Update: Word2Vec 추가

#38 토큰들 간의 유사도를 알아내기 위해 Word2Vec 과정 추가
tukcomCD2024 · May 13, 2024 · 204a5f0 · 204a5f0
1 parent cb09b32
commit 204a5f0
Showing 1 changed file with 26 additions and 3 deletions.
diff --git a/AI/사전 생성.ipynb b/AI/사전 생성.ipynb
@@ -206,7 +206,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -227,7 +227,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [
     {
@@ -14903,7 +14903,7 @@
        " ...]"
       ]
      },
-     "execution_count": 11,
+     "execution_count": 5,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -14912,6 +14912,29 @@
     "standard_okt_data"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from gensim.models import Word2Vec\n",
+    "import matplotlib.pyplot as plt"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dialect_word2vec = Word2Vec(sentences=dialect_okt_data, vector_size=100, min_count=1, window=5, workers=4)\n",
+    "standard_word2vec = Word2Vec(sentences=standard_okt_data, vector_size=100, min_count=1, window=5, workers=4)\n",
+    "\n",
+    "dialect_word2vec.save(\"dialect_word2vec.bin\")\n",
+    "standard_word2vec.save(\"standard_word2vec.bin\")"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 12,