langchain/docs/docs/integrations/tools/polygon.ipynb
Virat Singh cafffe8a21
community: Add PolygonAggregates tool (#18882)
**Description:**
In this PR, I am adding a `PolygonAggregates` tool, which can be used to
get historical stock price data (called aggregates by Polygon) for a
given ticker.

Polygon
[docs](https://polygon.io/docs/stocks/get_v2_aggs_ticker__stocksticker__range__multiplier___timespan___from___to)
for this endpoint.

**Twitter**: 
[@virattt](https://twitter.com/virattt)
2024-03-11 11:58:10 -07:00

409 lines
17 KiB
Plaintext

{
"cells": [
{
"cell_type": "markdown",
"id": "245a954a",
"metadata": {
"id": "245a954a"
},
"source": [
"# Polygon Stock Market API Tools\n",
"\n",
">[Polygon](https://polygon.io/) The Polygon.io Stocks API provides REST endpoints that let you query the latest market data from all US stock exchanges.\n",
"\n",
"This notebook uses tools to get stock market data like the latest quote and news for a ticker from Polygon."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "34bb5968",
"metadata": {
"id": "34bb5968",
"is_executing": true,
"scrolled": true
},
"outputs": [
{
"name": "stdin",
"output_type": "stream",
"text": [
" ········\n"
]
}
],
"source": [
"import getpass\n",
"import os\n",
"\n",
"os.environ[\"POLYGON_API_KEY\"] = getpass.getpass()"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "ac4910f8",
"metadata": {
"id": "ac4910f8",
"is_executing": true
},
"outputs": [],
"source": [
"from langchain_community.tools.polygon.aggregates import PolygonAggregates\n",
"from langchain_community.tools.polygon.financials import PolygonFinancials\n",
"from langchain_community.tools.polygon.last_quote import PolygonLastQuote\n",
"from langchain_community.tools.polygon.ticker_news import PolygonTickerNews\n",
"from langchain_community.utilities.polygon import PolygonAPIWrapper"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "8660b910-905b-46f3-9541-920b9fc3d4d6",
"metadata": {},
"outputs": [],
"source": [
"api_wrapper = PolygonAPIWrapper()\n",
"ticker = \"AAPL\""
]
},
{
"cell_type": "markdown",
"id": "347f6951-b383-4675-b116-9b7d16c1f505",
"metadata": {},
"source": [
"### Get latest quote for ticker"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "84b8f773",
"metadata": {
"id": "84b8f773"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Tool output: {\"P\": 170.5, \"S\": 2, \"T\": \"AAPL\", \"X\": 11, \"i\": [604], \"p\": 170.48, \"q\": 106666224, \"s\": 1, \"t\": 1709945992614283138, \"x\": 12, \"y\": 1709945992614268948, \"z\": 3}\n"
]
}
],
"source": [
"# Get the last quote for ticker\n",
"last_quote_tool = PolygonLastQuote(api_wrapper=api_wrapper)\n",
"last_quote = last_quote_tool.run(ticker)\n",
"print(f\"Tool output: {last_quote}\")"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "068991a6",
"metadata": {
"id": "068991a6",
"outputId": "c5cdc6ec-03cf-4084-cc6f-6ae792d91d39"
},
"outputs": [],
"source": [
"import json\n",
"\n",
"# Convert the last quote response to JSON\n",
"last_quote = last_quote_tool.run(ticker)\n",
"last_quote_json = json.loads(last_quote)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "174e2556-eb3e-48a4-bde6-9a3309fae9c9",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Latest price for AAPL is $170.48\n"
]
}
],
"source": [
"# Print the latest price for ticker\n",
"latest_price = last_quote_json[\"p\"]\n",
"print(f\"Latest price for {ticker} is ${latest_price}\")"
]
},
{
"cell_type": "markdown",
"id": "1f478364-f41b-47f2-ac4b-d3154f1c7faa",
"metadata": {},
"source": [
"### Get aggregates (historical prices) for ticker"
]
},
{
"cell_type": "code",
"execution_count": 20,
"id": "5e14e091-3150-4bd5-bfd3-de17caa75ee1",
"metadata": {},
"outputs": [],
"source": [
"from langchain_community.tools.polygon.aggregates import PolygonAggregatesSchema\n",
"\n",
"# Define param\n",
"params = PolygonAggregatesSchema(\n",
" ticker=ticker,\n",
" timespan=\"day\",\n",
" timespan_multiplier=1,\n",
" from_date=\"2024-03-01\",\n",
" to_date=\"2024-03-08\",\n",
")\n",
"# Get aggregates for ticker\n",
"aggregates_tool = PolygonAggregates(api_wrapper=api_wrapper)\n",
"aggregates = aggregates_tool.run(tool_input=params.dict())\n",
"aggregates_json = json.loads(aggregates)"
]
},
{
"cell_type": "code",
"execution_count": 25,
"id": "a01f3888-d233-400d-b8c4-298d27c8f793",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Total aggregates: 6\n",
"Aggregates: [{'v': 73450582.0, 'vw': 179.0322, 'o': 179.55, 'c': 179.66, 'h': 180.53, 'l': 177.38, 't': 1709269200000, 'n': 911077}, {'v': 81505451.0, 'vw': 174.8938, 'o': 176.15, 'c': 175.1, 'h': 176.9, 'l': 173.79, 't': 1709528400000, 'n': 1167166}, {'v': 94702355.0, 'vw': 170.3234, 'o': 170.76, 'c': 170.12, 'h': 172.04, 'l': 169.62, 't': 1709614800000, 'n': 1108820}, {'v': 68568907.0, 'vw': 169.5506, 'o': 171.06, 'c': 169.12, 'h': 171.24, 'l': 168.68, 't': 1709701200000, 'n': 896297}, {'v': 71763761.0, 'vw': 169.3619, 'o': 169.15, 'c': 169, 'h': 170.73, 'l': 168.49, 't': 1709787600000, 'n': 825405}, {'v': 76267041.0, 'vw': 171.5322, 'o': 169, 'c': 170.73, 'h': 173.7, 'l': 168.94, 't': 1709874000000, 'n': 925213}]\n"
]
}
],
"source": [
"print(f\"Total aggregates: {len(aggregates_json)}\")\n",
"print(f\"Aggregates: {aggregates_json}\")"
]
},
{
"cell_type": "markdown",
"id": "04f1b612-f91f-471c-8264-9cc8c14bdaef",
"metadata": {},
"source": [
"### Get latest news for ticker"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "024982db-1402-4bd7-9788-6cb369a9565d",
"metadata": {},
"outputs": [],
"source": [
"ticker_news_tool = PolygonTickerNews(api_wrapper=api_wrapper)\n",
"ticker_news = ticker_news_tool.run(ticker)"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "dfd26ef6-2d92-483e-9780-484091bd3774",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Total news items: 10\n"
]
}
],
"source": [
"# Convert the news response to JSON array\n",
"ticker_news_json = json.loads(ticker_news)\n",
"print(f\"Total news items: {len(ticker_news_json)}\")"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "dbbb4b43-1096-45f3-8000-45538b3c73ee",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Title: An AI surprise could fuel a 20% rally for the S&P 500 in 2024, says UBS\n",
"Description: If Gen AI causes a big productivity boost, stocks could see an unexpected rally this year, say UBS strategists.\n",
"Publisher: MarketWatch\n",
"URL: https://www.marketwatch.com/story/an-ai-surprise-could-fuel-a-20-rally-for-the-s-p-500-in-2024-says-ubs-1044d716\n"
]
}
],
"source": [
"# Inspect the first news item\n",
"news_item = ticker_news_json[0]\n",
"print(f\"Title: {news_item['title']}\")\n",
"print(f\"Description: {news_item['description']}\")\n",
"print(f\"Publisher: {news_item['publisher']['name']}\")\n",
"print(f\"URL: {news_item['article_url']}\")"
]
},
{
"cell_type": "markdown",
"id": "675cbae0-a754-45b0-be01-738333c3255e",
"metadata": {},
"source": [
"### Get financials for ticker"
]
},
{
"cell_type": "code",
"execution_count": 28,
"id": "f46a8c88-8793-470d-8fce-31e8d4b1f77c",
"metadata": {},
"outputs": [],
"source": [
"financials_tool = PolygonFinancials(api_wrapper=api_wrapper)\n",
"financials = financials_tool.run(ticker)"
]
},
{
"cell_type": "code",
"execution_count": 30,
"id": "3495021c-a31b-4dba-8daf-811c43e24bd9",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Total reporting periods: 10\n"
]
}
],
"source": [
"# Convert the financials response to JSON\n",
"financials_json = json.loads(financials)\n",
"print(f\"Total reporting periods: {len(financials_json)}\")"
]
},
{
"cell_type": "code",
"execution_count": 31,
"id": "86215a03-a927-4334-a82b-54cb9574ed05",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Company name: APPLE INC\n",
"CIK: 0000320193\n",
"Fiscal period: TTM\n",
"End date: 2023-12-30\n",
"Start date: 2022-12-31\n"
]
}
],
"source": [
"# Print the latest reporting period's financials metadata\n",
"financial_data = financials_json[0]\n",
"print(f\"Company name: {financial_data['company_name']}\")\n",
"print(f\"CIK: {financial_data['cik']}\")\n",
"print(f\"Fiscal period: {financial_data['fiscal_period']}\")\n",
"print(f\"End date: {financial_data['end_date']}\")\n",
"print(f\"Start date: {financial_data['start_date']}\")"
]
},
{
"cell_type": "code",
"execution_count": 32,
"id": "2665d48b-fd44-4279-a2fe-e42836d3acdb",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Income statement: {'diluted_earnings_per_share': {'value': 6.42, 'unit': 'USD / shares', 'label': 'Diluted Earnings Per Share', 'order': 4300}, 'costs_and_expenses': {'value': 267270000000.0, 'unit': 'USD', 'label': 'Costs And Expenses', 'order': 600}, 'net_income_loss_attributable_to_noncontrolling_interest': {'value': 0, 'unit': 'USD', 'label': 'Net Income/Loss Attributable To Noncontrolling Interest', 'order': 3300}, 'net_income_loss_attributable_to_parent': {'value': 100913000000.0, 'unit': 'USD', 'label': 'Net Income/Loss Attributable To Parent', 'order': 3500}, 'income_tax_expense_benefit': {'value': 17523000000.0, 'unit': 'USD', 'label': 'Income Tax Expense/Benefit', 'order': 2200}, 'income_loss_from_continuing_operations_before_tax': {'value': 118436000000.0, 'unit': 'USD', 'label': 'Income/Loss From Continuing Operations Before Tax', 'order': 1500}, 'operating_expenses': {'value': 55013000000.0, 'unit': 'USD', 'label': 'Operating Expenses', 'order': 1000}, 'benefits_costs_expenses': {'value': 267270000000.0, 'unit': 'USD', 'label': 'Benefits Costs and Expenses', 'order': 200}, 'diluted_average_shares': {'value': 47151996000.0, 'unit': 'shares', 'label': 'Diluted Average Shares', 'order': 4500}, 'cost_of_revenue': {'value': 212035000000.0, 'unit': 'USD', 'label': 'Cost Of Revenue', 'order': 300}, 'operating_income_loss': {'value': 118658000000.0, 'unit': 'USD', 'label': 'Operating Income/Loss', 'order': 1100}, 'net_income_loss_available_to_common_stockholders_basic': {'value': 100913000000.0, 'unit': 'USD', 'label': 'Net Income/Loss Available To Common Stockholders, Basic', 'order': 3700}, 'preferred_stock_dividends_and_other_adjustments': {'value': 0, 'unit': 'USD', 'label': 'Preferred Stock Dividends And Other Adjustments', 'order': 3900}, 'research_and_development': {'value': 29902000000.0, 'unit': 'USD', 'label': 'Research and Development', 'order': 1030}, 'revenues': {'value': 385706000000.0, 'unit': 'USD', 'label': 'Revenues', 'order': 100}, 'participating_securities_distributed_and_undistributed_earnings_loss_basic': {'value': 0, 'unit': 'USD', 'label': 'Participating Securities, Distributed And Undistributed Earnings/Loss, Basic', 'order': 3800}, 'selling_general_and_administrative_expenses': {'value': 25111000000.0, 'unit': 'USD', 'label': 'Selling, General, and Administrative Expenses', 'order': 1010}, 'nonoperating_income_loss': {'value': -222000000.0, 'unit': 'USD', 'label': 'Nonoperating Income/Loss', 'order': 900}, 'income_loss_from_continuing_operations_after_tax': {'value': 100913000000.0, 'unit': 'USD', 'label': 'Income/Loss From Continuing Operations After Tax', 'order': 1400}, 'basic_earnings_per_share': {'value': 6.46, 'unit': 'USD / shares', 'label': 'Basic Earnings Per Share', 'order': 4200}, 'basic_average_shares': {'value': 46946265000.0, 'unit': 'shares', 'label': 'Basic Average Shares', 'order': 4400}, 'gross_profit': {'value': 173671000000.0, 'unit': 'USD', 'label': 'Gross Profit', 'order': 800}, 'net_income_loss': {'value': 100913000000.0, 'unit': 'USD', 'label': 'Net Income/Loss', 'order': 3200}}\n"
]
}
],
"source": [
"# Print the latest reporting period's income statement\n",
"print(f\"Income statement: {financial_data['financials']['income_statement']}\")"
]
},
{
"cell_type": "code",
"execution_count": 34,
"id": "9e24d339-c0d5-4b6a-9ba6-3f97e46ff6df",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Balance sheet: {'equity_attributable_to_noncontrolling_interest': {'value': 0, 'unit': 'USD', 'label': 'Equity Attributable To Noncontrolling Interest', 'order': 1500}, 'other_noncurrent_liabilities': {'value': 39441000000.0, 'unit': 'USD', 'label': 'Other Non-current Liabilities', 'order': 820}, 'equity': {'value': 74100000000.0, 'unit': 'USD', 'label': 'Equity', 'order': 1400}, 'liabilities': {'value': 279414000000.0, 'unit': 'USD', 'label': 'Liabilities', 'order': 600}, 'noncurrent_assets': {'value': 209822000000.0, 'unit': 'USD', 'label': 'Noncurrent Assets', 'order': 300}, 'equity_attributable_to_parent': {'value': 74100000000.0, 'unit': 'USD', 'label': 'Equity Attributable To Parent', 'order': 1600}, 'liabilities_and_equity': {'value': 353514000000.0, 'unit': 'USD', 'label': 'Liabilities And Equity', 'order': 1900}, 'other_current_liabilities': {'value': 75827000000.0, 'unit': 'USD', 'label': 'Other Current Liabilities', 'order': 740}, 'inventory': {'value': 6511000000.0, 'unit': 'USD', 'label': 'Inventory', 'order': 230}, 'other_noncurrent_assets': {'value': 166156000000.0, 'unit': 'USD', 'label': 'Other Non-current Assets', 'order': 350}, 'other_current_assets': {'value': 137181000000.0, 'unit': 'USD', 'label': 'Other Current Assets', 'order': 250}, 'current_liabilities': {'value': 133973000000.0, 'unit': 'USD', 'label': 'Current Liabilities', 'order': 700}, 'noncurrent_liabilities': {'value': 145441000000.0, 'unit': 'USD', 'label': 'Noncurrent Liabilities', 'order': 800}, 'fixed_assets': {'value': 43666000000.0, 'unit': 'USD', 'label': 'Fixed Assets', 'order': 320}, 'long_term_debt': {'value': 106000000000.0, 'unit': 'USD', 'label': 'Long-term Debt', 'order': 810}, 'current_assets': {'value': 143692000000.0, 'unit': 'USD', 'label': 'Current Assets', 'order': 200}, 'assets': {'value': 353514000000.0, 'unit': 'USD', 'label': 'Assets', 'order': 100}, 'accounts_payable': {'value': 58146000000.0, 'unit': 'USD', 'label': 'Accounts Payable', 'order': 710}}\n"
]
}
],
"source": [
"# Print the latest reporting period's balance sheet\n",
"print(f\"Balance sheet: {financial_data['financials']['balance_sheet']}\")"
]
},
{
"cell_type": "code",
"execution_count": 33,
"id": "4bfb47f1-8b9e-4293-be18-c4e9ab945d51",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Cash flow statement: {'net_cash_flow_continuing': {'value': 20000000000.0, 'unit': 'USD', 'label': 'Net Cash Flow, Continuing', 'order': 1200}, 'net_cash_flow_from_investing_activities_continuing': {'value': 7077000000.0, 'unit': 'USD', 'label': 'Net Cash Flow From Investing Activities, Continuing', 'order': 500}, 'net_cash_flow_from_investing_activities': {'value': 7077000000.0, 'unit': 'USD', 'label': 'Net Cash Flow From Investing Activities', 'order': 400}, 'net_cash_flow_from_financing_activities_continuing': {'value': -103510000000.0, 'unit': 'USD', 'label': 'Net Cash Flow From Financing Activities, Continuing', 'order': 800}, 'net_cash_flow_from_operating_activities': {'value': 116433000000.0, 'unit': 'USD', 'label': 'Net Cash Flow From Operating Activities', 'order': 100}, 'net_cash_flow_from_financing_activities': {'value': -103510000000.0, 'unit': 'USD', 'label': 'Net Cash Flow From Financing Activities', 'order': 700}, 'net_cash_flow_from_operating_activities_continuing': {'value': 116433000000.0, 'unit': 'USD', 'label': 'Net Cash Flow From Operating Activities, Continuing', 'order': 200}, 'net_cash_flow': {'value': 20000000000.0, 'unit': 'USD', 'label': 'Net Cash Flow', 'order': 1100}}\n"
]
}
],
"source": [
"# Print the latest reporting period's cash flow statement\n",
"print(f\"Cash flow statement: {financial_data['financials']['cash_flow_statement']}\")"
]
}
],
"metadata": {
"colab": {
"provenance": []
},
"kernelspec": {
"display_name": "Python (langchain)",
"language": "python",
"name": "langchain"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.18"
},
"vscode": {
"interpreter": {
"hash": "53f3bc57609c7a84333bb558594977aa5b4026b1d6070b93987956689e367341"
}
}
},
"nbformat": 4,
"nbformat_minor": 5
}