henry/paraphrase_detector
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

notebook2

Browse Source
This commit is contained in:
Henry Dowd
2025-12-10 19:43:28 +00:00
parent a370b68cb1
commit 726c6b276b
1 changed files with 13 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

27
notebooks/02_baseline_experiments.ipynb
View File

@@ -121,7 +121,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 57, "execution_count": 1,
"id": "0b68fdcd", "id": "0b68fdcd",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
@@ -130,19 +130,18 @@
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"Sentence 1 Sentence 2: Similarities -> Char: Word:\n", "Sentence 1 Sentence 2: Similarities -> Char: Word:\n",
"====================================================================================================\n", "====================================================================================================\n"
"The cat sat on the mat. vs The cat sat on the mat. 1.000 1.000 \n", ]
"The cat sat on the mat. vs The cat sat on the mat 0.957 0.833 \n", },
"The cat sat on the mat. vs The cat sat on the mat. 0.821 1.000 \n", {
"The cat sat on the mat. vs On the mat, the cat was sitting. 0.344 0.143 \n", "ename": "NameError",
"The cat sat on the mat. vs The feline rested on the rug. 0.517 0.500 \n", "evalue": "name 'test_pairs' is not defined",
"The quick brown fox jumps. vs A fast brown fox leaps. 0.577 0.400 \n", "output_type": "error",
"The cat sat on the mat. vs The dog ran in the park. 0.625 0.333 \n", "traceback": [
"I love programming. vs She enjoys reading books. 0.200 0.000 \n", "\u001b[31m---------------------------------------------------------------------------\u001b[39m",
"The weather is nice today. vs It's raining outside. 0.192 0.000 \n", "\u001b[31mNameError\u001b[39m Traceback (most recent call last)",
"Short. vs Short. 1.000 1.000 \n", "\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[1]\u001b[39m\u001b[32m, line 31\u001b[39m\n\u001b[32m 28\u001b[39m \u001b[38;5;28mprint\u001b[39m(\u001b[33mf\u001b[39m\u001b[33m\"\u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[33m'\u001b[39m\u001b[33mSentence 1\u001b[39m\u001b[33m'\u001b[39m\u001b[38;5;132;01m:\u001b[39;00m\u001b[33m<41\u001b[39m\u001b[38;5;132;01m}\u001b[39;00m\u001b[33m \u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[33m'\u001b[39m\u001b[33mSentence 2:\u001b[39m\u001b[33m'\u001b[39m\u001b[38;5;132;01m:\u001b[39;00m\u001b[33m<20\u001b[39m\u001b[38;5;132;01m}\u001b[39;00m\u001b[33m \u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[33m'\u001b[39m\u001b[33mSimilarities ->\u001b[39m\u001b[33m'\u001b[39m\u001b[38;5;132;01m:\u001b[39;00m\u001b[33m<19\u001b[39m\u001b[38;5;132;01m}\u001b[39;00m\u001b[33m \u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[33m'\u001b[39m\u001b[33mChar:\u001b[39m\u001b[33m'\u001b[39m\u001b[38;5;132;01m:\u001b[39;00m\u001b[33m<10\u001b[39m\u001b[38;5;132;01m}\u001b[39;00m\u001b[33m \u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[33m'\u001b[39m\u001b[33mWord:\u001b[39m\u001b[33m'\u001b[39m\u001b[38;5;132;01m}\u001b[39;00m\u001b[33m\"\u001b[39m)\n\u001b[32m 29\u001b[39m \u001b[38;5;28mprint\u001b[39m(\u001b[33m\"\u001b[39m\u001b[33m=\u001b[39m\u001b[33m\"\u001b[39m * \u001b[32m100\u001b[39m)\n\u001b[32m---> \u001b[39m\u001b[32m31\u001b[39m \u001b[38;5;28;01mfor\u001b[39;00m sent1, sent2 \u001b[38;5;129;01min\u001b[39;00m \u001b[43mtest_pairs\u001b[49m:\n\u001b[32m 32\u001b[39m char_similarity = char_levenshtein_similarity(sent1, sent2)\n\u001b[32m 33\u001b[39m word_similarity = word_levenshtein_similarity(sent1, sent2)\n",
"A B C D E F G vs A B C D E F G 1.000 1.000 \n", "\u001b[31mNameError\u001b[39m: name 'test_pairs' is not defined"
" vs 1.000 1.000 \n"
] ]
} }
], ],