{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# ! uv pip install E:\\Work\\ruzt\\msyrs --upgrade"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Import Python packages\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import macrosynergy\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "import polars as pl\n",
    "import os\n",
    "\n",
    "from macrosynergy.panel import view_timelines\n",
    "from macrosynergy.management.types import QuantamentalDataFrame\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Import Python bindings - `msyrs`\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import msyrs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "DATA_FOLDER_PATH = \"E:/Work/jpmaqs-data\"\n",
    "# DATA_FOLDER_PATH = \"C:/Users/PalashTyagi/Code/go-dataquery/jpmaqs-data\"\n",
    "DQ_CLIENT_ID = os.getenv(\"DQ_CLIENT_ID\")\n",
    "DQ_CLIENT_SECRET = os.getenv(\"DQ_CLIENT_SECRET\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import time\n",
    "\n",
    "nb_start_time = time.time()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "dfpath = f\"{DATA_FOLDER_PATH}/data/ADPEMPL_SA_P1M1ML1/USD_ADPEMPL_SA_P1M1ML1.csv\"\n",
    "\n",
    "starttime = time.time()\n",
    "ldf: pl.DataFrame = msyrs.qdf.load_qdf(dfpath)\n",
    "print(f\"Time taken to load qdf: {time.time() - starttime}\")\n",
    "ldf.head(5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cids_dm = \"AUD.CAD.CHF.EUR.GBP.JPY.NOK.NZD.SEK.USD\".split(\".\")\n",
    "cids_em = \"CLP.COP.CZK.HUF.IDR.ILS.INR.KRW.MXN.PLN.THB.TRY.TWD.ZAR\".split(\".\")\n",
    "cids = cids_dm + cids_em\n",
    "cids_dux = list(set(cids) - set([\"IDR\", \"NZD\"]))\n",
    "ecos = (\n",
    "    \"CPIC_SA_P1M1ML12.CPIC_SJA_P3M3ML3AR.CPIC_SJA_P6M6ML6AR.CPIH_SA_P1M1ML12.\"\n",
    "    \"CPIH_SJA_P3M3ML3AR.CPIH_SJA_P6M6ML6AR.INFTEFF_NSA.INTRGDP_NSA_P1M1ML12_3MMA.\"\n",
    "    \"INTRGDPv5Y_NSA_P1M1ML12_3MMA.PCREDITGDP_SJA_D1M1ML12.RGDP_SA_P1Q1QL4_20QMA.\"\n",
    "    \"RYLDIRS02Y_NSA.RYLDIRS05Y_NSA.PCREDITBN_SJA_P1M1ML12\".split(\".\")\n",
    ")\n",
    "\n",
    "mkts = (\n",
    "    \"DU02YXR_NSA.DU05YXR_NSA.DU02YXR_VT10.DU05YXR_VT10.EQXR_NSA.EQXR_VT10.\"\n",
    "    \"FXXR_NSA.FXXR_VT10.FXCRR_NSA.FXTARGETED_NSA.FXUNTRADABLE_NSA\".split(\".\")\n",
    ")\n",
    "xcats = ecos + mkts\n",
    "\n",
    "tickers = [f\"{c}_{x}\" for c in cids for x in xcats]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "starttime = time.time()\n",
    "\n",
    "big_df: pl.DataFrame = msyrs.qdf.load_qdf_from_download_bank(\n",
    "    folder_path=DATA_FOLDER_PATH,\n",
    "    xcats=xcats,\n",
    ")\n",
    "print(f\"Time taken to load qdf batch: {time.time() - starttime}\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "big_df.estimated_size(\"mb\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "starttime = time.time()\n",
    "\n",
    "test_df = msyrs.qdf.reduce_dataframe(df=big_df, xcats=mkts)\n",
    "\n",
    "print(f\"Time taken to reduce qdf: {time.time() - starttime}\")\n",
    "print(test_df.estimated_size(\"mb\"))\n",
    "test_df = None"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "sel_cids = [\"USD\", \"EUR\", \"GBP\", \"AUD\", \"CAD\", \"CHF\", \"JPY\", \"INR\"]\n",
    "start = \"2000-01-01\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "eq_xcats = [xc for xc in xcats if xc.startswith(\"EQ\")]\n",
    "starttime = time.time()\n",
    "\n",
    "eq_df = msyrs.qdf.reduce_dataframe(\n",
    "    df=big_df, cids=sel_cids, xcats=eq_xcats, start=start\n",
    ")\n",
    "\n",
    "print(f\"Time taken to reduce qdf: {time.time() - starttime}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "fx_xcats = [xc for xc in xcats if xc.startswith(\"FX\")]\n",
    "\n",
    "starttime = time.time()\n",
    "\n",
    "fx_df = msyrs.qdf.reduce_dataframe(\n",
    "    df=big_df, cids=sel_cids, xcats=fx_xcats, start=start\n",
    ")\n",
    "new_df: pl.DataFrame = msyrs.qdf.update_dataframe(df=eq_df, df_add=fx_df)\n",
    "\n",
    "print(f\"Time taken to reduce qdf: {time.time() - starttime}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "starttime = time.time()\n",
    "\n",
    "new_df: pl.DataFrame = msyrs.qdf.update_dataframe(df=eq_df, df_add=fx_df)\n",
    "\n",
    "print(f\"Time taken to update qdf: {time.time() - starttime}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "msyrs.utils.get_bdates_series_default_opt(start_date='1971-01-01', end_date='2040-05-01', freq='D')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "msyrs.utils.get_bdates_series_default_pl(start_date='2000-01-01', end_date='2020-05-01', freq='D').dtype"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "wdf = QuantamentalDataFrame(new_df.to_pandas()).to_wide()\n",
    "# wdf.values[np.random.rand(*wdf.shape) < 0.0001] = np.nan\n",
    "wdf = QuantamentalDataFrame.from_wide(wdf, categorical=False)\n",
    "# cast column 'real_date' to pl.Date\n",
    "new_df = pl.DataFrame(wdf).with_columns(\n",
    "    pl.col(\"real_date\").cast(pl.Date, strict=True)\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "msyrs.utils.create_blacklist_from_qdf(new_df)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "view_timelines(df=new_df.to_pandas())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "end_time = time.time()\n",
    "print(f\"Time taken: {end_time - nb_start_time} seconds\")"
   ]
  }
 ],
 "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": "3.12.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}