{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "# Build and install the package\n", "\n", "First patch `pyo3-polars`:\n", "\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", "\n", "Install the package:\n", "\n", "```bash\n", "python -m venv .venv\n", "\n", "# source .venv/bin/activate\n", "./.venv/Scripts/activate\n", "\n", "pip install maturin ipywidgets\n", "\n", "maturin develop --release\n", "```\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Import Python packages\n" ] }, { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [], "source": [ "import macrosynergy\n", "import pandas as pd\n", "import numpy as np\n", "import polars as pl\n", "import os" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Import Python bindings - `msyrs`\n" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [], "source": [ "import msyrs" ] }, { "cell_type": "code", "execution_count": 3, "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": 4, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "shape: (5, 7)
real_datecidxcatvaluegradingeop_lagmop_lag
datestrstrf64f64i64i64
2010-03-03"USD""ADPEMPL_SA_P1M1ML1"-0.1738063.0333
2010-03-04"USD""ADPEMPL_SA_P1M1ML1"-0.1738063.0434
2010-03-05"USD""ADPEMPL_SA_P1M1ML1"-0.1738063.0535
2010-03-08"USD""ADPEMPL_SA_P1M1ML1"-0.1738063.0838
2010-03-09"USD""ADPEMPL_SA_P1M1ML1"-0.1738063.0939
" ], "text/plain": [ "shape: (5, 7)\n", "┌────────────┬─────┬────────────────────┬───────────┬─────────┬─────────┬─────────┐\n", "│ real_date ┆ cid ┆ xcat ┆ value ┆ grading ┆ eop_lag ┆ mop_lag │\n", "│ --- ┆ --- ┆ --- ┆ --- ┆ --- ┆ --- ┆ --- │\n", "│ date ┆ str ┆ str ┆ f64 ┆ f64 ┆ i64 ┆ i64 │\n", "╞════════════╪═════╪════════════════════╪═══════════╪═════════╪═════════╪═════════╡\n", "│ 2010-03-03 ┆ USD ┆ ADPEMPL_SA_P1M1ML1 ┆ -0.173806 ┆ 3.0 ┆ 3 ┆ 33 │\n", "│ 2010-03-04 ┆ USD ┆ ADPEMPL_SA_P1M1ML1 ┆ -0.173806 ┆ 3.0 ┆ 4 ┆ 34 │\n", "│ 2010-03-05 ┆ USD ┆ ADPEMPL_SA_P1M1ML1 ┆ -0.173806 ┆ 3.0 ┆ 5 ┆ 35 │\n", "│ 2010-03-08 ┆ USD ┆ ADPEMPL_SA_P1M1ML1 ┆ -0.173806 ┆ 3.0 ┆ 8 ┆ 38 │\n", "│ 2010-03-09 ┆ USD ┆ ADPEMPL_SA_P1M1ML1 ┆ -0.173806 ┆ 3.0 ┆ 9 ┆ 39 │\n", "└────────────┴─────┴────────────────────┴───────────┴─────────┴─────────┴─────────┘" ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" } ], "source": [ "dfpath = f\"{DATA_FOLDER_PATH}/data/ADPEMPL_SA_P1M1ML1/USD_ADPEMPL_SA_P1M1ML1.csv\"\n", "\n", "\n", "ldf: pl.DataFrame = msyrs.qdf.load_qdf(dfpath)\n", "ldf.head(5)" ] }, { "cell_type": "code", "execution_count": 5, "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": 6, "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": 7, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "shape: (5, 7)
real_datecidxcatvaluegradingeop_lagmop_lag
datestrstrf64f64i64i64
1990-04-26"AUD""CPIC_SA_P1M1ML12"6.4345992.026223
1990-04-27"AUD""CPIC_SA_P1M1ML12"6.4345992.027224
1990-04-30"AUD""CPIC_SA_P1M1ML12"6.4345992.030227
1990-05-01"AUD""CPIC_SA_P1M1ML12"6.4345992.031228
1990-05-02"AUD""CPIC_SA_P1M1ML12"6.4345992.032229
" ], "text/plain": [ "shape: (5, 7)\n", "┌────────────┬─────┬──────────────────┬──────────┬─────────┬─────────┬─────────┐\n", "│ real_date ┆ cid ┆ xcat ┆ value ┆ grading ┆ eop_lag ┆ mop_lag │\n", "│ --- ┆ --- ┆ --- ┆ --- ┆ --- ┆ --- ┆ --- │\n", "│ date ┆ str ┆ str ┆ f64 ┆ f64 ┆ i64 ┆ i64 │\n", "╞════════════╪═════╪══════════════════╪══════════╪═════════╪═════════╪═════════╡\n", "│ 1990-04-26 ┆ AUD ┆ CPIC_SA_P1M1ML12 ┆ 6.434599 ┆ 2.0 ┆ 26 ┆ 223 │\n", "│ 1990-04-27 ┆ AUD ┆ CPIC_SA_P1M1ML12 ┆ 6.434599 ┆ 2.0 ┆ 27 ┆ 224 │\n", "│ 1990-04-30 ┆ AUD ┆ CPIC_SA_P1M1ML12 ┆ 6.434599 ┆ 2.0 ┆ 30 ┆ 227 │\n", "│ 1990-05-01 ┆ AUD ┆ CPIC_SA_P1M1ML12 ┆ 6.434599 ┆ 2.0 ┆ 31 ┆ 228 │\n", "│ 1990-05-02 ┆ AUD ┆ CPIC_SA_P1M1ML12 ┆ 6.434599 ┆ 2.0 ┆ 32 ┆ 229 │\n", "└────────────┴─────┴──────────────────┴──────────┴─────────┴─────────┴─────────┘" ] }, "execution_count": 7, "metadata": {}, "output_type": "execute_result" } ], "source": [ "big_df: pl.DataFrame = msyrs.qdf.load_qdf_from_download_bank(\n", " folder_path=DATA_FOLDER_PATH, xcats=xcats\n", ")\n", "big_df.head(5)" ] }, { "cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "275.7717933654785" ] }, "execution_count": 8, "metadata": {}, "output_type": "execute_result" } ], "source": [ "big_df.estimated_size(\"mb\")" ] }, { "cell_type": "code", "execution_count": 9, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "870.6678009033203" ] }, "execution_count": 9, "metadata": {}, "output_type": "execute_result" } ], "source": [ "big_df.to_pandas().memory_usage(deep=True).sum() / 1024**2" ] }, { "cell_type": "code", "execution_count": 10, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "211.74823188781738" ] }, "execution_count": 10, "metadata": {}, "output_type": "execute_result" } ], "source": [ "macrosynergy.management.types.QuantamentalDataFrame(big_df.to_pandas()).memory_usage(\n", " deep=True\n", ").sum() / 1024**2" ] }, { "cell_type": "code", "execution_count": 11, "metadata": {}, "outputs": [], "source": [ "sel_cids = [\"USD\", \"EUR\", \"GBP\", \"AUD\", \"CAD\"]\n", "start = \"2024-11-14\"" ] }, { "cell_type": "code", "execution_count": 12, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "shape: (30, 7)
real_datecidxcatvaluegradingeop_lagmop_lag
datestrstrf64f64i64i64
2024-11-14"AUD""EQXR_NSA"0.3291881.000
2024-11-15"AUD""EQXR_NSA"0.8263461.000
2024-11-18"AUD""EQXR_NSA"0.1566831.000
2024-11-14"CAD""EQXR_NSA"0.1994021.000
2024-11-15"CAD""EQXR_NSA"-0.6965171.000
…………………
2024-11-15"GBP""EQXR_VT10"-0.0687781.000
2024-11-18"GBP""EQXR_VT10"0.4886261.000
2024-11-14"USD""EQXR_VT10"-0.5499831.000
2024-11-15"USD""EQXR_VT10"-1.1985441.000
2024-11-18"USD""EQXR_VT10"0.3493121.000
" ], "text/plain": [ "shape: (30, 7)\n", "┌────────────┬─────┬───────────┬───────────┬─────────┬─────────┬─────────┐\n", "│ real_date ┆ cid ┆ xcat ┆ value ┆ grading ┆ eop_lag ┆ mop_lag │\n", "│ --- ┆ --- ┆ --- ┆ --- ┆ --- ┆ --- ┆ --- │\n", "│ date ┆ str ┆ str ┆ f64 ┆ f64 ┆ i64 ┆ i64 │\n", "╞════════════╪═════╪═══════════╪═══════════╪═════════╪═════════╪═════════╡\n", "│ 2024-11-14 ┆ AUD ┆ EQXR_NSA ┆ 0.329188 ┆ 1.0 ┆ 0 ┆ 0 │\n", "│ 2024-11-15 ┆ AUD ┆ EQXR_NSA ┆ 0.826346 ┆ 1.0 ┆ 0 ┆ 0 │\n", "│ 2024-11-18 ┆ AUD ┆ EQXR_NSA ┆ 0.156683 ┆ 1.0 ┆ 0 ┆ 0 │\n", "│ 2024-11-14 ┆ CAD ┆ EQXR_NSA ┆ 0.199402 ┆ 1.0 ┆ 0 ┆ 0 │\n", "│ 2024-11-15 ┆ CAD ┆ EQXR_NSA ┆ -0.696517 ┆ 1.0 ┆ 0 ┆ 0 │\n", "│ … ┆ … ┆ … ┆ … ┆ … ┆ … ┆ … │\n", "│ 2024-11-15 ┆ GBP ┆ EQXR_VT10 ┆ -0.068778 ┆ 1.0 ┆ 0 ┆ 0 │\n", "│ 2024-11-18 ┆ GBP ┆ EQXR_VT10 ┆ 0.488626 ┆ 1.0 ┆ 0 ┆ 0 │\n", "│ 2024-11-14 ┆ USD ┆ EQXR_VT10 ┆ -0.549983 ┆ 1.0 ┆ 0 ┆ 0 │\n", "│ 2024-11-15 ┆ USD ┆ EQXR_VT10 ┆ -1.198544 ┆ 1.0 ┆ 0 ┆ 0 │\n", "│ 2024-11-18 ┆ USD ┆ EQXR_VT10 ┆ 0.349312 ┆ 1.0 ┆ 0 ┆ 0 │\n", "└────────────┴─────┴───────────┴───────────┴─────────┴─────────┴─────────┘" ] }, "execution_count": 12, "metadata": {}, "output_type": "execute_result" } ], "source": [ "eq_df = msyrs.qdf.reduce_dataframe(\n", " df=big_df,\n", " cids=sel_cids,\n", " xcats=[\"EQXR_NSA\", \"EQXR_VT10\"],\n", " start=start,\n", ")\n", "eq_df" ] }, { "cell_type": "code", "execution_count": 13, "metadata": {}, "outputs": [], "source": [ "fx_xcats = [xc for xc in xcats if xc.startswith(\"FX\")]\n", "fx_df = msyrs.qdf.reduce_dataframe(\n", " df=big_df, cids=sel_cids, start=start, xcats=fx_xcats, intersect=True\n", ")" ] }, { "cell_type": "code", "execution_count": 14, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "shape: (10, 7)
real_datecidxcatvaluegradingeop_lagmop_lag
datestrstrf64f64i64i64
2024-11-14"AUD""EQXR_NSA"0.3291881.000
2024-11-15"AUD""EQXR_NSA"0.8263461.000
2024-11-18"AUD""EQXR_NSA"0.1566831.000
2024-11-14"CAD""EQXR_NSA"0.1994021.000
2024-11-15"CAD""EQXR_NSA"-0.6965171.000
2024-11-18"CAD""EQXR_NSA"0.1469611.000
2024-11-14"EUR""EQXR_NSA"2.0248891.000
2024-11-15"EUR""EQXR_NSA"-0.6615671.000
2024-11-18"EUR""EQXR_NSA"-0.1456821.000
2024-11-14"GBP""EQXR_NSA"0.5965331.000
" ], "text/plain": [ "shape: (10, 7)\n", "┌────────────┬─────┬──────────┬───────────┬─────────┬─────────┬─────────┐\n", "│ real_date ┆ cid ┆ xcat ┆ value ┆ grading ┆ eop_lag ┆ mop_lag │\n", "│ --- ┆ --- ┆ --- ┆ --- ┆ --- ┆ --- ┆ --- │\n", "│ date ┆ str ┆ str ┆ f64 ┆ f64 ┆ i64 ┆ i64 │\n", "╞════════════╪═════╪══════════╪═══════════╪═════════╪═════════╪═════════╡\n", "│ 2024-11-14 ┆ AUD ┆ EQXR_NSA ┆ 0.329188 ┆ 1.0 ┆ 0 ┆ 0 │\n", "│ 2024-11-15 ┆ AUD ┆ EQXR_NSA ┆ 0.826346 ┆ 1.0 ┆ 0 ┆ 0 │\n", "│ 2024-11-18 ┆ AUD ┆ EQXR_NSA ┆ 0.156683 ┆ 1.0 ┆ 0 ┆ 0 │\n", "│ 2024-11-14 ┆ CAD ┆ EQXR_NSA ┆ 0.199402 ┆ 1.0 ┆ 0 ┆ 0 │\n", "│ 2024-11-15 ┆ CAD ┆ EQXR_NSA ┆ -0.696517 ┆ 1.0 ┆ 0 ┆ 0 │\n", "│ 2024-11-18 ┆ CAD ┆ EQXR_NSA ┆ 0.146961 ┆ 1.0 ┆ 0 ┆ 0 │\n", "│ 2024-11-14 ┆ EUR ┆ EQXR_NSA ┆ 2.024889 ┆ 1.0 ┆ 0 ┆ 0 │\n", "│ 2024-11-15 ┆ EUR ┆ EQXR_NSA ┆ -0.661567 ┆ 1.0 ┆ 0 ┆ 0 │\n", "│ 2024-11-18 ┆ EUR ┆ EQXR_NSA ┆ -0.145682 ┆ 1.0 ┆ 0 ┆ 0 │\n", "│ 2024-11-14 ┆ GBP ┆ EQXR_NSA ┆ 0.596533 ┆ 1.0 ┆ 0 ┆ 0 │\n", "└────────────┴─────┴──────────┴───────────┴─────────┴─────────┴─────────┘" ] }, "execution_count": 14, "metadata": {}, "output_type": "execute_result" } ], "source": [ "new_df: pl.DataFrame = msyrs.qdf.update_dataframe(df=eq_df, df_add=fx_df)\n", "\n", "new_df.head(10)" ] }, { "cell_type": "code", "execution_count": 15, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "shape: (10, 7)
real_datecidxcatvaluegradingeop_lagmop_lag
datestrstrf64f64i64i64
2024-11-18"AUD""FXXR_VT10"0.5185011.000
2024-11-14"CAD""FXXR_VT10"-1.1323141.000
2024-11-15"CAD""FXXR_VT10"-1.7556051.000
2024-11-18"CAD""FXXR_VT10"0.7516751.000
2024-11-14"EUR""FXXR_VT10"-0.2924221.000
2024-11-15"EUR""FXXR_VT10"-0.8551081.000
2024-11-18"EUR""FXXR_VT10"0.7918661.000
2024-11-14"GBP""FXXR_VT10"-0.1105261.000
2024-11-15"GBP""FXXR_VT10"-0.7009771.000
2024-11-18"GBP""FXXR_VT10"-0.1408051.000
" ], "text/plain": [ "shape: (10, 7)\n", "┌────────────┬─────┬───────────┬───────────┬─────────┬─────────┬─────────┐\n", "│ real_date ┆ cid ┆ xcat ┆ value ┆ grading ┆ eop_lag ┆ mop_lag │\n", "│ --- ┆ --- ┆ --- ┆ --- ┆ --- ┆ --- ┆ --- │\n", "│ date ┆ str ┆ str ┆ f64 ┆ f64 ┆ i64 ┆ i64 │\n", "╞════════════╪═════╪═══════════╪═══════════╪═════════╪═════════╪═════════╡\n", "│ 2024-11-18 ┆ AUD ┆ FXXR_VT10 ┆ 0.518501 ┆ 1.0 ┆ 0 ┆ 0 │\n", "│ 2024-11-14 ┆ CAD ┆ FXXR_VT10 ┆ -1.132314 ┆ 1.0 ┆ 0 ┆ 0 │\n", "│ 2024-11-15 ┆ CAD ┆ FXXR_VT10 ┆ -1.755605 ┆ 1.0 ┆ 0 ┆ 0 │\n", "│ 2024-11-18 ┆ CAD ┆ FXXR_VT10 ┆ 0.751675 ┆ 1.0 ┆ 0 ┆ 0 │\n", "│ 2024-11-14 ┆ EUR ┆ FXXR_VT10 ┆ -0.292422 ┆ 1.0 ┆ 0 ┆ 0 │\n", "│ 2024-11-15 ┆ EUR ┆ FXXR_VT10 ┆ -0.855108 ┆ 1.0 ┆ 0 ┆ 0 │\n", "│ 2024-11-18 ┆ EUR ┆ FXXR_VT10 ┆ 0.791866 ┆ 1.0 ┆ 0 ┆ 0 │\n", "│ 2024-11-14 ┆ GBP ┆ FXXR_VT10 ┆ -0.110526 ┆ 1.0 ┆ 0 ┆ 0 │\n", "│ 2024-11-15 ┆ GBP ┆ FXXR_VT10 ┆ -0.700977 ┆ 1.0 ┆ 0 ┆ 0 │\n", "│ 2024-11-18 ┆ GBP ┆ FXXR_VT10 ┆ -0.140805 ┆ 1.0 ┆ 0 ┆ 0 │\n", "└────────────┴─────┴───────────┴───────────┴─────────┴─────────┴─────────┘" ] }, "execution_count": 15, "metadata": {}, "output_type": "execute_result" } ], "source": [ "new_df.tail(10)" ] }, { "cell_type": "code", "execution_count": 16, "metadata": {}, "outputs": [ { "ename": "PanicException", "evalue": "called `Result::unwrap()` on an `Err` value: Duplicate(ErrString(\"unable to hstack, column with name \\\"value_right\\\" already exists\"))", "output_type": "error", "traceback": [ "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", "\u001b[1;31mPanicException\u001b[0m Traceback (most recent call last)", "Cell \u001b[1;32mIn[16], line 1\u001b[0m\n\u001b[1;32m----> 1\u001b[0m \u001b[43mmsyrs\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mqdf\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mpivot_dataframe_by_ticker\u001b[49m\u001b[43m(\u001b[49m\u001b[43mdf\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mnew_df\u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241m.\u001b[39mhead(\u001b[38;5;241m10\u001b[39m)\n", "\u001b[1;31mPanicException\u001b[0m: called `Result::unwrap()` on an `Err` value: Duplicate(ErrString(\"unable to hstack, column with name \\\"value_right\\\" already exists\"))" ] } ], "source": [ "msyrs.qdf.pivot_dataframe_by_ticker(df=new_df).head(10)" ] } ], "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": "3.11.0" } }, "nbformat": 4, "nbformat_minor": 4 }