remove opt cost for normalized levenshtein & update doc

README.rst

@@ -3,8 +3,12 @@ RLTK
 
 Record Linkage ToolKit (RLTK)
 
+.. image:: https://readthedocs.org/projects/rltk/badge/?version=latest
+    :target: http://rltk.readthedocs.io/en/latest/
+    :alt: Documents
+
 Documentation
 =============
 
-* `Tutorials <#>`_
-* `API Reference <#>`_
+* `Tutorials <http://rltk.readthedocs.io>`_
+* `API Reference <http://rltk.readthedocs.io>`_

docs/conf.py

@@ -88,7 +88,13 @@
 # further.  For a list of options available for each theme, see the
 # documentation.
 #
-# html_theme_options = {}
+html_theme_options = {
+    'page_width': '1600px',
+    'sidebar_width': '300px',
+    'github_user': 'usc-isi-i2',
+    'github_repo': 'rltk',
+    'github_banner': 'true',
+}
 
 # 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,

docs/index.rst

@@ -26,18 +26,13 @@ In RLTK, you can simply load the the resource you need and give it name, then re
 Example 2::
 
    >>> import rltk
-   >>>
    >>> edit_distance_cost = {'insert': {'c':50}, 'insert_default':100, 'delete_default':100, 'substitute_default':100}
-   >>>
    >>> tk = rltk.init()
    >>> tk.load_edit_distance_table('A1', edit_distance_cost) # load resource
    >>> tk.levenshtein_distance('a', 'abc')
    >>> 2
    >>> tk.levenshtein_distance('a', 'abc', name='A1')
    >>> 150
-   >>> tk.normalized_levenshtein_distance('a', 'abc', name='A1')
-   >>> 50.0
-
 
 API Reference
 --------------

examples/ex1.py

@@ -10,5 +10,4 @@
 
 print tk.levenshtein_distance('a', 'abc')
 print tk.levenshtein_distance('a', 'abc', name='A1')
-print tk.normalized_levenshtein_distance('a', 'abc', name='A1')
 print tk.tf_idf(['a', 'b', 'a'], ['a', 'c','d','f'], name='B1')

rltk/core.py

@@ -110,7 +110,7 @@ def hamming_distance(self, s1, s2):
         """
         return hamming_distance(s1, s2)
 
-    def levenshtein_similarity(self, s1, s2, name=None):
+    def levenshtein_similarity(self, s1, s2):
         """
         The Levenshtein similarity is computed as 1 - normalized_levenshtein_distance.
 
@@ -122,19 +122,7 @@ def levenshtein_similarity(self, s1, s2, name=None):
         Returns:
             float: Levenshtein Similarity between [0.0, 1.0].
         """
-        if name is None:
-            return levenshtein_similarity(s1, s2)
-        else:
-            self._has_resource(name, 'edit_distance_table')
-
-            insert = self._rs_dict[name]['data']['insert']
-            delete = self._rs_dict[name]['data']['delete']
-            substitute = self._rs_dict[name]['data']['substitute']
-            insert_default = self._rs_dict[name]['data']['insert_default']
-            delete_default = self._rs_dict[name]['data']['delete_default']
-            substitute_default = self._rs_dict[name]['data']['substitute_default']
-            return levenshtein_similarity(s1, s2, insert, delete, substitute,
-                               insert_default, delete_default, substitute_default)
+        return levenshtein_similarity(s1, s2)
 
     def levenshtein_distance(self, s1, s2, name=None):
         """
@@ -169,31 +157,19 @@ def levenshtein_distance(self, s1, s2, name=None):
             return levenshtein_distance(s1, s2, insert, delete, substitute,
                                insert_default, delete_default, substitute_default)
 
-    def normalized_levenshtein_distance(self, s1, s2, name=None):
+    def normalized_levenshtein_distance(self, s1, s2):
         """
-        This distance is computed as levenshtein distance divided by the length of the longest string.
+        This distance is computed as levenshtein distance divided by the length of the longest string. This method
+        doesn't support customization of operation cost.
 
         Args:
             s1 (str): Sequence 1.
             s2 (str): Sequence 2.
-            name (str): Name of resource (edit distance table).
 
         Returns:
             float: Normalized Levenshtein Distance between [0.0, 1.0].
         """
-        if name is None:
-            return normalized_levenshtein_distance(s1, s2)
-        else:
-            self._has_resource(name, 'edit_distance_table')
-
-            insert = self._rs_dict[name]['data']['insert']
-            delete = self._rs_dict[name]['data']['delete']
-            substitute = self._rs_dict[name]['data']['substitute']
-            insert_default = self._rs_dict[name]['data']['insert_default']
-            delete_default = self._rs_dict[name]['data']['delete_default']
-            substitute_default = self._rs_dict[name]['data']['substitute_default']
-            return normalized_levenshtein_distance(s1, s2, insert, delete, substitute,
-                               insert_default, delete_default, substitute_default)
+        return normalized_levenshtein_distance(s1, s2)
 
     def damerau_levenshtein_distance(self, s1, s2):
         """

rltk/similarity/levenshtein.py

@@ -2,8 +2,8 @@
 
 import utils
 
-def _levenshtein(s1, s2, insert, delete, substitute,
-                 insert_default, delete_default, substitute_default):
+def _levenshtein(s1, s2, insert={}, delete={}, substitute={},
+                 insert_default=1, delete_default=1, substitute_default=1):
     utils.check_for_none(s1, s2)
     utils.check_for_type(str, s1, s2)
 
@@ -45,27 +45,19 @@ def _levenshtein(s1, s2, insert, delete, substitute,
                                    dp[i-1][j-1] + substitute_cost)
     return dp[n1][n2]
 
-def levenshtein_similarity(s1, s2, insert={}, delete={}, substitute={},
-                           insert_default=1, delete_default=1, substitute_default=1):
+def levenshtein_similarity(s1, s2):
     """
     The Levenshtein similarity is computed as 1 - normalized_levenshtein_distance.
 
     Args:
         s1 (str): Sequence 1.
         s2 (str): Sequence 2.
-        insert (dict(str, int), optional): Insert cost of characters. Defaults to empty dict.
-        delete (dict(str, int), optional): Delete cost of characters. Defaults to empty dict.
-        substitute (dict(str, dict(str, int)), optional): Substitute cost of characters. Defaults to empty dict.
-        insert_default (int, optional): Default value of insert cost. Defaults to 1.
-        delete_default (int, optional): Default value of delete cost. Defaults to 1.
-        substitute_default (int, optional): Default value of substitute cost. Defaults to 1.
 
     Returns:
         float: Levenshtein Similarity between [0.0, 1.0].
     """
 
-    return 1 - _normalized_levenshtein(s1, s2, insert, delete, substitute,
-                           insert_default, delete_default, substitute_default)
+    return 1 - _normalized_levenshtein(s1, s2)
 
 def levenshtein_distance(s1, s2, insert={}, delete={}, substitute={},
                            insert_default=1, delete_default=1, substitute_default=1):
@@ -97,44 +89,31 @@ def levenshtein_distance(s1, s2, insert={}, delete={}, substitute={},
                            insert_default, delete_default, substitute_default)
 
 
-def _normalized_levenshtein(s1, s2, insert, delete, substitute,
-                           insert_default, delete_default, substitute_default):
-    lev = _levenshtein(s1, s2, insert, delete, substitute,
-                           insert_default, delete_default, substitute_default)
+def _normalized_levenshtein(s1, s2):
+    lev = _levenshtein(s1, s2)
 
     max_len = max(len(s1), len(s2))
     if max_len == 0:
         return 0
 
     return float(lev) / max_len
 
-def normalized_levenshtein_distance(s1, s2, insert={}, delete={}, substitute={},
-                           insert_default=1, delete_default=1, substitute_default=1):
+def normalized_levenshtein_distance(s1, s2):
     """
     This distance is computed as levenshtein distance divided by the length of the longest string.
 
     Args:
         s1 (str): Sequence 1.
         s2 (str): Sequence 2.
-        insert (dict(str, int), optional): Insert cost of characters. Defaults to empty dict.
-        delete (dict(str, int), optional): Delete cost of characters. Defaults to empty dict.
-        substitute (dict(str, dict(str, int)), optional): Substitute cost of characters. Defaults to empty dict.
-        insert_default (int, optional): Default value of insert cost. Defaults to 1.
-        delete_default (int, optional): Default value of delete cost. Defaults to 1.
-        substitute_default (int, optional): Default value of substitute cost. Defaults to 1.
 
     Returns:
         float: Normalized Levenshtein Distance between [0.0, 1.0].
 
     Examples:
         >>> rltk.normalized_levenshtein_distance('ab', 'abc')
         0.333333333333
-        >>> rltk.normalized_levenshtein_distance('a', 'abc', insert = {'c':50},
-        ... insert_default=100, delete_default=100, substitute_default=100)
-        50.0
     """
-    return _normalized_levenshtein(s1, s2, insert, delete, substitute,
-                           insert_default, delete_default, substitute_default)
+    return _normalized_levenshtein(s1, s2)
 
 def damerau_levenshtein_distance(s1, s2):
     """