Add files via upload

Christopher-Thornton · Aug 19, 2020 · 6d7a293 · 6d7a293
1 parent 912bbbc
commit 6d7a293
Showing 1 changed file with 4 additions and 15 deletions.
diff --git a/dev/model_building.ipynb b/dev/model_building.ipynb
@@ -58,16 +58,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "alt_names = pd.read_csv('name_pairs.txt', sep=\",\", header=None)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "alt_names.columns = ['name_a', 'name_b']"
+    "alt_names = pd.read_csv('name_pairs.txt', sep=\",\", names=['name_a', 'name_b'], header=None)"
    ]
   },
   {
@@ -187,8 +178,7 @@
     "import unidecode\n",
     "from fuzzywuzzy import fuzz\n",
     "\n",
-    "from syllable_tokenizer import SyllableTokenizer\n",
-    "ST = SyllableTokenizer()\n",
+    "import syllable_tokenizer\n",
     "\n",
     "from abydos.distance import (IterativeSubString, BISIM, DiscountedLevenshtein, Prefix, LCSstr, MLIPNS, Strcmp95,\n",
     "MRA, Editex, SAPS, FlexMetric, JaroWinkler, HigueraMico, Sift4, Eudex, ALINE, Covington, PhoneticEditDistance)\n",
@@ -288,9 +278,8 @@
     "    df['name_b'] = df.apply(lambda row: re.sub(\n",
     "        '[^a-zA-Z]+', '', unidecode.unidecode(row['b']).lower().strip()), axis=1)\n",
     "    \n",
-    "    df['syll_a'] = df.apply(lambda row: ST.tokenize(row.name_a), axis=1)\n",
-    "    df['syll_a'] = df.apply(lambda row: ST.tokenize(row.name_a), axis=1)\n",
-    "    df['syll_b'] = df.apply(lambda row: ST.tokenize(row.name_b), axis=1)\n",
+    "    df['syll_a'] = df.apply(lambda row: syllable_tokenizer.tokenize(row.name_a), axis=1)\n",
+    "    df['syll_b'] = df.apply(lambda row: syllable_tokenizer.tokenize(row.name_b), axis=1)\n",
     "    \n",
     "    df['partial'] = df.apply(lambda row: fuzz.partial_ratio(row.syll_a,row.syll_b), axis=1)\n",
     "    df['tkn_sort'] = df.apply(lambda row: fuzz.token_sort_ratio(row.syll_a,row.syll_b), axis=1)\n",