Luca Moretti
4 years ago
commit
e52d98b32e
@ -0,0 +1,3 @@ |
||||
[run] |
||||
omit = |
||||
*/tests/* |
||||
Binary file not shown.
@ -0,0 +1,9 @@ |
||||
include MANIFEST.in |
||||
include setup.py |
||||
include README.rst |
||||
prune PyCTBN/test_data |
||||
prune PyCTBN/tests |
||||
prune tests |
||||
prune test_data |
||||
prune *tests* |
||||
prune *test* |
||||
@ -1,8 +1,8 @@ |
||||
import PyCTBN.estimators |
||||
from PyCTBN.estimators import * |
||||
import PyCTBN.optimizers |
||||
from PyCTBN.optimizers import * |
||||
import PyCTBN.structure_graph |
||||
from PyCTBN.structure_graph import * |
||||
import PyCTBN.utility |
||||
from PyCTBN.utility import * |
||||
import PyCTBN.PyCTBN.estimators |
||||
from PyCTBN.PyCTBN.estimators import * |
||||
import PyCTBN.PyCTBN.optimizers |
||||
from PyCTBN.PyCTBN.optimizers import * |
||||
import PyCTBN.PyCTBN.structure_graph |
||||
from PyCTBN.PyCTBN.structure_graph import * |
||||
import PyCTBN.PyCTBN.utility |
||||
from PyCTBN.PyCTBN.utility import * |
||||
@ -0,0 +1,2 @@ |
||||
import PyCTBN.PyCTBN |
||||
from PyCTBN.PyCTBN import * |
||||
Binary file not shown.
Binary file not shown.
Binary file not shown.
@ -0,0 +1,118 @@ |
||||
|
||||
import glob |
||||
import math |
||||
import os |
||||
import unittest |
||||
import json |
||||
import networkx as nx |
||||
import numpy as np |
||||
import timeit |
||||
|
||||
from ...PyCTBN.utility.cache import Cache |
||||
from ...PyCTBN.structure_graph.sample_path import SamplePath |
||||
from ...PyCTBN.estimators.structure_constraint_based_estimator import StructureConstraintBasedEstimator |
||||
from ...PyCTBN.utility.json_importer import JsonImporter |
||||
|
||||
|
||||
class TestStructureEstimator(unittest.TestCase): |
||||
|
||||
@classmethod |
||||
def setUpClass(cls): |
||||
cls.read_files = glob.glob(os.path.join('./PyCTBN/test_data', "*.json")) |
||||
cls.importer = JsonImporter('./PyCTBN/test_data/networks_and_trajectories_binary_data_01_3.json', 'samples', 'dyn.str', 'variables', 'Time', 'Name') |
||||
cls.importer.import_data(0) |
||||
cls.s1 = SamplePath(cls.importer) |
||||
cls.s1.build_trajectories() |
||||
cls.s1.build_structure() |
||||
|
||||
def test_init(self): |
||||
exp_alfa = 0.1 |
||||
chi_alfa = 0.1 |
||||
se1 = StructureConstraintBasedEstimator(self.s1, exp_alfa, chi_alfa) |
||||
self.assertEqual(self.s1, se1._sample_path) |
||||
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, Cache) |
||||
|
||||
def test_build_complete_graph(self): |
||||
exp_alfa = 0.1 |
||||
chi_alfa = 0.1 |
||||
nodes_numb = len(self.s1.structure.nodes_labels) |
||||
se1 = StructureConstraintBasedEstimator(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) |
||||
#se1.save_plot_estimated_structure_graph() |
||||
|
||||
def test_build_removable_edges_matrix(self): |
||||
exp_alfa = 0.1 |
||||
chi_alfa = 0.1 |
||||
known_edges = self.s1.structure.edges[0:2] |
||||
se1 = StructureConstraintBasedEstimator(self.s1, exp_alfa, chi_alfa, known_edges) |
||||
for edge in known_edges: |
||||
i = self.s1.structure.get_node_indx(edge[0]) |
||||
j = self.s1.structure.get_node_indx(edge[1]) |
||||
self.assertFalse(se1._removable_edges_matrix[i][j]) |
||||
|
||||
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 = StructureConstraintBasedEstimator(self.s1, exp_alfa, chi_alfa) |
||||
|
||||
for node in self.s1.structure.nodes_labels: |
||||
for b in range(nodes_numb): |
||||
sets = StructureConstraintBasedEstimator.generate_possible_sub_sets_of_size(self.s1.structure.nodes_labels, b, node) |
||||
sets2 = StructureConstraintBasedEstimator.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): |
||||
known_edges = [] |
||||
se1 = StructureConstraintBasedEstimator(self.s1, 0.1, 0.1, known_edges,25) |
||||
exec_time = timeit.timeit(se1.ctpc_algorithm, number=1) |
||||
print("Execution Time: ", exec_time) |
||||
for ed in self.s1.structure.edges: |
||||
self.assertIn(tuple(ed), se1._complete_graph.edges) |
||||
#print("Spurious Edges:", se1.spurious_edges()) |
||||
#se1.save_plot_estimated_structure_graph() |
||||
|
||||
def test_save_results(self): |
||||
se1 = StructureConstraintBasedEstimator(self.s1, 0.1, 0.1) |
||||
se1.ctpc_algorithm() |
||||
se1.save_results() |
||||
name = self.s1._importer.file_path.rsplit('/', 1)[-1] |
||||
name = name.split('.', 1)[0] |
||||
name += '_' + str(self.s1._importer.dataset_id()) |
||||
name += '.json' |
||||
file_name = 'results_' + name |
||||
with open(file_name) as f: |
||||
js_graph = json.load(f) |
||||
result_graph = nx.json_graph.node_link_graph(js_graph) |
||||
self.assertFalse(nx.difference(se1._complete_graph, result_graph).edges) |
||||
os.remove(file_name) |
||||
|
||||
def test_adjacency_matrix(self): |
||||
se1 = StructureConstraintBasedEstimator(self.s1, 0.1, 0.1) |
||||
se1.ctpc_algorithm() |
||||
adj_matrix = nx.adj_matrix(se1._complete_graph).toarray().astype(bool) |
||||
self.assertTrue(np.array_equal(adj_matrix, se1.adjacency_matrix())) |
||||
|
||||
def test_save_plot_estimated_graph(self): |
||||
se1 = StructureConstraintBasedEstimator(self.s1, 0.1, 0.1) |
||||
edges = se1.estimate_structure(disable_multiprocessing=True) |
||||
se1.save_plot_estimated_structure_graph('./networks_and_trajectories_ternary_data_3.png') |
||||
|
||||
|
||||
if __name__ == '__main__': |
||||
unittest.main() |
||||
@ -0,0 +1,125 @@ |
||||
PyCTBN |
||||
====== |
||||
|
||||
A Continuous Time Bayesian Networks Library |
||||
|
||||
Installation/Usage |
||||
******************* |
||||
Download the release in .tar.gz or .whl format and simply use pip install to install it:: |
||||
|
||||
$ pip install PyCTBN-1.0.tar.gz |
||||
|
||||
Documentation |
||||
************* |
||||
Please refer to https://philipmartini.github.io/PyCTBN/ for the full project documentation. |
||||
|
||||
Implementing your own data importer |
||||
*********************************** |
||||
.. code-block:: python |
||||
|
||||
"""This example demonstrates the implementation of a simple data importer the extends the class abstract importer to import data in csv format. |
||||
The net in exam has three ternary nodes and no prior net structure. |
||||
""" |
||||
|
||||
from PyCTBN import AbstractImporter |
||||
|
||||
class CSVImporter(AbstractImporter): |
||||
|
||||
def __init__(self, file_path): |
||||
self._df_samples_list = None |
||||
super(CSVImporter, self).__init__(file_path) |
||||
|
||||
def import_data(self): |
||||
self.read_csv_file() |
||||
self._sorter = self.build_sorter(self._df_samples_list[0]) |
||||
self.import_variables() |
||||
self.compute_row_delta_in_all_samples_frames(self._df_samples_list) |
||||
|
||||
def read_csv_file(self): |
||||
df = pd.read_csv(self._file_path) |
||||
df.drop(df.columns[[0]], axis=1, inplace=True) |
||||
self._df_samples_list = [df] |
||||
|
||||
def import_variables(self): |
||||
values_list = [3 for var in self._sorter] |
||||
# initialize dict of lists |
||||
data = {'Name':self._sorter, 'Value':values_list} |
||||
# Create the pandas DataFrame |
||||
self._df_variables = pd.DataFrame(data) |
||||
|
||||
def build_sorter(self, sample_frame: pd.DataFrame) -> typing.List: |
||||
return list(sample_frame.columns)[1:] |
||||
|
||||
def dataset_id(self) -> object: |
||||
pass |
||||
|
||||
Parameters Estimation Example |
||||
***************************** |
||||
|
||||
.. code-block:: python |
||||
|
||||
from PyCTBN import JsonImporter |
||||
from PyCTBN import SamplePath |
||||
from PyCTBN import NetworkGraph |
||||
from PyCTBN import ParametersEstimator |
||||
|
||||
|
||||
def main(): |
||||
read_files = glob.glob(os.path.join('./data', "*.json")) #Take all json files in this dir |
||||
#import data |
||||
importer = JsonImporter(read_files[0], 'samples', 'dyn.str', 'variables', 'Time', 'Name') |
||||
importer.import_data(0) |
||||
#Create a SamplePath Obj passing an already filled AbstractImporter object |
||||
s1 = SamplePath(importer) |
||||
#Build The trajectries and the structural infos |
||||
s1.build_trajectories() |
||||
s1.build_structure() |
||||
print(s1.structure.edges) |
||||
print(s1.structure.nodes_values) |
||||
#From The Structure Object build the Graph |
||||
g = NetworkGraph(s1.structure) |
||||
#Select a node you want to estimate the parameters |
||||
node = g.nodes[2] |
||||
print("Node", node) |
||||
#Init the _graph specifically for THIS node |
||||
g.fast_init(node) |
||||
#Use SamplePath and Grpah to create a ParametersEstimator Object |
||||
p1 = ParametersEstimator(s1.trajectories, g) |
||||
#Init the peEst specifically for THIS node |
||||
p1.fast_init(node) |
||||
#Compute the parameters |
||||
sofc1 = p1.compute_parameters_for_node(node) |
||||
#The est CIMS are inside the resultant SetOfCIms Obj |
||||
print(sofc1.actual_cims) |
||||
|
||||
Structure Estimation Example |
||||
**************************** |
||||
|
||||
.. code-block:: python |
||||
|
||||
from PyCTBN import JsonImporter |
||||
from PyCTBN import SamplePath |
||||
from PyCTBN import StructureEstimator |
||||
|
||||
def structure_estimation_example(): |
||||
|
||||
# read the json files in ./data path |
||||
read_files = glob.glob(os.path.join('./data', "*.json")) |
||||
# initialize a JsonImporter object for the first file |
||||
importer = JsonImporter(read_files[0], 'samples', 'dyn.str', 'variables', 'Time', 'Name') |
||||
# import the data at index 0 of the outer json array |
||||
importer.import_data(0) |
||||
# construct a SamplePath Object passing a filled AbstractImporter |
||||
s1 = SamplePath(importer) |
||||
# build the trajectories |
||||
s1.build_trajectories() |
||||
# build the real structure |
||||
s1.build_structure() |
||||
# construct a StructureEstimator object |
||||
se1 = StructureEstimator(s1, 0.1, 0.1) |
||||
# call the ctpc algorithm |
||||
se1.ctpc_algorithm() |
||||
# the adjacency matrix of the estimated structure |
||||
print(se1.adjacency_matrix()) |
||||
# save results to a json file |
||||
se1.save_results() |
||||
@ -0,0 +1,41 @@ |
||||
import glob |
||||
import os |
||||
|
||||
import sys |
||||
sys.path.append("./PyCTBN/") |
||||
|
||||
import structure_graph.network_graph as ng |
||||
import structure_graph.sample_path as sp |
||||
import structure_graph.set_of_cims as sofc |
||||
import estimators.parameters_estimator as pe |
||||
import utility.json_importer as ji |
||||
|
||||
|
||||
def main(): |
||||
read_files = glob.glob(os.path.join('./data', "*.json")) #Take all json files in this dir |
||||
#import data |
||||
importer = ji.JsonImporter(read_files[0], 'samples', 'dyn.str', 'variables', 'Time', 'Name') |
||||
#Create a SamplePath Obj |
||||
s1 = sp.SamplePath(importer) |
||||
#Build The trajectries and the structural infos |
||||
s1.build_trajectories() |
||||
s1.build_structure() |
||||
#From The Structure Object build the Graph |
||||
g = ng.NetworkGraph(s1.structure) |
||||
#Select a node you want to estimate the parameters |
||||
node = g.nodes[1] |
||||
#Init the graph specifically for THIS node |
||||
g.fast_init(node) |
||||
#Use SamplePath and Grpah to create a ParametersEstimator Object |
||||
p1 = pe.ParametersEstimator(s1, g) |
||||
#Init the peEst specifically for THIS node |
||||
p1.fast_init(node) |
||||
#Compute the parameters |
||||
sofc1 = p1.compute_parameters_for_node(node) |
||||
#The est CIMS are inside the resultant SetOfCIms Obj |
||||
print(sofc1.actual_cims) |
||||
|
||||
if __name__ == "__main__": |
||||
main() |
||||
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@ -0,0 +1,22 @@ |
||||
from setuptools import setup, find_packages |
||||
|
||||
|
||||
setup(name='PyCTBN', |
||||
version='1.0', |
||||
url='https://github.com/philipMartini/PyCTBN', |
||||
license='MIT', |
||||
author=['Alessandro Bregoli', 'Filippo Martini','Luca Moretti'], |
||||
author_email=['a.bregoli1@campus.unimib.it', 'f.martini@campus.unimib.it','lucamoretti96@gmail.com'], |
||||
description='A Continuous Time Bayesian Networks Library', |
||||
packages=find_packages(exclude=['*test*','test_data','tests','PyCTBN.tests','PyCTBN.test_data']), |
||||
exclude_package_data={'': ['*test*','test_data','tests','PyCTBN.tests','PyCTBN.test_data']}, |
||||
#packages=['PyCTBN.PyCTBN'], |
||||
install_requires=[ |
||||
'numpy', 'pandas', 'networkx', 'scipy', 'matplotlib', 'tqdm'], |
||||
dependency_links=['https://github.com/numpy/numpy', 'https://github.com/pandas-dev/pandas', |
||||
'https://github.com/networkx/networkx', 'https://github.com/scipy/scipy', |
||||
'https://github.com/tqdm/tqdm'], |
||||
#long_description=open('../README.md').read(), |
||||
zip_safe=False, |
||||
include_package_data=True, |
||||
python_requires='>=3.6') |
||||
Reference in new issue