Merge 8d6f119 into c9805b4

duecredit/collector.py

@@ -49,14 +49,15 @@ def __init__(self, entry, description=None, path=None, version=None,
           core packages whenever it is reasonable to assume that its import constitute
           its use (e.g. numpy)
         tags: list of str, optional
-          Add tags for the reference for this method.  Some tags have associated
-          semantics in duecredit, e.g.
+          Tags to associate with the given code/reference combination.  Some tags have
+          associated semantics in duecredit, e.g.
           - "implementation" [default] tag describes as an implementation of the cited
-             method
-          - "reference" tag describes as the original implementation of
-            the cited method
+            method
+          - "reference-implementation" tag describes as the original implementation (ideally
+            by the authors of the paper) of the cited method
+          - "another-implementation" tag describes some other implementation of the method
           - "use" tag points to publications demonstrating a worthwhile noting use
-             the method
+            the method
           - "edu" references to tutorials, textbooks and other materials useful to learn
             more
           - "donate" should be commonly used with Url entries to point to the websites

duecredit/injections/mod_sklearn.py

@@ -9,7 +9,7 @@
 """Automatic injection of bibliography entries for numpy module
 """
 
-from ..entries import Doi, BibTeX
+from ..entries import Doi, BibTeX, Url
 
 # If defined, would determine from which to which version of the corresponding
 # module to care about
@@ -32,3 +32,45 @@ def inject(injector):
         publisher={JMLR. org}
         }
     """), description="Machine Learning library")
+
+    # sklearn.cluster.affinity_propagation_
+    injector.add('sklearn.cluster.affinity_propagation_', None, Doi('10.1126/science.1136800'),
+                 description="Affinity propagation clustering algorithm", tags=['implementation'])
+
+    # sklearn.cluster.bicluster
+    injector.add('sklearn.cluster.bicluster', 'SpectralCoclustering', Doi('10.1.1.140.301'),
+                 description="Spectral Coclustering algorithm", tags=['implementation'])
+    injector.add('sklearn.cluster.bicluster', 'SpectralBiclustering', Doi('10.1.1.135.1608'),
+                 description="Spectral Biclustering algorithm", tags=['implementation'])
+
+    # sklearn.cluster.birch
+    injector.add('sklearn.cluster.birch', 'Birch', Doi('10.1145/233269.233324'),
+                 description="BIRCH clustering algorithm", tags=['implementation'])
+    injector.add('sklearn.cluster.birch', 'Birch', Url('https://code.google.com/p/jbirch/'),
+                 description="Java implementation of BIRCH clustering algorithm", tags=['another-implementation'])
+
+    # sklearn.cluster.dbscan_
+    injector.add('sklearn.cluster.dbscan_', 'dbscan',
+                 BibTeX("""@inproceedings{ester1996density,
+  title={A density-based algorithm for discovering clusters in large spatial databases with noise.},
+  author={Ester, Martin and Kriegel, Hans-Peter and Sander, J{\"o}rg and Xu, Xiaowei},
+  booktitle={Kdd},
+  volume={96},
+  number={34},
+  pages={226--231},
+  year={1996}
+}"""), description="dbscan clustering algorithm", tags=['implementation'])
+
+    # sklearn.cluster.mean_shift_
+    injector.add('sklearn.cluster.mean_shift_', 'MeanShift', Doi('10.1109/34.1000236'),
+                 description="Mean shift clustering algorithm", tags=['implementation'])
+
+    # sklearn.cluster.spectral
+    injector.add('sklearn.cluster.spectral', 'discretize', Doi('10.1109/ICCV.2003.1238361'),
+                 description="Multiclass spectral clustering", tags=['reference'])
+    injector.add('sklearn.cluster.spectral', 'spectral_clustering', Doi('10.1.1.160.2324'),
+                 description="Spectral clustering", tags=['implementation'])
+    injector.add('sklearn.cluster.spectral', 'spectral_clustering', Doi('10.1.1.165.9323'),
+                 description="Spectral clustering", tags=['implementation'])
+
+

duecredit/io.py

@@ -62,7 +62,7 @@ def dump(self, tags=None):
 
         # TODO: all that configuration/options should be done outside
         if not tags:
-            tags = os.environ.get('DUECREDIT_REPORT_TAGS', 'reference,implementation').split(',')
+            tags = os.environ.get('DUECREDIT_REPORT_TAGS', 'reference-implementation,implementation').split(',')
         tags = set(tags)
 
         citations = self.collector.citations