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

more notebook testing

Browse Source
This commit is contained in:
Henry Dowd
2025-11-19 00:31:43 +00:00
parent 8d6b1cab2c
commit 7ad4068a55
4 changed files with 165 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
notebooks/02_baseline_experiments.ipynb
View File

@@ -3,12 +3,15 @@
{
"metadata": {
"ExecuteTime": {
"end_time": "2025-11-18T23:15:35.056834Z",
"start_time": "2025-11-18T23:15:35.051218Z"
"end_time": "2025-11-19T00:00:04.962487Z",
"start_time": "2025-11-19T00:00:04.958995Z"
}
},
"cell_type": "code",
"source": [
"import import_ipynb\n",
"from notebooks.01_data_exploration import *\n",
"\n",
"def jaccard_similarity(sent1, sent2):\n",
" # make lowercase and split into words\n",
" words1 = set(sent1.lower().split())\n",
@@ -30,16 +33,15 @@
"id": "e60d024e969254a",
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"'The cat sat on the mat.' vs 'The cat sat on the mat.': 1.000\n",
"'The cat sat on the mat.' vs 'On the mat sat the cat.': 0.429\n",
"'The cat sat on the mat.' vs 'The dog ran in the park': 0.111\n"
"ename": "SyntaxError",
"evalue": "invalid decimal literal (2501033926.py, line 2)",
"output_type": "error",
"traceback": [
" \u001B[36mCell\u001B[39m\u001B[36m \u001B[39m\u001B[32mIn[8]\u001B[39m\u001B[32m, line 2\u001B[39m\n\u001B[31m \u001B[39m\u001B[31mfrom notebooks.01_data_exploration import *\u001B[39m\n ^\n\u001B[31mSyntaxError\u001B[39m\u001B[31m:\u001B[39m invalid decimal literal\n"
]
}
],
"execution_count": 7
"execution_count": 8
}
],
"metadata": {