mirror of
https://github.com/openai/openai-cookbook
synced 2024-11-04 06:00:33 +00:00
193 lines
6.2 KiB
Plaintext
193 lines
6.2 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## 1. Load the dataset\n",
|
|
"\n",
|
|
"The dataset used in this example is [fine-food reviews](https://www.kaggle.com/snap/amazon-fine-food-reviews) from Amazon. The dataset contains a total of 568,454 food reviews Amazon users left up to October 2012. We will use a subset of this dataset, consisting of 1,000 most recent reviews for illustration purposes. The reviews are in English and tend to be positive or negative. Each review has a ProductId, UserId, Score, review title (Summary) and review body (Text).\n",
|
|
"\n",
|
|
"We will combine the review summary and review text into a single combined text. The model will encode this combined text and it will output a single vector embedding."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 1,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/html": [
|
|
"<div>\n",
|
|
"<style scoped>\n",
|
|
" .dataframe tbody tr th:only-of-type {\n",
|
|
" vertical-align: middle;\n",
|
|
" }\n",
|
|
"\n",
|
|
" .dataframe tbody tr th {\n",
|
|
" vertical-align: top;\n",
|
|
" }\n",
|
|
"\n",
|
|
" .dataframe thead th {\n",
|
|
" text-align: right;\n",
|
|
" }\n",
|
|
"</style>\n",
|
|
"<table border=\"1\" class=\"dataframe\">\n",
|
|
" <thead>\n",
|
|
" <tr style=\"text-align: right;\">\n",
|
|
" <th></th>\n",
|
|
" <th>Time</th>\n",
|
|
" <th>ProductId</th>\n",
|
|
" <th>UserId</th>\n",
|
|
" <th>Score</th>\n",
|
|
" <th>Summary</th>\n",
|
|
" <th>Text</th>\n",
|
|
" <th>combined</th>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>Id</th>\n",
|
|
" <th></th>\n",
|
|
" <th></th>\n",
|
|
" <th></th>\n",
|
|
" <th></th>\n",
|
|
" <th></th>\n",
|
|
" <th></th>\n",
|
|
" <th></th>\n",
|
|
" </tr>\n",
|
|
" </thead>\n",
|
|
" <tbody>\n",
|
|
" <tr>\n",
|
|
" <th>1</th>\n",
|
|
" <td>1303862400</td>\n",
|
|
" <td>B001E4KFG0</td>\n",
|
|
" <td>A3SGXH7AUHU8GW</td>\n",
|
|
" <td>5</td>\n",
|
|
" <td>Good Quality Dog Food</td>\n",
|
|
" <td>I have bought several of the Vitality canned d...</td>\n",
|
|
" <td>Title: Good Quality Dog Food; Content: I have ...</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2</th>\n",
|
|
" <td>1346976000</td>\n",
|
|
" <td>B00813GRG4</td>\n",
|
|
" <td>A1D87F6ZCVE5NK</td>\n",
|
|
" <td>1</td>\n",
|
|
" <td>Not as Advertised</td>\n",
|
|
" <td>Product arrived labeled as Jumbo Salted Peanut...</td>\n",
|
|
" <td>Title: Not as Advertised; Content: Product arr...</td>\n",
|
|
" </tr>\n",
|
|
" </tbody>\n",
|
|
"</table>\n",
|
|
"</div>"
|
|
],
|
|
"text/plain": [
|
|
" Time ProductId UserId Score Summary \\\n",
|
|
"Id \n",
|
|
"1 1303862400 B001E4KFG0 A3SGXH7AUHU8GW 5 Good Quality Dog Food \n",
|
|
"2 1346976000 B00813GRG4 A1D87F6ZCVE5NK 1 Not as Advertised \n",
|
|
"\n",
|
|
" Text \\\n",
|
|
"Id \n",
|
|
"1 I have bought several of the Vitality canned d... \n",
|
|
"2 Product arrived labeled as Jumbo Salted Peanut... \n",
|
|
"\n",
|
|
" combined \n",
|
|
"Id \n",
|
|
"1 Title: Good Quality Dog Food; Content: I have ... \n",
|
|
"2 Title: Not as Advertised; Content: Product arr... "
|
|
]
|
|
},
|
|
"execution_count": 1,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"import pandas as pd\n",
|
|
"\n",
|
|
"df = pd.read_csv('input/Reviews.csv', index_col=0)\n",
|
|
"df = df[['Time', 'ProductId', 'UserId', 'Score', 'Summary', 'Text']]\n",
|
|
"df = df.dropna()\n",
|
|
"df['combined'] = \"Title: \" + df.Summary.str.strip() + \"; Content: \" + df.Text.str.strip()\n",
|
|
"df.head(2)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 2,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"1000"
|
|
]
|
|
},
|
|
"execution_count": 2,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"# subsample to 1k most recent reviews and remove samples that are too long\n",
|
|
"df = df.sort_values('Time').tail(1_100)\n",
|
|
"df.drop('Time', axis=1, inplace=True)\n",
|
|
"\n",
|
|
"from transformers import GPT2TokenizerFast\n",
|
|
"tokenizer = GPT2TokenizerFast.from_pretrained(\"gpt2\")\n",
|
|
"\n",
|
|
"# remove reviews that are too long\n",
|
|
"df['n_tokens'] = df.combined.apply(lambda x: len(tokenizer.encode(x)))\n",
|
|
"df = df[df.n_tokens<2000].tail(1_000)\n",
|
|
"len(df)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"### 2. Get embeddings and save them for future reuse"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 3,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from openai.embeddings_utils import get_embedding\n",
|
|
"\n",
|
|
"# This will take just under 10 minutes\n",
|
|
"df['babbage_similarity'] = df.combined.apply(lambda x: get_embedding(x, engine='text-similarity-babbage-001'))\n",
|
|
"df['babbage_search'] = df.combined.apply(lambda x: get_embedding(x, engine='text-search-babbage-doc-001'))\n",
|
|
"df.to_csv('output/embedded_1k_reviews.csv')"
|
|
]
|
|
}
|
|
],
|
|
"metadata": {
|
|
"interpreter": {
|
|
"hash": "be4b5d5b73a21c599de40d6deb1129796d12dc1cc33a738f7bac13269cfcafe8"
|
|
},
|
|
"kernelspec": {
|
|
"display_name": "Python 3.7.3 64-bit ('base': conda)",
|
|
"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": "3.9.9"
|
|
},
|
|
"orig_nbformat": 4
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 2
|
|
}
|