diff --git a/.gitignore b/.gitignore
index 30fca9137a69c533e197b568a14895feeec3d5c6..02bc55d7f3f7ffc75a668ac79b0b6a935683ccb5 100644
--- a/.gitignore
+++ b/.gitignore
@@ -210,7 +210,7 @@ instance/
.scrapy
# Sphinx documentation
-docs/_build/
+doc/build/
# PyBuilder
.pybuilder/
@@ -286,4 +286,5 @@ visualisation
results
outputs
notebooks
-.idea/
\ No newline at end of file
+.idea/
+erosion_test.ipynb
\ No newline at end of file
diff --git a/doc/Makefile b/doc/Makefile
new file mode 100644
index 0000000000000000000000000000000000000000..d0c3cbf1020d5c292abdedf27627c6abe25e2293
--- /dev/null
+++ b/doc/Makefile
@@ -0,0 +1,20 @@
+# Minimal makefile for Sphinx documentation
+#
+
+# You can set these variables from the command line, and also
+# from the environment for the first two.
+SPHINXOPTS ?=
+SPHINXBUILD ?= sphinx-build
+SOURCEDIR = source
+BUILDDIR = build
+
+# Put it first so that "make" without argument is like "make help".
+help:
+ @$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
+
+.PHONY: help Makefile
+
+# Catch-all target: route all unknown targets to Sphinx using the new
+# "make mode" option. $(O) is meant as a shortcut for $(SPHINXOPTS).
+%: Makefile
+ @$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
diff --git a/doc/logo.drawio b/doc/logo.drawio
new file mode 100644
index 0000000000000000000000000000000000000000..da3edc2b0eb8a4fed67eadd2fcc30dc07d4b348c
--- /dev/null
+++ b/doc/logo.drawio
@@ -0,0 +1 @@
+<mxfile host="Electron" modified="2021-05-04T12:27:55.299Z" agent="5.0 (Macintosh; Intel Mac OS X 10_16_0) AppleWebKit/537.36 (KHTML, like Gecko) draw.io/12.9.13 Chrome/80.0.3987.163 Electron/8.2.1 Safari/537.36" etag="0mYTPV5g55D7n4PHjvws" version="12.9.13" type="device"><diagram id="Whi_XeIdqUOBZHivEhyE" name="Page-1">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</diagram></mxfile>
\ No newline at end of file
diff --git a/doc/make.bat b/doc/make.bat
new file mode 100644
index 0000000000000000000000000000000000000000..9534b018135ed7d5caed6298980c55e8b1d2ec82
--- /dev/null
+++ b/doc/make.bat
@@ -0,0 +1,35 @@
+@ECHO OFF
+
+pushd %~dp0
+
+REM Command file for Sphinx documentation
+
+if "%SPHINXBUILD%" == "" (
+ set SPHINXBUILD=sphinx-build
+)
+set SOURCEDIR=source
+set BUILDDIR=build
+
+if "%1" == "" goto help
+
+%SPHINXBUILD% >NUL 2>NUL
+if errorlevel 9009 (
+ echo.
+ echo.The 'sphinx-build' command was not found. Make sure you have Sphinx
+ echo.installed, then set the SPHINXBUILD environment variable to point
+ echo.to the full path of the 'sphinx-build' executable. Alternatively you
+ echo.may add the Sphinx directory to PATH.
+ echo.
+ echo.If you don't have Sphinx installed, grab it from
+ echo.http://sphinx-doc.org/
+ exit /b 1
+)
+
+%SPHINXBUILD% -M %1 %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
+goto end
+
+:help
+%SPHINXBUILD% -M help %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
+
+:end
+popd
diff --git a/doc/source/_static/css/custom.css b/doc/source/_static/css/custom.css
new file mode 100644
index 0000000000000000000000000000000000000000..ae8f9d1401f4c3ea41b09e7758bc7ac1167f1423
--- /dev/null
+++ b/doc/source/_static/css/custom.css
@@ -0,0 +1,6 @@
+dl{
+ margin-top: 0.5em !important;
+}
+div.sphinxsidebarwrapper p.logo {
+ padding:2em !important;
+}
\ No newline at end of file
diff --git a/doc/source/conf.py b/doc/source/conf.py
new file mode 100644
index 0000000000000000000000000000000000000000..3bde0b973a7c965fff7d2e069aa66024b93a3275
--- /dev/null
+++ b/doc/source/conf.py
@@ -0,0 +1,76 @@
+# Configuration file for the Sphinx documentation builder.
+#
+# This file only contains a selection of the most common options. For a full
+# list see the documentation:
+# https://www.sphinx-doc.org/en/master/usage/configuration.html
+
+# -- Path setup --------------------------------------------------------------
+
+# If extensions (or modules to document with autodoc) are in another directory,
+# add these directories to sys.path here. If the directory is relative to the
+# documentation root, use os.path.abspath to make it absolute, like shown here.
+#
+import os
+import sys
+sys.path.insert(0, os.path.abspath('../..'))
+
+
+# -- Project information -----------------------------------------------------
+
+project = 'Link Prediction'
+copyright = '2021, Jacques Fize'
+author = 'Jacques Fize'
+
+# The full version, including alpha/beta/rc tags
+release = '0.6'
+
+
+# -- General configuration ---------------------------------------------------
+
+# Add any Sphinx extension module names here, as strings. They can be
+# extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
+# ones.
+extensions = [
+ 'sphinx.ext.autodoc',
+ 'sphinx.ext.coverage',
+ 'sphinx.ext.napoleon',
+ 'sphinx.ext.autosectionlabel'
+]
+
+# Add any paths that contain templates here, relative to this directory.
+templates_path = ['_templates']
+
+# The language for content autogenerated by Sphinx. Refer to documentation
+# for a list of supported languages.
+#
+# This is also used if you do content translation via gettext catalogs.
+# Usually you set "language" from the command line for these cases.
+language = 'en'
+
+# List of patterns, relative to source directory, that match files and
+# directories to ignore when looking for source files.
+# This pattern also affects html_static_path and html_extra_path.
+exclude_patterns = []
+
+
+# -- Options for HTML output -------------------------------------------------
+
+# The theme to use for HTML and HTML Help pages. See the documentation for
+# a list of builtin themes.
+#
+html_theme = 'alabaster'
+
+# Add any paths that contain custom static files (such as style sheets) here,
+# relative to this directory. They are copied after the builtin static files,
+# so a file named "default.css" will overwrite the builtin "default.css".
+html_static_path = ['_static']
+html_css_files = [
+ 'css/custom.css',
+]
+html_logo = "logo.png"
+
+
+napoleon_google_docstring = False
+napoleon_use_param = False
+napoleon_use_ivar = True
+
diff --git a/doc/source/get_started.rst b/doc/source/get_started.rst
new file mode 100644
index 0000000000000000000000000000000000000000..531109f4bc6a44e1d41d9619c7d571839752730c
--- /dev/null
+++ b/doc/source/get_started.rst
@@ -0,0 +1,32 @@
+Get Started
+===========
+
+Installation
+------------
+
+See :ref:`Installation`
+
+Generate a graph with a model
+-----------------------------
+
+We developed a serie of functions for generating graph based on the following models:
+
+* Spatial model
+* Stochastic Block Model
+* Configuration Model
+* Random (ER)
+* Mixed Model (Spatial + SBM
+
+For example, if you want to generate a graph based on a stochastic block model, use the following code :
+
+.. code-block:: python
+
+ from lib.random import stochastic_block_model_graph
+ G = stochastic_block_model_graph(nb_nodes=300,nb_edges=1200,nb_com=5,percentage_edge_betw=0.01)
+
+If you wish to generate a dataset containing generated graph with different configurations,
+you can use the script generate_random_graph.py` using the following command :
+
+.. code-block:: shell
+
+ python generate_theoric_random_graph.py <output_dir>
\ No newline at end of file
diff --git a/doc/source/graph_generator.rst b/doc/source/graph_generator.rst
new file mode 100644
index 0000000000000000000000000000000000000000..52128c3204fe942f64880cfaaa6c5855b3649227
--- /dev/null
+++ b/doc/source/graph_generator.rst
@@ -0,0 +1,113 @@
+
+
+Graph Generators
+===================
+
+All graph generator can be found in the module `lib.random`. For every graph generator, you can set the number of edges and nodes
+in the resulting graph.
+
+For example, if you want to generate a graph following the stochastic block model, use the follwing code :
+
+.. code-block:: python
+
+ from lib.random import stochastic_block_model_graph
+ G = stochastic_block_model_graph(nb_nodes=300,nb_edges=1200,nb_com=5,percentage_edge_betw=0.01)
+
+Stochastic Block Model
+----------------------
+This model partitions :math:`n` vertices in :math:`k` blocks, and places edges between pairs of nodes with a probability that depends on the vertices membership. The probability of a pair of nodes is computed based four parameter, the number of vertices :math:`|V|` and edges :math:`|E|`, the number of blocks :math:`|B|` and finally, the percentage of interlinks :math:`per_{betw}`, i.e number of selected pairs of nodes that belongs to different blocks.
+
+First, we assign randomly a block :math:`b_i \in B` for each node :math:`v \in V`. In this model, all blocks are associated with the same number of nodes :math:`\frac{|V|}{|B|}`. Second, to compute the probability of a pair of nodes to be connected, we use the function :math:`f(u,v)` defined as follows:
+
+.. math::
+
+ f(u,v)=\begin{cases}
+ p_{in}, & if b_u == b_v\\
+ p_{out}, & otherwise
+ \end{cases}
+
+
+where :math:`p_{in}` is the probability of a pair of nodes from the same block to be connected, and :math:`p_{out}` is the probability of a pair of nodes with different block membership to be connected. :math:`b_u` and :math:`b_v` correspond the block membership for the nodes :math:`u` and :math:`v`.
+
+
+To compute the :math:`p_{in}` and :math:`p_{out}`, we do the following:
+
+.. math::
+
+ \begin{eqnarray}
+ U_{in} = \sum\limits_{b\in B} \frac{N_b\times(N_b-1)}{2}\\
+ U = \frac{|V| \times(|V| -1)}{2}\\
+ U_{out} = U-U_{in}\\
+ L_{out} = |E| * per_{betw}\\
+ L_{in} = |E| - L_out\\
+ \\p_{in} = L_{in}/U_{in}\\
+ p_{out} = L_{out}/U_{out}
+ \end{eqnarray}
+
+
+Spatial Model
+-------------
+This model generate a graph with $n$ vertices and $e$ edges selected randomly. Edges are selected using the deterrence function defined in the following formula:
+
+.. math::
+ err(u,v) = \frac{1}{|p_u - p_v|^2 +\epsilon}
+
+where :math:`u` and :math:`v` are two vertices and :math:`p_u` and :math:`p_v` correspond to their position.
+
+Nodes coordinates can be generated randomly or randomly selected from existing places (here countries centroids).
+
+ER Random Graph
+---------------
+The model returns a Erdős-Rényi graph or a binomial graph. Basically,
+the model generates a graph :math:`G_{n,m}` where :math:`n` corresponds to the number of vertices
+and :math:`m` the number of edges in :math:`G_{n,m}`. In this model, each pair of nodes has the same
+probability to be connected.
+
+Configuration model
+-------------------
+
+The configuration model generates a graph (graph with parallel edges and self loops) by randomly assigning edges to match a given degree distribution. In our case, generated graph degree distribution follows a powerlaw. We use the Molloy-Reed approach [molloy1995critical]_ to generate the graph.
+
+.. [molloy1995critical] Molloy, M., & Reed, B. (1995). A critical point for random graphs with a given degree sequence. Random structures & algorithms, 6(2â€3), 161-180.
+Generate a graph dataset based on different models and configurations
+---------------------------------------------------------------------
+
+If you wish to generate a dataset containing generated graph with different configurations,
+you can use the script generate_random_graph.py` using the following command :
+
+.. code-block:: shell
+
+ python generate_theoric_random_graph.py <output_dir>
+
+
+You can modify the parameters of each configuration for each model in the script source code.
+
+Graph parameters
+^^^^^^^^^^^^^^^^
+
+.. code-block:: python
+
+ GRAPH_SIZE = [80,800,5000]
+ EDGE_FACTOR = [2,4,5,10]
+ sample_per_params = 10
+
+Model parameters
+^^^^^^^^^^^^^^^^
+
+.. code-block:: python
+
+ parameters = {
+ "stochastic_block_model_graph": {
+ "nb_nodes":GRAPH_SIZE,
+ "nb_edges":EDGE_FACTOR,
+ "nb_com" :[2,5,8,16,10,25],
+ "percentage_edge_betw":[0.1,0.01],
+ },
+ #...
+ }
+
+
+API Reference
+-------------
+.. automodule:: lib.random
+ :members:
\ No newline at end of file
diff --git a/doc/source/index.rst b/doc/source/index.rst
new file mode 100644
index 0000000000000000000000000000000000000000..13a6a5c047e4bae3876cbd53fbdcbded87b55ad8
--- /dev/null
+++ b/doc/source/index.rst
@@ -0,0 +1,29 @@
+.. Link Prediction documentation master file, created by
+ sphinx-quickstart on Tue May 4 13:26:48 2021.
+ You can adapt this file completely to your liking, but it should at least
+ contain the root `toctree` directive.
+
+Welcome to Link Prediction's documentation!
+===========================================
+
+Summary
+-------
+.. toctree::
+ :maxdepth: 2
+
+ installation
+ get_started
+ graph_generator
+ link_pred_eval
+
+
+
+
+
+
+Indices and tables
+==================
+
+* :ref:`genindex`
+* :ref:`modindex`
+* :ref:`search`
diff --git a/doc/source/installation.rst b/doc/source/installation.rst
new file mode 100644
index 0000000000000000000000000000000000000000..984e0c3c06318e46df1bcfb8648d567dd7ee6ddc
--- /dev/null
+++ b/doc/source/installation.rst
@@ -0,0 +1,20 @@
+Installation
+============
+
+To use the code in this repo, first you'll need to install Python requirements using the following command
+
+.. code-block:: shell
+
+ pip install -r requirements.txt
+
+
+Then, install our custom version of EvalNE using pip
+
+.. code-block:: shell
+
+ pip install git+https://github.com/thunlp/OpenNE.git
+ pip install git+https://github.com/Jacobe2169/EvalNE
+
+
+Finally, install the Python library `graph-tool
+<https://graph-tool.skewed.de>`_.
\ No newline at end of file
diff --git a/doc/source/link_pred_eval.rst b/doc/source/link_pred_eval.rst
new file mode 100644
index 0000000000000000000000000000000000000000..82573ee20705d9c16d79bfe682747960fc836c8e
--- /dev/null
+++ b/doc/source/link_pred_eval.rst
@@ -0,0 +1,2 @@
+Link Prediction Evaluation
+==========================
diff --git a/doc/source/logo.png b/doc/source/logo.png
new file mode 100644
index 0000000000000000000000000000000000000000..23d8b54dc7122fc7bdb43e2a0507706aba0dca57
Binary files /dev/null and b/doc/source/logo.png differ
diff --git a/evalNE_script.py b/evalNE_script.py
index faa3c6e3341f5f71e342a6981afe7dfbdb9baa8a..ceef7564c427a328b9a9a3ae53c0ef6545e69592 100644
--- a/evalNE_script.py
+++ b/evalNE_script.py
@@ -1,13 +1,17 @@
+import argparse
+
+from lib.utils import load_edgelist
+
from evalne.evaluation.evaluator import LPEvaluator
from evalne.evaluation.split import EvalSplit as LPEvalSplit
from evalne.evaluation.score import Scoresheet
from evalne.utils import preprocess as pp
+
import networkx as nx
from tqdm import tqdm
-from lib.utils import load_edgelist
-import argparse
+
parser = argparse.ArgumentParser()
parser.add_argument("graph_filename")
diff --git a/eval_mixed_model.py b/eval_mixed_model.py
index 22c8b7bc689d5c3f6a29296350e1212448646ee3..aaa89da1873224c8500549132de5b7b9ff5e494c 100644
--- a/eval_mixed_model.py
+++ b/eval_mixed_model.py
@@ -1,17 +1,17 @@
# coding = utf-8
import argparse
import time
+import glob
+
+from lib.erosion_model import eval_erosion_model
+from lib.utils import load_edgelist
import pandas as pd
+import networkx as nx
-from lib.random import mixed_model_spat_sbm
-from lib.erosion_model import eval_erosion_model
from joblib import Parallel,delayed
-import networkx as nx
-import glob
from tqdm import tqdm
-from lib.utils import load_edgelist
parser = argparse.ArgumentParser()
parser.add_argument("graph_dir")
diff --git a/generate_graph_atlas.py b/generate_graph_atlas.py
index 1c90fe92fd289c9c1dfe233a1b0a6c84c2d79e50..844edb1d62d5bd1579ba16833477b1ab492b4b0e 100644
--- a/generate_graph_atlas.py
+++ b/generate_graph_atlas.py
@@ -1,15 +1,17 @@
# coding = utf-8
-
-import networkx as nx
-import matplotlib.pyplot as plt
-import seaborn as sns
import glob
-import numpy as np
import re
-import pandas as pd
import argparse
import os
+import pandas as pd
+import numpy as np
+import networkx as nx
+
+import matplotlib.pyplot as plt
+import seaborn as sns
+
+
parser = argparse.ArgumentParser()
parser.add_argument("graph_directory")
parser.add_argument("output_directory")
diff --git a/generate_mixed_model_graph.py b/generate_mixed_model_graph.py
index 6a6d80c5f624b51325168c2d7a821337bec7c3ba..2eb32e9976850eb21ff0bf7644ba0f850ed00aea 100644
--- a/generate_mixed_model_graph.py
+++ b/generate_mixed_model_graph.py
@@ -1,11 +1,12 @@
# coding = utf-8
import itertools
import os
+import argparse
+
+import lib.random as ra
import networkx as nx
-import argparse
from tqdm import tqdm
-import lib.random as ra
# COMMAND PARSING
parser = argparse.ArgumentParser()
diff --git a/generate_theoric_random_graph.py b/generate_theoric_random_graph.py
index 51ca442da1585eb8a584de318966febf2f94fb44..fba4cc234617d1c1cca511440b9ced836243b02f 100644
--- a/generate_theoric_random_graph.py
+++ b/generate_theoric_random_graph.py
@@ -1,11 +1,13 @@
# coding = utf-8
import itertools
import os
+import argparse
+
+import lib.random as ra
import networkx as nx
-import argparse
from tqdm import tqdm
-import lib.random as ra
+
# COMMAND PARSING
parser = argparse.ArgumentParser()
diff --git a/lib/draw.py b/lib/draw.py
index a1f8d6b01f917c1af163d1e3fc1d069a77b3e28c..5f13a181988d3f1d2e9eeff118c04976583bb4b1 100644
--- a/lib/draw.py
+++ b/lib/draw.py
@@ -1,13 +1,13 @@
-import matplotlib.pyplot as plt
-import matplotlib.patheffects as path_effects
-import seaborn as sns
-import networkx as nx
+from glob import glob
+
import pandas as pd
import numpy as np
-from glob import glob
+import networkx as nx
from fa2 import ForceAtlas2
-
+import matplotlib.pyplot as plt
+import matplotlib.patheffects as path_effects
+import seaborn as sns
def get_force_atlas(weight_influence=0, scaling_ratio=3.0, gravity=5):
"""
diff --git a/lib/erosion_model.py b/lib/erosion_model.py
index 48eb731473891ac9edc82570336532d1bcb5798b..74c330649ca0e4e738b4a9f9a95d6ab8f68e6337 100644
--- a/lib/erosion_model.py
+++ b/lib/erosion_model.py
@@ -1,8 +1,5 @@
# coding = utf-8
-from sklearn.linear_model import LogisticRegression
-from sklearn.metrics import roc_auc_score
-
from .link_prediction_eval import get_auc_heuristics, split_train_test, get_all_possible_edges
from .lambda_func import euclid_dist as dist
from .lambda_func import hash_func
@@ -15,6 +12,9 @@ import networkx as nx
import numpy as np
float_epsilon = np.finfo(float).eps
+from sklearn.linear_model import LogisticRegression
+from sklearn.metrics import roc_auc_score
+
VERBOSE = True
def log(x):
if VERBOSE:
diff --git a/lib/helpers.py b/lib/helpers.py
index e5db269b09e8292ab00595ad05d369c72e10442f..a71fe46c3cb3b84fa1fcefa2b0f5a1c4f12dac8c 100644
--- a/lib/helpers.py
+++ b/lib/helpers.py
@@ -1,14 +1,14 @@
+from .link_prediction_eval import get_all_possible_edges
+
import numpy as np
import networkx as nx
import pandas as pd
-from .link_prediction_eval import get_all_possible_edges
-
-
try:
import graph_tool as gt
except:
- pass
+ raise ImportError("Graph-tool must be installed !")
+
def parse_evalne_output(string):
def foo(x):
diff --git a/lib/link_prediction_eval.py b/lib/link_prediction_eval.py
index c022e833c213aa480effdc3956074d0a7f3f0289..0b69165f04fc47fde8cb7797da984c4c09d33b0f 100644
--- a/lib/link_prediction_eval.py
+++ b/lib/link_prediction_eval.py
@@ -1,10 +1,11 @@
# coding = utf-8
+from .lambda_func import hash_func
from evalne.evaluation.evaluator import LPEvaluator
from evalne.evaluation.split import EvalSplit as LPEvalSplit
from evalne.utils import preprocess as pp
-from .lambda_func import hash_func
+
def get_auc_heuristics(G,timeout=60):
H, _ = pp.prep_graph(G.copy(),maincc=True,relabel=False)
diff --git a/lib/random.py b/lib/random.py
index 5b4f1c4ec451fcbdbc13440a1e7734103f4da649..70cdf8df0934d659df3de909a4a1eb892c229dec 100644
--- a/lib/random.py
+++ b/lib/random.py
@@ -1,19 +1,20 @@
# coding = utf-8
from collections import Iterable
+import random
import numpy as np
-import networkx as nx
import pandas as pd
+import networkx as nx
from networkx.generators.degree_seq import _to_stublist
-import random
-float_epsilon = np.finfo(float).eps
-
+float_epsilon = np.finfo(float).eps
def powerlaw(nb_nodes, nb_edges, exponent=2, tries=100, min_deg=1):
"""
Return a degree distribution that fit the power law and specified number of edges and vertices.
+ ddd
+
Parameters
----------
nb_nodes : int
@@ -64,6 +65,7 @@ def powerlaw(nb_nodes, nb_edges, exponent=2, tries=100, min_deg=1):
def get_countries_coords():
"""
Return the coordinates of each country in the world.
+
Returns
-------
np.ndarray
@@ -108,6 +110,7 @@ def powerlaw_graph(nb_nodes, nb_edges, exponent=2, tries=1000, min_deg=0):
"""
Generate a graph with a defined number of vertices, edges, and a degree distribution that fit the power law.
Using the Molloy-Reed algorithm to
+
Parameters
----------
nb_nodes : int
@@ -157,6 +160,7 @@ def spatial_graph(nb_nodes, nb_edges, coords="country", dist_func=lambda a, b: n
self_link=False, weighted=False):
"""
Generate a spatial graph with a specific number of vertices and edges
+
Parameters
----------
nb_nodes : int
@@ -253,6 +257,7 @@ def spatial_graph(nb_nodes, nb_edges, coords="country", dist_func=lambda a, b: n
def ER_graph(nb_nodes, nb_edges):
"""
Generate a random graph with a specific nb of nodes and edges.
+
Parameters
----------
nb_nodes : int
@@ -269,6 +274,7 @@ def ER_graph(nb_nodes, nb_edges):
def stochastic_block_model_graph(nb_nodes, nb_edges, nb_com, percentage_edge_betw, verbose=False):
"""
Generate a stochastic block model graph with defined number of vertices and edges.
+
Parameters
----------
nb_nodes : int
@@ -352,6 +358,7 @@ def equilibrate(G, nb_nodes, percentage_edge_betw, percentage_edge_within, inter
"""
Sometimes the generated graph from the stochastic block model have some missing nodes due to the sampling method.
This function fix this issue.
+
Parameters
----------
G
@@ -512,57 +519,3 @@ def mixed_model_spat_sbm(nb_nodes, nb_edges, nb_com, alpha, percentage_edge_betw
return G2#,all_probs_sbm,all_probs_spa
-
-def get_sbm_probs(G, percentage_edge_betw, verbose=False):
- hash_func = lambda x: "_".join(sorted([str(x[0]), str(x[1])]))
- def nb_of_pair(N):
- return (N*(N-1))/2
-
- block_assign = nx.get_node_attributes(G, "block")
- nb_com = len(set(block_assign.values()))
- nb_nodes=len(G)
- nb_edges = G.size()
- b_assign_array = np.asarray(list(nx.get_node_attributes(G,"block").values()))
-
-
-
- u_in = sum([nb_of_pair((b_assign_array==b).sum()) for b in range(nb_com)])
- u_out = nb_of_pair(len(G)) - u_in
- l_out = nb_edges*percentage_edge_betw
- p_out = l_out/u_out
- l_in = nb_edges - l_out
-
- p_in = l_in / u_in
-
- inter_edges, intra_edges = get_inter_intra_edges(G,G.is_directed())
- inter_edges = np.asarray(inter_edges)
- intra_edges = np.asarray(intra_edges)
- inter_N, intra_N = len(inter_edges), len(intra_edges)
- probs_inter = np.ones(inter_N) * p_out
- probs_intra = np.ones(intra_N) * p_in
-
- all_edges = np.concatenate((inter_edges, intra_edges))
- all_probs = np.concatenate((probs_inter, probs_intra))
- del probs_inter
- del probs_intra
- return all_edges,all_probs
-
-
-def get_spat_probs(G,dist = lambda a,b : np.linalg.norm(a-b)**2):
- hash_func = lambda x: "_".join(sorted([str(x[0]), str(x[1])]))
- pos = nx.get_node_attributes(G, "pos")
- spat_model = lambda u, v: 1 / (float_epsilon + dist(pos[u], pos[v]))
- register = set([])
- edges, probs = [], []
- for n1 in list(G.nodes()):
- for n2 in list(G.nodes()):
- if n1 != n2 and hash_func((n1, n2)) not in register:
- edges.append([n1, n2])
- probs.append(spat_model(n1, n2))
- register.add(hash_func((n1, n2)))
-
- return edges, probs
-
-
-
-
diff --git a/lib/visualisation.py b/lib/visualisation.py
index ed5d6f45019642453fefadd22d49577ed93bbca3..9e8bdab8cbaee7a616d5af788ae608c2b420ee95 100644
--- a/lib/visualisation.py
+++ b/lib/visualisation.py
@@ -1,13 +1,12 @@
# coding = utf-8
-
-import pandas as pd
-import seaborn as sns
-import matplotlib.pyplot as plt
import re
import os
+import pandas as pd
import networkx as nx
+import seaborn as sns
+import matplotlib.pyplot as plt
def get_graph_attr(fn, graph_dir):
g_fn = os.path.join(graph_dir, fn)
diff --git a/requirements.txt b/requirements.txt
index 4d553c63be14c3096820ec8f69537515720c856a..fd69055a7735a5490422fd5c1764c32be2d04590 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -10,3 +10,5 @@ seaborn
joblib
tqdm
scikit-learn
+fa2
+numpydoc