+            self.assertTrue(np.array_equal(g2.p_combs, g1.p_combs[indx]))
+
+    def test_get_parents_by_id(self):
+        g1 = ng.NetworkGraph(self.s1.structure)
+        g1.add_nodes(self.s1.structure.nodes_labels)
+        g1.add_edges(self.s1.structure.edges)
+        for node in g1.nodes:
+            self.assertListEqual(g1.get_parents_by_id(node), list(g1.graph.predecessors(node)))
 
+    def test_get_states_number(self):
+        g1 = ng.NetworkGraph(self.s1.structure)
+        g1.add_nodes(self.s1.structure.nodes_labels)
+        g1.add_edges(self.s1.structure.edges)
+        for node, val in zip(g1.nodes, g1.nodes_values):
+            self.assertEqual(val, g1.get_states_number(node))
 
+    def test_get_node_indx(self):
+        g1 = ng.NetworkGraph(self.s1.structure)
+        g1.add_nodes(self.s1.structure.nodes_labels)
+        g1.add_edges(self.s1.structure.edges)
+        for node, indx in zip(g1.nodes, g1.nodes_indexes):
+            self.assertEqual(indx, g1.get_node_indx(node))
 
-#TODO mancano i test sulle property e sui getters_vari
 if __name__ == '__main__':
     unittest.main()

main_package/tests/test_parameters_estimator.py

@@ -1,24 +1,69 @@
 import unittest
 import numpy as np
+import glob
+import os
 from line_profiler import LineProfiler
 
 import network_graph as ng
 import sample_path as sp
-import sets_of_cims_container as scc
+import set_of_cims as sofc
 import parameters_estimator as pe
 import json_importer as ji
 
-#TODO bisogna trovare un modo per testare i metodi che stimano i tempi e le transizioni per i singoli nodi
+
 class TestParametersEstimatior(unittest.TestCase):
 
     @classmethod
     def setUpClass(cls) -> None:
-        cls.s1 = sp.SamplePath('../data', 'samples', 'dyn.str', 'variables', 'Time', 'Name')
+        cls.read_files = glob.glob(os.path.join('../data', "*.json"))
+        cls.importer = ji.JsonImporter(cls.read_files[0], 'samples', 'dyn.str', 'variables', 'Time', 'Name')
+        cls.s1 = sp.SamplePath(cls.importer)
         cls.s1.build_trajectories()
         cls.s1.build_structure()
         cls.g1 = ng.NetworkGraph(cls.s1.structure)
         cls.g1.init_graph()
 
+    def test_fast_init(self):
+        for node in self.g1.nodes:
+            g = ng.NetworkGraph(self.s1.structure)
+            g.fast_init(node)
+            p1 = pe.ParametersEstimator(self.s1, g)
+            self.assertEqual(p1.sample_path, self.s1)
+            self.assertEqual(p1.net_graph, g)
+            self.assertIsNone(p1.single_set_of_cims)
+            p1.fast_init(node)
+            self.assertIsInstance(p1.single_set_of_cims, sofc.SetOfCims)
+
+    def test_compute_parameters_for_node(self):
+        for indx, node in enumerate(self.g1.nodes):
+            print(node)
+            g = ng.NetworkGraph(self.s1.structure)
+            g.fast_init(node)
+            p1 = pe.ParametersEstimator(self.s1, g)
+            p1.fast_init(node)
+            sofc1 = p1.compute_parameters_for_node(node)
+            sampled_cims = self.aux_import_sampled_cims('dyn.cims')
+            sc = list(sampled_cims.values())
+            #print(sc[indx])
+            self.equality_of_cims_of_node(sc[indx], sofc1.actual_cims)
+
+    def equality_of_cims_of_node(self, sampled_cims, estimated_cims):
+        #print(sampled_cims)
+        #print(estimated_cims)
+        self.assertEqual(len(sampled_cims), len(estimated_cims))
+        for c1, c2 in zip(sampled_cims, estimated_cims):
+            self.cim_equality_test(c1, c2.cim)
+
+    def cim_equality_test(self, cim1, cim2):
+        for r1, r2 in zip(cim1, cim2):
+            self.assertTrue(np.all(np.isclose(r1, r2, 1e-01, 1e-01) == True))
+
+    def aux_import_sampled_cims(self, cims_label):
+        i1 = ji.JsonImporter(self.read_files[0], '', '', '', '', '')
+        raw_data = i1.read_json_file()
+        return i1.import_sampled_cims(raw_data, 0, cims_label)
+
+    """
     def test_init(self):
         self.aux_test_init(self.s1, self.g1)
 
@@ -38,47 +83,6 @@ class TestParametersEstimatior(unittest.TestCase):
 
     def test_compute_parameters(self):
         self.aux_test_compute_parameters(self.s1, self.g1)
-
-    def aux_test_compute_parameters(self, sample_p, graph):
-        pe1 = pe.ParametersEstimator(sample_p, graph)
-        pe1.init_sets_cims_container()
-        pe1.compute_parameters()
-        samples_cims = self.aux_import_sampled_cims('dyn.cims')
-        for indx, sc in enumerate(samples_cims.values()):
-            self.equality_of_cims_of_node(sc, pe1.sets_of_cims_struct.get_set_of_cims(indx).get_cims())
-
-    def equality_of_cims_of_node(self, sampled_cims, estimated_cims):
-        self.assertEqual(len(sampled_cims), len(estimated_cims))
-        for c1, c2 in zip(sampled_cims, estimated_cims):
-            self.cim_equality_test(c1, c2.cim)
-
-    def cim_equality_test(self, cim1, cim2):
-        for r1, r2 in zip(cim1, cim2):
-            self.assertTrue(np.all(np.isclose(r1, r2, 1e-01, 1e-01) == True))
-
-    def test_compute_parameters_for_node(self):#TODO Questo non è un test
-        self.g1.remove_node('Y')
-        print(self.g1.time_filtering)
-        pe1 = pe.ParametersEstimator(self.s1, self.g1)
-        pe1.init_sets_cims_container()
-        lp = LineProfiler()
-        #lp.add_function(pe1.init_sets_cims_container)
-        lp_wrapper = lp(pe1.compute_parameters_for_node)
-        lp_wrapper('X')
-        lp.print_stats()
-        #pe1.init_sets_cims_container()
-        #pe1.compute_parameters_for_node('Y')
-        print(pe1.sets_of_cims_struct.get_set_of_cims(0).actual_cims)
-
-
-    def aux_import_sampled_cims(self, cims_label):
-        i1 = ji.JsonImporter('../data', '', '', '', '', '')
-        raw_data = i1.read_json_file()
-        return i1.import_sampled_cims(raw_data, 0, cims_label)
-
-
-
-
-
+        """
 if __name__ == '__main__':
     unittest.main()

main_package/tests/test_sample_path.py

@@ -1,4 +1,7 @@
 import unittest
+import glob
+import os
+import json_importer as ji
 import sample_path as sp
 import trajectory as tr
 import structure as st
@@ -6,8 +9,13 @@ import structure as st
 
 class TestSamplePath(unittest.TestCase):
 
+    @classmethod
+    def setUpClass(cls) -> None:
+        cls.read_files = glob.glob(os.path.join('../data', "*.json"))
+        cls.importer = ji.JsonImporter(cls.read_files[0], 'samples', 'dyn.str', 'variables', 'Time', 'Name')
+
     def test_init(self):
-        s1 = sp.SamplePath('../data', 'samples', 'dyn.str', 'variables', 'Time', 'Name')
+        s1 = sp.SamplePath(self.importer)
         s1.build_trajectories()
         self.assertIsNotNone(s1.trajectories)
         self.assertIsInstance(s1.trajectories, tr.Trajectory)

main_package/tests/test_setofcims.py

@@ -11,64 +11,84 @@ class TestSetOfCims(unittest.TestCase):
     def setUpClass(cls) -> None:
         cls.node_id = 'X'
         cls.possible_cardinalities = [2, 3]
-        #cls.possible_states = [[0,1], [0, 1, 2]]
+        cls.possible_states = [[0,1], [0, 1, 2]]
         cls.node_states_number = range(2, 4)
 
     def test_init(self):
         # empty parent set
         for sn in self.node_states_number:
-            self.aux_test_init(self.node_id, [], sn)
+            p_combs = self.build_p_comb_structure_for_a_node([])
+            self.aux_test_init(self.node_id, [], sn, p_combs)
         # one parent
         for sn in self.node_states_number:
             for p in itertools.product(self.possible_cardinalities, repeat=1):
-                self.aux_test_init(self.node_id, list(p), sn)
+                p_combs = self.build_p_comb_structure_for_a_node(list(p))
+                self.aux_test_init(self.node_id, list(p), sn, p_combs)
         #two parents
         for sn in self.node_states_number:
             for p in itertools.product(self.possible_cardinalities, repeat=2):
-                self.aux_test_init(self.node_id, list(p), sn)
+                p_combs = self.build_p_comb_structure_for_a_node(list(p))
+                self.aux_test_init(self.node_id, list(p), sn, p_combs)
 
-    def test_indexes_converter(self):
+    def test_build_cims(self):
         # empty parent set
         for sn in self.node_states_number:
-            self.aux_test_indexes_converter(self.node_id, [], sn)
+            p_combs = self.build_p_comb_structure_for_a_node([])
+            self.aux_test_build_cims(self.node_id, [], sn, p_combs)
         # one parent
         for sn in self.node_states_number:
             for p in itertools.product(self.possible_cardinalities, repeat=1):
-                self.aux_test_init(self.node_id, list(p), sn)
-        # two parents
+                p_combs = self.build_p_comb_structure_for_a_node(list(p))
+                self.aux_test_build_cims(self.node_id, list(p), sn, p_combs)
+        #two parents
         for sn in self.node_states_number:
             for p in itertools.product(self.possible_cardinalities, repeat=2):
-                self.aux_test_init(self.node_id, list(p), sn)
-
-    def aux_test_indexes_converter(self, node_id, parents_states_number, node_states_number):
-        sofcims = soci.SetOfCims(node_id, parents_states_number, node_states_number)
-        if not parents_states_number:
-            self.assertEqual(sofcims.indexes_converter([]), 0)
-        else:
-            parents_possible_values = []
-            for cardi in parents_states_number:
-                parents_possible_values.extend(range(0, cardi))
-            for p in itertools.permutations(parents_possible_values, len(parents_states_number)):
-                self.assertEqual(sofcims.indexes_converter(list(p)), np.ravel_multi_index(list(p), parents_states_number))
+                p_combs = self.build_p_comb_structure_for_a_node(list(p))
+                self.aux_test_build_cims(self.node_id, list(p), sn, p_combs)
 
-    def test_build_cims(self):
+    def test_filter_cims_with_mask(self):
+        p_combs = self.build_p_comb_structure_for_a_node(self.possible_cardinalities)
+        sofc1 = soci.SetOfCims('X', self.possible_cardinalities, 3, p_combs)
         state_res_times_list = []
         transition_matrices_list = []
-        so1 = soci.SetOfCims('X',[3], 3)
-        for i in range(0, 3):
+        for i in range(len(p_combs)):
             state_res_times = np.random.rand(1, 3)[0]
             state_res_times = state_res_times * 1000
             state_transition_matrix = np.random.randint(1, 10000, (3, 3))
             state_res_times_list.append(state_res_times)
             transition_matrices_list.append(state_transition_matrix)
+        sofc1.build_cims(state_res_times_list, transition_matrices_list)
+        for length_of_mask in range(3):
+            for mask in list(itertools.permutations([True, False],r=length_of_mask)):
+                m = np.array(mask)
+                for parent_value in range(self.possible_cardinalities[0]):
+                    cims = sofc1.filter_cims_with_mask(m, [parent_value])
+                    if length_of_mask == 0 or length_of_mask == 1:
+                        self.assertTrue(np.array_equal(sofc1.actual_cims, cims))
+                    else:
+                        indxs = self.another_filtering_method(p_combs, m, [parent_value])
+                        self.assertTrue(np.array_equal(cims, sofc1.actual_cims[indxs]))
+
+    def aux_test_build_cims(self, node_id, p_values, node_states, p_combs):
+        state_res_times_list = []
+        transition_matrices_list = []
+        so1 = soci.SetOfCims(node_id, p_values, node_states, p_combs)
+        for i in range(len(p_combs)):
+            state_res_times = np.random.rand(1, node_states)[0]
+            state_res_times = state_res_times * 1000
+            state_transition_matrix = np.random.randint(1, 10000, (node_states, node_states))
+            state_res_times_list.append(state_res_times)
+            transition_matrices_list.append(state_transition_matrix)
         so1.build_cims(state_res_times_list, transition_matrices_list)
         self.assertEqual(len(state_res_times_list), so1.get_cims_number())
+        self.assertIsInstance(so1.actual_cims, np.ndarray)
         self.assertIsNone(so1.transition_matrices)
         self.assertIsNone(so1.state_residence_times)
 
-    def aux_test_init(self, node_id, parents_states_number, node_states_number):
-        sofcims = soci.SetOfCims(node_id, parents_states_number, node_states_number)
+    def aux_test_init(self, node_id, parents_states_number, node_states_number, p_combs):
+        sofcims = soci.SetOfCims(node_id, parents_states_number, node_states_number, p_combs)
         self.assertEqual(sofcims.node_id, node_id)
+        self.assertTrue(np.array_equal(sofcims.p_combs, p_combs))
         self.assertTrue(np.array_equal(sofcims.parents_states_number, parents_states_number))
         self.assertEqual(sofcims.node_states_number, node_states_number)
         self.assertFalse(sofcims.actual_cims)
@@ -77,7 +97,46 @@ class TestSetOfCims(unittest.TestCase):
         self.assertEqual(sofcims.transition_matrices.shape[0], np.prod(np.array(parents_states_number)))
         self.assertEqual(len(sofcims.transition_matrices[0][0]), node_states_number)
 
+    def aux_test_indexes_converter(self, node_id, parents_states_number, node_states_number):
+        sofcims = soci.SetOfCims(node_id, parents_states_number, node_states_number)
+        if not parents_states_number:
+            self.assertEqual(sofcims.indexes_converter([]), 0)
+        else:
+            parents_possible_values = []
+            for cardi in parents_states_number:
+                parents_possible_values.extend(range(0, cardi))
+            for p in itertools.permutations(parents_possible_values, len(parents_states_number)):
+                self.assertEqual(sofcims.indexes_converter(list(p)), np.ravel_multi_index(list(p), parents_states_number))
+
+    def build_p_comb_structure_for_a_node(self, parents_values):
+        """
+        Builds the combinatory structure that contains the combinations of all the values contained in parents_values.
+
+        Parameters:
+            parents_values: the cardinalities of the nodes
+        Returns:
+            a numpy matrix containing a grid of the combinations
+        """
+        tmp = []
+        for val in parents_values:
+            tmp.append([x for x in range(val)])
+        if len(parents_values) > 0:
+            parents_comb = np.array(np.meshgrid(*tmp)).T.reshape(-1, len(parents_values))
+            if len(parents_values) > 1:
+                tmp_comb = parents_comb[:, 1].copy()
+                parents_comb[:, 1] = parents_comb[:, 0].copy()
+                parents_comb[:, 0] = tmp_comb
+        else:
+            parents_comb = np.array([[]], dtype=np.int)
+        return parents_comb
 
+    def another_filtering_method(self,p_combs, mask, parent_value):
+        masked_combs = p_combs[:, mask]
+        indxs = []
+        for indx, val in enumerate(masked_combs):
+            if val == parent_value:
+                indxs.append(indx)
+        return np.array(indxs)
 
 if __name__ == '__main__':
     unittest.main()

main_package/tests/test_structure.py

@@ -1,80 +1,73 @@
 import sys
 sys.path.append("/Users/Zalum/Desktop/Tesi/CTBN_Project/main_package/classes/")
 import unittest
-import pandas as pd
+import numpy as np
 import structure as st
 
 
 class TestStructure(unittest.TestCase):
-    def setUp(self):
-        self.structure_frame = pd.DataFrame([{"From":"X","To":"Z"}, {"From":"X","To":"Y"},{"From":"Y","To":"X"},
-                                             {"From":"Y","To":"Z"},{"From":"Z","To":"Y"}, {"From":"Z","To":"X"} ])
-        self.variables_frame = pd.DataFrame([{"Name":"X","Value":3},{"Name":"Y","Value":3},{"Name":"Z","Value":3}])
+    @classmethod
+    def setUpClass(cls):
+        cls.labels = ['X','Y','Z']
+        cls.indxs = np.array([0,1,2])
+        cls.vals = np.array([3,3,3])
+        cls.edges = [('X','Z'),('Y','Z'), ('Z','Y')]
+        cls.vars_numb = len(cls.labels)
 
     def test_init(self):
-        s1 = st.Structure(self.structure_frame, self.variables_frame, len(self.variables_frame.index))
-        self.assertTrue(self.structure_frame.equals(s1.structure_frame))
-        self.assertTrue(self.variables_frame.equals(s1.variables_frame))
-        self.assertEqual(self.variables_frame.columns.values[0], s1.name_label)
-        self.assertEqual(self.variables_frame.columns.values[1], s1.value_label)
-        #print(len(self.variables_frame.index))
-        self.assertEqual(len(self.variables_frame.index), s1.total_variables_number)
-
-    def test_list_of_edges(self):
-        s1 = st.Structure(self.structure_frame, self.variables_frame, len(self.variables_frame.index))
-        records = self.structure_frame.to_records(index=False)
-        result = list(records)
-        for e1, e2 in zip(result, s1.list_of_edges()):
-           self.assertEqual(e1, e2)
-
-    def test_list_of_nodes_labels(self):
-        s1 = st.Structure(self.structure_frame, self.variables_frame, len(self.variables_frame.index))
-        self.assertEqual(list(self.variables_frame['Name']), s1.list_of_nodes_labels())
+        s1 = st.Structure(self.labels, self.indxs, self.vals, self.edges, self.vars_numb)
+        self.assertListEqual(self.labels,s1.nodes_labels)
+        self.assertIsInstance(s1.nodes_indexes, np.ndarray)
+        self.assertTrue(np.array_equal(self.indxs, s1.nodes_indexes))
+        self.assertIsInstance(s1.nodes_values, np.ndarray)
+        self.assertTrue(np.array_equal(self.vals, s1.nodes_values))
+        self.assertListEqual(self.edges, s1.edges)
+        self.assertEqual(self.vars_numb, s1.total_variables_number)
 
     def test_get_node_id(self):
-        s1 = st.Structure(self.structure_frame, self.variables_frame, len(self.variables_frame.index))
-        for indx, var in enumerate(list(self.variables_frame['Name'])):
+        s1 = st.Structure(self.labels, self.indxs, self.vals, self.edges, self.vars_numb)
+        for indx, var in enumerate(self.labels):
             self.assertEqual(var, s1.get_node_id(indx))
 
     def test_get_node_indx(self):
-        filtered_frame = self.variables_frame.drop(self.variables_frame[self.variables_frame['Name'] == 'Y'].index)
-        #print(filtered_frame)
-        s1 = st.Structure(self.structure_frame, filtered_frame, len(self.variables_frame.index))
-        for indx, var in zip(filtered_frame.index, filtered_frame['Name']):
+        l2 = self.labels[:]
+        l2.remove('Y')
+        i2 = self.indxs.copy()
+        np.delete(i2, 1)
+        v2 = self.vals.copy()
+        np.delete(v2, 1)
+        e2 = [('X','Z')]
+        n2 = self.vars_numb - 1
+        s1 = st.Structure(l2, i2, v2, e2, n2)
+        for indx, var in zip(i2, l2):
             self.assertEqual(indx, s1.get_node_indx(var))
 
-    def test_list_of_node_indxs(self):
-        filtered_frame = self.variables_frame.drop(self.variables_frame[self.variables_frame['Name'] == 'Y'].index)
-        # print(filtered_frame)
-        s1 = st.Structure(self.structure_frame, filtered_frame, len(self.variables_frame.index))
-
-        for indx1, indx2 in zip(filtered_frame.index, s1.list_of_nodes_indexes()):
-            self.assertEqual(indx1, indx2)
-
     def test_get_positional_node_indx(self):
-        filtered_frame = self.variables_frame.drop(self.variables_frame[self.variables_frame['Name'] == 'Y'].index)
-        # print(filtered_frame)
-        s1 = st.Structure(self.structure_frame, filtered_frame, len(self.variables_frame.index))
-        for indx, var in enumerate(s1.list_of_nodes_labels()):
+        l2 = self.labels[:]
+        l2.remove('Y')
+        i2 = self.indxs.copy()
+        np.delete(i2, 1)
+        v2 = self.vals.copy()
+        np.delete(v2, 1)
+        e2 = [('X', 'Z')]
+        n2 = self.vars_numb - 1
+        s1 = st.Structure(l2, i2, v2, e2, n2)
+        for indx, var in enumerate(s1.nodes_labels):
             self.assertEqual(indx, s1.get_positional_node_indx(var))
 
     def test_get_states_number(self):
-        s1 = st.Structure(self.structure_frame, self.variables_frame, len(self.variables_frame.index))
-        for indx, row in self.variables_frame.iterrows():
-            self.assertEqual(row[1], s1.get_states_number(row[0]))
-
-    def test_get_states_numeber_by_indx(self):
-        s1 = st.Structure(self.structure_frame, self.variables_frame, len(self.variables_frame.index))
-        for indx, row in self.variables_frame.iterrows():
-            self.assertEqual(row[1], s1.get_states_number_by_indx(indx))
+        l2 = self.labels[:]
+        l2.remove('Y')
+        i2 = self.indxs.copy()
+        np.delete(i2, 1)
+        v2 = self.vals.copy()
+        np.delete(v2, 1)
+        e2 = [('X', 'Z')]
+        n2 = self.vars_numb - 1
+        s1 = st.Structure(l2, i2, v2, e2, n2)
+        for val, node in zip(v2, l2):
+            self.assertEqual(val, s1.get_states_number(node))
 
-    def test_remove_node(self):
-        s1 = st.Structure(self.structure_frame, self.variables_frame, len(self.variables_frame.index))
-        s1.remove_node('Y')
-        print(s1.variables_frame)
-        print(s1.structure_frame)
-        print(s1.get_node_indx('Z'))
-        print(s1.get_positional_node_indx('Z'))
 
 if __name__ == '__main__':
     unittest.main()

main_package/tests/test_structure_estimator.py

@@ -1,39 +1,97 @@
 import unittest
+import numpy as np
+import networkx as nx
+import glob
+import os
+import math
 from line_profiler import LineProfiler
+import psutil
 
+import json_importer as ji
 import sample_path as sp
 import structure_estimator as se
+import cache as ch
+
 
 class TestStructureEstimator(unittest.TestCase):
 
     @classmethod
     def setUpClass(cls) -> None:
-        cls.s1 = sp.SamplePath('../data', 'samples', 'dyn.str', 'variables', 'Time', 'Name')
+        cls.read_files = glob.glob(os.path.join('../data', "*.json"))
+        cls.importer = ji.JsonImporter(cls.read_files[0], 'samples', 'dyn.str', 'variables', 'Time', 'Name')
+        cls.s1 = sp.SamplePath(cls.importer)
         cls.s1.build_trajectories()
         cls.s1.build_structure()
 
     def test_init(self):
-        se1 = se.StructureEstimator(self.s1)
+        exp_alfa = 0.1
+        chi_alfa = 0.1
+        se1 = se.StructureEstimator(self.s1, exp_alfa, chi_alfa)
         self.assertEqual(self.s1, se1.sample_path)
-        self.assertEqual(se1.complete_graph_frame.shape[0],
-                         self.s1.total_variables_count *(self.s1.total_variables_count - 1))
+        self.assertTrue(np.array_equal(se1.nodes, np.array(self.s1.structure.nodes_labels)))
+        self.assertTrue(np.array_equal(se1.nodes_indxs, self.s1.structure.nodes_indexes))
+        self.assertTrue(np.array_equal(se1.nodes_vals, self.s1.structure.nodes_values))
+        self.assertEqual(se1.exp_test_sign, exp_alfa)
+        self.assertEqual(se1.chi_test_alfa, chi_alfa)
+        self.assertIsInstance(se1.complete_graph, nx.DiGraph)
+        self.assertIsInstance(se1.cache, ch.Cache)
+
+    def test_build_complete_graph(self):
+        exp_alfa = 0.1
+        chi_alfa = 0.1
+        nodes_numb = len(self.s1.structure.nodes_labels)
+        se1 = se.StructureEstimator(self.s1, exp_alfa, chi_alfa)
+        cg = se1.build_complete_graph(self.s1.structure.nodes_labels)
+        self.assertEqual(len(cg.edges), nodes_numb*(nodes_numb - 1))
+        for node in self.s1.structure.nodes_labels:
+            no_self_loops = self.s1.structure.nodes_labels[:]
+            no_self_loops.remove(node)
+            for n2 in no_self_loops:
+                self.assertIn((node, n2), cg.edges)
+
+    def test_generate_possible_sub_sets_of_size(self):
+        exp_alfa = 0.1
+        chi_alfa = 0.1
+        nodes_numb = len(self.s1.structure.nodes_labels)
+        se1 = se.StructureEstimator(self.s1, exp_alfa, chi_alfa)
 
-    def test_one_iteration(self):
+        for node in self.s1.structure.nodes_labels:
+            for b in range(nodes_numb):
+                sets = se1.generate_possible_sub_sets_of_size(self.s1.structure.nodes_labels, b, node)
+                sets2 = se1.generate_possible_sub_sets_of_size(self.s1.structure.nodes_labels, b, node)
+                self.assertEqual(len(list(sets)), math.floor(math.factorial(nodes_numb - 1) /
+                                                             (math.factorial(b)*math.factorial(nodes_numb -1 - b))))
+                for sset in sets2:
+                    self.assertFalse(node in sset)
+
+    def test_time(self):
         se1 = se.StructureEstimator(self.s1, 0.1, 0.1)
-        #se1.one_iteration_of_CTPC_algorithm('X')
-        #self.aux_test_complete_test(se1, 'X', 'Y', ['Z'])
         lp = LineProfiler()
         lp.add_function(se1.complete_test)
         lp.add_function(se1.one_iteration_of_CTPC_algorithm)
+        lp.add_function(se1.independence_test)
         lp_wrapper = lp(se1.ctpc_algorithm)
         lp_wrapper()
         lp.print_stats()
-        #se1.ctpc_algorithm()
         print(se1.complete_graph.edges)
+        print(self.s1.structure.edges)
+        for ed in self.s1.structure.edges:
+            self.assertIn(tuple(ed), se1.complete_graph.edges)
+        tuples_edges = [tuple(rec) for rec in self.s1.structure.edges]
+        spurious_edges = []
+        for ed in se1.complete_graph.edges:
+            if not(ed in tuples_edges):
+                spurious_edges.append(ed)
 
-    def aux_test_complete_test(self, estimator, test_par, test_child, p_set):
-        estimator.complete_test(test_par, test_child, p_set)
+        print("Spurious Edges:",spurious_edges)
+        se1.save_results()
 
+    def test_memory(self):
+        se1 = se.StructureEstimator(self.s1, 0.1, 0.1)
+        se1.ctpc_algorithm()
+        current_process = psutil.Process(os.getpid())
+        mem = current_process.memory_info().rss
+        print("Average Memory Usage in MB:", mem / 10**6)
 
 if __name__ == '__main__':
     unittest.main()

main_package/tests/test_trajectory.py

@@ -8,7 +8,7 @@ class TestTrajectory(unittest.TestCase):
 
     def test_init(self):
         cols_list = [np.array([1.2,1.3,.14]), np.arange(1,4), np.arange(4,7)]
-        t1 = tr.Trajectory(cols_list, len(cols_list))
+        t1 = tr.Trajectory(cols_list, len(cols_list) - 2)
         self.assertTrue(np.array_equal(cols_list[0], t1.times))
         self.assertTrue(np.array_equal(np.ravel(t1.complete_trajectory[:, : 1]), cols_list[1]))
         self.assertTrue(np.array_equal(np.ravel(t1.complete_trajectory[:, 1: 2]), cols_list[2]))
@@ -19,6 +19,21 @@ class TestTrajectory(unittest.TestCase):
         cols_list = [np.arange(1, 4), np.arange(4, 7), np.array([1.2, 1.3, .14])]
         self.assertRaises(TypeError, tr.Trajectory, cols_list, len(cols_list))
 
+    def test_complete_trajectory(self):
+        cols_list = [np.array([1.2, 1.3, .14]), np.arange(1, 4), np.arange(4, 7)]
+        t1 = tr.Trajectory(cols_list, len(cols_list) - 2)
+        complete = np.column_stack((cols_list[1], cols_list[2]))
+        self.assertTrue(np.array_equal(t1.complete_trajectory, complete))
+
+    def test_trajectory(self):
+        cols_list = [np.array([1.2, 1.3, .14]), np.arange(1, 4), np.arange(4, 7)]
+        t1 = tr.Trajectory(cols_list, len(cols_list) - 2)
+        self.assertTrue(np.array_equal(cols_list[1], t1.trajectory.ravel()))
+
+    def test_times(self):
+        cols_list = [np.array([1.2, 1.3, .14]), np.arange(1, 4), np.arange(4, 7)]
+        t1 = tr.Trajectory(cols_list, len(cols_list) - 2)
+        self.assertTrue(np.array_equal(cols_list[0], t1.times))
 
 
 if __name__ == '__main__':