Merge pull request #25 from KrishnaswamyLab/dev

Bump to graphtools v0.1.10

Author: scottgigante

LICENSE

@@ -37,7 +37,8 @@
               'sphinx.ext.doctest',
               'sphinx.ext.coverage',
               'sphinx.ext.mathjax',
-              'sphinx.ext.viewcode']
+              'sphinx.ext.viewcode',
+              'sphinxcontrib.bibtex']
 
 # Add any paths that contain templates here, relative to this directory.
 templates_path = ['ytemplates']

doc/source/conf.py

@@ -36,12 +36,3 @@ Utilities
     :undoc-members:
     :inherited-members:
     :show-inheritance:
-
-Logging
--------
-
-.. automodule:: graphtools.logging
-    :members:
-    :undoc-members:
-    :inherited-members:
-    :show-inheritance:

doc/source/reference.rst

@@ -5,3 +5,4 @@ scikit-learn>=0.19.1
 future
 sphinx
 sphinxcontrib-napoleon
+sphinxcontrib-bibtex

doc/source/requirements.txt

@@ -1,10 +1,9 @@
 import numpy as np
 import warnings
+import tasklogger
 
-from .logging import (set_logging,
-                      log_debug)
-from .base import PyGSPGraph
-from .graphs import kNNGraph, TraditionalGraph, MNNGraph, LandmarkGraph
+from . import base
+from . import graphs
 
 
 def Graph(data,
@@ -138,7 +137,7 @@ def Graph(data,
     ------
     ValueError : if selected parameters are incompatible.
     """
-    set_logging(verbose)
+    tasklogger.set_level(verbose)
     if sample_idx is not None and len(np.unique(sample_idx)) == 1:
         warnings.warn("Only one unique sample. "
                       "Not using MNNGraph")
@@ -159,7 +158,7 @@ def Graph(data,
 
     # set base graph type
     if graphtype == "knn":
-        base = kNNGraph
+        basegraph = graphs.kNNGraph
         if precomputed is not None:
             raise ValueError("kNNGraph does not support precomputed "
                              "values. Use `graphtype='exact'` or "
@@ -170,13 +169,13 @@ def Graph(data,
                              "`sample_idx=None`")
 
     elif graphtype == "mnn":
-        base = MNNGraph
+        basegraph = graphs.MNNGraph
         if precomputed is not None:
             raise ValueError("MNNGraph does not support precomputed "
                              "values. Use `graphtype='exact'` and "
                              "`sample_idx=None` or `precomputed=None`")
     elif graphtype == "exact":
-        base = TraditionalGraph
+        basegraph = graphs.TraditionalGraph
         if sample_idx is not None:
             raise ValueError("TraditionalGraph does not support batch "
                              "correction. Use `graphtype='mnn'` or "
@@ -186,32 +185,24 @@ def Graph(data,
                          "['knn', 'mnn', 'exact', 'auto']")
 
     # set add landmarks if necessary
-    parent_classes = [base]
+    parent_classes = [basegraph]
     msg = "Building {} graph".format(graphtype)
     if n_landmark is not None:
-        parent_classes.append(LandmarkGraph)
+        parent_classes.append(graphs.LandmarkGraph)
         msg = msg + " with landmarks"
     if use_pygsp:
-        parent_classes.append(PyGSPGraph)
+        parent_classes.append(base.PyGSPGraph)
         if len(parent_classes) > 2:
             msg = msg + " with PyGSP inheritance"
         else:
             msg = msg + " and PyGSP inheritance"
 
-    log_debug(msg)
-
-    # Python3 syntax only
-    # class Graph(*parent_classes):
-    #     pass
-    if len(parent_classes) == 1:
-        Graph = parent_classes[0]
-    elif len(parent_classes) == 2:
-        class Graph(parent_classes[0], parent_classes[1]):
-            pass
-    elif len(parent_classes) == 3:
-        class Graph(parent_classes[0], parent_classes[1], parent_classes[2]):
-            pass
-    else:
+    tasklogger.log_debug(msg)
+
+    class_names = [p.__name__.replace("Graph", "") for p in parent_classes]
+    try:
+        Graph = eval("graphs." + "".join(class_names) + "Graph")
+    except NameError:
         raise RuntimeError("unknown graph classes {}".format(parent_classes))
 
     params = kwargs
@@ -224,7 +215,7 @@ class Graph(parent_classes[0], parent_classes[1], parent_classes[2]):
                 pass
 
     # build graph and return
-    log_debug("Initializing {} with arguments {}".format(
+    tasklogger.log_debug("Initializing {} with arguments {}".format(
         parent_classes,
         ", ".join(["{}='{}'".format(key, value)
                    for key, value in params.items()

graphtools/api.py

@@ -9,6 +9,8 @@
 from scipy import sparse
 import warnings
 import numbers
+import tasklogger
+
 try:
     import pandas as pd
 except ImportError:
@@ -24,10 +26,6 @@
 from .utils import (elementwise_minimum,
                     elementwise_maximum,
                     set_diagonal)
-from .logging import (set_logging,
-                      log_start,
-                      log_complete,
-                      log_debug)
 
 
 class Base(object):
@@ -67,6 +65,9 @@ def _get_param_names(cls):
 
         return parameters
 
+    def set_params(self, **kwargs):
+        return self
+
 
 class Data(Base):
     """Parent class that handles the import and dimensionality reduction of data
@@ -152,7 +153,7 @@ def _reduce_data(self):
         Reduced data matrix
         """
         if self.n_pca is not None and self.n_pca < self.data.shape[1]:
-            log_start("PCA")
+            tasklogger.log_start("PCA")
             if sparse.issparse(self.data):
                 if isinstance(self.data, sparse.coo_matrix) or \
                         isinstance(self.data, sparse.lil_matrix) or \
@@ -166,7 +167,7 @@ def _reduce_data(self):
                                     random_state=self.random_state)
             self.data_pca.fit(self.data)
             data_nu = self.data_pca.transform(self.data)
-            log_complete("PCA")
+            tasklogger.log_complete("PCA")
             return data_nu
         else:
             data_nu = self.data
@@ -204,6 +205,7 @@ def set_params(self, **params):
             raise ValueError("Cannot update n_pca. Please create a new graph")
         if 'random_state' in params:
             self.random_state = params['random_state']
+        super().set_params(**params)
         return self
 
     def transform(self, Y):
@@ -342,10 +344,10 @@ def __init__(self, kernel_symm='+',
         self._check_symmetrization(kernel_symm, gamma)
 
         if initialize:
-            log_debug("Initializing kernel...")
+            tasklogger.log_debug("Initializing kernel...")
             self.K
         else:
-            log_debug("Not initializing kernel.")
+            tasklogger.log_debug("Not initializing kernel.")
         super().__init__(**kwargs)
 
     def _check_symmetrization(self, kernel_symm, gamma):
@@ -363,7 +365,8 @@ def _check_symmetrization(self, kernel_symm, gamma):
                 warnings.warn("kernel_symm='gamma' but gamma not given. "
                               "Defaulting to gamma=0.5.")
                 self.gamma = gamma = 0.5
-            elif not isinstance(gamma, numbers.Number) or gamma < 0 or gamma > 1:
+            elif not isinstance(gamma, numbers.Number) or \
+                    gamma < 0 or gamma > 1:
                 raise ValueError("gamma {} not recognized. Expected "
                                  "a float between 0 and 1".format(gamma))
 
@@ -392,18 +395,18 @@ def _build_kernel(self):
     def symmetrize_kernel(self, K):
         # symmetrize
         if self.kernel_symm == "+":
-            log_debug("Using addition symmetrization.")
+            tasklogger.log_debug("Using addition symmetrization.")
             K = (K + K.T) / 2
         elif self.kernel_symm == "*":
-            log_debug("Using multiplication symmetrization.")
+            tasklogger.log_debug("Using multiplication symmetrization.")
             K = K.multiply(K.T)
         elif self.kernel_symm == 'gamma':
-            log_debug(
+            tasklogger.log_debug(
                 "Using gamma symmetrization (gamma = {}).".format(self.gamma))
             K = self.gamma * elementwise_minimum(K, K.T) + \
                 (1 - self.gamma) * elementwise_maximum(K, K.T)
         elif self.kernel_symm is None:
-            log_debug("Using no symmetrization.")
+            tasklogger.log_debug("Using no symmetrization.")
             pass
         else:
             # this should never happen
@@ -438,9 +441,11 @@ def set_params(self, **params):
         """
         if 'gamma' in params and params['gamma'] != self.gamma:
             raise ValueError("Cannot update gamma. Please create a new graph")
-        if 'kernel_symm' in params and params['kernel_symm'] != self.kernel_symm:
+        if 'kernel_symm' in params and \
+                params['kernel_symm'] != self.kernel_symm:
             raise ValueError(
                 "Cannot update kernel_symm. Please create a new graph")
+        super().set_params(**params)
         return self
 
     @property
@@ -462,6 +467,31 @@ def P(self):
             self._diff_op = normalize(self.kernel, 'l1', axis=1)
             return self._diff_op
 
+    @property
+    def diff_aff(self):
+        """Symmetric diffusion affinity matrix
+
+        Return or calculate the symmetric diffusion affinity matrix
+
+        .. math:: A(x,y) = K(x,y) (d(x) d(y))^{-1/2}
+
+        where :math:`d` is the degrees (row sums of the kernel.)
+
+        Returns
+        -------
+
+        diff_aff : array-like, shape=[n_samples, n_samples]
+            symmetric diffusion affinity matrix defined as a
+            doubly-stochastic form of the kernel matrix
+        """
+        row_degrees = np.array(self.kernel.sum(axis=1)).reshape(-1, 1)
+        col_degrees = np.array(self.kernel.sum(axis=0)).reshape(1, -1)
+        if sparse.issparse(self.kernel):
+            return self.kernel.multiply(1 / np.sqrt(row_degrees)).multiply(
+                1 / np.sqrt(col_degrees))
+        else:
+            return (self.kernel / np.sqrt(row_degrees)) / np.sqrt(col_degrees)
+
     @property
     def diff_op(self):
         """Synonym for P
@@ -597,7 +627,7 @@ def __init__(self, data,
         # kwargs are ignored
         self.n_jobs = n_jobs
         self.verbose = verbose
-        set_logging(verbose)
+        tasklogger.set_level(verbose)
         super().__init__(data, **kwargs)
 
     def get_params(self):