83 lines
2.4 KiB
Plaintext
83 lines
2.4 KiB
Plaintext
|
{
|
||
|
|
"cells": [
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 3,
|
||
|
|
"id": "58e6167e-1e30-4bbf-93a1-af6ab5cb4673",
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [],
|
||
|
|
"source": [
|
||
|
|
"import pandas as pd\n",
|
||
|
|
"\n",
|
||
|
|
"def preprocess_test(test_solutions_path: str, test_tasks_path: str, test_tests_path: str, save_path: str) -> None:\n",
|
||
|
|
" def read_files(*paths):\n",
|
||
|
|
" return (pd.read_excel(path) for path in paths)\n",
|
||
|
|
"\n",
|
||
|
|
" solutions_df, tasks_df, tests_df = read_files(test_solutions_path, test_tasks_path, test_tests_path)\n",
|
||
|
|
"\n",
|
||
|
|
" test_dataset = pd.merge(pd.merge(solutions_df, tasks_df, left_on='task_id', right_on='id', how='inner'), \n",
|
||
|
|
" tests_df, on='task_id', how='inner')\n",
|
||
|
|
"\n",
|
||
|
|
" test_dataset['input_output'] = test_dataset.apply(\n",
|
||
|
|
" lambda row: f\"{row['input']}->{row['output']}\" if pd.notna(row['input']) or pd.notna(row['output']) else \"\", \n",
|
||
|
|
" axis=1\n",
|
||
|
|
" )\n",
|
||
|
|
"\n",
|
||
|
|
" test_dataset = test_dataset[['id', 'student_solution', 'description', 'author_solution', 'input_output']]\n",
|
||
|
|
" test_dataset.to_excel(save_path, index=False)"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 4,
|
||
|
|
"id": "e561a852-007c-4b78-a7e1-697f80272169",
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [],
|
||
|
|
"source": [
|
||
|
|
"base = 'data/raw/test/{}'\n",
|
||
|
|
"\n",
|
||
|
|
"preprocess_test(base.format('solutions.xlsx'), base.format('tasks.xlsx'), base.format('tests.xlsx'), './test.xlsx')"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 18,
|
||
|
|
"id": "2c15dbb7-1034-41a7-96be-69e2418bf98e",
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [],
|
||
|
|
"source": []
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 19,
|
||
|
|
"id": "d923d6c4-f962-4646-a041-999862bb3950",
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [],
|
||
|
|
"source": [
|
||
|
|
"preprocess_test(base.format('solutions.xlsx'), base.format('tasks.xlsx'), base.format('tests.xlsx'), './test2.xlsx')"
|
||
|
|
]
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"metadata": {
|
||
|
|
"kernelspec": {
|
||
|
|
"display_name": "Python [conda env:.conda-poetry]",
|
||
|
|
"language": "python",
|
||
|
|
"name": "conda-env-.conda-poetry-py"
|
||
|
|
},
|
||
|
|
"language_info": {
|
||
|
|
"codemirror_mode": {
|
||
|
|
"name": "ipython",
|
||
|
|
"version": 3
|
||
|
|
},
|
||
|
|
"file_extension": ".py",
|
||
|
|
"mimetype": "text/x-python",
|
||
|
|
"name": "python",
|
||
|
|
"nbconvert_exporter": "python",
|
||
|
|
"pygments_lexer": "ipython3",
|
||
|
|
"version": "3.11.10"
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"nbformat": 4,
|
||
|
|
"nbformat_minor": 5
|
||
|
|
}
|