Update to use new models and new client approach (#1579)
This commit is contained in:
Lee Spacagna
GitHub
parent
4e9bc47058
commit
fa926368ca
4 changed files with 102386 additions and 254 deletions
|
|
@ -30,20 +30,20 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"execution_count": 2,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# imports\n",
|
||||
"import mwclient # for downloading example Wikipedia articles\n",
|
||||
"import mwparserfromhell # for splitting Wikipedia articles into sections\n",
|
||||
"import openai # for generating embeddings\n",
|
||||
"from openai import OpenAI # for generating embeddings\n",
|
||||
"import os # for environment variables\n",
|
||||
"import pandas as pd # for DataFrames to store article sections and embeddings\n",
|
||||
"import re # for cutting <ref> links out of Wikipedia articles\n",
|
||||
"import tiktoken # for counting tokens\n",
|
||||
"\n",
|
||||
"client = openai.OpenAI(api_key=os.environ.get(\"OPENAI_API_KEY\", \"<your OpenAI API key if not set as env var>\"))"
|
||||
"client = OpenAI(api_key=os.environ.get(\"OPENAI_API_KEY\", \"<your OpenAI API key if not set as env var>\"))"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
|
@ -84,14 +84,14 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Found 731 article titles in Category:2022 Winter Olympics.\n"
|
||||
"Found 179 article titles in Category:2022 Winter Olympics.\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
|
|
@ -145,7 +145,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
|
|
@ -230,14 +230,14 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"execution_count": 6,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Found 5730 sections in 731 pages.\n"
|
||||
"Found 1838 sections in 179 pages.\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
|
|
@ -252,14 +252,14 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"execution_count": 7,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Filtered out 530 sections, leaving 5200 sections.\n"
|
||||
"Filtered out 89 sections, leaving 1749 sections.\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
|
|
@ -296,20 +296,20 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"execution_count": 8,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"['Lviv bid for the 2022 Winter Olympics']\n"
|
||||
"['Concerns and controversies at the 2022 Winter Olympics']\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'{{Olympic bid|2022|Winter|\\n| Paralympics = yes\\n| logo = Lviv 2022 Winter Olym...'"
|
||||
"'{{Short description|Overview of concerns and controversies surrounding the Ga...'"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
|
|
@ -320,13 +320,13 @@
|
|||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"['Lviv bid for the 2022 Winter Olympics', '==History==']\n"
|
||||
"['Concerns and controversies at the 2022 Winter Olympics', '==Criticism of host selection==']\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'[[Image:Lwów - Rynek 01.JPG|thumb|right|200px|View of Rynok Square in Lviv]]\\n...'"
|
||||
"'American sportscaster [[Bob Costas]] criticized the [[International Olympic C...'"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
|
|
@ -337,13 +337,13 @@
|
|||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"['Lviv bid for the 2022 Winter Olympics', '==Venues==']\n"
|
||||
"['Concerns and controversies at the 2022 Winter Olympics', '==Organizing concerns and controversies==', '===Cost and climate===']\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'{{Location map+\\n|Ukraine\\n|border =\\n|caption = Venue areas\\n|float = left\\n|widt...'"
|
||||
"'Several cities withdrew their applications during [[Bids for the 2022 Winter ...'"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
|
|
@ -354,13 +354,13 @@
|
|||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"['Lviv bid for the 2022 Winter Olympics', '==Venues==', '===City zone===']\n"
|
||||
"['Concerns and controversies at the 2022 Winter Olympics', '==Organizing concerns and controversies==', '===Promotional song===']\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'The main Olympic Park would be centered around the [[Arena Lviv]], hosting th...'"
|
||||
"'Some commentators alleged that one of the early promotional songs for the [[2...'"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
|
|
@ -371,13 +371,13 @@
|
|||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"['Lviv bid for the 2022 Winter Olympics', '==Venues==', '===Mountain zone===', '====Venue cluster Tysovets-Panasivka====']\n"
|
||||
"['Concerns and controversies at the 2022 Winter Olympics', '== Diplomatic boycotts or non-attendance ==']\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'An existing military ski training facility in [[Tysovets, Skole Raion|Tysovet...'"
|
||||
"'<section begin=boycotts />\\n[[File:2022 Winter Olympics (Beijing) diplomatic b...'"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
|
|
@ -419,11 +419,11 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"execution_count": 10,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"GPT_MODEL = \"gpt-3.5-turbo\" # only matters insofar as it selects which tokenizer to use\n",
|
||||
"GPT_MODEL = \"gpt-4o-mini\" # only matters insofar as it selects which tokenizer to use\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"def num_tokens(text: str, model: str = GPT_MODEL) -> int:\n",
|
||||
|
|
@ -517,14 +517,14 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"execution_count": 11,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"5200 Wikipedia sections split into 6059 strings.\n"
|
||||
"1749 Wikipedia sections split into 2052 strings.\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
|
|
@ -540,32 +540,20 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"execution_count": 12,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Lviv bid for the 2022 Winter Olympics\n",
|
||||
"Concerns and controversies at the 2022 Winter Olympics\n",
|
||||
"\n",
|
||||
"==History==\n",
|
||||
"==Criticism of host selection==\n",
|
||||
"\n",
|
||||
"[[Image:Lwów - Rynek 01.JPG|thumb|right|200px|View of Rynok Square in Lviv]]\n",
|
||||
"American sportscaster [[Bob Costas]] criticized the [[International Olympic Committee]]'s (IOC) decision to award the games to China saying \"The IOC deserves all of the disdain and disgust that comes their way for going back to China yet again\" referencing China's human rights record.\n",
|
||||
"\n",
|
||||
"On 27 May 2010, [[President of Ukraine]] [[Viktor Yanukovych]] stated during a visit to [[Lviv]] that Ukraine \"will start working on the official nomination of our country as the holder of the Winter Olympic Games in [[Carpathian Mountains|Carpathians]]\".\n",
|
||||
"\n",
|
||||
"In September 2012, [[government of Ukraine]] approved a document about the technical-economic substantiation of the national project \"Olympic Hope 2022\". This was announced by Vladyslav Kaskiv, the head of Ukraine´s Derzhinvestproekt (State investment project). The organizers announced on their website venue plans featuring Lviv as the host city and location for the \"ice sport\" venues, [[Volovets]] (around {{convert|185|km|mi|abbr=on}} from Lviv) as venue for the [[Alpine skiing]] competitions and [[Tysovets, Skole Raion|Tysovets]] (around {{convert|130|km|mi|abbr=on}} from Lviv) as venue for all other \"snow sport\" competitions. By March 2013 no other preparations than the feasibility study had been approved.\n",
|
||||
"\n",
|
||||
"On 24 October 2013, session of the Lviv City Council adopted a resolution \"About submission to the International Olympic Committee for nomination of city to participate in the procedure for determining the host city of Olympic and Paralympic Winter Games in 2022\".\n",
|
||||
"\n",
|
||||
"On 5 November 2013, it was confirmed that Lviv was bidding to host the [[2022 Winter Olympics]]. Lviv would host the ice sport events, while the skiing events would be held in the [[Carpathian]] mountains. This was the first bid Ukraine had ever submitted for an Olympic Games.\n",
|
||||
"\n",
|
||||
"On 30 June 2014, the International Olympic Committee announced \"Lviv will turn its attention to an Olympic bid for 2026, and not continue with its application for 2022. The decision comes as a result of the present political and economic circumstances in Ukraine.\"\n",
|
||||
"\n",
|
||||
"Ukraine's Deputy Prime Minister Oleksandr Vilkul said that the Winter Games \"will be an impetus not just for promotion of sports and tourism in Ukraine, but a very important component in the economic development of Ukraine, the attraction of the investments, the creation of new jobs, opening Ukraine to the world, returning Ukrainians working abroad to their motherland.\"\n",
|
||||
"\n",
|
||||
"Lviv was one of the host cities of [[UEFA Euro 2012]].\n"
|
||||
"After winning two gold medals and returning to his home country of Sweden skater [[Nils van der Poel]] criticized the IOC's selection of China as the host saying \"I think it is extremely irresponsible to give it to a country that violates human rights as blatantly as the Chinese regime is doing.\" He had declined to criticize China before leaving for the games saying \"I don't think it would be particularly wise for me to criticize the system I'm about to transition to, if I want to live a long and productive life.\"\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
|
|
@ -588,7 +576,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"execution_count": 13,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
|
|
@ -597,11 +585,7 @@
|
|||
"text": [
|
||||
"Batch 0 to 999\n",
|
||||
"Batch 1000 to 1999\n",
|
||||
"Batch 2000 to 2999\n",
|
||||
"Batch 3000 to 3999\n",
|
||||
"Batch 4000 to 4999\n",
|
||||
"Batch 5000 to 5999\n",
|
||||
"Batch 6000 to 6999\n"
|
||||
"Batch 2000 to 2999\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
|
|
@ -637,7 +621,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"execution_count": 14,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
|
|
@ -665,7 +649,7 @@
|
|||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.9.9"
|
||||
"version": "3.12.6"
|
||||
},
|
||||
"orig_nbformat": 4
|
||||
},
|
||||
|
|
|
|||
|
|
@ -11,7 +11,7 @@
|
|||
"GPT excels at answering questions, but only on topics it remembers from its training data.\n",
|
||||
"\n",
|
||||
"What should you do if you want GPT to answer questions about unfamiliar topics? E.g.,\n",
|
||||
"- Recent events after October 2023 for GPT 4 models\n",
|
||||
"- Recent events after October 2023 for GPT 4 series models\n",
|
||||
"- Your non-public documents\n",
|
||||
"- Information from past conversations\n",
|
||||
"- etc.\n",
|
||||
|
|
@ -45,8 +45,8 @@
|
|||
"\n",
|
||||
"| Model | Maximum text length |\n",
|
||||
"|-----------------|---------------------------|\n",
|
||||
"| `gpt-4o-mini` | 1,28,000 tokens (~384 pages)|\n",
|
||||
"| `gpt-4o` | 1,28,000 tokens (~384 pages)|\n",
|
||||
"| `gpt-4o-mini` | 128,000 tokens (~384 pages)|\n",
|
||||
"| `gpt-4o` | 128,000 tokens (~384 pages)|\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"Continuing the analogy, you can think of the model like a student who can only look at a few pages of notes at a time, despite potentially having shelves of textbooks to draw upon.\n",
|
||||
|
|
@ -97,7 +97,7 @@
|
|||
"\n",
|
||||
"### Costs\n",
|
||||
"\n",
|
||||
"Because GPT is more expensive than embeddings search, a system with a decent volume of queries will have its costs dominated by step 3.\n",
|
||||
"Because GPT models are more expensive than embeddings search, a system with a decent volume of queries will have its costs dominated by step 3.\n",
|
||||
"\n",
|
||||
"- For `gpt-4o`, considering ~1000 tokens per query, it costs ~$0.0025 per query, or ~450 queries per dollar (as of Nov 2024)\n",
|
||||
"- For `gpt-4o-mini`, using ~1000 tokens per query, it costs ~$0.00015 per query, or ~6000 queries per dollar (as of Nov 2024)\n",
|
||||
|
|
@ -121,7 +121,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"execution_count": 6,
|
||||
"id": "9e3839a6-9146-4f60-b74b-19abbc24278d",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
|
|
@ -137,7 +137,7 @@
|
|||
"# create a list of models \n",
|
||||
"GPT_MODELS = [\"gpt-4o\", \"gpt-4o-mini\"]\n",
|
||||
"# models\n",
|
||||
"EMBEDDING_MODEL = \"text-embedding-ada-002\"\n",
|
||||
"EMBEDDING_MODEL = \"text-embedding-3-small\"\n",
|
||||
"\n",
|
||||
"client = OpenAI(api_key=os.environ.get(\"OPENAI_API_KEY\", \"<your OpenAI API key if not set as env var>\"))\n"
|
||||
]
|
||||
|
|
@ -181,7 +181,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"execution_count": 7,
|
||||
"id": "a167516c-7c19-4bda-afa5-031aa0ae13bb",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
|
|
@ -189,7 +189,7 @@
|
|||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"I'm sorry, but I don't have information on the outcomes of the 2024 Summer Olympics, including which athletes won the most gold medals. My training only includes data up to October 2023, and the Olympics are scheduled to take place after that. You might want to check the latest updates from reliable sports news sources or the official Olympics website for the most current information.\n"
|
||||
"I'm sorry, but I don't have information on the outcomes of the 2024 Summer Olympics, including which athletes won the most gold medals. My training only includes data up to October 2023, and the Olympics are scheduled to take place in Paris from July 26 to August 11, 2024. You might want to check the latest updates from reliable sports news sources or the official Olympics website for the most current information.\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
|
|
@ -220,7 +220,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 12,
|
||||
"execution_count": 8,
|
||||
"id": "6d83a4de",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
|
|
@ -260,7 +260,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"execution_count": 9,
|
||||
"id": "02e7281d",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
|
|
@ -432,7 +432,7 @@
|
|||
"source": [
|
||||
"# download pre-chunked text and pre-computed embeddings\n",
|
||||
"# this file is ~200 MB, so may take a minute depending on your connection speed\n",
|
||||
"embeddings_path = \"https://cdn.openai.com/API/examples/data/winter_olympics_2022.csv\"\n",
|
||||
"embeddings_path = \"data/winter_olympics_2022.csv\"\n",
|
||||
"\n",
|
||||
"df = pd.read_csv(embeddings_path)"
|
||||
]
|
||||
|
|
@ -482,28 +482,28 @@
|
|||
" <tbody>\n",
|
||||
" <tr>\n",
|
||||
" <th>0</th>\n",
|
||||
" <td>Lviv bid for the 2022 Winter Olympics\\n\\n{{Oly...</td>\n",
|
||||
" <td>[-0.005021067801862955, 0.00026050032465718687...</td>\n",
|
||||
" <td>Concerns and controversies at the 2022 Winter ...</td>\n",
|
||||
" <td>[-0.0002789763093460351, -0.019866080954670906...</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>1</th>\n",
|
||||
" <td>Lviv bid for the 2022 Winter Olympics\\n\\n==His...</td>\n",
|
||||
" <td>[0.0033927420154213905, -0.007447326090186834,...</td>\n",
|
||||
" <td>Concerns and controversies at the 2022 Winter ...</td>\n",
|
||||
" <td>[0.03143217787146568, -0.01637469232082367, 0....</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>2</th>\n",
|
||||
" <td>Lviv bid for the 2022 Winter Olympics\\n\\n==Ven...</td>\n",
|
||||
" <td>[-0.00915789045393467, -0.008366798982024193, ...</td>\n",
|
||||
" <td>Concerns and controversies at the 2022 Winter ...</td>\n",
|
||||
" <td>[0.007305950857698917, -0.047566406428813934, ...</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>3</th>\n",
|
||||
" <td>Lviv bid for the 2022 Winter Olympics\\n\\n==Ven...</td>\n",
|
||||
" <td>[0.0030951891094446182, -0.006064314860850573,...</td>\n",
|
||||
" <td>Concerns and controversies at the 2022 Winter ...</td>\n",
|
||||
" <td>[0.04308851435780525, -0.03256875276565552, 0....</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>4</th>\n",
|
||||
" <td>Lviv bid for the 2022 Winter Olympics\\n\\n==Ven...</td>\n",
|
||||
" <td>[-0.002936174161732197, -0.006185177247971296,...</td>\n",
|
||||
" <td>Concerns and controversies at the 2022 Winter ...</td>\n",
|
||||
" <td>[-0.02730855718255043, 0.013410222716629505, 0...</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>...</th>\n",
|
||||
|
|
@ -511,63 +511,63 @@
|
|||
" <td>...</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>6054</th>\n",
|
||||
" <td>Anaïs Chevalier-Bouchet\\n\\n==Personal life==\\n...</td>\n",
|
||||
" <td>[-0.027750400826334953, 0.001746018067933619, ...</td>\n",
|
||||
" <th>2047</th>\n",
|
||||
" <td>Bosnia and Herzegovina at the 2022 Winter Olym...</td>\n",
|
||||
" <td>[-0.005553364288061857, -0.0020143764559179544...</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>6055</th>\n",
|
||||
" <td>Uliana Nigmatullina\\n\\n{{short description|Rus...</td>\n",
|
||||
" <td>[-0.021714167669415474, 0.016001321375370026, ...</td>\n",
|
||||
" <th>2048</th>\n",
|
||||
" <td>Bosnia and Herzegovina at the 2022 Winter Olym...</td>\n",
|
||||
" <td>[-0.006751345470547676, -0.025454100221395493,...</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>6056</th>\n",
|
||||
" <td>Uliana Nigmatullina\\n\\n==Biathlon results==\\n\\...</td>\n",
|
||||
" <td>[-0.029143543913960457, 0.014654331840574741, ...</td>\n",
|
||||
" <th>2049</th>\n",
|
||||
" <td>Bosnia and Herzegovina at the 2022 Winter Olym...</td>\n",
|
||||
" <td>[0.005279782693833113, 0.0019363078754395247, ...</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>6057</th>\n",
|
||||
" <td>Uliana Nigmatullina\\n\\n==Biathlon results==\\n\\...</td>\n",
|
||||
" <td>[-0.024266039952635765, 0.011665306985378265, ...</td>\n",
|
||||
" <th>2050</th>\n",
|
||||
" <td>Bosnia and Herzegovina at the 2022 Winter Olym...</td>\n",
|
||||
" <td>[0.018893223255872726, 0.025041205808520317, 0...</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>6058</th>\n",
|
||||
" <td>Uliana Nigmatullina\\n\\n==Biathlon results==\\n\\...</td>\n",
|
||||
" <td>[-0.021818075329065323, 0.005420385394245386, ...</td>\n",
|
||||
" <th>2051</th>\n",
|
||||
" <td>Bosnia and Herzegovina at the 2022 Winter Olym...</td>\n",
|
||||
" <td>[-0.005912619177252054, 0.006518505979329348, ...</td>\n",
|
||||
" </tr>\n",
|
||||
" </tbody>\n",
|
||||
"</table>\n",
|
||||
"<p>6059 rows × 2 columns</p>\n",
|
||||
"<p>2052 rows × 2 columns</p>\n",
|
||||
"</div>"
|
||||
],
|
||||
"text/plain": [
|
||||
" text \\\n",
|
||||
"0 Lviv bid for the 2022 Winter Olympics\\n\\n{{Oly... \n",
|
||||
"1 Lviv bid for the 2022 Winter Olympics\\n\\n==His... \n",
|
||||
"2 Lviv bid for the 2022 Winter Olympics\\n\\n==Ven... \n",
|
||||
"3 Lviv bid for the 2022 Winter Olympics\\n\\n==Ven... \n",
|
||||
"4 Lviv bid for the 2022 Winter Olympics\\n\\n==Ven... \n",
|
||||
"0 Concerns and controversies at the 2022 Winter ... \n",
|
||||
"1 Concerns and controversies at the 2022 Winter ... \n",
|
||||
"2 Concerns and controversies at the 2022 Winter ... \n",
|
||||
"3 Concerns and controversies at the 2022 Winter ... \n",
|
||||
"4 Concerns and controversies at the 2022 Winter ... \n",
|
||||
"... ... \n",
|
||||
"6054 Anaïs Chevalier-Bouchet\\n\\n==Personal life==\\n... \n",
|
||||
"6055 Uliana Nigmatullina\\n\\n{{short description|Rus... \n",
|
||||
"6056 Uliana Nigmatullina\\n\\n==Biathlon results==\\n\\... \n",
|
||||
"6057 Uliana Nigmatullina\\n\\n==Biathlon results==\\n\\... \n",
|
||||
"6058 Uliana Nigmatullina\\n\\n==Biathlon results==\\n\\... \n",
|
||||
"2047 Bosnia and Herzegovina at the 2022 Winter Olym... \n",
|
||||
"2048 Bosnia and Herzegovina at the 2022 Winter Olym... \n",
|
||||
"2049 Bosnia and Herzegovina at the 2022 Winter Olym... \n",
|
||||
"2050 Bosnia and Herzegovina at the 2022 Winter Olym... \n",
|
||||
"2051 Bosnia and Herzegovina at the 2022 Winter Olym... \n",
|
||||
"\n",
|
||||
" embedding \n",
|
||||
"0 [-0.005021067801862955, 0.00026050032465718687... \n",
|
||||
"1 [0.0033927420154213905, -0.007447326090186834,... \n",
|
||||
"2 [-0.00915789045393467, -0.008366798982024193, ... \n",
|
||||
"3 [0.0030951891094446182, -0.006064314860850573,... \n",
|
||||
"4 [-0.002936174161732197, -0.006185177247971296,... \n",
|
||||
"0 [-0.0002789763093460351, -0.019866080954670906... \n",
|
||||
"1 [0.03143217787146568, -0.01637469232082367, 0.... \n",
|
||||
"2 [0.007305950857698917, -0.047566406428813934, ... \n",
|
||||
"3 [0.04308851435780525, -0.03256875276565552, 0.... \n",
|
||||
"4 [-0.02730855718255043, 0.013410222716629505, 0... \n",
|
||||
"... ... \n",
|
||||
"6054 [-0.027750400826334953, 0.001746018067933619, ... \n",
|
||||
"6055 [-0.021714167669415474, 0.016001321375370026, ... \n",
|
||||
"6056 [-0.029143543913960457, 0.014654331840574741, ... \n",
|
||||
"6057 [-0.024266039952635765, 0.011665306985378265, ... \n",
|
||||
"6058 [-0.021818075329065323, 0.005420385394245386, ... \n",
|
||||
"2047 [-0.005553364288061857, -0.0020143764559179544... \n",
|
||||
"2048 [-0.006751345470547676, -0.025454100221395493,... \n",
|
||||
"2049 [0.005279782693833113, 0.0019363078754395247, ... \n",
|
||||
"2050 [0.018893223255872726, 0.025041205808520317, 0... \n",
|
||||
"2051 [-0.005912619177252054, 0.006518505979329348, ... \n",
|
||||
"\n",
|
||||
"[6059 rows x 2 columns]"
|
||||
"[2052 rows x 2 columns]"
|
||||
]
|
||||
},
|
||||
"execution_count": 15,
|
||||
|
|
@ -599,7 +599,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 18,
|
||||
"execution_count": 16,
|
||||
"id": "b9a8c713-c8a9-47dc-85a4-871ee1395566",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
|
|
@ -628,7 +628,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 19,
|
||||
"execution_count": 17,
|
||||
"id": "da034bd2",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
|
|
@ -636,7 +636,7 @@
|
|||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"relatedness=0.879\n"
|
||||
"relatedness=0.630\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
|
@ -652,13 +652,13 @@
|
|||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"relatedness=0.872\n"
|
||||
"relatedness=0.576\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\"Curling at the 2022 Winter Olympics\\n\\n==Results summary==\\n\\n===Women's tournament===\\n\\n====Playoffs====\\n\\n=====Gold medal game=====\\n\\n''Sunday, 20 February, 9:05''\\n{{#lst:Curling at the 2022 Winter Olympics – Women's tournament|GM}}\\n{{Player percentages\\n| team1 = {{flagIOC|JPN|2022 Winter}}\\n| [[Yurika Yoshida]] | 97%\\n| [[Yumi Suzuki]] | 82%\\n| [[Chinami Yoshida]] | 64%\\n| [[Satsuki Fujisawa]] | 69%\\n| teampct1 = 78%\\n| team2 = {{flagIOC|GBR|2022 Winter}}\\n| [[Hailey Duff]] | 90%\\n| [[Jennifer Dodds]] | 89%\\n| [[Vicky Wright]] | 89%\\n| [[Eve Muirhead]] | 88%\\n| teampct2 = 89%\\n}}\""
|
||||
"\"Curling at the 2022 Winter Olympics\\n\\n==Results summary==\\n\\n===Men's tournament===\\n\\n====Playoffs====\\n\\n=====Gold medal game=====\\n\\n''Saturday, 19 February, 14:50''\\n{{#lst:Curling at the 2022 Winter Olympics – Men's tournament|GM}}\\n{{Player percentages\\n| team1 = {{flagIOC|GBR|2022 Winter}}\\n| [[Hammy McMillan Jr.]] | 95%\\n| [[Bobby Lammie]] | 80%\\n| [[Grant Hardie]] | 94%\\n| [[Bruce Mouat]] | 89%\\n| teampct1 = 90%\\n| team2 = {{flagIOC|SWE|2022 Winter}}\\n| [[Christoffer Sundgren]] | 99%\\n| [[Rasmus Wranå]] | 95%\\n| [[Oskar Eriksson]] | 93%\\n| [[Niklas Edin]] | 87%\\n| teampct2 = 94%\\n}}\""
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
|
|
@ -668,13 +668,13 @@
|
|||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"relatedness=0.869\n"
|
||||
"relatedness=0.569\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'Curling at the 2022 Winter Olympics\\n\\n==Results summary==\\n\\n===Mixed doubles tournament===\\n\\n====Playoffs====\\n\\n=====Gold medal game=====\\n\\n\\'\\'Tuesday, 8 February, 20:05\\'\\'\\n{{#lst:Curling at the 2022 Winter Olympics – Mixed doubles tournament|GM}}\\n{| class=\"wikitable\"\\n!colspan=4 width=400|Player percentages\\n|-\\n!colspan=2 width=200 style=\"white-space:nowrap;\"| {{flagIOC|ITA|2022 Winter}}\\n!colspan=2 width=200 style=\"white-space:nowrap;\"| {{flagIOC|NOR|2022 Winter}}\\n|-\\n| [[Stefania Constantini]] || 83%\\n| [[Kristin Skaslien]] || 70%\\n|-\\n| [[Amos Mosaner]] || 90%\\n| [[Magnus Nedregotten]] || 69%\\n|-\\n| \\'\\'\\'Total\\'\\'\\' || 87%\\n| \\'\\'\\'Total\\'\\'\\' || 69%\\n|}'"
|
||||
"\"Curling at the 2022 Winter Olympics\\n\\n==Results summary==\\n\\n===Men's tournament===\\n\\n====Playoffs====\\n\\n{{4TeamBracket-with 3rd\\n| Team-Width = 150\\n| RD1 = Semifinals\\n| RD2 = Gold medal game\\n| RD2b = Bronze medal game\\n\\n| RD1-seed1 = 1\\n| RD1-team1 = '''{{flagIOC|GBR|2022 Winter}}'''\\n| RD1-score1 = '''8'''\\n| RD1-seed2 = 4\\n| RD1-team2 = {{flagIOC|USA|2022 Winter}}\\n| RD1-score2 = 4\\n| RD1-seed3 = 2\\n| RD1-team3 = '''{{flagIOC|SWE|2022 Winter}}'''\\n| RD1-score3 = '''5'''\\n| RD1-seed4 = 3\\n| RD1-team4 = {{flagIOC|CAN|2022 Winter}}\\n| RD1-score4 = 3\\n\\n| RD2-seed1 = 1\\n| RD2-team1 = {{flagIOC|GBR|2022 Winter}}\\n| RD2-score1 = 4\\n| RD2-seed2 = 2\\n| RD2-team2 = '''{{flagIOC|SWE|2022 Winter}}'''\\n| RD2-score2 = '''5'''\\n\\n| RD2b-seed1 = 4\\n| RD2b-team1 = {{flagIOC|USA|2022 Winter}}\\n| RD2b-score1 = 5\\n| RD2b-seed2 = 3\\n| RD2b-team2 = '''{{flagIOC|CAN|2022 Winter}}'''\\n| RD2b-score2 = '''8'''\\n}}\""
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
|
|
@ -684,7 +684,7 @@
|
|||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"relatedness=0.868\n"
|
||||
"relatedness=0.565\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
|
@ -700,13 +700,13 @@
|
|||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"relatedness=0.867\n"
|
||||
"relatedness=0.561\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\"Curling at the 2022 Winter Olympics\\n\\n==Results summary==\\n\\n===Men's tournament===\\n\\n====Playoffs====\\n\\n=====Gold medal game=====\\n\\n''Saturday, 19 February, 14:50''\\n{{#lst:Curling at the 2022 Winter Olympics – Men's tournament|GM}}\\n{{Player percentages\\n| team1 = {{flagIOC|GBR|2022 Winter}}\\n| [[Hammy McMillan Jr.]] | 95%\\n| [[Bobby Lammie]] | 80%\\n| [[Grant Hardie]] | 94%\\n| [[Bruce Mouat]] | 89%\\n| teampct1 = 90%\\n| team2 = {{flagIOC|SWE|2022 Winter}}\\n| [[Christoffer Sundgren]] | 99%\\n| [[Rasmus Wranå]] | 95%\\n| [[Oskar Eriksson]] | 93%\\n| [[Niklas Edin]] | 87%\\n| teampct2 = 94%\\n}}\""
|
||||
"\"Curling at the 2022 Winter Olympics\\n\\n==Results summary==\\n\\n===Mixed doubles tournament===\\n\\n====Playoffs====\\n\\n{{4TeamBracket-with 3rd\\n| Team-Width = 150\\n| RD1 = Semifinals\\n| RD2 = Gold medal game\\n| RD2b = Bronze medal game\\n\\n| RD1-seed1 = 1\\n| RD1-team1 = '''{{flagIOC|ITA|2022 Winter}}'''\\n| RD1-score1 = '''8'''\\n| RD1-seed2 = 4\\n| RD1-team2 = {{flagIOC|SWE|2022 Winter}}\\n| RD1-score2 = 1\\n| RD1-seed3 = 2\\n| RD1-team3 = '''{{flagIOC|NOR|2022 Winter}}'''\\n| RD1-score3 = '''6'''\\n| RD1-seed4 = 3\\n| RD1-team4 = {{flagIOC|GBR|2022 Winter}}\\n| RD1-score4 = 5\\n\\n| RD2-seed1 = 1\\n| RD2-team1 = '''{{flagIOC|ITA|2022 Winter}}'''\\n| RD2-score1 = '''8'''\\n| RD2-seed2 = 2\\n| RD2-team2 = {{flagIOC|NOR|2022 Winter}}\\n| RD2-score2 = 5\\n\\n| RD2b-seed1 = 4\\n| RD2b-team1 = '''{{flagIOC|SWE|2022 Winter}}'''\\n| RD2b-score1 = '''9'''\\n| RD2b-seed2 = 3\\n| RD2b-team2 = {{flagIOC|GBR|2022 Winter}}\\n| RD2b-score2 = 3\\n}}\""
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
|
|
@ -741,7 +741,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 20,
|
||||
"execution_count": 18,
|
||||
"id": "1f45cecc",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
|
|
@ -813,25 +813,17 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 21,
|
||||
"execution_count": 19,
|
||||
"id": "e11f53ab",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"/Users/shikhar/openai_projects/github_repos/.venv/lib/python3.9/site-packages/urllib3/__init__.py:35: NotOpenSSLWarning: urllib3 v2 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
|
||||
" warnings.warn(\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\"The athletes who won the gold medal in curling at the 2022 Winter Olympics are:\\n\\n- Men's tournament: Niklas Edin, Oskar Eriksson, Rasmus Wranå, Christoffer Sundgren, and Daniel Magnusson from Sweden.\\n- Women's tournament: Eve Muirhead, Vicky Wright, Jennifer Dodds, Hailey Duff, and Mili Smith from Great Britain.\\n- Mixed doubles tournament: Stefania Constantini and Amos Mosaner from Italy.\""
|
||||
]
|
||||
},
|
||||
"execution_count": 21,
|
||||
"execution_count": 19,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
|
|
@ -871,7 +863,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 22,
|
||||
"execution_count": 20,
|
||||
"id": "aa965e36",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
|
|
@ -911,36 +903,6 @@
|
|||
"\"\"\"\n",
|
||||
"Curling at the 2022 Winter Olympics\n",
|
||||
"\n",
|
||||
"==Results summary==\n",
|
||||
"\n",
|
||||
"===Women's tournament===\n",
|
||||
"\n",
|
||||
"====Playoffs====\n",
|
||||
"\n",
|
||||
"=====Gold medal game=====\n",
|
||||
"\n",
|
||||
"''Sunday, 20 February, 9:05''\n",
|
||||
"{{#lst:Curling at the 2022 Winter Olympics – Women's tournament|GM}}\n",
|
||||
"{{Player percentages\n",
|
||||
"| team1 = {{flagIOC|JPN|2022 Winter}}\n",
|
||||
"| [[Yurika Yoshida]] | 97%\n",
|
||||
"| [[Yumi Suzuki]] | 82%\n",
|
||||
"| [[Chinami Yoshida]] | 64%\n",
|
||||
"| [[Satsuki Fujisawa]] | 69%\n",
|
||||
"| teampct1 = 78%\n",
|
||||
"| team2 = {{flagIOC|GBR|2022 Winter}}\n",
|
||||
"| [[Hailey Duff]] | 90%\n",
|
||||
"| [[Jennifer Dodds]] | 89%\n",
|
||||
"| [[Vicky Wright]] | 89%\n",
|
||||
"| [[Eve Muirhead]] | 88%\n",
|
||||
"| teampct2 = 89%\n",
|
||||
"}}\n",
|
||||
"\"\"\"\n",
|
||||
"\n",
|
||||
"Wikipedia article section:\n",
|
||||
"\"\"\"\n",
|
||||
"Curling at the 2022 Winter Olympics\n",
|
||||
"\n",
|
||||
"==Medal summary==\n",
|
||||
"\n",
|
||||
"===Medal table===\n",
|
||||
|
|
@ -964,36 +926,6 @@
|
|||
"\"\"\"\n",
|
||||
"Curling at the 2022 Winter Olympics\n",
|
||||
"\n",
|
||||
"==Results summary==\n",
|
||||
"\n",
|
||||
"===Men's tournament===\n",
|
||||
"\n",
|
||||
"====Playoffs====\n",
|
||||
"\n",
|
||||
"=====Gold medal game=====\n",
|
||||
"\n",
|
||||
"''Saturday, 19 February, 14:50''\n",
|
||||
"{{#lst:Curling at the 2022 Winter Olympics – Men's tournament|GM}}\n",
|
||||
"{{Player percentages\n",
|
||||
"| team1 = {{flagIOC|GBR|2022 Winter}}\n",
|
||||
"| [[Hammy McMillan Jr.]] | 95%\n",
|
||||
"| [[Bobby Lammie]] | 80%\n",
|
||||
"| [[Grant Hardie]] | 94%\n",
|
||||
"| [[Bruce Mouat]] | 89%\n",
|
||||
"| teampct1 = 90%\n",
|
||||
"| team2 = {{flagIOC|SWE|2022 Winter}}\n",
|
||||
"| [[Christoffer Sundgren]] | 99%\n",
|
||||
"| [[Rasmus Wranå]] | 95%\n",
|
||||
"| [[Oskar Eriksson]] | 93%\n",
|
||||
"| [[Niklas Edin]] | 87%\n",
|
||||
"| teampct2 = 94%\n",
|
||||
"}}\n",
|
||||
"\"\"\"\n",
|
||||
"\n",
|
||||
"Wikipedia article section:\n",
|
||||
"\"\"\"\n",
|
||||
"Curling at the 2022 Winter Olympics\n",
|
||||
"\n",
|
||||
"==Medal summary==\n",
|
||||
"\n",
|
||||
"===Medalists===\n",
|
||||
|
|
@ -1027,23 +959,94 @@
|
|||
"\n",
|
||||
"====Playoffs====\n",
|
||||
"\n",
|
||||
"=====Bronze medal game=====\n",
|
||||
"=====Gold medal game=====\n",
|
||||
"\n",
|
||||
"''Friday, 18 February, 14:05''\n",
|
||||
"{{#lst:Curling at the 2022 Winter Olympics – Men's tournament|BM}}\n",
|
||||
"''Saturday, 19 February, 14:50''\n",
|
||||
"{{#lst:Curling at the 2022 Winter Olympics – Men's tournament|GM}}\n",
|
||||
"{{Player percentages\n",
|
||||
"| team1 = {{flagIOC|USA|2022 Winter}}\n",
|
||||
"| [[John Landsteiner]] | 80%\n",
|
||||
"| [[Matt Hamilton (curler)|Matt Hamilton]] | 86%\n",
|
||||
"| [[Chris Plys]] | 74%\n",
|
||||
"| [[John Shuster]] | 69%\n",
|
||||
"| teampct1 = 77%\n",
|
||||
"| team2 = {{flagIOC|CAN|2022 Winter}}\n",
|
||||
"| [[Geoff Walker (curler)|Geoff Walker]] | 84%\n",
|
||||
"| [[Brett Gallant]] | 86%\n",
|
||||
"| [[Mark Nichols (curler)|Mark Nichols]] | 78%\n",
|
||||
"| [[Brad Gushue]] | 78%\n",
|
||||
"| teampct2 = 82%\n",
|
||||
"| team1 = {{flagIOC|GBR|2022 Winter}}\n",
|
||||
"| [[Hammy McMillan Jr.]] | 95%\n",
|
||||
"| [[Bobby Lammie]] | 80%\n",
|
||||
"| [[Grant Hardie]] | 94%\n",
|
||||
"| [[Bruce Mouat]] | 89%\n",
|
||||
"| teampct1 = 90%\n",
|
||||
"| team2 = {{flagIOC|SWE|2022 Winter}}\n",
|
||||
"| [[Christoffer Sundgren]] | 99%\n",
|
||||
"| [[Rasmus Wranå]] | 95%\n",
|
||||
"| [[Oskar Eriksson]] | 93%\n",
|
||||
"| [[Niklas Edin]] | 87%\n",
|
||||
"| teampct2 = 94%\n",
|
||||
"}}\n",
|
||||
"\"\"\"\n",
|
||||
"\n",
|
||||
"Wikipedia article section:\n",
|
||||
"\"\"\"\n",
|
||||
"Curling at the 2022 Winter Olympics\n",
|
||||
"\n",
|
||||
"==Results summary==\n",
|
||||
"\n",
|
||||
"===Men's tournament===\n",
|
||||
"\n",
|
||||
"====Playoffs====\n",
|
||||
"\n",
|
||||
"{{4TeamBracket-with 3rd\n",
|
||||
"| Team-Width = 150\n",
|
||||
"| RD1 = Semifinals\n",
|
||||
"| RD2 = Gold medal game\n",
|
||||
"| RD2b = Bronze medal game\n",
|
||||
"\n",
|
||||
"| RD1-seed1 = 1\n",
|
||||
"| RD1-team1 = '''{{flagIOC|GBR|2022 Winter}}'''\n",
|
||||
"| RD1-score1 = '''8'''\n",
|
||||
"| RD1-seed2 = 4\n",
|
||||
"| RD1-team2 = {{flagIOC|USA|2022 Winter}}\n",
|
||||
"| RD1-score2 = 4\n",
|
||||
"| RD1-seed3 = 2\n",
|
||||
"| RD1-team3 = '''{{flagIOC|SWE|2022 Winter}}'''\n",
|
||||
"| RD1-score3 = '''5'''\n",
|
||||
"| RD1-seed4 = 3\n",
|
||||
"| RD1-team4 = {{flagIOC|CAN|2022 Winter}}\n",
|
||||
"| RD1-score4 = 3\n",
|
||||
"\n",
|
||||
"| RD2-seed1 = 1\n",
|
||||
"| RD2-team1 = {{flagIOC|GBR|2022 Winter}}\n",
|
||||
"| RD2-score1 = 4\n",
|
||||
"| RD2-seed2 = 2\n",
|
||||
"| RD2-team2 = '''{{flagIOC|SWE|2022 Winter}}'''\n",
|
||||
"| RD2-score2 = '''5'''\n",
|
||||
"\n",
|
||||
"| RD2b-seed1 = 4\n",
|
||||
"| RD2b-team1 = {{flagIOC|USA|2022 Winter}}\n",
|
||||
"| RD2b-score1 = 5\n",
|
||||
"| RD2b-seed2 = 3\n",
|
||||
"| RD2b-team2 = '''{{flagIOC|CAN|2022 Winter}}'''\n",
|
||||
"| RD2b-score2 = '''8'''\n",
|
||||
"}}\n",
|
||||
"\"\"\"\n",
|
||||
"\n",
|
||||
"Wikipedia article section:\n",
|
||||
"\"\"\"\n",
|
||||
"Curling at the 2022 Winter Olympics\n",
|
||||
"\n",
|
||||
"==Participating nations==\n",
|
||||
"\n",
|
||||
"A total of 114 athletes from 14 nations (including the IOC's designation of ROC) were scheduled to participate (the numbers of athletes are shown in parentheses). Some curlers competed in both the 4-person and mixed doubles tournament, therefore, the numbers included on this list are the total athletes sent by each NOC to the Olympics, not how many athletes they qualified. Both Australia and the Czech Republic made their Olympic sport debuts.\n",
|
||||
"\n",
|
||||
"{{columns-list|colwidth=20em|\n",
|
||||
"* {{flagIOC|AUS|2022 Winter|2}}\n",
|
||||
"* {{flagIOC|CAN|2022 Winter|12}}\n",
|
||||
"* {{flagIOC|CHN|2022 Winter|12}}\n",
|
||||
"* {{flagIOC|CZE|2022 Winter|2}}\n",
|
||||
"* {{flagIOC|DEN|2022 Winter|10}}\n",
|
||||
"* {{flagIOC|GBR|2022 Winter|10}}\n",
|
||||
"* {{flagIOC|ITA|2022 Winter|6}}\n",
|
||||
"* {{flagIOC|JPN|2022 Winter|5}}\n",
|
||||
"* {{flagIOC|NOR|2022 Winter|6}}\n",
|
||||
"* {{flagIOC|ROC|2022 Winter|10}}\n",
|
||||
"* {{flagIOC|KOR|2022 Winter|5}}\n",
|
||||
"* {{flagIOC|SWE|2022 Winter|11}}\n",
|
||||
"* {{flagIOC|SUI|2022 Winter|12}}\n",
|
||||
"* {{flagIOC|USA|2022 Winter|11}}\n",
|
||||
"}}\n",
|
||||
"\"\"\"\n",
|
||||
"\n",
|
||||
|
|
@ -1109,26 +1112,26 @@
|
|||
"\n",
|
||||
"==Results summary==\n",
|
||||
"\n",
|
||||
"===Women's tournament===\n",
|
||||
"===Men's tournament===\n",
|
||||
"\n",
|
||||
"====Playoffs====\n",
|
||||
"\n",
|
||||
"=====Bronze medal game=====\n",
|
||||
"\n",
|
||||
"''Saturday, 19 February, 20:05''\n",
|
||||
"{{#lst:Curling at the 2022 Winter Olympics – Women's tournament|BM}}\n",
|
||||
"''Friday, 18 February, 14:05''\n",
|
||||
"{{#lst:Curling at the 2022 Winter Olympics – Men's tournament|BM}}\n",
|
||||
"{{Player percentages\n",
|
||||
"| team1 = {{flagIOC|SUI|2022 Winter}}\n",
|
||||
"| [[Melanie Barbezat]] | 79%\n",
|
||||
"| [[Esther Neuenschwander]] | 75%\n",
|
||||
"| [[Silvana Tirinzoni]] | 81%\n",
|
||||
"| [[Alina Pätz]] | 64%\n",
|
||||
"| teampct1 = 75%\n",
|
||||
"| team2 = {{flagIOC|SWE|2022 Winter}}\n",
|
||||
"| [[Sofia Mabergs]] | 89%\n",
|
||||
"| [[Agnes Knochenhauer]] | 80%\n",
|
||||
"| [[Sara McManus]] | 81%\n",
|
||||
"| [[Anna Hasselborg]] | 76%\n",
|
||||
"| team1 = {{flagIOC|USA|2022 Winter}}\n",
|
||||
"| [[John Landsteiner]] | 80%\n",
|
||||
"| [[Matt Hamilton (curler)|Matt Hamilton]] | 86%\n",
|
||||
"| [[Chris Plys]] | 74%\n",
|
||||
"| [[John Shuster]] | 69%\n",
|
||||
"| teampct1 = 77%\n",
|
||||
"| team2 = {{flagIOC|CAN|2022 Winter}}\n",
|
||||
"| [[Geoff Walker (curler)|Geoff Walker]] | 84%\n",
|
||||
"| [[Brett Gallant]] | 86%\n",
|
||||
"| [[Mark Nichols (curler)|Mark Nichols]] | 78%\n",
|
||||
"| [[Brad Gushue]] | 78%\n",
|
||||
"| teampct2 = 82%\n",
|
||||
"}}\n",
|
||||
"\"\"\"\n",
|
||||
|
|
@ -1139,29 +1142,43 @@
|
|||
"\n",
|
||||
"==Results summary==\n",
|
||||
"\n",
|
||||
"===Mixed doubles tournament===\n",
|
||||
"===Women's tournament===\n",
|
||||
"\n",
|
||||
"====Playoffs====\n",
|
||||
"\n",
|
||||
"=====Gold medal game=====\n",
|
||||
"{{4TeamBracket-with 3rd\n",
|
||||
"| Team-Width = 150\n",
|
||||
"| RD1 = Semifinals\n",
|
||||
"| RD2 = Gold medal game\n",
|
||||
"| RD2b = Bronze medal game\n",
|
||||
"\n",
|
||||
"''Tuesday, 8 February, 20:05''\n",
|
||||
"{{#lst:Curling at the 2022 Winter Olympics – Mixed doubles tournament|GM}}\n",
|
||||
"{| class=\"wikitable\"\n",
|
||||
"!colspan=4 width=400|Player percentages\n",
|
||||
"|-\n",
|
||||
"!colspan=2 width=200 style=\"white-space:nowrap;\"| {{flagIOC|ITA|2022 Winter}}\n",
|
||||
"!colspan=2 width=200 style=\"white-space:nowrap;\"| {{flagIOC|NOR|2022 Winter}}\n",
|
||||
"|-\n",
|
||||
"| [[Stefania Constantini]] || 83%\n",
|
||||
"| [[Kristin Skaslien]] || 70%\n",
|
||||
"|-\n",
|
||||
"| [[Amos Mosaner]] || 90%\n",
|
||||
"| [[Magnus Nedregotten]] || 69%\n",
|
||||
"|-\n",
|
||||
"| '''Total''' || 87%\n",
|
||||
"| '''Total''' || 69%\n",
|
||||
"|}\n",
|
||||
"| RD1-seed1 = 1\n",
|
||||
"| RD1-team1 = {{flagIOC|SUI|2022 Winter}}\n",
|
||||
"| RD1-score1 = 6\n",
|
||||
"| RD1-seed2 = 4\n",
|
||||
"| RD1-team2 = '''{{flagIOC|JPN|2022 Winter}}'''\n",
|
||||
"| RD1-score2 = '''8'''\n",
|
||||
"| RD1-seed3 = 2\n",
|
||||
"| RD1-team3 = {{flagIOC|SWE|2022 Winter}}\n",
|
||||
"| RD1-score3 = 11\n",
|
||||
"| RD1-seed4 = 3\n",
|
||||
"| RD1-team4 = '''{{flagIOC|GBR|2022 Winter}}'''\n",
|
||||
"| RD1-score4 = '''12'''\n",
|
||||
"\n",
|
||||
"| RD2-seed1 = 4\n",
|
||||
"| RD2-team1 = {{flagIOC|JPN|2022 Winter}}\n",
|
||||
"| RD2-score1 = 3\n",
|
||||
"| RD2-seed2 = 3\n",
|
||||
"| RD2-team2 = '''{{flagIOC|GBR|2022 Winter}}'''\n",
|
||||
"| RD2-score2 = '''10'''\n",
|
||||
"\n",
|
||||
"| RD2b-seed1 = 1\n",
|
||||
"| RD2b-team1 = {{flagIOC|SUI|2022 Winter}}\n",
|
||||
"| RD2b-score1 = 7\n",
|
||||
"| RD2b-seed2 = 2\n",
|
||||
"| RD2b-team2 = '''{{flagIOC|SWE|2022 Winter}}'''\n",
|
||||
"| RD2b-score2 = '''9'''\n",
|
||||
"}}\n",
|
||||
"\"\"\"\n",
|
||||
"\n",
|
||||
"Question: Which athletes won the gold medal in curling at the 2022 Winter Olympics?\n"
|
||||
|
|
@ -1173,7 +1190,7 @@
|
|||
"\"The athletes who won the gold medal in curling at the 2022 Winter Olympics are:\\n\\n- Men's tournament: Niklas Edin, Oskar Eriksson, Rasmus Wranå, Christoffer Sundgren, and Daniel Magnusson from Sweden.\\n- Women's tournament: Eve Muirhead, Vicky Wright, Jennifer Dodds, Hailey Duff, and Mili Smith from Great Britain.\\n- Mixed doubles tournament: Stefania Constantini and Amos Mosaner from Italy.\""
|
||||
]
|
||||
},
|
||||
"execution_count": 22,
|
||||
"execution_count": 20,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
|
|
@ -1196,7 +1213,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 29,
|
||||
"execution_count": 21,
|
||||
"id": "d6cb292f",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
|
|
@ -1206,7 +1223,7 @@
|
|||
"\"The gold medal in curling at the 2022 Winter Olympics was won by the following athletes:\\n\\n- Men's tournament: Niklas Edin, Oskar Eriksson, Rasmus Wranå, Christoffer Sundgren, Daniel Magnusson from Sweden.\\n- Women's tournament: Eve Muirhead, Vicky Wright, Jennifer Dodds, Hailey Duff, Mili Smith from Great Britain.\\n- Mixed doubles: Stefania Constantini and Amos Mosaner from Italy.\""
|
||||
]
|
||||
},
|
||||
"execution_count": 29,
|
||||
"execution_count": 21,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
|
|
@ -1237,17 +1254,17 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 30,
|
||||
"execution_count": 22,
|
||||
"id": "05fb04ef",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'I could not find an answer.'"
|
||||
"'There were 2 world records and 24 Olympic records set at the 2022 Winter Olympics.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 30,
|
||||
"execution_count": 22,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
|
|
@ -1259,17 +1276,17 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 31,
|
||||
"execution_count": 24,
|
||||
"id": "30da5271",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\"Jamaica had more athletes at the 2022 Winter Olympics. Jamaica's team consisted of seven athletes. There is no information provided about Cuba's participation in the 2022 Winter Olympics in the articles, so it is unclear if Cuba had any athletes at the event.\""
|
||||
"\"Jamaica had more athletes at the 2022 Winter Olympics. Jamaica's team consisted of seven athletes. There is no information provided about Cuba's participation in the 2022 Winter Olympics, so I cannot determine the number of athletes they had, if any.\""
|
||||
]
|
||||
},
|
||||
"execution_count": 31,
|
||||
"execution_count": 24,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
|
|
@ -1281,7 +1298,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 32,
|
||||
"execution_count": 23,
|
||||
"id": "42449926",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
|
|
@ -1291,7 +1308,7 @@
|
|||
"'I could not find an answer.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 32,
|
||||
"execution_count": 23,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
|
|
@ -1325,17 +1342,17 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 34,
|
||||
"execution_count": 25,
|
||||
"id": "57d13b1f",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'I could not find an answer.'"
|
||||
"'I am here to provide information about the 2022 Winter Olympics. If you have any questions related to that topic, feel free to ask!'"
|
||||
]
|
||||
},
|
||||
"execution_count": 34,
|
||||
"execution_count": 25,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
|
|
@ -1472,7 +1489,7 @@
|
|||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.9.6"
|
||||
"version": "3.12.7"
|
||||
},
|
||||
"vscode": {
|
||||
"interpreter": {
|
||||
|
|
|
|||
102131
examples/data/winter_olympics_2022.csv
Normal file
102131
examples/data/winter_olympics_2022.csv
Normal file
File diff suppressed because one or more lines are too long
|
|
@ -83,7 +83,7 @@
|
|||
|
||||
- title: Embedding Wikipedia articles for search
|
||||
path: examples/Embedding_Wikipedia_articles_for_search.ipynb
|
||||
date: 2023-04-14
|
||||
date: 2024-11-26
|
||||
authors:
|
||||
- ted-at-openai
|
||||
tags:
|
||||
|
|
|
|||
Loading…
Reference in a new issue