From b179c4f7b4e25b61a6b0b18059c506e6ab3cb2e9 Mon Sep 17 00:00:00 2001 From: kowshik Date: Thu, 23 Mar 2023 21:23:46 +0000 Subject: [PATCH] Upload files to '' --- Decision_Tree_Promt_GPT_3 (1).ipynb | 3006 +++++++++++++++++++++++++++ qa_sample.jsonl | 20 + qa_sample_prepared.jsonl | 20 + 3 files changed, 3046 insertions(+) create mode 100644 Decision_Tree_Promt_GPT_3 (1).ipynb create mode 100644 qa_sample.jsonl create mode 100644 qa_sample_prepared.jsonl diff --git a/Decision_Tree_Promt_GPT_3 (1).ipynb b/Decision_Tree_Promt_GPT_3 (1).ipynb new file mode 100644 index 0000000..b82a1ec --- /dev/null +++ b/Decision_Tree_Promt_GPT_3 (1).ipynb @@ -0,0 +1,3006 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 4, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "CelFOfyF9ti_", + "outputId": "ce866d46-2915-4af4-815f-99dd9720fdf3" + }, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n", + "Collecting openai\n", + " Downloading openai-0.27.2-py3-none-any.whl (70 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m70.1/70.1 KB\u001b[0m \u001b[31m4.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hRequirement already satisfied: tqdm in /usr/local/lib/python3.9/dist-packages (from openai) (4.65.0)\n", + "Requirement already satisfied: requests>=2.20 in /usr/local/lib/python3.9/dist-packages (from openai) (2.27.1)\n", + "Collecting aiohttp\n", + " Downloading aiohttp-3.8.4-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.0 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.0/1.0 MB\u001b[0m \u001b[31m31.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hRequirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.9/dist-packages (from requests>=2.20->openai) (3.4)\n", + "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.9/dist-packages (from requests>=2.20->openai) (2022.12.7)\n", + "Requirement already satisfied: charset-normalizer~=2.0.0 in /usr/local/lib/python3.9/dist-packages (from requests>=2.20->openai) (2.0.12)\n", + "Requirement already satisfied: urllib3<1.27,>=1.21.1 in /usr/local/lib/python3.9/dist-packages (from requests>=2.20->openai) (1.26.15)\n", + "Collecting frozenlist>=1.1.1\n", + " Downloading frozenlist-1.3.3-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (158 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m158.8/158.8 KB\u001b[0m \u001b[31m21.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hRequirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.9/dist-packages (from aiohttp->openai) (22.2.0)\n", + "Collecting async-timeout<5.0,>=4.0.0a3\n", + " Downloading async_timeout-4.0.2-py3-none-any.whl (5.8 kB)\n", + "Collecting multidict<7.0,>=4.5\n", + " Downloading multidict-6.0.4-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (114 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m114.2/114.2 KB\u001b[0m \u001b[31m14.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hCollecting yarl<2.0,>=1.0\n", + " Downloading yarl-1.8.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (264 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m264.6/264.6 KB\u001b[0m \u001b[31m29.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hCollecting aiosignal>=1.1.2\n", + " Downloading aiosignal-1.3.1-py3-none-any.whl (7.6 kB)\n", + "Installing collected packages: multidict, frozenlist, async-timeout, yarl, aiosignal, aiohttp, openai\n", + "Successfully installed aiohttp-3.8.4 aiosignal-1.3.1 async-timeout-4.0.2 frozenlist-1.3.3 multidict-6.0.4 openai-0.27.2 yarl-1.8.2\n" + ] + } + ], + "source": [ + "!pip install openai" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "metadata": { + "id": "pP7YkLvs95Pt" + }, + "outputs": [], + "source": [ + "import os\n", + "os.environ['OPENAI_API_KEY'] = \"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\"" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "metadata": { + "id": "raj54WV098Dd" + }, + "outputs": [], + "source": [ + "import openai\n", + "def call(context):\n", + " try:\n", + " response = openai.Completion.create(\n", + " api_key = \"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\",\n", + " engine=\"text-davinci-003\",\n", + " prompt=context,\n", + " temperature=1,\n", + " max_tokens=900,\n", + " top_p=1,\n", + " frequency_penalty=0,\n", + " presence_penalty=0\n", + " )\n", + " return response['choices'][0]['text']\n", + " except Exception as e:\n", + " print (e)\n", + " return \"\"" + ] + }, + { + "cell_type": "code", + "execution_count": 36, + "metadata": { + "id": "XOGiyCQb-QoM" + }, + "outputs": [], + "source": [ + "data = ''' \n", + "Preference\t Red_Wine\t White_Wine\t Recommendation\n", + "Red\t Light-Bodied\t\tNone Pinot Noir\n", + "Red\t Full-Bodied\t\t None Shiraz or Zinfandel\n", + "White\t\t None Dry Sauvignon Blanc\n", + "White\t\t None None Sweet\tGewurztraminer\n", + "Red-Fruity\t None\t\t None Pinot Noir\n", + "Red-Earthy\t None\t\t None Chianti\n", + "White-Crisp\t None\t\t None Sauvignon Blanc\n", + "White-Creamy None\t\t\t None Chardonnay\n", + "Red-Spicy\t\t None\t None Shiraz or Zinfandel\n", + "Red-Rich\t\t None \t None Cabernet Sauvignon\n", + "White-Floral None\t\t\t None Gewurztraminer\n", + "White-Citrus None\t\t\t None Riesling\n", + "Red\t\t\t None None Pinot Noir\n", + "Red\t\t\t None None Chianti\n", + "White\t\t\t None None Sauvignon Blanc\n", + "White\t\t\t None None Chardonnay\n", + "Red\t\t\t None None Shiraz or Zinfandel\n", + "Red\t\t\t None None Cabernet Sauvignon\n", + "White\t\t\t None None Gewurztraminer\n", + "White\t\t\t None None Riesling\n", + "Red-Fruity\t Light-Bodied\t\tNone Pinot Noir\n", + "Red-Fruity\t Full-Bodied\t\t None Shiraz or Zinfandel\n", + "Red-Earthy\t Light-Bodied\t\tNone Pinot Noir\n", + "Red-Earthy\t Full-Bodied\t\t None Cabernet Sauvignon\n", + "White-Crisp\t Dry\t\t None Sauvignon Blanc\n", + "White-Crisp\t Sweet\t\t None Pinot Noir\n", + "White-Creamy Dry\t\t None Pinot Noir\n", + "White-Creamy Sweet\t\t None Chardonnay\n", + "Red-Spicy\t Light-Bodied\t\tNone Pinot Noir\n", + "Red-Spicy\t Full-Bodied\t\t None Shiraz or Zinfandel\n", + "Red-Rich\t Light-Bodied\t\tNone Pinot Noir\n", + "Red-Rich\t Full-Bodied\t\t None Cabernet Sauvignon\n", + "White-Floral\tDry\t\t None Pinot Noir\n", + "White-Floral\tSweet\t\t None Gewurztraminer\n", + "White-Citrus\tDry\t\t None Sauvignon Blanc\n", + "White-Citrus\tSweet\t\t None Riesling\n", + "Red-Fruity\t\tNone\t Sweet Pinot Noir\n", + "Red-Fruity\t\tNone\t Dry Pinot Noir\n", + "Red-Earthy\t\tNone\t Sweet Chianti\n", + "Red-Earthy\t\tNone\t Dry Pinot Noir\n", + "\n", + "\n", + "Based on the data generate 10 different choices and recommended based on the choices\n", + "'''\n" + ] + }, + { + "cell_type": "code", + "execution_count": 39, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "NBVKb7ZOBTtg", + "outputId": "98da1540-213a-4221-c866-ca0f880aaf05" + }, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "\n", + "1. Pinot Noir (Red-Fruity, Light-Bodied, Sweet) \n", + "2. Sauvignon Blanc (White-Crisp, Dry)\n", + "3. Chardonnay (White-Creamy, Sweet)\n", + "4. Chianti (Red-Earthy, Sweet) \n", + "5. Riesling (White-Citrus, Sweet)\n", + "6. Shiraz or Zinfandel (Red-Spicy, Full-Bodied)\n", + "7. Cabernet Sauvignon (Red-Rich, Full-Bodied)\n", + "8. Gewurztraminer (White-Floral, Sweet) \n", + "9. Pinot Noir (Red-Earthy, Light-Bodied)\n", + "10. Pinot Noir (Red-Fruity, Dry)\n" + ] + } + ], + "source": [ + "print(call(data))" + ] + }, + { + "cell_type": "code", + "execution_count": 40, + "metadata": { + "id": "hvcX7UWqBblL" + }, + "outputs": [], + "source": [ + "data1 = '''\n", + "Preference\t Red_Wine\t White_Wine\t Recommendation\n", + "Red\t Light-Bodied\t\tNone Pinot Noir\n", + "Red\t Full-Bodied\t\t None Shiraz or Zinfandel\n", + "White\t\t None Dry Sauvignon Blanc\n", + "White\t\t None None Sweet\tGewurztraminer\n", + "Red-Fruity\t None\t\t None Pinot Noir\n", + "Red-Earthy\t None\t\t None Chianti\n", + "White-Crisp\t None\t\t None Sauvignon Blanc\n", + "White-Creamy None\t\t\t None Chardonnay\n", + "Red-Spicy\t\t None\t None Shiraz or Zinfandel\n", + "Red-Rich\t\t None \t None Cabernet Sauvignon\n", + "White-Floral None\t\t\t None Gewurztraminer\n", + "White-Citrus None\t\t\t None Riesling\n", + "Red\t\t\t None None Pinot Noir\n", + "Red\t\t\t None None Chianti\n", + "White\t\t\t None None Sauvignon Blanc\n", + "White\t\t\t None None Chardonnay\n", + "Red\t\t\t None None Shiraz or Zinfandel\n", + "Red\t\t\t None None Cabernet Sauvignon\n", + "White\t\t\t None None Gewurztraminer\n", + "White\t\t\t None None Riesling\n", + "Red-Fruity\t Light-Bodied\t\tNone Pinot Noir\n", + "Red-Fruity\t Full-Bodied\t\t None Shiraz or Zinfandel\n", + "Red-Earthy\t Light-Bodied\t\tNone Pinot Noir\n", + "Red-Earthy\t Full-Bodied\t\t None Cabernet Sauvignon\n", + "White-Crisp\t Dry\t\t None Sauvignon Blanc\n", + "White-Crisp\t Sweet\t\t None Pinot Noir\n", + "White-Creamy Dry\t\t None Pinot Noir\n", + "White-Creamy Sweet\t\t None Chardonnay\n", + "Red-Spicy\t Light-Bodied\t\tNone Pinot Noir\n", + "Red-Spicy\t Full-Bodied\t\t None Shiraz or Zinfandel\n", + "Red-Rich\t Light-Bodied\t\tNone Pinot Noir\n", + "Red-Rich\t Full-Bodied\t\t None Cabernet Sauvignon\n", + "White-Floral\tDry\t\t None Pinot Noir\n", + "White-Floral\tSweet\t\t None Gewurztraminer\n", + "White-Citrus\tDry\t\t None Sauvignon Blanc\n", + "White-Citrus\tSweet\t\t None Riesling\n", + "Red-Fruity\t\tNone\t Sweet Pinot Noir\n", + "Red-Fruity\t\tNone\t Dry Pinot Noir\n", + "Red-Earthy\t\tNone\t Sweet Chianti\n", + "Red-Earthy\t\tNone\t Dry Pinot Noir\n", + "\n", + "\n", + "Customer 1: Red,Dry?\n", + "Customer 2: White?\n", + "Customer 3: White-Earthry?\n", + "Customer 4: White-Floral,Light-Bodied?\n", + "Customer 5: Red-Spicy,Dry?\n", + "Customer 6: Red-Rich,Full-Bodied?\n", + "Customer 7: White-Creamy?\n", + "Customer 8: White-Crisp,Light-Bodied?\n", + "Customer 9: White-Crisp,Full-Bodied?\n", + "Customer 10: White-Crisp,Dry?\n", + "'''\n", + "result = call(data1)" + ] + }, + { + "cell_type": "code", + "execution_count": 41, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 54 + }, + "id": "j2huyLpSByd7", + "outputId": "b97dd46c-43b4-44b3-960c-4f2250bf1e27" + }, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "'\\nRecommendation\\nCustomer 1: Pinot Noir\\nCustomer 2: Sauvignon Blanc\\nCustomer 3: Pinot Noir\\nCustomer 4: Pinot Noir \\nCustomer 5: Shiraz or Zinfandel\\nCustomer 6: Cabernet Sauvignon\\nCustomer 7: Chardonnay\\nCustomer 8: Sauvignon Blanc\\nCustomer 9: Pinot Noir\\nCustomer 10: Sauvignon Blanc'" + ], + "application/vnd.google.colaboratory.intrinsic+json": { + "type": "string" + } + }, + "metadata": {}, + "execution_count": 41 + } + ], + "source": [ + "result" + ] + }, + { + "cell_type": "code", + "execution_count": 42, + "metadata": { + "id": "WQ0o-f8ZDorN" + }, + "outputs": [], + "source": [ + "import re\n", + "results = re.split('Customer |[0-9]|:|\\n|Recommendation',result)" + ] + }, + { + "cell_type": "code", + "execution_count": 43, + "metadata": { + "id": "D1NJZE5zHcHE" + }, + "outputs": [], + "source": [ + "fin_res = [res for res in results if len(res)>0]" + ] + }, + { + "cell_type": "code", + "execution_count": 44, + "metadata": { + "id": "GSW3EX85DraE" + }, + "outputs": [], + "source": [ + "data = {\n", + " 'Query':['Red,Dry?','White?','White-Earthry?','White-Floral,Light-Bodied?','Red-Spicy,Dry?','Red-Rich,Full-Bodied?','White-Creamy?','White-Crisp,Light-Bodied?','White-Crisp,Full-Bodied?','White-Crisp,Dry?'],\n", + " 'Recommendation': fin_res\n", + "}" + ] + }, + { + "cell_type": "code", + "execution_count": 45, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "fJbCVsgNHotD", + "outputId": "8f6571f8-ceba-43f0-bf2a-0e6253f903ec" + }, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "{'Query': ['Red,Dry?',\n", + " 'White?',\n", + " 'White-Earthry?',\n", + " 'White-Floral,Light-Bodied?',\n", + " 'Red-Spicy,Dry?',\n", + " 'Red-Rich,Full-Bodied?',\n", + " 'White-Creamy?',\n", + " 'White-Crisp,Light-Bodied?',\n", + " 'White-Crisp,Full-Bodied?',\n", + " 'White-Crisp,Dry?'],\n", + " 'Recommendation': [' Pinot Noir',\n", + " ' Sauvignon Blanc',\n", + " ' Pinot Noir',\n", + " ' Pinot Noir ',\n", + " ' Shiraz or Zinfandel',\n", + " ' Cabernet Sauvignon',\n", + " ' Chardonnay',\n", + " ' Sauvignon Blanc',\n", + " ' Pinot Noir',\n", + " ' Sauvignon Blanc']}" + ] + }, + "metadata": {}, + "execution_count": 45 + } + ], + "source": [ + "data" + ] + }, + { + "cell_type": "code", + "execution_count": 46, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 206 + }, + "id": "lq1YFA-FHtmq", + "outputId": "9f2b43e9-1f61-49b0-d324-4a6dbeea6133" + }, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + " Query Recommendation\n", + "0 Red,Dry? Pinot Noir\n", + "1 White? Sauvignon Blanc\n", + "2 White-Earthry? Pinot Noir\n", + "3 White-Floral,Light-Bodied? Pinot Noir \n", + "4 Red-Spicy,Dry? Shiraz or Zinfandel" + ], + "text/html": [ + "\n", + "
\n", + "
\n", + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
QueryRecommendation
0Red,Dry?Pinot Noir
1White?Sauvignon Blanc
2White-Earthry?Pinot Noir
3White-Floral,Light-Bodied?Pinot Noir
4Red-Spicy,Dry?Shiraz or Zinfandel
\n", + "
\n", + " \n", + " \n", + " \n", + "\n", + " \n", + "
\n", + "
\n", + " " + ] + }, + "metadata": {}, + "execution_count": 46 + } + ], + "source": [ + "import pandas as pd\n", + "df = pd.DataFrame(data)\n", + "df.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 47, + "metadata": { + "id": "hZJksWOkH6VS" + }, + "outputs": [], + "source": [ + "data_4 = ''' \n", + "Preference\t Red_Wine\t White_Wine\t Recommendation\n", + "Red\t Light-Bodied\t\tNone Pinot Noir\n", + "Red\t Full-Bodied\t\t None Shiraz or Zinfandel\n", + "White\t\t None Dry Sauvignon Blanc\n", + "White\t\t None None Sweet\tGewurztraminer\n", + "Red-Fruity\t None\t\t None Pinot Noir\n", + "Red-Earthy\t None\t\t None Chianti\n", + "White-Crisp\t None\t\t None Sauvignon Blanc\n", + "White-Creamy None\t\t\t None Chardonnay\n", + "Red-Spicy\t\t None\t None Shiraz or Zinfandel\n", + "Red-Rich\t\t None \t None Cabernet Sauvignon\n", + "White-Floral None\t\t\t None Gewurztraminer\n", + "White-Citrus None\t\t\t None Riesling\n", + "Red\t\t\t None None Pinot Noir\n", + "Red\t\t\t None None Chianti\n", + "White\t\t\t None None Sauvignon Blanc\n", + "White\t\t\t None None Chardonnay\n", + "Red\t\t\t None None Shiraz or Zinfandel\n", + "Red\t\t\t None None Cabernet Sauvignon\n", + "White\t\t\t None None Gewurztraminer\n", + "White\t\t\t None None Riesling\n", + "Red-Fruity\t Light-Bodied\t\tNone Pinot Noir\n", + "Red-Fruity\t Full-Bodied\t\t None Shiraz or Zinfandel\n", + "Red-Earthy\t Light-Bodied\t\tNone Pinot Noir\n", + "Red-Earthy\t Full-Bodied\t\t None Cabernet Sauvignon\n", + "White-Crisp\t Dry\t\t None Sauvignon Blanc\n", + "White-Crisp\t Sweet\t\t None Pinot Noir\n", + "White-Creamy Dry\t\t None Pinot Noir\n", + "White-Creamy Sweet\t\t None Chardonnay\n", + "Red-Spicy\t Light-Bodied\t\tNone Pinot Noir\n", + "Red-Spicy\t Full-Bodied\t\t None Shiraz or Zinfandel\n", + "Red-Rich\t Light-Bodied\t\tNone Pinot Noir\n", + "Red-Rich\t Full-Bodied\t\t None Cabernet Sauvignon\n", + "White-Floral\tDry\t\t None Pinot Noir\n", + "White-Floral\tSweet\t\t None Gewurztraminer\n", + "White-Citrus\tDry\t\t None Sauvignon Blanc\n", + "White-Citrus\tSweet\t\t None Riesling\n", + "Red-Fruity\t\tNone\t Sweet Pinot Noir\n", + "Red-Fruity\t\tNone\t Dry Pinot Noir\n", + "Red-Earthy\t\tNone\t Sweet Chianti\n", + "Red-Earthy\t\tNone\t Dry Pinot Noir\n", + "\n", + "\n", + "Based on the data generate 20 different choices and recommended based on the choices\n", + "'''\n" + ] + }, + { + "cell_type": "code", + "execution_count": 48, + "metadata": { + "id": "VF7kwoFuYIT4" + }, + "outputs": [], + "source": [ + "Questions = call(data_4)" + ] + }, + { + "cell_type": "code", + "execution_count": 49, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 109 + }, + "id": "zSwiyj-QYNYo", + "outputId": "042d5f15-2dc9-4856-e2bc-2e59b43643a9" + }, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "'\\n1. Pinot Noir (Red-Fruity, Dry)\\n2. Shiraz or Zinfandel (Red-Fruity, Full-Bodied)\\n3. Sauvignon Blanc (White-Crisp, Dry)\\n4. Sweet Gewurztraminer (White, None)\\n5. Chianti (Red-Earthy, None)\\n6. Chardonnay (White-Creamy, Sweet)\\n7. Cabernet Sauvignon (Red-Rich, Full-Bodied)\\n8. Pinot Noir (Red, Light-Bodied)\\n9. Shiraz or Zinfandel (Red-Spicy, Light-Bodied)\\n10. Pinot Noir (Red, None)\\n11. Chianti (Red, None)\\n12. Sauvignon Blanc (White, None)\\n13. Chardonnay (White, None)\\n14. Shiraz or Zinfandel (Red, None)\\n15. Cabernet Sauvignon (Red, None)\\n16. Gewurztraminer (White-Floral, Sweet)\\n17. Riesling (White-Citrus, Sweet)\\n18. Pinot Noir (Red-Earthy, Light-Bodied)\\n19. Cabernet Sauvignon (Red-Rich, Light-Bodied)\\n20. Pinot Noir (White-Crisp, Sweet)'" + ], + "application/vnd.google.colaboratory.intrinsic+json": { + "type": "string" + } + }, + "metadata": {}, + "execution_count": 49 + } + ], + "source": [ + "Questions" + ] + }, + { + "cell_type": "code", + "execution_count": 51, + "metadata": { + "id": "YaP0OU8MYtJ4" + }, + "outputs": [], + "source": [ + "temp = re.split('[0-9]|\\n|\\.',Questions)" + ] + }, + { + "cell_type": "code", + "execution_count": 52, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "pGeywgUbZC1w", + "outputId": "6d3fff60-6c31-4a24-d50b-7f7e8c9a1a54" + }, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "[' Pinot Noir (Red-Fruity, Dry)',\n", + " ' Shiraz or Zinfandel (Red-Fruity, Full-Bodied)',\n", + " ' Sauvignon Blanc (White-Crisp, Dry)',\n", + " ' Sweet Gewurztraminer (White, None)',\n", + " ' Chianti (Red-Earthy, None)',\n", + " ' Chardonnay (White-Creamy, Sweet)',\n", + " ' Cabernet Sauvignon (Red-Rich, Full-Bodied)',\n", + " ' Pinot Noir (Red, Light-Bodied)',\n", + " ' Shiraz or Zinfandel (Red-Spicy, Light-Bodied)',\n", + " ' Pinot Noir (Red, None)',\n", + " ' Chianti (Red, None)',\n", + " ' Sauvignon Blanc (White, None)',\n", + " ' Chardonnay (White, None)',\n", + " ' Shiraz or Zinfandel (Red, None)',\n", + " ' Cabernet Sauvignon (Red, None)',\n", + " ' Gewurztraminer (White-Floral, Sweet)',\n", + " ' Riesling (White-Citrus, Sweet)',\n", + " ' Pinot Noir (Red-Earthy, Light-Bodied)',\n", + " ' Cabernet Sauvignon (Red-Rich, Light-Bodied)',\n", + " ' Pinot Noir (White-Crisp, Sweet)']" + ] + }, + "metadata": {}, + "execution_count": 52 + } + ], + "source": [ + "QA = [tem for tem in temp if len(tem)>0]\n", + "QA" + ] + }, + { + "cell_type": "code", + "execution_count": 53, + "metadata": { + "id": "LtK-srHkaHU4" + }, + "outputs": [], + "source": [ + "ques = []\n", + "ans = []\n", + "\n", + "for item in QA:\n", + " a = item\n", + " b = re.split('[()]|\\|',a)\n", + " ans.append(b[0])\n", + " j = 0\n", + " str_temp = \"(\"\n", + " for i in b:\n", + " if j==0:\n", + " j = -1\n", + " continue\n", + " elif len(i):\n", + " str_temp += i\n", + " str_temp += \"|\"\n", + "\n", + " str_temp = str_temp.rstrip(\"|\")\n", + " str_temp += \")\" \n", + " ques.append(str_temp)\n", + " str_temp = \"\"\n", + " " + ] + }, + { + "cell_type": "code", + "execution_count": 54, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "KpOLQ105an9v", + "outputId": "e3f94de1-e03b-48ae-fc9e-809221f0b111" + }, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "['(Red-Fruity, Dry)',\n", + " '(Red-Fruity, Full-Bodied)',\n", + " '(White-Crisp, Dry)',\n", + " '(White, None)',\n", + " '(Red-Earthy, None)',\n", + " '(White-Creamy, Sweet)',\n", + " '(Red-Rich, Full-Bodied)',\n", + " '(Red, Light-Bodied)',\n", + " '(Red-Spicy, Light-Bodied)',\n", + " '(Red, None)',\n", + " '(Red, None)',\n", + " '(White, None)',\n", + " '(White, None)',\n", + " '(Red, None)',\n", + " '(Red, None)',\n", + " '(White-Floral, Sweet)',\n", + " '(White-Citrus, Sweet)',\n", + " '(Red-Earthy, Light-Bodied)',\n", + " '(Red-Rich, Light-Bodied)',\n", + " '(White-Crisp, Sweet)']" + ] + }, + "metadata": {}, + "execution_count": 54 + } + ], + "source": [ + "ques" + ] + }, + { + "cell_type": "code", + "execution_count": 55, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "SBRw37z7cQ9I", + "outputId": "78c414b2-397f-41f6-8cb4-793bd72eed7f" + }, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "[' Pinot Noir ',\n", + " ' Shiraz or Zinfandel ',\n", + " ' Sauvignon Blanc ',\n", + " ' Sweet Gewurztraminer ',\n", + " ' Chianti ',\n", + " ' Chardonnay ',\n", + " ' Cabernet Sauvignon ',\n", + " ' Pinot Noir ',\n", + " ' Shiraz or Zinfandel ',\n", + " ' Pinot Noir ',\n", + " ' Chianti ',\n", + " ' Sauvignon Blanc ',\n", + " ' Chardonnay ',\n", + " ' Shiraz or Zinfandel ',\n", + " ' Cabernet Sauvignon ',\n", + " ' Gewurztraminer ',\n", + " ' Riesling ',\n", + " ' Pinot Noir ',\n", + " ' Cabernet Sauvignon ',\n", + " ' Pinot Noir ']" + ] + }, + "metadata": {}, + "execution_count": 55 + } + ], + "source": [ + "ans" + ] + }, + { + "cell_type": "code", + "execution_count": 70, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 206 + }, + "id": "iBEOQXdCdg1A", + "outputId": "bf03a995-170e-455f-8e98-433bb254fdfd" + }, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + " Question Answer\n", + "0 (Red-Fruity, Dry) Pinot Noir \n", + "1 (Red-Fruity, Full-Bodied) Shiraz or Zinfandel \n", + "2 (White-Crisp, Dry) Sauvignon Blanc \n", + "3 (White, None) Sweet Gewurztraminer \n", + "4 (Red-Earthy, None) Chianti " + ], + "text/html": [ + "\n", + "
\n", + "
\n", + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
QuestionAnswer
0(Red-Fruity, Dry)Pinot Noir
1(Red-Fruity, Full-Bodied)Shiraz or Zinfandel
2(White-Crisp, Dry)Sauvignon Blanc
3(White, None)Sweet Gewurztraminer
4(Red-Earthy, None)Chianti
\n", + "
\n", + " \n", + " \n", + " \n", + "\n", + " \n", + "
\n", + "
\n", + " " + ] + }, + "metadata": {}, + "execution_count": 70 + } + ], + "source": [ + "data_temp = {'Question':ques,'Answer':ans}\n", + "df1 = pd.DataFrame(data_temp)\n", + "df1.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 71, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 676 + }, + "id": "mrcR7rr7d2W3", + "outputId": "6f530435-9415-41f4-f4d4-8eca01ea877a" + }, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + " Question Answer\n", + "0 (Red-Fruity, Dry) Pinot Noir \n", + "1 (Red-Fruity, Full-Bodied) Shiraz or Zinfandel \n", + "2 (White-Crisp, Dry) Sauvignon Blanc \n", + "3 (White, None) Sweet Gewurztraminer \n", + "4 (Red-Earthy, None) Chianti \n", + "5 (White-Creamy, Sweet) Chardonnay \n", + "6 (Red-Rich, Full-Bodied) Cabernet Sauvignon \n", + "7 (Red, Light-Bodied) Pinot Noir \n", + "8 (Red-Spicy, Light-Bodied) Shiraz or Zinfandel \n", + "9 (Red, None) Pinot Noir \n", + "10 (Red, None) Chianti \n", + "11 (White, None) Sauvignon Blanc \n", + "12 (White, None) Chardonnay \n", + "13 (Red, None) Shiraz or Zinfandel \n", + "14 (Red, None) Cabernet Sauvignon \n", + "15 (White-Floral, Sweet) Gewurztraminer \n", + "16 (White-Citrus, Sweet) Riesling \n", + "17 (Red-Earthy, Light-Bodied) Pinot Noir \n", + "18 (Red-Rich, Light-Bodied) Cabernet Sauvignon \n", + "19 (White-Crisp, Sweet) Pinot Noir " + ], + "text/html": [ + "\n", + "
\n", + "
\n", + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
QuestionAnswer
0(Red-Fruity, Dry)Pinot Noir
1(Red-Fruity, Full-Bodied)Shiraz or Zinfandel
2(White-Crisp, Dry)Sauvignon Blanc
3(White, None)Sweet Gewurztraminer
4(Red-Earthy, None)Chianti
5(White-Creamy, Sweet)Chardonnay
6(Red-Rich, Full-Bodied)Cabernet Sauvignon
7(Red, Light-Bodied)Pinot Noir
8(Red-Spicy, Light-Bodied)Shiraz or Zinfandel
9(Red, None)Pinot Noir
10(Red, None)Chianti
11(White, None)Sauvignon Blanc
12(White, None)Chardonnay
13(Red, None)Shiraz or Zinfandel
14(Red, None)Cabernet Sauvignon
15(White-Floral, Sweet)Gewurztraminer
16(White-Citrus, Sweet)Riesling
17(Red-Earthy, Light-Bodied)Pinot Noir
18(Red-Rich, Light-Bodied)Cabernet Sauvignon
19(White-Crisp, Sweet)Pinot Noir
\n", + "
\n", + " \n", + " \n", + " \n", + "\n", + " \n", + "
\n", + "
\n", + " " + ] + }, + "metadata": {}, + "execution_count": 71 + } + ], + "source": [ + "df1" + ] + }, + { + "cell_type": "code", + "source": [ + "df1['Answer'] = df1['Answer'].str.replace(' END', '')" + ], + "metadata": { + "id": "C02VOrRdsJF1" + }, + "execution_count": 72, + "outputs": [] + }, + { + "cell_type": "code", + "source": [ + "df1" + ], + "metadata": { + "id": "o7JXsozXsMV9", + "outputId": "0d0e9530-d0d8-4dca-dd13-70f290220bfe", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 676 + } + }, + "execution_count": 73, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + " Question Answer\n", + "0 (Red-Fruity, Dry) Pinot Noir \n", + "1 (Red-Fruity, Full-Bodied) Shiraz or Zinfandel \n", + "2 (White-Crisp, Dry) Sauvignon Blanc \n", + "3 (White, None) Sweet Gewurztraminer \n", + "4 (Red-Earthy, None) Chianti \n", + "5 (White-Creamy, Sweet) Chardonnay \n", + "6 (Red-Rich, Full-Bodied) Cabernet Sauvignon \n", + "7 (Red, Light-Bodied) Pinot Noir \n", + "8 (Red-Spicy, Light-Bodied) Shiraz or Zinfandel \n", + "9 (Red, None) Pinot Noir \n", + "10 (Red, None) Chianti \n", + "11 (White, None) Sauvignon Blanc \n", + "12 (White, None) Chardonnay \n", + "13 (Red, None) Shiraz or Zinfandel \n", + "14 (Red, None) Cabernet Sauvignon \n", + "15 (White-Floral, Sweet) Gewurztraminer \n", + "16 (White-Citrus, Sweet) Riesling \n", + "17 (Red-Earthy, Light-Bodied) Pinot Noir \n", + "18 (Red-Rich, Light-Bodied) Cabernet Sauvignon \n", + "19 (White-Crisp, Sweet) Pinot Noir " + ], + "text/html": [ + "\n", + "
\n", + "
\n", + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
QuestionAnswer
0(Red-Fruity, Dry)Pinot Noir
1(Red-Fruity, Full-Bodied)Shiraz or Zinfandel
2(White-Crisp, Dry)Sauvignon Blanc
3(White, None)Sweet Gewurztraminer
4(Red-Earthy, None)Chianti
5(White-Creamy, Sweet)Chardonnay
6(Red-Rich, Full-Bodied)Cabernet Sauvignon
7(Red, Light-Bodied)Pinot Noir
8(Red-Spicy, Light-Bodied)Shiraz or Zinfandel
9(Red, None)Pinot Noir
10(Red, None)Chianti
11(White, None)Sauvignon Blanc
12(White, None)Chardonnay
13(Red, None)Shiraz or Zinfandel
14(Red, None)Cabernet Sauvignon
15(White-Floral, Sweet)Gewurztraminer
16(White-Citrus, Sweet)Riesling
17(Red-Earthy, Light-Bodied)Pinot Noir
18(Red-Rich, Light-Bodied)Cabernet Sauvignon
19(White-Crisp, Sweet)Pinot Noir
\n", + "
\n", + " \n", + " \n", + " \n", + "\n", + " \n", + "
\n", + "
\n", + " " + ] + }, + "metadata": {}, + "execution_count": 73 + } + ] + }, + { + "cell_type": "code", + "source": [ + "df1['Question'] = df1['Question'].str.strip()" + ], + "metadata": { + "id": "d66os-iBsRrf" + }, + "execution_count": 74, + "outputs": [] + }, + { + "cell_type": "code", + "source": [ + "df1" + ], + "metadata": { + "id": "YfWJRjzps_Xe", + "outputId": "2a3e9599-458b-45b0-ab62-a2579ff48b8c", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 676 + } + }, + "execution_count": 75, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + " Question Answer\n", + "0 (Red-Fruity, Dry) Pinot Noir \n", + "1 (Red-Fruity, Full-Bodied) Shiraz or Zinfandel \n", + "2 (White-Crisp, Dry) Sauvignon Blanc \n", + "3 (White, None) Sweet Gewurztraminer \n", + "4 (Red-Earthy, None) Chianti \n", + "5 (White-Creamy, Sweet) Chardonnay \n", + "6 (Red-Rich, Full-Bodied) Cabernet Sauvignon \n", + "7 (Red, Light-Bodied) Pinot Noir \n", + "8 (Red-Spicy, Light-Bodied) Shiraz or Zinfandel \n", + "9 (Red, None) Pinot Noir \n", + "10 (Red, None) Chianti \n", + "11 (White, None) Sauvignon Blanc \n", + "12 (White, None) Chardonnay \n", + "13 (Red, None) Shiraz or Zinfandel \n", + "14 (Red, None) Cabernet Sauvignon \n", + "15 (White-Floral, Sweet) Gewurztraminer \n", + "16 (White-Citrus, Sweet) Riesling \n", + "17 (Red-Earthy, Light-Bodied) Pinot Noir \n", + "18 (Red-Rich, Light-Bodied) Cabernet Sauvignon \n", + "19 (White-Crisp, Sweet) Pinot Noir " + ], + "text/html": [ + "\n", + "
\n", + "
\n", + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
QuestionAnswer
0(Red-Fruity, Dry)Pinot Noir
1(Red-Fruity, Full-Bodied)Shiraz or Zinfandel
2(White-Crisp, Dry)Sauvignon Blanc
3(White, None)Sweet Gewurztraminer
4(Red-Earthy, None)Chianti
5(White-Creamy, Sweet)Chardonnay
6(Red-Rich, Full-Bodied)Cabernet Sauvignon
7(Red, Light-Bodied)Pinot Noir
8(Red-Spicy, Light-Bodied)Shiraz or Zinfandel
9(Red, None)Pinot Noir
10(Red, None)Chianti
11(White, None)Sauvignon Blanc
12(White, None)Chardonnay
13(Red, None)Shiraz or Zinfandel
14(Red, None)Cabernet Sauvignon
15(White-Floral, Sweet)Gewurztraminer
16(White-Citrus, Sweet)Riesling
17(Red-Earthy, Light-Bodied)Pinot Noir
18(Red-Rich, Light-Bodied)Cabernet Sauvignon
19(White-Crisp, Sweet)Pinot Noir
\n", + "
\n", + " \n", + " \n", + " \n", + "\n", + " \n", + "
\n", + "
\n", + " " + ] + }, + "metadata": {}, + "execution_count": 75 + } + ] + }, + { + "cell_type": "code", + "source": [ + "df1['Question'] = 'Question: ' + df1['Question']" + ], + "metadata": { + "id": "x2U6hCOxtBef" + }, + "execution_count": 76, + "outputs": [] + }, + { + "cell_type": "code", + "source": [ + "df1" + ], + "metadata": { + "id": "YXChQOBzsVNl", + "outputId": "d0f70f77-8e4f-4ec1-bf4b-778fd016dfd2", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 676 + } + }, + "execution_count": 77, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + " Question Answer\n", + "0 Question: (Red-Fruity, Dry) Pinot Noir \n", + "1 Question: (Red-Fruity, Full-Bodied) Shiraz or Zinfandel \n", + "2 Question: (White-Crisp, Dry) Sauvignon Blanc \n", + "3 Question: (White, None) Sweet Gewurztraminer \n", + "4 Question: (Red-Earthy, None) Chianti \n", + "5 Question: (White-Creamy, Sweet) Chardonnay \n", + "6 Question: (Red-Rich, Full-Bodied) Cabernet Sauvignon \n", + "7 Question: (Red, Light-Bodied) Pinot Noir \n", + "8 Question: (Red-Spicy, Light-Bodied) Shiraz or Zinfandel \n", + "9 Question: (Red, None) Pinot Noir \n", + "10 Question: (Red, None) Chianti \n", + "11 Question: (White, None) Sauvignon Blanc \n", + "12 Question: (White, None) Chardonnay \n", + "13 Question: (Red, None) Shiraz or Zinfandel \n", + "14 Question: (Red, None) Cabernet Sauvignon \n", + "15 Question: (White-Floral, Sweet) Gewurztraminer \n", + "16 Question: (White-Citrus, Sweet) Riesling \n", + "17 Question: (Red-Earthy, Light-Bodied) Pinot Noir \n", + "18 Question: (Red-Rich, Light-Bodied) Cabernet Sauvignon \n", + "19 Question: (White-Crisp, Sweet) Pinot Noir " + ], + "text/html": [ + "\n", + "
\n", + "
\n", + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
QuestionAnswer
0Question: (Red-Fruity, Dry)Pinot Noir
1Question: (Red-Fruity, Full-Bodied)Shiraz or Zinfandel
2Question: (White-Crisp, Dry)Sauvignon Blanc
3Question: (White, None)Sweet Gewurztraminer
4Question: (Red-Earthy, None)Chianti
5Question: (White-Creamy, Sweet)Chardonnay
6Question: (Red-Rich, Full-Bodied)Cabernet Sauvignon
7Question: (Red, Light-Bodied)Pinot Noir
8Question: (Red-Spicy, Light-Bodied)Shiraz or Zinfandel
9Question: (Red, None)Pinot Noir
10Question: (Red, None)Chianti
11Question: (White, None)Sauvignon Blanc
12Question: (White, None)Chardonnay
13Question: (Red, None)Shiraz or Zinfandel
14Question: (Red, None)Cabernet Sauvignon
15Question: (White-Floral, Sweet)Gewurztraminer
16Question: (White-Citrus, Sweet)Riesling
17Question: (Red-Earthy, Light-Bodied)Pinot Noir
18Question: (Red-Rich, Light-Bodied)Cabernet Sauvignon
19Question: (White-Crisp, Sweet)Pinot Noir
\n", + "
\n", + " \n", + " \n", + " \n", + "\n", + " \n", + "
\n", + "
\n", + " " + ] + }, + "metadata": {}, + "execution_count": 77 + } + ] + }, + { + "cell_type": "code", + "source": [ + "df1.loc[0] = [\"Question: \\n\\nAnswer:\\n\\n\",\"END\"]" + ], + "metadata": { + "id": "IsUtstXYt-j1" + }, + "execution_count": 78, + "outputs": [] + }, + { + "cell_type": "code", + "source": [ + "df1" + ], + "metadata": { + "id": "JaRMnbmbuWIF", + "outputId": "95acf69b-6538-4270-bc03-f187eaa28e05", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 676 + } + }, + "execution_count": 79, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + " Question Answer\n", + "0 Question: \\n\\nAnswer:\\n\\n END\n", + "1 Question: (Red-Fruity, Full-Bodied) Shiraz or Zinfandel \n", + "2 Question: (White-Crisp, Dry) Sauvignon Blanc \n", + "3 Question: (White, None) Sweet Gewurztraminer \n", + "4 Question: (Red-Earthy, None) Chianti \n", + "5 Question: (White-Creamy, Sweet) Chardonnay \n", + "6 Question: (Red-Rich, Full-Bodied) Cabernet Sauvignon \n", + "7 Question: (Red, Light-Bodied) Pinot Noir \n", + "8 Question: (Red-Spicy, Light-Bodied) Shiraz or Zinfandel \n", + "9 Question: (Red, None) Pinot Noir \n", + "10 Question: (Red, None) Chianti \n", + "11 Question: (White, None) Sauvignon Blanc \n", + "12 Question: (White, None) Chardonnay \n", + "13 Question: (Red, None) Shiraz or Zinfandel \n", + "14 Question: (Red, None) Cabernet Sauvignon \n", + "15 Question: (White-Floral, Sweet) Gewurztraminer \n", + "16 Question: (White-Citrus, Sweet) Riesling \n", + "17 Question: (Red-Earthy, Light-Bodied) Pinot Noir \n", + "18 Question: (Red-Rich, Light-Bodied) Cabernet Sauvignon \n", + "19 Question: (White-Crisp, Sweet) Pinot Noir " + ], + "text/html": [ + "\n", + "
\n", + "
\n", + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
QuestionAnswer
0Question: \\n\\nAnswer:\\n\\nEND
1Question: (Red-Fruity, Full-Bodied)Shiraz or Zinfandel
2Question: (White-Crisp, Dry)Sauvignon Blanc
3Question: (White, None)Sweet Gewurztraminer
4Question: (Red-Earthy, None)Chianti
5Question: (White-Creamy, Sweet)Chardonnay
6Question: (Red-Rich, Full-Bodied)Cabernet Sauvignon
7Question: (Red, Light-Bodied)Pinot Noir
8Question: (Red-Spicy, Light-Bodied)Shiraz or Zinfandel
9Question: (Red, None)Pinot Noir
10Question: (Red, None)Chianti
11Question: (White, None)Sauvignon Blanc
12Question: (White, None)Chardonnay
13Question: (Red, None)Shiraz or Zinfandel
14Question: (Red, None)Cabernet Sauvignon
15Question: (White-Floral, Sweet)Gewurztraminer
16Question: (White-Citrus, Sweet)Riesling
17Question: (Red-Earthy, Light-Bodied)Pinot Noir
18Question: (Red-Rich, Light-Bodied)Cabernet Sauvignon
19Question: (White-Crisp, Sweet)Pinot Noir
\n", + "
\n", + " \n", + " \n", + " \n", + "\n", + " \n", + "
\n", + "
\n", + " " + ] + }, + "metadata": {}, + "execution_count": 79 + } + ] + }, + { + "cell_type": "code", + "execution_count": 80, + "metadata": { + "id": "z3ghh7CWd8KC" + }, + "outputs": [], + "source": [ + "df1.columns = ['prompt', 'completion']" + ] + }, + { + "cell_type": "code", + "execution_count": 81, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 206 + }, + "id": "gjDCSFdleC5n", + "outputId": "1b73d9ea-a7e4-43ff-82dc-813e84eb1c49" + }, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + " prompt completion\n", + "0 Question: \\n\\nAnswer:\\n\\n END\n", + "1 Question: (Red-Fruity, Full-Bodied) Shiraz or Zinfandel \n", + "2 Question: (White-Crisp, Dry) Sauvignon Blanc \n", + "3 Question: (White, None) Sweet Gewurztraminer \n", + "4 Question: (Red-Earthy, None) Chianti " + ], + "text/html": [ + "\n", + "
\n", + "
\n", + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
promptcompletion
0Question: \\n\\nAnswer:\\n\\nEND
1Question: (Red-Fruity, Full-Bodied)Shiraz or Zinfandel
2Question: (White-Crisp, Dry)Sauvignon Blanc
3Question: (White, None)Sweet Gewurztraminer
4Question: (Red-Earthy, None)Chianti
\n", + "
\n", + " \n", + " \n", + " \n", + "\n", + " \n", + "
\n", + "
\n", + " " + ] + }, + "metadata": {}, + "execution_count": 81 + } + ], + "source": [ + "df1.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 82, + "metadata": { + "id": "bUCjN6UVeERH" + }, + "outputs": [], + "source": [ + "df1.to_json('qa_sample.jsonl', orient='records', lines=True)" + ] + }, + { + "cell_type": "code", + "execution_count": 83, + "metadata": { + "id": "5pNltIc1eKpP" + }, + "outputs": [], + "source": [ + "import os\n", + "os.environ['OPENAI_API_KEY'] = \"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\"" + ] + }, + { + "cell_type": "code", + "execution_count": 84, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "qMKRiq8jeVN6", + "outputId": "68747b92-83c8-47c2-a7f5-690c0475df48" + }, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Analyzing...\n", + "\n", + "- Your file contains 20 prompt-completion pairs. In general, we recommend having at least a few hundred examples. We've found that performance tends to linearly increase for every doubling of the number of examples\n", + "- Your data does not contain a common separator at the end of your prompts. Having a separator string appended to the end of the prompt makes it clearer to the fine-tuned model where the completion should begin. See https://platform.openai.com/docs/guides/fine-tuning/preparing-your-dataset for more detail and examples. If you intend to do open-ended generation, then you should leave the prompts empty\n", + "- All prompts start with prefix `Question: `\n", + "- Your data does not contain a common ending at the end of your completions. Having a common ending string appended to the end of the completion makes it clearer to the fine-tuned model where the completion should end. See https://platform.openai.com/docs/guides/fine-tuning/preparing-your-dataset for more detail and examples.\n", + "- The completion should start with a whitespace character (` `). This tends to produce better results due to the tokenization we use. See https://platform.openai.com/docs/guides/fine-tuning/preparing-your-dataset for more details\n", + "\n", + "Based on the analysis we will perform the following actions:\n", + "- [Recommended] Add a suffix separator `\\n\\n###\\n\\n` to all prompts [Y/n]: Y\n", + "- [Recommended] Add a suffix ending `\\n` to all completions [Y/n]: Y\n", + "- [Recommended] Add a whitespace character to the beginning of the completion [Y/n]: Y\n", + "\n", + "\n", + "Your data will be written to a new JSONL file. Proceed [Y/n]: Y\n", + "\n", + "Wrote modified file to `qa_sample_prepared.jsonl`\n", + "Feel free to take a look!\n", + "\n", + "Now use that file when fine-tuning:\n", + "> openai api fine_tunes.create -t \"qa_sample_prepared.jsonl\"\n", + "\n", + "After you’ve fine-tuned a model, remember that your prompt has to end with the indicator string `\\n\\n###\\n\\n` for the model to start generating completions, rather than continuing with the prompt. Make sure to include `stop=[\"\\n\"]` so that the generated texts ends at the expected place.\n", + "Once your model starts training, it'll approximately take 2.72 minutes to train a `curie` model, and less for `ada` and `babbage`. Queue will approximately take half an hour per job ahead of you.\n" + ] + } + ], + "source": [ + "!openai tools fine_tunes.prepare_data -f qa_sample.jsonl" + ] + }, + { + "cell_type": "code", + "execution_count": 85, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "rB6S552FeNmn", + "outputId": "df95cacd-e10e-4f12-fd7d-b93047e03ed8" + }, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "\rUpload progress: 0% 0.00/1.72k [00:00\n" + ] + } + ], + "source": [ + "!openai api fine_tunes.follow -i ft-rtDJX5c4gZGQsathmhgkAdMZ" + ] + }, + { + "cell_type": "code", + "execution_count": 97, + "metadata": { + "id": "pwdFktBKe_On", + "colab": { + "base_uri": "https://localhost:8080/" + }, + "outputId": "3a817df0-479b-430b-995b-a184878aff87" + }, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Answer the question based on DataSet Q: (White-Floral, Sweet) \n", + " Answer: Moscato d'Asti\n", + "\n", + "Q:\n" + ] + } + ], + "source": [ + "!openai api completions.create -m davinci:ft-global-corporate-holdings-2023-03-23-18-39-55 -p \"Answer the question based on DataSet Q: (White-Floral, Sweet)\"" + ] + }, + { + "cell_type": "code", + "source": [ + "import openai\n", + "def get_answers_api(question):\n", + " try:\n", + " response = openai.Completion.create(\n", + " api_key = \"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\",\n", + " engine=\"davinci:ft-global-corporate-holdings-2023-03-23-18-39-55\",\n", + " prompt=f\"Answer the question based on DataSet Q:\\n{question}\\n\\nAnswer:\",\n", + " temperature=0,\n", + " max_tokens=900,\n", + " top_p=1,\n", + " frequency_penalty=0,\n", + " presence_penalty=0\n", + " )\n", + " return response['choices'][0]['text']\n", + " except Exception as e:\n", + " print (e)\n", + " return \"\"\n", + "\n", + "print(get_answers_api('White-Floral, Sweet'))" + ], + "metadata": { + "id": "FOpiYqihxjUo", + "outputId": "87e7b8a2-c785-492c-b844-9535036aa9bc", + "colab": { + "base_uri": "https://localhost:8080/" + } + }, + "execution_count": 99, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "\n", + "\n", + "The correct answer is:\n", + "\n", + "\"Chardonnay\"\n", + "\n", + "The correct answer is:\n", + "\n", + "\"Chardonnay\"\n", + "\n", + "The correct answer is:\n", + "\n", + "\"Chardonnay\"\n", + "\n", + "The correct answer is:\n", + "\n", + "\"Chardonnay\"\n", + "\n", + "The correct answer is:\n", + "\n", + "\"Chardonnay\"\n", + "\n", + "The correct answer is:\n", + "\n", + "\"Chardonnay\"\n", + "\n", + "The correct answer is:\n", + "\n", + "\"Chardonnay\"\n", + "\n", + "The correct answer is:\n", + "\n", + "\"Chardonnay\"\n", + "\n", + "The correct answer is:\n", + "\n", + "\"Chardonnay\"\n", + "\n", + "The correct answer is:\n", + "\n", + "\"Chardonnay\"\n", + "\n", + "The correct answer is:\n", + "\n", + "\"Chardonnay\"\n", + "\n", + "The correct answer is:\n", + "\n", + "\"Chardonnay\"\n", + "\n", + "The correct answer is:\n", + "\n", + "\"Chardonnay\"\n", + "\n", + "The correct answer is:\n", + "\n", + "\"Chardonnay\"\n", + "\n", + "The correct answer is:\n", + "\n", + "\"Chardonnay\"\n", + "\n", + "The correct answer is:\n", + "\n", + "\"Chardonnay\"\n", + "\n", + "The correct answer is:\n", + "\n", + "\"Chardonnay\"\n", + "\n", + "The correct answer is:\n", + "\n", + "\"Chardonnay\"\n", + "\n", + "The correct answer is:\n", + "\n", + "\"Chardonnay\"\n", + "\n", + "The correct answer is:\n", + "\n", + "\"Chardonnay\"\n", + "\n", + "The correct answer is:\n", + "\n", + "\"Chardonnay\"\n", + "\n", + "The correct answer is:\n", + "\n", + "\"Chardonnay\"\n", + "\n", + "The correct answer is:\n", + "\n", + "\"Chardonnay\"\n", + "\n", + "The correct answer is:\n", + "\n", + "\"Chardonnay\"\n", + "\n", + "The correct answer is:\n", + "\n", + "\"Chardonnay\"\n", + "\n", + "The correct answer is:\n", + "\n", + "\"Chardonnay\"\n", + "\n", + "The correct answer is:\n", + "\n", + "\"Chardonnay\"\n", + "\n", + "The correct answer is:\n", + "\n", + "\"Chardonnay\"\n", + "\n", + "The correct answer is:\n", + "\n", + "\"Chardonnay\"\n", + "\n", + "The correct answer is:\n", + "\n", + "\"Chardonnay\"\n", + "\n", + "The correct answer is:\n", + "\n", + "\"Chardonnay\"\n", + "\n", + "The correct answer is:\n", + "\n", + "\"Chardonnay\"\n", + "\n", + "The correct answer is:\n", + "\n", + "\"Chardonnay\"\n", + "\n", + "The correct answer is:\n", + "\n", + "\"Chardonnay\"\n", + "\n", + "The correct answer is:\n", + "\n", + "\"Chardonnay\"\n", + "\n", + "The correct answer is:\n", + "\n", + "\"Chardonnay\"\n", + "\n", + "The correct answer is:\n", + "\n", + "\"Chardonnay\"\n", + "\n", + "The correct answer is:\n", + "\n", + "\"Chardonnay\"\n", + "\n", + "The correct answer is:\n", + "\n", + "\"Chardonnay\"\n", + "\n", + "The correct answer is:\n", + "\n", + "\"Chardonnay\"\n", + "\n", + "The correct answer is:\n", + "\n", + "\"Chardonnay\"\n", + "\n", + "The correct answer is:\n", + "\n", + "\"Chardonnay\"\n", + "\n", + "The correct answer is:\n", + "\n", + "\"Chardonnay\"\n", + "\n", + "The correct answer is:\n", + "\n", + "\"Chardonnay\"\n", + "\n", + "The correct answer is:\n", + "\n", + "\"Chardonnay\"\n", + "\n", + "The correct answer is:\n", + "\n", + "\"Chardonnay\"\n", + "\n", + "The correct answer is:\n", + "\n", + "\"Chardonnay\"\n", + "\n", + "The correct answer is:\n", + "\n", + "\"Chardonnay\"\n", + "\n", + "The correct answer is:\n", + "\n", + "\"Chardonnay\"\n", + "\n", + "The correct answer is:\n", + "\n", + "\"Chardonnay\"\n", + "\n", + "The correct answer is:\n", + "\n", + "\"Chardonnay\"\n", + "\n", + "The correct answer is:\n", + "\n", + "\"Chardonnay\"\n", + "\n", + "The correct answer is:\n", + "\n", + "\"Chardonnay\"\n", + "\n", + "The correct answer is:\n", + "\n", + "\"Chardonnay\"\n", + "\n", + "The correct answer is:\n", + "\n", + "\"Chardonnay\"\n", + "\n", + "The correct answer is:\n", + "\n", + "\"Chardonnay\"\n", + "\n", + "The correct answer is:\n", + "\n", + "\"Chardonnay\"\n", + "\n", + "The correct answer is:\n", + "\n", + "\"Chardonnay\"\n", + "\n", + "The correct answer is:\n", + "\n", + "\"Chardonnay\"\n", + "\n", + "The correct answer is:\n", + "\n", + "\"Chardonnay\"\n" + ] + } + ] + }, + { + "cell_type": "code", + "source": [ + "import openai\n", + "openai.api_key = \"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\"\n", + "response = openai.ChatCompletion.create(\n", + " model=\"gpt-3.5-turbo\",\n", + " messages= [{\n", + " \"role\": \"system\",\n", + " \"content\": \"You are a assistant\"\n", + " },\n", + "\n", + " {\n", + " \"role\": \"user\",\n", + " \"content\": \"Can you recommend wine based on my taste?\"\n", + " },\n", + "\n", + " {\n", + " \"content\": \"Of course! Please provide me with some details about your wine, such as Preference(Red,White,Red-Fruity,Red-Earthy,White-Crisp,Red-Spicy,Red-Rich), Red_Wine characteristics(Light-Bodied,Full-Bodied,Dry,Sweet,None), White_Wine Characteristics(Dry,Sweet,None) and the recommended wine such as (Pinot Noir,Gewurztraminer,Sauvignon Blanc,Shiraz or Zinfandel,Chianti,Chardonnay,Cabernet Sauvignon,Riesling).\",\n", + " \"role\": \"assistant\"\n", + " }, \n", + " {\n", + " \"role\": \"user\",\n", + " \"content\": \"(Red,Light-Bodied,None)\"\n", + " }\n", + "\n", + " \n", + " ]\n", + " )\n", + "print(response)" + ], + "metadata": { + "id": "nbEDdjmgyNLE", + "outputId": "c5b79e79-346d-4bde-b750-98e2cb58c813", + "colab": { + "base_uri": "https://localhost:8080/" + } + }, + "execution_count": 101, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "{\n", + " \"choices\": [\n", + " {\n", + " \"finish_reason\": \"stop\",\n", + " \"index\": 0,\n", + " \"message\": {\n", + " \"content\": \"Based on your preferences, I would suggest trying a Pinot Noir from Oregon or Burgundy. Both regions are known for producing Pinot Noir wines that are light-bodied with delicate fruit flavors, and have a lower tannin profile. Some specific recommendations include:\\n\\n- Erath Pinot Noir (Oregon)\\n- Domaine William F\\u00e8vre Chablis \\\"Le Domaine\\\" Pinot Noir (Burgundy, France)\\n- Joseph Drouhin LaFor\\u00eat Bourgogne Pinot Noir (Burgundy, France)\",\n", + " \"role\": \"assistant\"\n", + " }\n", + " }\n", + " ],\n", + " \"created\": 1679597713,\n", + " \"id\": \"chatcmpl-6xKNdM2Ye333AhWnzhF8hwOLTSjhT\",\n", + " \"model\": \"gpt-3.5-turbo-0301\",\n", + " \"object\": \"chat.completion\",\n", + " \"usage\": {\n", + " \"completion_tokens\": 108,\n", + " \"prompt_tokens\": 164,\n", + " \"total_tokens\": 272\n", + " }\n", + "}\n" + ] + } + ] + }, + { + "cell_type": "code", + "source": [], + "metadata": { + "id": "F_H-PxFL0lzw" + }, + "execution_count": null, + "outputs": [] + } + ], + "metadata": { + "colab": { + "provenance": [] + }, + "kernelspec": { + "display_name": "Python 3", + "name": "python3" + }, + "language_info": { + "name": "python" + }, + "accelerator": "GPU", + "gpuClass": "standard" + }, + "nbformat": 4, + "nbformat_minor": 0 +} \ No newline at end of file diff --git a/qa_sample.jsonl b/qa_sample.jsonl new file mode 100644 index 0000000..766b54c --- /dev/null +++ b/qa_sample.jsonl @@ -0,0 +1,20 @@ +{"prompt":"Question: (Red-Fruity, Dry)\n\nAnswer:\n\n","completion":" Pinot Noir "} +{"prompt":"Question: (Red-Fruity, Full-Bodied)\n\nAnswer:\n\n","completion":" Shiraz or Zinfandel "} +{"prompt":"Question: (White-Crisp, Dry)\n\nAnswer:\n\n","completion":" Sauvignon Blanc "} +{"prompt":"Question: (White, None)\n\nAnswer:\n\n","completion":" Sweet Gewurztraminer "} +{"prompt":"Question: (Red-Earthy, None)\n\nAnswer:\n\n","completion":" Chianti "} +{"prompt":"Question: (White-Creamy, Sweet)\n\nAnswer:\n\n","completion":" Chardonnay "} +{"prompt":"Question: (Red-Rich, Full-Bodied)\n\nAnswer:\n\n","completion":" Cabernet Sauvignon "} +{"prompt":"Question: (Red, Light-Bodied)\n\nAnswer:\n\n","completion":" Pinot Noir "} +{"prompt":"Question: (Red-Spicy, Light-Bodied)\n\nAnswer:\n\n","completion":" Shiraz or Zinfandel "} +{"prompt":"Question: (Red, None)\n\nAnswer:\n\n","completion":" Pinot Noir "} +{"prompt":"Question: (Red, None)\n\nAnswer:\n\n","completion":" Chianti "} +{"prompt":"Question: (White, None)\n\nAnswer:\n\n","completion":" Sauvignon Blanc "} +{"prompt":"Question: (White, None)\n\nAnswer:\n\n","completion":" Chardonnay "} +{"prompt":"Question: (Red, None)\n\nAnswer:\n\n","completion":" Shiraz or Zinfandel "} +{"prompt":"Question: (Red, None)\n\nAnswer:\n\n","completion":" Cabernet Sauvignon "} +{"prompt":"Question: (White-Floral, Sweet)\n\nAnswer:\n\n","completion":" Gewurztraminer "} +{"prompt":"Question: (White-Citrus, Sweet)\n\nAnswer:\n\n","completion":" Riesling "} +{"prompt":"Question: (Red-Earthy, Light-Bodied)\n\nAnswer:\n\n","completion":" Pinot Noir "} +{"prompt":"Question: (Red-Rich, Light-Bodied)\n\nAnswer:\n\n","completion":" Cabernet Sauvignon "} +{"prompt":"Question: (White-Crisp, Sweet)\n\nAnswer:\n\n","completion":" Pinot Noir "} diff --git a/qa_sample_prepared.jsonl b/qa_sample_prepared.jsonl new file mode 100644 index 0000000..75d5edc --- /dev/null +++ b/qa_sample_prepared.jsonl @@ -0,0 +1,20 @@ +{"prompt":"Question: \n\nAnswer:\n\n\n\n###\n\n","completion":" END\n"} +{"prompt":"Question: (Red-Fruity, Full-Bodied)\n\n###\n\n","completion":" Shiraz or Zinfandel \n"} +{"prompt":"Question: (White-Crisp, Dry)\n\n###\n\n","completion":" Sauvignon Blanc \n"} +{"prompt":"Question: (White, None)\n\n###\n\n","completion":" Sweet Gewurztraminer \n"} +{"prompt":"Question: (Red-Earthy, None)\n\n###\n\n","completion":" Chianti \n"} +{"prompt":"Question: (White-Creamy, Sweet)\n\n###\n\n","completion":" Chardonnay \n"} +{"prompt":"Question: (Red-Rich, Full-Bodied)\n\n###\n\n","completion":" Cabernet Sauvignon \n"} +{"prompt":"Question: (Red, Light-Bodied)\n\n###\n\n","completion":" Pinot Noir \n"} +{"prompt":"Question: (Red-Spicy, Light-Bodied)\n\n###\n\n","completion":" Shiraz or Zinfandel \n"} +{"prompt":"Question: (Red, None)\n\n###\n\n","completion":" Pinot Noir \n"} +{"prompt":"Question: (Red, None)\n\n###\n\n","completion":" Chianti \n"} +{"prompt":"Question: (White, None)\n\n###\n\n","completion":" Sauvignon Blanc \n"} +{"prompt":"Question: (White, None)\n\n###\n\n","completion":" Chardonnay \n"} +{"prompt":"Question: (Red, None)\n\n###\n\n","completion":" Shiraz or Zinfandel \n"} +{"prompt":"Question: (Red, None)\n\n###\n\n","completion":" Cabernet Sauvignon \n"} +{"prompt":"Question: (White-Floral, Sweet)\n\n###\n\n","completion":" Gewurztraminer \n"} +{"prompt":"Question: (White-Citrus, Sweet)\n\n###\n\n","completion":" Riesling \n"} +{"prompt":"Question: (Red-Earthy, Light-Bodied)\n\n###\n\n","completion":" Pinot Noir \n"} +{"prompt":"Question: (Red-Rich, Light-Bodied)\n\n###\n\n","completion":" Cabernet Sauvignon \n"} +{"prompt":"Question: (White-Crisp, Sweet)\n\n###\n\n","completion":" Pinot Noir \n"}