{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Loading trades and vectorized aggregation\n",
"Describes how to fetch trades (remote/cached) and use new vectorized aggregation to aggregate bars of given type (time, volume, dollar) and resolution\n",
"\n",
"`fetch_trades_parallel` enables to fetch trades of given symbol and interval, also can filter conditions and minimum size. return `trades_df`\n",
"`aggregate_trades` acceptss `trades_df` and ressolution and type of bars (VOLUME, TIME, DOLLAR) and return aggregated ohlcv dataframe `ohlcv_df`"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"Activating profile profile1\n",
"\n"
],
"text/plain": [
"Activating profile profile1\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"trades_df-BAC-2024-01-11T09:30:00-2024-01-12T16:00:00.parquet\n",
"trades_df-SPY-2024-01-01T09:30:00-2024-05-14T16:00:00.parquet\n",
"ohlcv_df-BAC-2024-01-11T09:30:00-2024-01-12T16:00:00.parquet\n",
"ohlcv_df-SPY-2024-01-01T09:30:00-2024-05-14T16:00:00.parquet\n"
]
}
],
"source": [
"import pandas as pd\n",
"import numpy as np\n",
"from numba import jit\n",
"from alpaca.data.historical import StockHistoricalDataClient\n",
"from v2realbot.config import ACCOUNT1_PAPER_API_KEY, ACCOUNT1_PAPER_SECRET_KEY, DATA_DIR\n",
"from alpaca.data.requests import StockTradesRequest\n",
"from v2realbot.enums.enums import BarType\n",
"import time\n",
"from datetime import datetime\n",
"from v2realbot.utils.utils import parse_alpaca_timestamp, ltp, zoneNY, send_to_telegram, fetch_calendar_data\n",
"import pyarrow\n",
"from v2realbot.loader.aggregator_vectorized import fetch_daily_stock_trades, fetch_trades_parallel, generate_time_bars_nb, aggregate_trades\n",
"import vectorbtpro as vbt\n",
"import v2realbot.utils.config_handler as cfh\n",
"\n",
"vbt.settings.set_theme(\"dark\")\n",
"vbt.settings['plotting']['layout']['width'] = 1280\n",
"vbt.settings.plotting.auto_rangebreaks = True\n",
"# Set the option to display with pagination\n",
"pd.set_option('display.notebook_repr_html', True)\n",
"pd.set_option('display.max_rows', 20) # Number of rows per page\n",
"# pd.set_option('display.float_format', '{:.9f}'.format)\n",
"\n",
"\n",
"#trade filtering\n",
"exclude_conditions = cfh.config_handler.get_val('AGG_EXCLUDED_TRADES') #standard ['C','O','4','B','7','V','P','W','U','Z','F']\n",
"minsize = 100\n",
"\n",
"symbol = \"SPY\"\n",
"#datetime in zoneNY \n",
"day_start = datetime(2024, 1, 1, 9, 30, 0)\n",
"day_stop = datetime(2024, 1, 14, 16, 00, 0)\n",
"day_start = zoneNY.localize(day_start)\n",
"day_stop = zoneNY.localize(day_stop)\n",
"#filename of trades_df parquet, date are in isoformat but without time zone part\n",
"dir = DATA_DIR + \"/notebooks/\"\n",
"#parquet interval cache contains exclude conditions and minsize filtering\n",
"file_trades = dir + f\"trades_df-{symbol}-{day_start.strftime('%Y-%m-%dT%H:%M:%S')}-{day_stop.strftime('%Y-%m-%dT%H:%M:%S')}-{exclude_conditions}-{minsize}.parquet\"\n",
"#file_trades = dir + f\"trades_df-{symbol}-{day_start.strftime('%Y-%m-%dT%H:%M:%S')}-{day_stop.strftime('%Y-%m-%dT%H:%M:%S')}.parquet\"\n",
"file_ohlcv = dir + f\"ohlcv_df-{symbol}-{day_start.strftime('%Y-%m-%dT%H:%M:%S')}-{day_stop.strftime('%Y-%m-%dT%H:%M:%S')}-{exclude_conditions}-{minsize}.parquet\"\n",
"\n",
"#PRINT all parquet in directory\n",
"import os\n",
"files = [f for f in os.listdir(dir) if f.endswith(\".parquet\")]\n",
"for f in files:\n",
" print(f)"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"NOT FOUND. Fetching from remote\n"
]
},
{
"ename": "KeyboardInterrupt",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)",
"Cell \u001b[0;32mIn[2], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m trades_df \u001b[38;5;241m=\u001b[39m \u001b[43mfetch_daily_stock_trades\u001b[49m\u001b[43m(\u001b[49m\u001b[43msymbol\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mday_start\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mday_stop\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mexclude_conditions\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mexclude_conditions\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mminsize\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mminsize\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mforce_remote\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mmax_retries\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m5\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mbackoff_factor\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m1\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[1;32m 2\u001b[0m trades_df\n",
"File \u001b[0;32m~/Documents/Development/python/v2trading/v2realbot/loader/aggregator_vectorized.py:200\u001b[0m, in \u001b[0;36mfetch_daily_stock_trades\u001b[0;34m(symbol, start, end, exclude_conditions, minsize, force_remote, max_retries, backoff_factor)\u001b[0m\n\u001b[1;32m 198\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m attempt \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mrange\u001b[39m(max_retries):\n\u001b[1;32m 199\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 200\u001b[0m tradesResponse \u001b[38;5;241m=\u001b[39m \u001b[43mclient\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget_stock_trades\u001b[49m\u001b[43m(\u001b[49m\u001b[43mstockTradeRequest\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 201\u001b[0m is_empty \u001b[38;5;241m=\u001b[39m \u001b[38;5;129;01mnot\u001b[39;00m tradesResponse[symbol]\n\u001b[1;32m 202\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mRemote fetched: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mis_empty\u001b[38;5;132;01m=}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m, start, end)\n",
"File \u001b[0;32m~/Documents/Development/python/v2trading/.venv/lib/python3.10/site-packages/alpaca/data/historical/stock.py:144\u001b[0m, in \u001b[0;36mStockHistoricalDataClient.get_stock_trades\u001b[0;34m(self, request_params)\u001b[0m\n\u001b[1;32m 141\u001b[0m params \u001b[38;5;241m=\u001b[39m request_params\u001b[38;5;241m.\u001b[39mto_request_fields()\n\u001b[1;32m 143\u001b[0m \u001b[38;5;66;03m# paginated get request for market data api\u001b[39;00m\n\u001b[0;32m--> 144\u001b[0m raw_trades \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_data_get\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 145\u001b[0m \u001b[43m \u001b[49m\u001b[43mendpoint_data_type\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mtrades\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 146\u001b[0m \u001b[43m \u001b[49m\u001b[43mendpoint_asset_class\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mstocks\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 147\u001b[0m \u001b[43m \u001b[49m\u001b[43mapi_version\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mv2\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 148\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mparams\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 149\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 151\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_use_raw_data:\n\u001b[1;32m 152\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m raw_trades\n",
"File \u001b[0;32m~/Documents/Development/python/v2trading/.venv/lib/python3.10/site-packages/alpaca/data/historical/stock.py:338\u001b[0m, in \u001b[0;36mStockHistoricalDataClient._data_get\u001b[0;34m(self, endpoint_asset_class, endpoint_data_type, api_version, symbol_or_symbols, limit, page_limit, extension, **kwargs)\u001b[0m\n\u001b[1;32m 335\u001b[0m params[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mlimit\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m actual_limit\n\u001b[1;32m 336\u001b[0m params[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mpage_token\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m page_token\n\u001b[0;32m--> 338\u001b[0m response \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[43mpath\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mpath\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mdata\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mparams\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mapi_version\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mapi_version\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 340\u001b[0m \u001b[38;5;66;03m# TODO: Merge parsing if possible\u001b[39;00m\n\u001b[1;32m 341\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m extension \u001b[38;5;241m==\u001b[39m DataExtensionType\u001b[38;5;241m.\u001b[39mSNAPSHOT:\n",
"File \u001b[0;32m~/Documents/Development/python/v2trading/.venv/lib/python3.10/site-packages/alpaca/common/rest.py:221\u001b[0m, in \u001b[0;36mRESTClient.get\u001b[0;34m(self, path, data, **kwargs)\u001b[0m\n\u001b[1;32m 210\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mget\u001b[39m(\u001b[38;5;28mself\u001b[39m, path: \u001b[38;5;28mstr\u001b[39m, data: Union[\u001b[38;5;28mdict\u001b[39m, \u001b[38;5;28mstr\u001b[39m] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m HTTPResult:\n\u001b[1;32m 211\u001b[0m \u001b[38;5;250m \u001b[39m\u001b[38;5;124;03m\"\"\"Performs a single GET request\u001b[39;00m\n\u001b[1;32m 212\u001b[0m \n\u001b[1;32m 213\u001b[0m \u001b[38;5;124;03m Args:\u001b[39;00m\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 219\u001b[0m \u001b[38;5;124;03m dict: The response\u001b[39;00m\n\u001b[1;32m 220\u001b[0m \u001b[38;5;124;03m \"\"\"\u001b[39;00m\n\u001b[0;32m--> 221\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_request\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mGET\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mpath\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mdata\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
"File \u001b[0;32m~/Documents/Development/python/v2trading/.venv/lib/python3.10/site-packages/alpaca/common/rest.py:129\u001b[0m, in \u001b[0;36mRESTClient._request\u001b[0;34m(self, method, path, data, base_url, api_version)\u001b[0m\n\u001b[1;32m 127\u001b[0m \u001b[38;5;28;01mwhile\u001b[39;00m retry \u001b[38;5;241m>\u001b[39m\u001b[38;5;241m=\u001b[39m \u001b[38;5;241m0\u001b[39m:\n\u001b[1;32m 128\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 129\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_one_request\u001b[49m\u001b[43m(\u001b[49m\u001b[43mmethod\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43murl\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mopts\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mretry\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 130\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m RetryException:\n\u001b[1;32m 131\u001b[0m time\u001b[38;5;241m.\u001b[39msleep(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_retry_wait)\n",
"File \u001b[0;32m~/Documents/Development/python/v2trading/.venv/lib/python3.10/site-packages/alpaca/common/rest.py:193\u001b[0m, in \u001b[0;36mRESTClient._one_request\u001b[0;34m(self, method, url, opts, retry)\u001b[0m\n\u001b[1;32m 174\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m_one_request\u001b[39m(\u001b[38;5;28mself\u001b[39m, method: \u001b[38;5;28mstr\u001b[39m, url: \u001b[38;5;28mstr\u001b[39m, opts: \u001b[38;5;28mdict\u001b[39m, retry: \u001b[38;5;28mint\u001b[39m) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m \u001b[38;5;28mdict\u001b[39m:\n\u001b[1;32m 175\u001b[0m \u001b[38;5;250m \u001b[39m\u001b[38;5;124;03m\"\"\"Perform one request, possibly raising RetryException in the case\u001b[39;00m\n\u001b[1;32m 176\u001b[0m \u001b[38;5;124;03m the response is 429. Otherwise, if error text contain \"code\" string,\u001b[39;00m\n\u001b[1;32m 177\u001b[0m \u001b[38;5;124;03m then it decodes to json object and returns APIError.\u001b[39;00m\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 191\u001b[0m \u001b[38;5;124;03m dict: The response data\u001b[39;00m\n\u001b[1;32m 192\u001b[0m \u001b[38;5;124;03m \"\"\"\u001b[39;00m\n\u001b[0;32m--> 193\u001b[0m response \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_session\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mrequest\u001b[49m\u001b[43m(\u001b[49m\u001b[43mmethod\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43murl\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mopts\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 195\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m 196\u001b[0m response\u001b[38;5;241m.\u001b[39mraise_for_status()\n",
"File \u001b[0;32m~/Documents/Development/python/v2trading/.venv/lib/python3.10/site-packages/requests/sessions.py:589\u001b[0m, in \u001b[0;36mSession.request\u001b[0;34m(self, method, url, params, data, headers, cookies, files, auth, timeout, allow_redirects, proxies, hooks, stream, verify, cert, json)\u001b[0m\n\u001b[1;32m 584\u001b[0m send_kwargs \u001b[38;5;241m=\u001b[39m {\n\u001b[1;32m 585\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mtimeout\u001b[39m\u001b[38;5;124m\"\u001b[39m: timeout,\n\u001b[1;32m 586\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mallow_redirects\u001b[39m\u001b[38;5;124m\"\u001b[39m: allow_redirects,\n\u001b[1;32m 587\u001b[0m }\n\u001b[1;32m 588\u001b[0m send_kwargs\u001b[38;5;241m.\u001b[39mupdate(settings)\n\u001b[0;32m--> 589\u001b[0m resp \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msend\u001b[49m\u001b[43m(\u001b[49m\u001b[43mprep\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43msend_kwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 591\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m resp\n",
"File \u001b[0;32m~/Documents/Development/python/v2trading/.venv/lib/python3.10/site-packages/requests/sessions.py:703\u001b[0m, in \u001b[0;36mSession.send\u001b[0;34m(self, request, **kwargs)\u001b[0m\n\u001b[1;32m 700\u001b[0m start \u001b[38;5;241m=\u001b[39m preferred_clock()\n\u001b[1;32m 702\u001b[0m \u001b[38;5;66;03m# Send the request\u001b[39;00m\n\u001b[0;32m--> 703\u001b[0m r \u001b[38;5;241m=\u001b[39m \u001b[43madapter\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msend\u001b[49m\u001b[43m(\u001b[49m\u001b[43mrequest\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 705\u001b[0m \u001b[38;5;66;03m# Total elapsed time of the request (approximately)\u001b[39;00m\n\u001b[1;32m 706\u001b[0m elapsed \u001b[38;5;241m=\u001b[39m preferred_clock() \u001b[38;5;241m-\u001b[39m start\n",
"File \u001b[0;32m~/Documents/Development/python/v2trading/.venv/lib/python3.10/site-packages/requests/adapters.py:486\u001b[0m, in \u001b[0;36mHTTPAdapter.send\u001b[0;34m(self, request, stream, timeout, verify, cert, proxies)\u001b[0m\n\u001b[1;32m 483\u001b[0m timeout \u001b[38;5;241m=\u001b[39m TimeoutSauce(connect\u001b[38;5;241m=\u001b[39mtimeout, read\u001b[38;5;241m=\u001b[39mtimeout)\n\u001b[1;32m 485\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 486\u001b[0m resp \u001b[38;5;241m=\u001b[39m \u001b[43mconn\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43murlopen\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 487\u001b[0m \u001b[43m \u001b[49m\u001b[43mmethod\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrequest\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mmethod\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 488\u001b[0m \u001b[43m \u001b[49m\u001b[43murl\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43murl\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 489\u001b[0m \u001b[43m \u001b[49m\u001b[43mbody\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrequest\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mbody\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 490\u001b[0m \u001b[43m \u001b[49m\u001b[43mheaders\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrequest\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mheaders\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 491\u001b[0m \u001b[43m \u001b[49m\u001b[43mredirect\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[1;32m 492\u001b[0m \u001b[43m \u001b[49m\u001b[43massert_same_host\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[1;32m 493\u001b[0m \u001b[43m \u001b[49m\u001b[43mpreload_content\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[1;32m 494\u001b[0m \u001b[43m \u001b[49m\u001b[43mdecode_content\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[1;32m 495\u001b[0m \u001b[43m \u001b[49m\u001b[43mretries\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mmax_retries\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 496\u001b[0m \u001b[43m \u001b[49m\u001b[43mtimeout\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtimeout\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 497\u001b[0m \u001b[43m \u001b[49m\u001b[43mchunked\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mchunked\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 498\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 500\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m (ProtocolError, \u001b[38;5;167;01mOSError\u001b[39;00m) \u001b[38;5;28;01mas\u001b[39;00m err:\n\u001b[1;32m 501\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mConnectionError\u001b[39;00m(err, request\u001b[38;5;241m=\u001b[39mrequest)\n",
"File \u001b[0;32m~/Documents/Development/python/v2trading/.venv/lib/python3.10/site-packages/urllib3/connectionpool.py:703\u001b[0m, in \u001b[0;36mHTTPConnectionPool.urlopen\u001b[0;34m(self, method, url, body, headers, retries, redirect, assert_same_host, timeout, pool_timeout, release_conn, chunked, body_pos, **response_kw)\u001b[0m\n\u001b[1;32m 700\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_prepare_proxy(conn)\n\u001b[1;32m 702\u001b[0m \u001b[38;5;66;03m# Make the request on the httplib connection object.\u001b[39;00m\n\u001b[0;32m--> 703\u001b[0m httplib_response \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_make_request\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 704\u001b[0m \u001b[43m \u001b[49m\u001b[43mconn\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 705\u001b[0m \u001b[43m \u001b[49m\u001b[43mmethod\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 706\u001b[0m \u001b[43m \u001b[49m\u001b[43murl\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 707\u001b[0m \u001b[43m \u001b[49m\u001b[43mtimeout\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtimeout_obj\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 708\u001b[0m \u001b[43m \u001b[49m\u001b[43mbody\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mbody\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 709\u001b[0m \u001b[43m \u001b[49m\u001b[43mheaders\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mheaders\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 710\u001b[0m \u001b[43m \u001b[49m\u001b[43mchunked\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mchunked\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 711\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 713\u001b[0m \u001b[38;5;66;03m# If we're going to release the connection in ``finally:``, then\u001b[39;00m\n\u001b[1;32m 714\u001b[0m \u001b[38;5;66;03m# the response doesn't need to know about the connection. Otherwise\u001b[39;00m\n\u001b[1;32m 715\u001b[0m \u001b[38;5;66;03m# it will also try to release it and we'll have a double-release\u001b[39;00m\n\u001b[1;32m 716\u001b[0m \u001b[38;5;66;03m# mess.\u001b[39;00m\n\u001b[1;32m 717\u001b[0m response_conn \u001b[38;5;241m=\u001b[39m conn \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m release_conn \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n",
"File \u001b[0;32m~/Documents/Development/python/v2trading/.venv/lib/python3.10/site-packages/urllib3/connectionpool.py:449\u001b[0m, in \u001b[0;36mHTTPConnectionPool._make_request\u001b[0;34m(self, conn, method, url, timeout, chunked, **httplib_request_kw)\u001b[0m\n\u001b[1;32m 444\u001b[0m httplib_response \u001b[38;5;241m=\u001b[39m conn\u001b[38;5;241m.\u001b[39mgetresponse()\n\u001b[1;32m 445\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mBaseException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m 446\u001b[0m \u001b[38;5;66;03m# Remove the TypeError from the exception chain in\u001b[39;00m\n\u001b[1;32m 447\u001b[0m \u001b[38;5;66;03m# Python 3 (including for exceptions like SystemExit).\u001b[39;00m\n\u001b[1;32m 448\u001b[0m \u001b[38;5;66;03m# Otherwise it looks like a bug in the code.\u001b[39;00m\n\u001b[0;32m--> 449\u001b[0m \u001b[43msix\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mraise_from\u001b[49m\u001b[43m(\u001b[49m\u001b[43me\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m)\u001b[49m\n\u001b[1;32m 450\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m (SocketTimeout, BaseSSLError, SocketError) \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m 451\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_raise_timeout(err\u001b[38;5;241m=\u001b[39me, url\u001b[38;5;241m=\u001b[39murl, timeout_value\u001b[38;5;241m=\u001b[39mread_timeout)\n",
"File \u001b[0;32m:3\u001b[0m, in \u001b[0;36mraise_from\u001b[0;34m(value, from_value)\u001b[0m\n",
"File \u001b[0;32m~/Documents/Development/python/v2trading/.venv/lib/python3.10/site-packages/urllib3/connectionpool.py:444\u001b[0m, in \u001b[0;36mHTTPConnectionPool._make_request\u001b[0;34m(self, conn, method, url, timeout, chunked, **httplib_request_kw)\u001b[0m\n\u001b[1;32m 441\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mTypeError\u001b[39;00m:\n\u001b[1;32m 442\u001b[0m \u001b[38;5;66;03m# Python 3\u001b[39;00m\n\u001b[1;32m 443\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 444\u001b[0m httplib_response \u001b[38;5;241m=\u001b[39m \u001b[43mconn\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mgetresponse\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 445\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mBaseException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m 446\u001b[0m \u001b[38;5;66;03m# Remove the TypeError from the exception chain in\u001b[39;00m\n\u001b[1;32m 447\u001b[0m \u001b[38;5;66;03m# Python 3 (including for exceptions like SystemExit).\u001b[39;00m\n\u001b[1;32m 448\u001b[0m \u001b[38;5;66;03m# Otherwise it looks like a bug in the code.\u001b[39;00m\n\u001b[1;32m 449\u001b[0m six\u001b[38;5;241m.\u001b[39mraise_from(e, \u001b[38;5;28;01mNone\u001b[39;00m)\n",
"File \u001b[0;32m/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/http/client.py:1375\u001b[0m, in \u001b[0;36mHTTPConnection.getresponse\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 1373\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m 1374\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m-> 1375\u001b[0m \u001b[43mresponse\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mbegin\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1376\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mConnectionError\u001b[39;00m:\n\u001b[1;32m 1377\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mclose()\n",
"File \u001b[0;32m/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/http/client.py:318\u001b[0m, in \u001b[0;36mHTTPResponse.begin\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 316\u001b[0m \u001b[38;5;66;03m# read until we get a non-100 response\u001b[39;00m\n\u001b[1;32m 317\u001b[0m \u001b[38;5;28;01mwhile\u001b[39;00m \u001b[38;5;28;01mTrue\u001b[39;00m:\n\u001b[0;32m--> 318\u001b[0m version, status, reason \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_read_status\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 319\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m status \u001b[38;5;241m!=\u001b[39m CONTINUE:\n\u001b[1;32m 320\u001b[0m \u001b[38;5;28;01mbreak\u001b[39;00m\n",
"File \u001b[0;32m/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/http/client.py:279\u001b[0m, in \u001b[0;36mHTTPResponse._read_status\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 278\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m_read_status\u001b[39m(\u001b[38;5;28mself\u001b[39m):\n\u001b[0;32m--> 279\u001b[0m line \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mstr\u001b[39m(\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfp\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mreadline\u001b[49m\u001b[43m(\u001b[49m\u001b[43m_MAXLINE\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m+\u001b[39;49m\u001b[43m \u001b[49m\u001b[38;5;241;43m1\u001b[39;49m\u001b[43m)\u001b[49m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124miso-8859-1\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m 280\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(line) \u001b[38;5;241m>\u001b[39m _MAXLINE:\n\u001b[1;32m 281\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m LineTooLong(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mstatus line\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n",
"File \u001b[0;32m/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/socket.py:705\u001b[0m, in \u001b[0;36mSocketIO.readinto\u001b[0;34m(self, b)\u001b[0m\n\u001b[1;32m 703\u001b[0m \u001b[38;5;28;01mwhile\u001b[39;00m \u001b[38;5;28;01mTrue\u001b[39;00m:\n\u001b[1;32m 704\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 705\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_sock\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mrecv_into\u001b[49m\u001b[43m(\u001b[49m\u001b[43mb\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 706\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m timeout:\n\u001b[1;32m 707\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_timeout_occurred \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mTrue\u001b[39;00m\n",
"File \u001b[0;32m/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/ssl.py:1274\u001b[0m, in \u001b[0;36mSSLSocket.recv_into\u001b[0;34m(self, buffer, nbytes, flags)\u001b[0m\n\u001b[1;32m 1270\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m flags \u001b[38;5;241m!=\u001b[39m \u001b[38;5;241m0\u001b[39m:\n\u001b[1;32m 1271\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[1;32m 1272\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mnon-zero flags not allowed in calls to recv_into() on \u001b[39m\u001b[38;5;132;01m%s\u001b[39;00m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;241m%\u001b[39m\n\u001b[1;32m 1273\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__class__\u001b[39m)\n\u001b[0;32m-> 1274\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mread\u001b[49m\u001b[43m(\u001b[49m\u001b[43mnbytes\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mbuffer\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1275\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 1276\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28msuper\u001b[39m()\u001b[38;5;241m.\u001b[39mrecv_into(buffer, nbytes, flags)\n",
"File \u001b[0;32m/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/ssl.py:1130\u001b[0m, in \u001b[0;36mSSLSocket.read\u001b[0;34m(self, len, buffer)\u001b[0m\n\u001b[1;32m 1128\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m 1129\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m buffer \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[0;32m-> 1130\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_sslobj\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mread\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mlen\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mbuffer\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1131\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 1132\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_sslobj\u001b[38;5;241m.\u001b[39mread(\u001b[38;5;28mlen\u001b[39m)\n",
"\u001b[0;31mKeyboardInterrupt\u001b[0m: "
]
}
],
"source": [
"trades_df = fetch_daily_stock_trades(symbol, day_start, day_stop, exclude_conditions=exclude_conditions, minsize=minsize, force_remote=False, max_retries=5, backoff_factor=1)\n",
"trades_df"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"#Either load trades or ohlcv from parquet if exists\n",
"\n",
"#trades_df = fetch_trades_parallel(symbol, day_start, day_stop, exclude_conditions=exclude_conditions, minsize=50, max_workers=20) #exclude_conditions=['C','O','4','B','7','V','P','W','U','Z','F'])\n",
"# trades_df.to_parquet(file_trades, engine='pyarrow', compression='gzip')\n",
"\n",
"trades_df = pd.read_parquet(file_trades,engine='pyarrow')\n",
"ohlcv_df = aggregate_trades(symbol=symbol, trades_df=trades_df, resolution=1, type=BarType.TIME)\n",
"ohlcv_df.to_parquet(file_ohlcv, engine='pyarrow', compression='gzip')\n",
"\n",
"# ohlcv_df = pd.read_parquet(file_ohlcv,engine='pyarrow')\n",
"# trades_df = pd.read_parquet(file_trades,engine='pyarrow')\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#list all files is dir directory with parquet extension\n",
"dir = DATA_DIR + \"/notebooks/\"\n",
"import os\n",
"files = [f for f in os.listdir(dir) if f.endswith(\".parquet\")]\n",
"file_name = \"\"\n",
"ohlcv_df = pd.read_parquet(file_ohlcv,engine='pyarrow')"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"ohlcv_df"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import matplotlib.pyplot as plt\n",
"import seaborn as sns\n",
"# Calculate daily returns\n",
"ohlcv_df['returns'] = ohlcv_df['close'].pct_change().dropna()\n",
"#same as above but pct_change is from 3 datapoints back, but only if it is the same date, else na\n",
"\n",
"\n",
"# Plot the probability distribution curve\n",
"plt.figure(figsize=(10, 6))\n",
"sns.histplot(df['returns'].dropna(), kde=True, stat='probability', bins=30)\n",
"plt.title('Probability Distribution of Daily Returns')\n",
"plt.xlabel('Daily Returns')\n",
"plt.ylabel('Probability')\n",
"plt.show()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"import numpy as np\n",
"from sklearn.model_selection import train_test_split\n",
"from sklearn.preprocessing import StandardScaler\n",
"from sklearn.linear_model import LogisticRegression\n",
"from sklearn.metrics import accuracy_score\n",
"\n",
"# Define the intervals from 5 to 20 s, returns for each interval\n",
"#maybe use rolling window?\n",
"intervals = range(5, 21, 5)\n",
"\n",
"# Create columns for percentage returns\n",
"rolling_window = 50\n",
"\n",
"# Normalize the returns using rolling mean and std\n",
"for N in intervals:\n",
" column_name = f'returns_{N}'\n",
" rolling_mean = ohlcv_df[column_name].rolling(window=rolling_window).mean()\n",
" rolling_std = ohlcv_df[column_name].rolling(window=rolling_window).std()\n",
" ohlcv_df[f'norm_{column_name}'] = (ohlcv_df[column_name] - rolling_mean) / rolling_std\n",
"\n",
"# Display the dataframe with normalized return columns\n",
"ohlcv_df\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Calculate the sum of the normalized return columns for each row\n",
"ohlcv_df['sum_norm_returns'] = ohlcv_df[[f'norm_returns_{N}' for N in intervals]].sum(axis=1)\n",
"\n",
"# Sort the DataFrame based on the sum of normalized returns in descending order\n",
"df_sorted = ohlcv_df.sort_values(by='sum_norm_returns', ascending=False)\n",
"\n",
"# Display the top rows with the highest sum of normalized returns\n",
"df_sorted\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Drop initial rows with NaN values due to pct_change\n",
"ohlcv_df.dropna(inplace=True)\n",
"\n",
"# Plotting the probability distribution curves\n",
"plt.figure(figsize=(14, 8))\n",
"for N in intervals:\n",
" sns.kdeplot(ohlcv_df[f'returns_{N}'].dropna(), label=f'Returns {N}', fill=True)\n",
"\n",
"plt.title('Probability Distribution of Percentage Returns')\n",
"plt.xlabel('Percentage Return')\n",
"plt.ylabel('Density')\n",
"plt.legend()\n",
"plt.show()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import matplotlib.pyplot as plt\n",
"import seaborn as sns\n",
"# Plot the probability distribution curve\n",
"plt.figure(figsize=(10, 6))\n",
"sns.histplot(ohlcv_df['returns'].dropna(), kde=True, stat='probability', bins=30)\n",
"plt.title('Probability Distribution of Daily Returns')\n",
"plt.xlabel('Daily Returns')\n",
"plt.ylabel('Probability')\n",
"plt.show()\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#show only rows from ohlcv_df where returns > 0.005\n",
"ohlcv_df[ohlcv_df['returns'] > 0.0005]\n",
"\n",
"#ohlcv_df[ohlcv_df['returns'] < -0.005]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#ohlcv where index = date 2024-03-13 and between hour 12\n",
"\n",
"a = ohlcv_df.loc['2024-03-13 12:00:00':'2024-03-13 13:00:00']\n",
"a"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"ohlcv_df"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"trades_df"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"ohlcv_df.info()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"trades_df.to_parquet(\"trades_df-spy-0111-0111.parquett\", engine='pyarrow', compression='gzip')\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"trades_df.to_parquet(\"trades_df-spy-111-0516.parquett\", engine='pyarrow', compression='gzip', allow_truncated_timestamps=True)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"ohlcv_df.to_parquet(\"ohlcv_df-spy-111-0516.parquett\", engine='pyarrow', compression='gzip')"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"basic_data = vbt.Data.from_data(vbt.symbol_dict({symbol: ohlcv_df}), tz_convert=zoneNY)\n",
"vbt.settings['plotting']['auto_rangebreaks'] = True\n",
"basic_data.ohlcv.plot()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#access just BCA\n",
"#df_filtered = df.loc[\"BAC\"]"
]
}
],
"metadata": {
"kernelspec": {
"display_name": ".venv",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.11"
}
},
"nbformat": 4,
"nbformat_minor": 2
}