Add new version of algorithm

main_package/classes/conditional_intensity_matrix.py

@@ -10,12 +10,11 @@ class ConditionalIntensityMatrix:
 
     def update_state_transition_count(self, element_indx):
         #print(element_indx)
-        self.state_transition_matrix[element_indx[0]][element_indx[1]] = \
-            self.state_transition_matrix[element_indx[0]][element_indx[1]] + 1
+        self.state_transition_matrix[element_indx[0]][element_indx[1]] += 1
 
     def update_state_residence_time_for_state(self, state, time):
         #print("Time updating In state", state, time)
-        self.state_residence_times[state] = self.state_residence_times[state] + time
+        self.state_residence_times[state] += time
 
     def compute_cim_coefficients(self):
         for i, row in enumerate(self.state_transition_matrix):

main_package/classes/json_importer.py

@@ -25,6 +25,7 @@ class JsonImporter(AbstractImporter):
         self.df_samples_list = []
         self.df_structure = pd.DataFrame()
         self.df_variables = pd.DataFrame()
+        self.concatenated_samples = None
         super(JsonImporter, self).__init__(files_path)
 
     def import_data(self):
@@ -96,14 +97,23 @@ class JsonImporter(AbstractImporter):
         for col_name in columns_header:
             if col_name == 'Time':
                 sample_frame[col_name + 'Delta'] = sample_frame[col_name].diff()
+            else:
+                sample_frame[col_name + 'Delta'] = (sample_frame[col_name].diff().bfill() != 0).astype(int)
         sample_frame['Time'] = sample_frame['TimeDelta']
         del sample_frame['TimeDelta']
         sample_frame['Time'] = sample_frame['Time'].shift(-1)
+        columns_header = list(sample_frame.columns.values)
+        #print(columns_header[4:])
+        for column in columns_header[4:]:
+            sample_frame[column] = sample_frame[column].shift(1)
+            sample_frame[column] = sample_frame[column].fillna(0)
         sample_frame.drop(sample_frame.tail(1).index, inplace=True)
+        #print(sample_frame)
 
     def compute_row_delta_in_all_samples_frames(self):
         for sample in self.df_samples_list:
             self.compute_row_delta_sigle_samples_frame(sample)
+        self.concatenated_samples = pd.concat(self.df_samples_list)
 
     def build_list_of_samples_array(self, data_frame):
         """

main_package/classes/network_graph.py

@@ -74,7 +74,7 @@ class NetworkGraph():
             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(tuple(indexes_for_a_node))
+            index_structure.append(np.array(indexes_for_a_node, dtype=np.int))
         return index_structure
 
     def get_nodes(self):

main_package/classes/parameters_estimator.py

@@ -1,8 +1,10 @@
 import os
 import time as tm
 from line_profiler import LineProfiler
+from multiprocessing import Process
 
-
+import numba as nb
+import numpy as np
 import network_graph as ng
 import sample_path as sp
 import amalgamated_cims as acims
@@ -58,20 +60,73 @@ class ParametersEstimator:
                 self.amalgamated_cims_struct.update_state_residence_time_for_matrix(
                     which_node, which_matrix, which_element, time)
 
-
-    def find_transition(self, current_row, next_row, row_length):
-        for indx in range(1, row_length):
-            if current_row[indx] != next_row[indx]:
-                return [indx - 1, (current_row[indx], next_row[indx])]
-
-
-    def compute_time_delta(self, current_row, next_row):
-        return next_row[0] - current_row[0]
-
     def which_matrix_to_update(self, current_row, node_indx):
-       return tuple(current_row.take(self.fancy_indexing_structure[node_indx]))
+        #print(type(self.fancy_indexing_structure[node_indx]))
+        return tuple(current_row.take(self.fancy_indexing_structure[node_indx]))
+        #return tuple(ParametersEstimator.taker(current_row, self.fancy_indexing_structure[node_indx]))
+
+    def parameters_estimation_for_variable_multiple_parents(self, node_indx, times, transitions ,variable_values, parents_values):
+        #print(times)
+        #print(variable_values)
+        #print(parents_values)
+
+        #print("Starting computing")
+        #t0 = tm.time()
+        for indx, row in enumerate(variable_values):
+            time = times[indx]
+            which_matrix = tuple(parents_values[indx])  # questo è un vettore
+            current_state = variable_values[indx]
+            """if transitions[indx] == 1:
+                prev_state = variable_values[indx - 1]
+                transition = [node_indx, (prev_state, current_state)]
+                #which_node = transition[0]
+                which_element = transition[1]
+                self.amalgamated_cims_struct.update_state_transition_for_matrix(node_indx, which_matrix, which_element)
+            #which_element = current_state"""
+            self.amalgamated_cims_struct.update_state_residence_time_for_matrix(node_indx, which_matrix,
+                                                                                    current_state,
+                                                                                    time)
 
+    def parameters_estimation_for_variable_single_parent(self, node_indx, times, transitions, variable_values,
+                                                                parents_values):
+            for indx, row in enumerate(variable_values):
+                time = times[indx]
+                which_matrix = parents_values[indx]  # Avendo un solo parent questo è uno scalare
+                current_state = variable_values[indx]
+                #which_matrix = ParametersEstimator.taker(parents_values, indx)
+                # print(which_matrix.dtype)
+                if transitions[indx] == 1:
+                    prev_state = variable_values[indx - 1]
+                    transition = [node_indx, (prev_state, current_state)]
+                    which_element = transition[1]
+                    self.amalgamated_cims_struct.update_state_transition_for_matrix(node_indx, which_matrix,
+                                                                                    which_element)
+                which_element = current_state
+                self.amalgamated_cims_struct.update_state_residence_time_for_matrix(node_indx, which_matrix,
+                                                                                    which_element,time)
+
+    def parameters_estimation_for_variable_no_parent(self, node_indx, times, transitions,variable_values):
+
+        for indx, row in enumerate(variable_values):
+            time = times[indx]
+
+            which_matrix = 0
+            current_state = variable_values[indx]
+            """if transitions[indx] == 1:
+                prev_state = variable_values[indx - 1]
+                #current_state = variable_values[indx]
+                transition = [node_indx, (prev_state, current_state)]
 
+                which_element = transition[1]
+                self.amalgamated_cims_struct.update_state_transition_for_matrix(node_indx, which_matrix,
+                                                                                            which_element)"""
+            which_element = current_state
+            self.amalgamated_cims_struct.update_state_residence_time_for_matrix(node_indx, which_matrix,
+                                                                                            which_element,
+                                                                                            time)
+
+        #t1 = tm.time() - t0
+        #print("Elapsed Time ", t1)
 
 
 
@@ -92,17 +147,46 @@ pe.init_amalgamated_cims_struct()
 print(pe.amalgamated_cims_struct.get_set_of_cims(0).get_cims_number())
 print(pe.amalgamated_cims_struct.get_set_of_cims(1).get_cims_number())
 print(pe.amalgamated_cims_struct.get_set_of_cims(2).get_cims_number())
+print(np.shape(s1.trajectories[0].transitions)[0])
+#pe.parameters_estimation_for_variable(0, pe.sample_path.trajectories[0].get_trajectory()[:, 0],
+                                     # pe.sample_path.trajectories[0].get_trajectory()[:, 1], [])
 #pe.parameters_estimation_single_trajectory(pe.sample_path.trajectories[0].get_trajectory())
-pe.parameters_estimation()
-"""lp = LineProfiler()
-lp.add_function(pe.compute_sufficient_statistics_for_row)   # add additional function to profile
-lp_wrapper = lp(pe.parameters_estimation_single_trajectory)
+#pe.parameters_estimation()
+lp = LineProfiler()
+#lp.add_function(pe.compute_sufficient_statistics_for_row)   # add additional function to profile
+#lp_wrapper = lp(pe.parameters_estimation_single_trajectory)
 #lp_wrapper = lp(pe.parameters_estimation)
-lp_wrapper(pe.sample_path.trajectories[0].get_trajectory())
-lp.print_stats()"""
+#lp_wrapper(pe.sample_path.trajectories[0].get_trajectory())
+#lp.print_stats()
+
+#lp_wrapper = lp(pe.parameters_estimation_for_variable)
+#lp_wrapper(2, pe.sample_path.trajectories[0].get_times(),
+                                      #pe.sample_path.trajectories[0].get_trajectory()[:, 2],
+           #pe.sample_path.trajectories[0].get_trajectory()[:, [0,1]])
+
+
+"""lp_wrapper = lp(pe.parameters_estimation_for_variable_single_parent)
+lp_wrapper(1, pe.sample_path.trajectories[0].get_times(),
+                                      pe.sample_path.trajectories[0].get_trajectory()[:, 1],
+           pe.sample_path.trajectories[0].get_trajectory()[:, 2])
+lp.print_stats()
+
+#print( pe.sample_path.trajectories[0].get_trajectory()[:, [1,2]])
 for matrix in pe.amalgamated_cims_struct.get_set_of_cims(1).actual_cims:
     print(matrix.state_residence_times)
     print(matrix.state_transition_matrix)
     matrix.compute_cim_coefficients()
-    print(matrix.cim)
-
+    print(matrix.cim)"""
+
+"""lp_wrapper = lp(pe.parameters_estimation_for_variable_no_parent)
+lp_wrapper(0, pe.sample_path.trajectories[0].get_times(), pe.sample_path.trajectories[0].transitions[:, 0],
+           pe.sample_path.trajectories[0].get_trajectory()[:, 0] )
+lp.print_stats()
+lp_wrapper = lp(pe.parameters_estimation_for_variable_single_parent)
+lp_wrapper(1, pe.sample_path.trajectories[0].get_times(), pe.sample_path.trajectories[0].transitions[:, 1],
+           pe.sample_path.trajectories[0].get_trajectory()[:,1], pe.sample_path.trajectories[0].get_trajectory()[:,2] )
+lp.print_stats()"""
+lp_wrapper = lp(pe.parameters_estimation_for_variable_multiple_parents)
+lp_wrapper(2, pe.sample_path.trajectories[0].get_times(), pe.sample_path.trajectories[0].transitions[:, 2],
+           pe.sample_path.trajectories[0].get_trajectory()[:,2], pe.sample_path.trajectories[0].get_trajectory()[:, [0,1]] )
+lp.print_stats()

main_package/classes/sample_path.py

@@ -26,9 +26,9 @@ class SamplePath:
 
     def build_trajectories(self):
         self.importer.import_data()
-        for traj_data_frame in self.importer.df_samples_list:
-            trajectory = tr.Trajectory(self.importer.build_list_of_samples_array(traj_data_frame))
-            self.trajectories.append(trajectory)
+        #for traj_data_frame in self.importer.df_samples_list:
+        trajectory = tr.Trajectory(self.importer.build_list_of_samples_array(self.importer.concatenated_samples))
+        self.trajectories.append(trajectory)
         self.importer.clear_data_frames()
 
     def build_structure(self):

main_package/classes/set_of_cims.py

@@ -43,10 +43,12 @@ class SetOfCims:
 
     def update_state_residence_time(self, which_matrix, which_element, time):
         #matrix_indx = self.indexes_converter(which_matrix)
-        #print(type(which_matrix))
+
         if not which_matrix:
             self.actual_cims[0].update_state_residence_time_for_state(which_element, time)
         else:
+            #print(type(which_matrix))
+            #print(self.actual_cims[(2,2)])
             self.actual_cims[which_matrix].update_state_residence_time_for_state(which_element, time)
 
     def build_actual_cims(self, cim_structure):

main_package/classes/trajectory.py

@@ -15,11 +15,16 @@ class Trajectory():
     """
 
     def __init__(self, list_of_columns):
-        self.actual_trajectory = np.array(list_of_columns, dtype=object).T
+        self.actual_trajectory = np.array(list_of_columns[1:], dtype=np.int).T
+        self.transitions = np.array(list_of_columns[4:], dtype=np.int).T
+        self.times = np.array(list_of_columns[0], dtype=np.float)
         
     def get_trajectory(self):
         return self.actual_trajectory
 
+    def get_times(self):
+        return self.times
+
     def size(self):
         return self.actual_trajectory.shape[0]