Merge pull request #30 from KrishnaswamyLab/dev

graphtools v0.2.1

README.rst

@@ -5,8 +5,8 @@ graphtools
 .. image:: https://img.shields.io/pypi/v/graphtools.svg
     :target: https://pypi.org/project/graphtools/
     :alt: Latest PyPi version
-.. image:: https://anaconda.org/conda-forge/tasklogger/badges/version.svg
-    :target: https://anaconda.org/conda-forge/tasklogger/
+.. image:: https://anaconda.org/conda-forge/graphtools/badges/version.svg
+    :target: https://anaconda.org/conda-forge/graphtools/
     :alt: Latest Conda version
 .. image:: https://api.travis-ci.com/KrishnaswamyLab/graphtools.svg?branch=master
     :target: https://travis-ci.com/KrishnaswamyLab/graphtools
@@ -39,11 +39,7 @@ Alternatively, graphtools can be installed using `Conda <https://conda.io/docs/>
 
 Or, to install the latest version from github::
 
-        pip install --user git+git://github.com/KrishnaswamyLab/graphtools.git
-        
-Alternatively, graphtools can be installed using [Conda](https://conda.io/docs/) (most easily obtained via the [Miniconda Python distribution](https://conda.io/miniconda.html)):
-
-        conda install -c conda-forge graphtools
+    pip install --user git+git://github.com/KrishnaswamyLab/graphtools.git
 
 Usage example
 -------------

doc/source/index.rst

@@ -6,6 +6,10 @@ graphtools
 
     <a href="https://pypi.org/project/graphtools/"><img src="https://img.shields.io/pypi/v/graphtools.svg" alt="Latest PyPi version"></a>
 
+.. raw:: html
+
+    <a href="https://anaconda.org/conda-forge/graphtools/"><img src="https://anaconda.org/conda-forge/graphtools/badges/version.svg" alt="Latest Conda version"></a>
+
 .. raw:: html
 
     <a href="https://travis-ci.com/KrishnaswamyLab/graphtools"><img src="https://api.travis-ci.com/KrishnaswamyLab/graphtools.svg?branch=master" alt="Travis CI Build"></a>

graphtools/api.py

@@ -15,6 +15,7 @@ def Graph(data,
           knn=5,
           decay=10,
           bandwidth=None,
+          anisotropy=0,
           distance='euclidean',
           thresh=1e-4,
           kernel_symm='+',
@@ -68,6 +69,10 @@ def Graph(data,
         bandwidth or a list-like (shape=[n_samples]) of bandwidths for each
         sample.
 
+    anisotropy : float, optional (default: 0)
+        Level of anisotropy between 0 and 1
+        (alpha in Coifman & Lafon, 2006)
+
     distance : `str`, optional (default: `'euclidean'`)
         Any metric from `scipy.spatial.distance` can be used
         distance metric for building kNN graph.
@@ -230,7 +235,7 @@ def Graph(data,
     return Graph(**params)
 
 
-def from_igraph(G, **kwargs):
+def from_igraph(G, attribute="weight", **kwargs):
     """Convert an igraph.Graph to a graphtools.Graph
 
     Creates a graphtools.graphs.TraditionalGraph with a
@@ -240,6 +245,9 @@ def from_igraph(G, **kwargs):
     ----------
     G : igraph.Graph
         Graph to be converted
+    attribute : str, optional (default: "weight")
+        attribute containing edge weights, if any.
+        If None, unweighted graph is built
     kwargs
         keyword arguments for graphtools.Graph
 
@@ -254,5 +262,13 @@ def from_igraph(G, **kwargs):
                 "Use 'adjacency' instead.".format(kwargs['precomputed']),
                 UserWarning)
         del kwargs['precomputed']
-    return Graph(sparse.coo_matrix(G.get_adjacency().data),
+    try:
+        K = G.get_adjacency(attribute=attribute).data
+    except ValueError as e:
+        if str(e) == "Attribute does not exist":
+            warnings.warn("Edge attribute {} not found. "
+                          "Returning unweighted graph".format(attribute),
+                          UserWarning)
+        K = G.get_adjacency(attribute=None).data
+    return Graph(sparse.coo_matrix(K),
                  precomputed='adjacency', **kwargs)

graphtools/base.py

@@ -23,9 +23,7 @@
     # anndata not installed
     pass
 
-from .utils import (elementwise_minimum,
-                    elementwise_maximum,
-                    set_diagonal)
+from . import utils
 
 
 class Base(object):
@@ -318,6 +316,10 @@ class BaseGraph(with_metaclass(abc.ABCMeta, Base)):
         Min-max symmetrization constant.
         K = `theta * min(K, K.T) + (1 - theta) * max(K, K.T)`
 
+    anisotropy : float, optional (default: 0)
+        Level of anisotropy between 0 and 1
+        (alpha in Coifman & Lafon, 2006)
+
     initialize : `bool`, optional (default : `True`)
         if false, don't create the kernel matrix.
 
@@ -336,8 +338,10 @@ class BaseGraph(with_metaclass(abc.ABCMeta, Base)):
     diff_op : synonym for `P`
     """
 
-    def __init__(self, kernel_symm='+',
+    def __init__(self,
+                 kernel_symm='+',
                  theta=None,
+                 anisotropy=0,
                  gamma=None,
                  initialize=True, **kwargs):
         if gamma is not None:
@@ -351,6 +355,10 @@ def __init__(self, kernel_symm='+',
         self.kernel_symm = kernel_symm
         self.theta = theta
         self._check_symmetrization(kernel_symm, theta)
+        if not (isinstance(anisotropy, numbers.Real) and 0 <= anisotropy <= 1):
+            raise ValueError("Expected 0 <= anisotropy <= 1. "
+                             "Got {}".format(anisotropy))
+        self.anisotropy = anisotropy
 
         if initialize:
             tasklogger.log_debug("Initializing kernel...")
@@ -395,6 +403,7 @@ def _build_kernel(self):
         """
         kernel = self.build_kernel()
         kernel = self.symmetrize_kernel(kernel)
+        kernel = self.apply_anisotropy(kernel)
         if (kernel - kernel.T).max() > 1e-5:
             warnings.warn("K should be symmetric", RuntimeWarning)
         if np.any(kernel.diagonal == 0):
@@ -412,8 +421,8 @@ def symmetrize_kernel(self, K):
         elif self.kernel_symm == 'theta':
             tasklogger.log_debug(
                 "Using theta symmetrization (theta = {}).".format(self.theta))
-            K = self.theta * elementwise_minimum(K, K.T) + \
-                (1 - self.theta) * elementwise_maximum(K, K.T)
+            K = self.theta * utils.elementwise_minimum(K, K.T) + \
+                (1 - self.theta) * utils.elementwise_maximum(K, K.T)
         elif self.kernel_symm is None:
             tasklogger.log_debug("Using no symmetrization.")
             pass
@@ -424,11 +433,27 @@ def symmetrize_kernel(self, K):
                 "Got {}".format(self.theta))
         return K
 
+    def apply_anisotropy(self, K):
+        if self.anisotropy == 0:
+            # do nothing
+            return K
+        else:
+            if sparse.issparse(K):
+                d = np.array(K.sum(1)).flatten()
+                K = K.tocoo()
+                K.data = K.data / ((d[K.row] * d[K.col]) ** self.anisotropy)
+                K = K.tocsr()
+            else:
+                d = K.sum(1)
+                K = K / (np.outer(d, d) ** self.anisotropy)
+        return K
+
     def get_params(self):
         """Get parameters from this object
         """
         return {'kernel_symm': self.kernel_symm,
-                'theta': self.theta}
+                'theta': self.theta,
+                'anisotropy': self.anisotropy}
 
     def set_params(self, **params):
         """Set parameters on this object
@@ -450,6 +475,9 @@ def set_params(self, **params):
         """
         if 'theta' in params and params['theta'] != self.theta:
             raise ValueError("Cannot update theta. Please create a new graph")
+        if 'anisotropy' in params and params['anisotropy'] != self.anisotropy:
+            raise ValueError(
+                "Cannot update anisotropy. Please create a new graph")
         if 'kernel_symm' in params and \
                 params['kernel_symm'] != self.kernel_symm:
             raise ValueError(
@@ -580,6 +608,30 @@ def to_pygsp(self, **kwargs):
                          precomputed="affinity", use_pygsp=True,
                          **kwargs)
 
+    def to_igraph(self, attribute="weight", **kwargs):
+        """Convert to an igraph Graph
+
+        Uses the igraph.Graph.Weighted_Adjacency constructor
+
+        Parameters
+        ----------
+        attribute : str, optional (default: "weight")
+        kwargs : additional arguments for igraph.Graph.Weighted_Adjacency
+        """
+        try:
+            import igraph as ig
+        except ImportError:
+            raise ImportError("Please install igraph with "
+                              "`pip install --user python-igraph`.")
+        try:
+            W = self.W
+        except AttributeError:
+            # not a pygsp graph
+            W = self.K.copy()
+            W = utils.set_diagonal(W, 0)
+        return ig.Graph.Weighted_Adjacency(utils.to_dense(W).tolist(),
+                                           attr=attribute, **kwargs)
+
 
 class PyGSPGraph(with_metaclass(abc.ABCMeta, pygsp.graphs.Graph, Base)):
     """Interface between BaseGraph and PyGSP.
@@ -634,7 +686,7 @@ def _build_weight_from_kernel(self, kernel):
 
         weight = kernel.copy()
         self._diagonal = weight.diagonal().copy()
-        weight = set_diagonal(weight, 0)
+        weight = utils.set_diagonal(weight, 0)
         return weight
 
 

graphtools/graphs.py

@@ -44,7 +44,8 @@ class kNNGraph(DataGraph):
 
     distance : `str`, optional (default: `'euclidean'`)
         Any metric from `scipy.spatial.distance` can be used
-        distance metric for building kNN graph.
+        distance metric for building kNN graph. Custom distance
+        functions of form `f(x, y) = d` are also accepted.
         TODO: actually sklearn.neighbors has even more choices
 
     thresh : `float`, optional (default: `1e-4`)

graphtools/utils.py

@@ -44,3 +44,9 @@ def set_diagonal(X, diag):
 def set_submatrix(X, i, j, values):
     X[np.ix_(i, j)] = values
     return X
+
+
+def to_dense(X):
+    if sparse.issparse(X):
+        X = X.toarray()
+    return X

graphtools/version.py

@@ -1 +1 @@
-__version__ = "0.2.0"
+__version__ = "0.2.1"

requirements.txt

@@ -1,6 +1,6 @@
 numpy>=1.14.0
 scipy>=1.1.0
 pygsp>=>=0.5.1
-scikit-learn>=0.19.1
+scikit-learn>=0.20.0
 future
 tasklogger>=0.4.0

setup.py

@@ -6,7 +6,7 @@
     'numpy>=1.14.0',
     'scipy>=1.1.0',
     'pygsp>=0.5.1',
-    'scikit-learn>=0.19.1',
+    'scikit-learn>=0.20.0',
     'future',
     'tasklogger>=0.4.0',
 ]

test/load_tests/__init__.py

@@ -17,6 +17,7 @@ def reset_warnings():
     warnings.simplefilter("error")
     ignore_numpy_warning()
     ignore_igraph_warning()
+    ignore_joblib_warning()
 
 
 def ignore_numpy_warning():
@@ -34,6 +35,13 @@ def ignore_igraph_warning():
         "ConfigParser directly instead")
 
 
+def ignore_joblib_warning():
+    warnings.filterwarnings(
+        "ignore", category=DeprecationWarning,
+        message="check_pickle is deprecated in joblib 0.12 and will be removed"
+        " in 0.13")
+
+
 reset_warnings()
 
 global digits

test/test_api.py

@@ -1,12 +1,10 @@
 from __future__ import print_function
 from load_tests import (
-    nose2,
     data,
     build_graph,
     raises,
     warns,
 )
-import warnings
 
 import igraph
 import numpy as np
@@ -21,6 +19,19 @@ def test_from_igraph():
         e = np.random.choice(n, 2, replace=False)
         K[e[0], e[1]] = K[e[1], e[0]] = 1
     g = igraph.Graph.Adjacency(K.tolist())
+    G = graphtools.from_igraph(g, attribute=None)
+    G2 = graphtools.Graph(K, precomputed='adjacency')
+    assert np.all(G.K == G2.K)
+
+
+def test_from_igraph_weighted():
+    n = 100
+    m = 500
+    K = np.zeros((n, n))
+    for _ in range(m):
+        e = np.random.choice(n, 2, replace=False)
+        K[e[0], e[1]] = K[e[1], e[0]] = np.random.uniform(0, 1)
+    g = igraph.Graph.Weighted_Adjacency(K.tolist())
     G = graphtools.from_igraph(g)
     G2 = graphtools.Graph(K, precomputed='adjacency')
     assert np.all(G.K == G2.K)
@@ -35,7 +46,19 @@ def test_from_igraph_invalid_precomputed():
         e = np.random.choice(n, 2, replace=False)
         K[e[0], e[1]] = K[e[1], e[0]] = 1
     g = igraph.Graph.Adjacency(K.tolist())
-    G = graphtools.from_igraph(g, precomputed='affinity')
+    G = graphtools.from_igraph(g, attribute=None, precomputed='affinity')
+
+
+@warns(UserWarning)
+def test_from_igraph_invalid_attribute():
+    n = 100
+    m = 500
+    K = np.zeros((n, n))
+    for _ in range(m):
+        e = np.random.choice(n, 2, replace=False)
+        K[e[0], e[1]] = K[e[1], e[0]] = 1
+    g = igraph.Graph.Adjacency(K.tolist())
+    G = graphtools.from_igraph(g, attribute="invalid")
 
 
 def test_to_pygsp():
@@ -45,6 +68,14 @@ def test_to_pygsp():
     assert np.all(G2.K == G.K)
 
 
+def test_to_igraph():
+    G = build_graph(data, use_pygsp=True)
+    G2 = G.to_igraph()
+    assert isinstance(G2, igraph.Graph)
+    assert np.all(np.array(G2.get_adjacency(
+        attribute="weight").data) == G.W)
+
+
 @warns(UserWarning)
 def test_to_pygsp_invalid_precomputed():
     G = build_graph(data)