exposes distfunc argument for full_word_similarity_evaluation

genepro · Apr 8, 2019 · c264cc4 · c264cc4
1 parent 1d5950a
commit c264cc4
Showing 1 changed file with 8 additions and 4 deletions.
diff --git a/hw1_wordsim.ipynb b/hw1_wordsim.ipynb
@@ -1103,14 +1103,18 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "def full_word_similarity_evaluation(df, readers=READERS):\n",
+    "def full_word_similarity_evaluation(df, readers=READERS, distfunc=vsm.cosine):\n",
     "    \"\"\"Evaluate a VSM against all datasets in `readers`.\n",
     "    \n",
     "    Parameters\n",
     "    ----------\n",
     "    df : pd.DataFrame\n",
     "    readers : tuple \n",
     "        The similarity dataset readers on which to evaluate.\n",
+    "    distfunc : function mapping vector pairs to floats.\n",
+    "        The measure of distance between vectors. Can also be \n",
+    "        `vsm.euclidean`, `vsm.matching`, `vsm.jaccard`, as well as \n",
+    "        any other distance measure between 1d vectors. \n",
     "    \n",
     "    Returns\n",
     "    -------\n",
@@ -1120,7 +1124,7 @@
     "    \"\"\"        \n",
     "    scores = {}     \n",
     "    for reader in readers:\n",
-    "        score, data_df = word_similarity_evaluation(reader, df)\n",
+    "        score, data_df = word_similarity_evaluation(reader, df, distfunc=distfunc)\n",
     "        scores[get_reader_name(reader)] = score\n",
     "    series = pd.Series(scores, name='Spearman r')\n",
     "    series['Macro-average'] = series.mean()\n",
@@ -1150,7 +1154,7 @@
     }
    ],
    "source": [
-    "full_word_similarity_evaluation(giga5)"
+    "full_word_similarity_evaluation(giga5, distfunc=vsm.cosine)"
    ]
   },
   {
@@ -1363,7 +1367,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.7.1"
+   "version": "3.7.3"
   },
   "widgets": {
    "state": {},