magnus167/msyrs
1
0
Fork 0
mirror of https://github.com/Magnus167/msyrs.git synced 2025-08-20 04:00:01 +00:00
Code Issues Packages Projects Releases Wiki Activity
msyrs/notebooks/python-notebook.ipynb
Palash Tyagi 9fad1fbae5 updating python notebook
2025-04-08 19:10:59 +01:00

635 lines
16 KiB
Plaintext
Vendored
Raw Blame History

{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Build and install the package\n",
"\n",
"First patch `pyo3-polars`:\n",
"\n",
"- Use [this diff](https://github.com/pola-rs/pyo3-polars/compare/main...Magnus167:pyo3-polars:main) to make changes to the `pyo3-polars` package.\n",
"\n",
"Install the package:\n",
"\n",
"```bash\n",
"python -m venv .venv\n",
"# source .venv/bin/activate\n",
"./.venv/Scripts/activate\n",
"pip install uv\n",
"uv pip install maturin jupyter notebook ipython ipywidgets pyarrow polars macrosynergy --upgrade\n",
"\n",
"maturin develop --release\n",
"```\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# ! uv pip install maturin jupyter notebook ipython ipywidgets pyarrow polars macrosynergy --upgrade\n"
]
},
{
"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 = \"CPIC_SA_P1M1ML12.CPIC_SJA_P3M3ML3AR.CPIC_SJA_P6M6ML6AR.CPIH_SA_P1M1ML12.CPIH_SJA_P3M3ML3AR.CPIH_SJA_P6M6ML6AR.INFTEFF_NSA.INTRGDP_NSA_P1M1ML12_3MMA.INTRGDPv5Y_NSA_P1M1ML12_3MMA.PCREDITGDP_SJA_D1M1ML12.RGDP_SA_P1Q1QL4_20QMA.RYLDIRS02Y_NSA.RYLDIRS05Y_NSA.PCREDITBN_SJA_P1M1ML12\".split(\n",
" \".\"\n",
")\n",
"\n",
"\n",
"mkts = \"DU02YXR_NSA.DU05YXR_NSA.DU02YXR_VT10.DU05YXR_VT10.EQXR_NSA.EQXR_VT10.FXXR_NSA.FXXR_VT10.FXCRR_NSA.FXTARGETED_NSA.FXUNTRADABLE_NSA\".split(\n",
" \".\"\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": [
"# downloaded_df: pl.DataFrame = msyrs.download.download_jpmaqs_indicators_as_df(\n",
"# client_id=DQ_CLIENT_ID,\n",
"# client_secret=DQ_CLIENT_SECRET,\n",
"# tickers=tickers,\n",
"# )\n",
"# downloaded_df.head(5)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"downloaded_df = None"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# pddf = macrosynergy.download.JPMaQSDownload().download(\n",
"# tickers=tickers,\n",
"# get_catalogue=True,\n",
"# show_progress=True,\n",
"# start_date=\"1990-01-01\",\n",
"# )\n",
"# pddf = macrosynergy.management.types.QuantamentalDataFrame(pddf)"
]
},
{
"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",
"\n",
" folder_path=DATA_FOLDER_PATH,\n",
" xcats=xcats,\n",
"\n",
" # folder_path=DATA_FOLDER_PATH, cids=cids\n",
"\n",
")\n",
"print(f\"Time taken to load qdf batch: {time.time() - starttime}\")\n",
"\n",
"\n",
"big_df.head(5)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"big_df.estimated_size(\"mb\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"big_df.to_pandas()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"big_df.to_pandas().memory_usage(deep=True).sum() / 1024**2"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"macrosynergy.management.types.QuantamentalDataFrame(big_df.to_pandas()).memory_usage(\n",
" deep=True\n",
").sum() / 1024**2"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"sel_cids = [\"USD\", \"EUR\", \"GBP\", \"AUD\", \"CAD\"]\n",
"start = \"1990-01-01\""
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"starttime = time.time()\n",
"eq_df = msyrs.qdf.reduce_dataframe(\n",
" df=big_df,\n",
" cids=sel_cids,\n",
" xcats=[\"EQXR_NSA\", \"EQXR_VT10\"],\n",
"\n",
" start=start,\n",
")\n",
"print(f\"Time taken to reduce qdf: {time.time() - starttime}\")\n",
"eq_df"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# starttime = time.time()\n",
"# eq_pd_df = pddf.reduce_df(cids=sel_cids, xcats=[\"EQXR_NSA\", \"EQXR_VT10\"], start=start)\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",
"starttime = time.time()\n",
"\n",
"fx_df = msyrs.qdf.reduce_dataframe(\n",
" df=big_df, cids=sel_cids, start=start, xcats=fx_xcats, intersect=True\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",
"# fx_pd_df = pddf.reduce_df(cids=sel_cids, xcats=fx_xcats, start=start, intersect=True)\n",
"# print(f\"Time taken to reduce qdf: {time.time() - starttime}\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"starttime = time.time()\n",
"new_df: pl.DataFrame = msyrs.qdf.update_dataframe(df=eq_df, df_add=fx_df)\n",
"print(\"Time taken: \", time.time() - starttime)\n",
"new_df.head(10)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# starttime = time.time()\n",
"# new_pd_df = pddf.update_df(df_add=eq_pd_df,)\n",
"# print(\"Time taken: \", time.time() - starttime)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"new_df.tail(10)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# df: polars::prelude::DataFrame,\n",
"# xcat: String,\n",
"# cids: Option<Vec<String>>,\n",
"# lback_periods: Option<usize>,\n",
"# lback_method: Option<String>,\n",
"# half_life: Option<f64>,\n",
"# start: Option<String>,\n",
"# end: Option<String>,\n",
"# est_freq: Option<String>,\n",
"# remove_zeros: Option<bool>,\n",
"# postfix: Option<String>,\n",
"# nan_tolerance: Option<f64>,\n",
"\n",
"starttime = time.time()\n",
"hv = msyrs.panel.historic_vol(\n",
" df=new_df,\n",
" xcat=\"EQXR_NSA\",\n",
" cids=None,\n",
" lback_periods=21,\n",
" lback_method=\"xma\",\n",
" half_life=11,\n",
" start=None,\n",
" end=None,\n",
" est_freq=\"D\",\n",
" remove_zeros=None,\n",
" postfix=\"_HV_RS\",\n",
" nan_tolerance=None,\n",
")\n",
"print(f\"Time taken: {time.time() - starttime}\")\n",
"\n",
"starttime = time.time()\n",
"a = 1 + 5\n",
"print(\"Time taken: \", time.time() - starttime)\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"\n",
"hdf = hv.to_pandas()\n",
"\n",
"hdf = QuantamentalDataFrame.from_wide(\n",
" (\n",
" \n",
" QuantamentalDataFrame(hdf)\n",
" .to_wide()\n",
" .reindex(\n",
" pd.bdate_range(\n",
" start=hdf[\"real_date\"].min(),\n",
" end=hdf[\"real_date\"].max(),\n",
" freq=\"B\",\n",
" ),\n",
" method=\"ffill\",\n",
" )\n",
" .dropna(axis=\"rows\", how=\"all\")\n",
" ).sort_index(),\n",
" categorical=False,\n",
")\n",
"\n",
"view_timelines(df=hdf)\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"starttime = time.time()\n",
"msyrs.qdf.pivot_dataframe_by_ticker(df=new_df).head(10)\n",
"print(\"Time taken: \", time.time() - starttime)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# new_pd_df = macrosynergy.management.types.QuantamentalDataFrame(new_pd_df)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from macrosynergy.panel.historic_vol import historic_vol\n",
"\n",
"new_df_pd = QuantamentalDataFrame(\n",
" new_df.to_pandas(), categorical=False\n",
")\n",
"cids = new_df_pd['cid'].unique().tolist()\n",
"\n",
"starttime = time.time()\n",
"hv_bench = historic_vol(\n",
" df=new_df_pd,\n",
" xcat='EQXR_NSA',\n",
" cids=cids,\n",
" lback_periods=21,\n",
" lback_meth=\"xma\",\n",
" half_life=11,\n",
" est_freq=\"D\",\n",
" blacklist=None,\n",
" remove_zeros=True,\n",
" postfix=\"_HV_PY\",\n",
" nan_tolerance=0.001,\n",
")\n",
"print(f\"Time taken: {time.time() - starttime}\")\n",
"\n",
"starttime = time.time()\n",
"a = 1 + 5\n",
"print(\"Time taken: \", time.time() - starttime)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"view_timelines(df=hv_bench)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"hv_bench = hv_bench.dropna(axis=\"rows\", how=\"any\").reset_index(drop=True)\n",
"bdr = pd.bdate_range(new_df_pd.real_date.min(), new_df_pd.real_date.max())\n",
"hv_bench = QuantamentalDataFrame.from_wide(\n",
" QuantamentalDataFrame(hv_bench).to_wide().reindex(bdr, method=\"ffill\"),\n",
" categorical=False,\n",
").reset_index(drop=True)\n",
"\n",
"view_timelines(df=hv_bench)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"def zscore_series(s: pd.Series) -> pd.Series:\n",
" return (s - s.mean()) / s.std()\n",
"\n",
"\n",
"a = QuantamentalDataFrame.from_wide(\n",
" QuantamentalDataFrame(hv_bench)\n",
" .to_wide()\n",
" .apply(lambda x: zscore_series(x), axis=1, result_type=\"expand\")\n",
")\n",
"\n",
"b = QuantamentalDataFrame.from_wide(\n",
" QuantamentalDataFrame(hdf)\n",
" .to_wide()\n",
" .apply(lambda x: zscore_series(x), axis=1, result_type=\"expand\")\n",
")\n",
"\n",
"view_timelines(QuantamentalDataFrame.from_qdf_list([a, b]).dropna(axis=\"rows\", how=\"any\").reset_index(drop=True))\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# a = QuantamentalDataFrame(hv_bench).to_wide().apply(lambda x: zscore_series(x), axis=1, result_type=\"expand\").rename(columns=lambda x: '_'.join(x.split(\"_\")[:-1]))\n",
"\n",
"# b = QuantamentalDataFrame(hdf).to_wide().apply(lambda x: zscore_series(x), axis=1, result_type=\"expand\").rename(columns=lambda x: '_'.join(x.split(\"_\")[:-1]))\n",
"\n",
"a = QuantamentalDataFrame(hv_bench).to_wide().rename(columns=lambda x: '_'.join(x.split(\"_\")[:-1]))\n",
"\n",
"b = QuantamentalDataFrame(hdf).to_wide().rename(columns=lambda x: '_'.join(x.split(\"_\")[:-1]))\n",
"\n",
"diff = (a - b) / (a.abs())\n",
"\n",
"view_timelines(QuantamentalDataFrame.from_wide(diff))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# starttime = time.time()\n",
"# new_pd_df.to_wide()\n",
"# print(\"Time taken: \", time.time() - starttime)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"end_time = time.time()\n",
"print(f\"Time taken: {end_time - nb_start_time} seconds\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# pub fn linear_composite(\n",
"# df: PyDataFrame,\n",
"# xcats: Vec<String>,\n",
"# cids: Vec<String>,\n",
"# weights: Option<Vec<f64>>,\n",
"# signs: Option<Vec<f64>>,\n",
"# weight_xcats: Option<Vec<String>>,\n",
"# normalize_weights: bool,\n",
"# start: Option<String>,\n",
"# end: Option<String>,\n",
"# blacklist: Option<std::collections::HashMap<String, Vec<String>>>,\n",
"# complete_xcats: bool,\n",
"# complete_cids: bool,\n",
"# new_xcat: Option<String>,\n",
"# new_cid: Option<String>,\n",
"# ) -> PyResult<PyDataFrame> {\n",
"\n",
"msyrs.panel.linear_composite(\n",
" df=new_df,\n",
" xcats=[\"EQXR_NSA\", \"EQXR_VT10\"],\n",
" cids=[\"USD\", \"EUR\", \"GBP\", \"AUD\", \"CAD\"],\n",
" weights=None,\n",
" signs=None,\n",
" weight_xcats=None,\n",
" normalize_weights=False,\n",
" start=None,\n",
" end=None,\n",
" blacklist=None,\n",
" complete_xcats=False,\n",
" complete_cids=False,\n",
" new_xcat=\"COMPOSITE\",\n",
" new_cid=\"USD\",\n",
")"
]
}
],
"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
}
Reference in New Issue View Git Blame Copy Permalink