142 lines
2.5 KiB
Plaintext
142 lines
2.5 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "475ac5f0",
|
|
"metadata": {},
|
|
"source": [
|
|
"# Libraries"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "108f20c8",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from datasets import load_dataset\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "43491a6a",
|
|
"metadata": {},
|
|
"source": [
|
|
"# Load Data"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 11,
|
|
"id": "76c78147",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from datasets import DatasetDict, load_dataset\n",
|
|
"from evidently import Dataset\n",
|
|
"import pandas as pd\n",
|
|
"\n",
|
|
"database_he = load_dataset(\"openai_humaneval\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 17,
|
|
"id": "e76eefff",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"DatasetDict({\n",
|
|
" test: Dataset({\n",
|
|
" features: ['task_id', 'prompt', 'canonical_solution', 'test', 'entry_point'],\n",
|
|
" num_rows: 164\n",
|
|
" })\n",
|
|
"})"
|
|
]
|
|
},
|
|
"execution_count": 17,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"database_he"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 12,
|
|
"id": "386395f1",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"database_he_df = database_he[\"test\"].to_pandas()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "ae12c1f3",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"database_he_df"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 13,
|
|
"id": "edfd2f52",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"mbpp = load_dataset(\"mbpp\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 16,
|
|
"id": "5c3d8120",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"mbpp_df = mbpp[\"train\"].to_pandas()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "3d59904c",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"mbpp_df"
|
|
]
|
|
}
|
|
],
|
|
"metadata": {
|
|
"kernelspec": {
|
|
"display_name": "assistance-engine",
|
|
"language": "python",
|
|
"name": "python3"
|
|
},
|
|
"language_info": {
|
|
"codemirror_mode": {
|
|
"name": "ipython",
|
|
"version": 3
|
|
},
|
|
"file_extension": ".py",
|
|
"mimetype": "text/x-python",
|
|
"name": "python",
|
|
"nbconvert_exporter": "python",
|
|
"pygments_lexer": "ipython3",
|
|
"version": "3.12.11"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 5
|
|
}
|