mirror of
https://github.com/Magnus167/msyrs.git
synced 2025-08-20 09:59:59 +00:00
736 lines
31 KiB
Plaintext
736 lines
31 KiB
Plaintext
{
|
|
"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",
|
|
"\n",
|
|
"# source .venv/bin/activate\n",
|
|
"./.venv/Scripts/activate\n",
|
|
"\n",
|
|
"pip install maturin ipywidgets\n",
|
|
"\n",
|
|
"maturin develop --release\n",
|
|
"```\n"
|
|
]
|
|
},
|
|
{
|
|
"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": [],
|
|
"source": [
|
|
"import time\n",
|
|
"\n",
|
|
"nb_start_time = time.time()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 5,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Time taken to load qdf: 0.007575511932373047\n"
|
|
]
|
|
},
|
|
{
|
|
"data": {
|
|
"text/html": [
|
|
"<div><style>\n",
|
|
".dataframe > thead > tr,\n",
|
|
".dataframe > tbody > tr {\n",
|
|
" text-align: right;\n",
|
|
" white-space: pre-wrap;\n",
|
|
"}\n",
|
|
"</style>\n",
|
|
"<small>shape: (5, 7)</small><table border=\"1\" class=\"dataframe\"><thead><tr><th>real_date</th><th>cid</th><th>xcat</th><th>value</th><th>grading</th><th>eop_lag</th><th>mop_lag</th></tr><tr><td>date</td><td>str</td><td>str</td><td>f64</td><td>f64</td><td>i64</td><td>i64</td></tr></thead><tbody><tr><td>2010-03-03</td><td>"USD"</td><td>"ADPEMPL_SA_P1M1ML1"</td><td>-0.173806</td><td>3.0</td><td>3</td><td>33</td></tr><tr><td>2010-03-04</td><td>"USD"</td><td>"ADPEMPL_SA_P1M1ML1"</td><td>-0.173806</td><td>3.0</td><td>4</td><td>34</td></tr><tr><td>2010-03-05</td><td>"USD"</td><td>"ADPEMPL_SA_P1M1ML1"</td><td>-0.173806</td><td>3.0</td><td>5</td><td>35</td></tr><tr><td>2010-03-08</td><td>"USD"</td><td>"ADPEMPL_SA_P1M1ML1"</td><td>-0.173806</td><td>3.0</td><td>8</td><td>38</td></tr><tr><td>2010-03-09</td><td>"USD"</td><td>"ADPEMPL_SA_P1M1ML1"</td><td>-0.173806</td><td>3.0</td><td>9</td><td>39</td></tr></tbody></table></div>"
|
|
],
|
|
"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": 5,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"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": 6,
|
|
"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": 7,
|
|
"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": 8,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Downloading the JPMAQS catalogue from DataQuery...\n",
|
|
"Downloaded JPMAQS catalogue with 18711 tickers.\n",
|
|
"Removed 21/600 expressions that are not in the JPMaQS catalogue.\n",
|
|
"Downloading data from JPMaQS.\n",
|
|
"Timestamp UTC: 2024-11-22 17:13:07\n",
|
|
"Connection successful!\n"
|
|
]
|
|
},
|
|
{
|
|
"name": "stderr",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Requesting data: 100%|██████████| 29/29 [00:05<00:00, 4.91it/s]\n",
|
|
"Downloading data: 100%|██████████| 29/29 [00:22<00:00, 1.26it/s]\n"
|
|
]
|
|
},
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Some dates are missing from the downloaded data. \n",
|
|
"2 out of 9107 dates are missing.\n"
|
|
]
|
|
}
|
|
],
|
|
"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": 9,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Time taken to load qdf batch: 1.8986454010009766\n"
|
|
]
|
|
},
|
|
{
|
|
"data": {
|
|
"text/html": [
|
|
"<div><style>\n",
|
|
".dataframe > thead > tr,\n",
|
|
".dataframe > tbody > tr {\n",
|
|
" text-align: right;\n",
|
|
" white-space: pre-wrap;\n",
|
|
"}\n",
|
|
"</style>\n",
|
|
"<small>shape: (5, 7)</small><table border=\"1\" class=\"dataframe\"><thead><tr><th>real_date</th><th>cid</th><th>xcat</th><th>value</th><th>grading</th><th>eop_lag</th><th>mop_lag</th></tr><tr><td>date</td><td>str</td><td>str</td><td>f64</td><td>f64</td><td>i64</td><td>i64</td></tr></thead><tbody><tr><td>1990-04-26</td><td>"AUD"</td><td>"CPIC_SA_P1M1ML12"</td><td>6.434599</td><td>2.0</td><td>26</td><td>223</td></tr><tr><td>1990-04-27</td><td>"AUD"</td><td>"CPIC_SA_P1M1ML12"</td><td>6.434599</td><td>2.0</td><td>27</td><td>224</td></tr><tr><td>1990-04-30</td><td>"AUD"</td><td>"CPIC_SA_P1M1ML12"</td><td>6.434599</td><td>2.0</td><td>30</td><td>227</td></tr><tr><td>1990-05-01</td><td>"AUD"</td><td>"CPIC_SA_P1M1ML12"</td><td>6.434599</td><td>2.0</td><td>31</td><td>228</td></tr><tr><td>1990-05-02</td><td>"AUD"</td><td>"CPIC_SA_P1M1ML12"</td><td>6.434599</td><td>2.0</td><td>32</td><td>229</td></tr></tbody></table></div>"
|
|
],
|
|
"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": 9,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"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": 10,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"275.89989376068115"
|
|
]
|
|
},
|
|
"execution_count": 10,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"big_df.estimated_size(\"mb\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 11,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"871.0723962783813"
|
|
]
|
|
},
|
|
"execution_count": 11,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"big_df.to_pandas().memory_usage(deep=True).sum() / 1024**2"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 12,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"211.8466453552246"
|
|
]
|
|
},
|
|
"execution_count": 12,
|
|
"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": 13,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"sel_cids = [\"USD\", \"EUR\", \"GBP\", \"AUD\", \"CAD\"]\n",
|
|
"start = \"1999-11-14\""
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 14,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Time taken to reduce qdf: 0.34674978256225586\n"
|
|
]
|
|
},
|
|
{
|
|
"data": {
|
|
"text/html": [
|
|
"<div><style>\n",
|
|
".dataframe > thead > tr,\n",
|
|
".dataframe > tbody > tr {\n",
|
|
" text-align: right;\n",
|
|
" white-space: pre-wrap;\n",
|
|
"}\n",
|
|
"</style>\n",
|
|
"<small>shape: (62_363, 7)</small><table border=\"1\" class=\"dataframe\"><thead><tr><th>real_date</th><th>cid</th><th>xcat</th><th>value</th><th>grading</th><th>eop_lag</th><th>mop_lag</th></tr><tr><td>date</td><td>str</td><td>str</td><td>f64</td><td>f64</td><td>i64</td><td>i64</td></tr></thead><tbody><tr><td>2000-05-04</td><td>"AUD"</td><td>"EQXR_NSA"</td><td>-1.251605</td><td>1.0</td><td>0</td><td>0</td></tr><tr><td>2000-05-05</td><td>"AUD"</td><td>"EQXR_NSA"</td><td>1.787455</td><td>1.0</td><td>0</td><td>0</td></tr><tr><td>2000-05-08</td><td>"AUD"</td><td>"EQXR_NSA"</td><td>-0.574713</td><td>1.0</td><td>0</td><td>0</td></tr><tr><td>2000-05-09</td><td>"AUD"</td><td>"EQXR_NSA"</td><td>-0.931278</td><td>1.0</td><td>0</td><td>0</td></tr><tr><td>2000-05-10</td><td>"AUD"</td><td>"EQXR_NSA"</td><td>-1.523501</td><td>1.0</td><td>0</td><td>0</td></tr><tr><td>…</td><td>…</td><td>…</td><td>…</td><td>…</td><td>…</td><td>…</td></tr><tr><td>2024-11-15</td><td>"USD"</td><td>"EQXR_VT10"</td><td>-1.198544</td><td>1.0</td><td>0</td><td>0</td></tr><tr><td>2024-11-18</td><td>"USD"</td><td>"EQXR_VT10"</td><td>0.349312</td><td>1.0</td><td>0</td><td>0</td></tr><tr><td>2024-11-19</td><td>"USD"</td><td>"EQXR_VT10"</td><td>0.2776</td><td>1.0</td><td>0</td><td>0</td></tr><tr><td>2024-11-20</td><td>"USD"</td><td>"EQXR_VT10"</td><td>-0.014759</td><td>1.0</td><td>0</td><td>0</td></tr><tr><td>2024-11-21</td><td>"USD"</td><td>"EQXR_VT10"</td><td>0.483426</td><td>1.0</td><td>0</td><td>0</td></tr></tbody></table></div>"
|
|
],
|
|
"text/plain": [
|
|
"shape: (62_363, 7)\n",
|
|
"┌────────────┬─────┬───────────┬───────────┬─────────┬─────────┬─────────┐\n",
|
|
"│ real_date ┆ cid ┆ xcat ┆ value ┆ grading ┆ eop_lag ┆ mop_lag │\n",
|
|
"│ --- ┆ --- ┆ --- ┆ --- ┆ --- ┆ --- ┆ --- │\n",
|
|
"│ date ┆ str ┆ str ┆ f64 ┆ f64 ┆ i64 ┆ i64 │\n",
|
|
"╞════════════╪═════╪═══════════╪═══════════╪═════════╪═════════╪═════════╡\n",
|
|
"│ 2000-05-04 ┆ AUD ┆ EQXR_NSA ┆ -1.251605 ┆ 1.0 ┆ 0 ┆ 0 │\n",
|
|
"│ 2000-05-05 ┆ AUD ┆ EQXR_NSA ┆ 1.787455 ┆ 1.0 ┆ 0 ┆ 0 │\n",
|
|
"│ 2000-05-08 ┆ AUD ┆ EQXR_NSA ┆ -0.574713 ┆ 1.0 ┆ 0 ┆ 0 │\n",
|
|
"│ 2000-05-09 ┆ AUD ┆ EQXR_NSA ┆ -0.931278 ┆ 1.0 ┆ 0 ┆ 0 │\n",
|
|
"│ 2000-05-10 ┆ AUD ┆ EQXR_NSA ┆ -1.523501 ┆ 1.0 ┆ 0 ┆ 0 │\n",
|
|
"│ … ┆ … ┆ … ┆ … ┆ … ┆ … ┆ … │\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",
|
|
"│ 2024-11-19 ┆ USD ┆ EQXR_VT10 ┆ 0.2776 ┆ 1.0 ┆ 0 ┆ 0 │\n",
|
|
"│ 2024-11-20 ┆ USD ┆ EQXR_VT10 ┆ -0.014759 ┆ 1.0 ┆ 0 ┆ 0 │\n",
|
|
"│ 2024-11-21 ┆ USD ┆ EQXR_VT10 ┆ 0.483426 ┆ 1.0 ┆ 0 ┆ 0 │\n",
|
|
"└────────────┴─────┴───────────┴───────────┴─────────┴─────────┴─────────┘"
|
|
]
|
|
},
|
|
"execution_count": 14,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"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": 15,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Time taken to reduce qdf: 0.13223624229431152\n"
|
|
]
|
|
}
|
|
],
|
|
"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": 16,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Time taken to reduce qdf: 0.3902719020843506\n"
|
|
]
|
|
}
|
|
],
|
|
"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": 17,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Time taken to reduce qdf: 0.171736478805542\n"
|
|
]
|
|
}
|
|
],
|
|
"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": 18,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Time taken: 0.024325132369995117\n"
|
|
]
|
|
},
|
|
{
|
|
"data": {
|
|
"text/html": [
|
|
"<div><style>\n",
|
|
".dataframe > thead > tr,\n",
|
|
".dataframe > tbody > tr {\n",
|
|
" text-align: right;\n",
|
|
" white-space: pre-wrap;\n",
|
|
"}\n",
|
|
"</style>\n",
|
|
"<small>shape: (10, 7)</small><table border=\"1\" class=\"dataframe\"><thead><tr><th>real_date</th><th>cid</th><th>xcat</th><th>value</th><th>grading</th><th>eop_lag</th><th>mop_lag</th></tr><tr><td>date</td><td>str</td><td>str</td><td>f64</td><td>f64</td><td>i64</td><td>i64</td></tr></thead><tbody><tr><td>2000-05-04</td><td>"AUD"</td><td>"EQXR_NSA"</td><td>-1.251605</td><td>1.0</td><td>0</td><td>0</td></tr><tr><td>2000-05-05</td><td>"AUD"</td><td>"EQXR_NSA"</td><td>1.787455</td><td>1.0</td><td>0</td><td>0</td></tr><tr><td>2000-05-08</td><td>"AUD"</td><td>"EQXR_NSA"</td><td>-0.574713</td><td>1.0</td><td>0</td><td>0</td></tr><tr><td>2000-05-09</td><td>"AUD"</td><td>"EQXR_NSA"</td><td>-0.931278</td><td>1.0</td><td>0</td><td>0</td></tr><tr><td>2000-05-10</td><td>"AUD"</td><td>"EQXR_NSA"</td><td>-1.523501</td><td>1.0</td><td>0</td><td>0</td></tr><tr><td>2000-05-11</td><td>"AUD"</td><td>"EQXR_NSA"</td><td>-1.579987</td><td>1.0</td><td>0</td><td>0</td></tr><tr><td>2000-05-12</td><td>"AUD"</td><td>"EQXR_NSA"</td><td>1.80602</td><td>1.0</td><td>0</td><td>0</td></tr><tr><td>2000-05-15</td><td>"AUD"</td><td>"EQXR_NSA"</td><td>0.295664</td><td>1.0</td><td>0</td><td>0</td></tr><tr><td>2000-05-16</td><td>"AUD"</td><td>"EQXR_NSA"</td><td>1.310187</td><td>1.0</td><td>0</td><td>0</td></tr><tr><td>2000-05-17</td><td>"AUD"</td><td>"EQXR_NSA"</td><td>-0.711284</td><td>1.0</td><td>0</td><td>0</td></tr></tbody></table></div>"
|
|
],
|
|
"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",
|
|
"│ 2000-05-04 ┆ AUD ┆ EQXR_NSA ┆ -1.251605 ┆ 1.0 ┆ 0 ┆ 0 │\n",
|
|
"│ 2000-05-05 ┆ AUD ┆ EQXR_NSA ┆ 1.787455 ┆ 1.0 ┆ 0 ┆ 0 │\n",
|
|
"│ 2000-05-08 ┆ AUD ┆ EQXR_NSA ┆ -0.574713 ┆ 1.0 ┆ 0 ┆ 0 │\n",
|
|
"│ 2000-05-09 ┆ AUD ┆ EQXR_NSA ┆ -0.931278 ┆ 1.0 ┆ 0 ┆ 0 │\n",
|
|
"│ 2000-05-10 ┆ AUD ┆ EQXR_NSA ┆ -1.523501 ┆ 1.0 ┆ 0 ┆ 0 │\n",
|
|
"│ 2000-05-11 ┆ AUD ┆ EQXR_NSA ┆ -1.579987 ┆ 1.0 ┆ 0 ┆ 0 │\n",
|
|
"│ 2000-05-12 ┆ AUD ┆ EQXR_NSA ┆ 1.80602 ┆ 1.0 ┆ 0 ┆ 0 │\n",
|
|
"│ 2000-05-15 ┆ AUD ┆ EQXR_NSA ┆ 0.295664 ┆ 1.0 ┆ 0 ┆ 0 │\n",
|
|
"│ 2000-05-16 ┆ AUD ┆ EQXR_NSA ┆ 1.310187 ┆ 1.0 ┆ 0 ┆ 0 │\n",
|
|
"│ 2000-05-17 ┆ AUD ┆ EQXR_NSA ┆ -0.711284 ┆ 1.0 ┆ 0 ┆ 0 │\n",
|
|
"└────────────┴─────┴──────────┴───────────┴─────────┴─────────┴─────────┘"
|
|
]
|
|
},
|
|
"execution_count": 18,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"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": 19,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Time taken: 0.8326597213745117\n"
|
|
]
|
|
}
|
|
],
|
|
"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": 20,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/html": [
|
|
"<div><style>\n",
|
|
".dataframe > thead > tr,\n",
|
|
".dataframe > tbody > tr {\n",
|
|
" text-align: right;\n",
|
|
" white-space: pre-wrap;\n",
|
|
"}\n",
|
|
"</style>\n",
|
|
"<small>shape: (10, 7)</small><table border=\"1\" class=\"dataframe\"><thead><tr><th>real_date</th><th>cid</th><th>xcat</th><th>value</th><th>grading</th><th>eop_lag</th><th>mop_lag</th></tr><tr><td>date</td><td>str</td><td>str</td><td>f64</td><td>f64</td><td>i64</td><td>i64</td></tr></thead><tbody><tr><td>2024-11-07</td><td>"GBP"</td><td>"FXXR_VT10"</td><td>0.806682</td><td>1.0</td><td>0</td><td>0</td></tr><tr><td>2024-11-08</td><td>"GBP"</td><td>"FXXR_VT10"</td><td>-0.247346</td><td>1.0</td><td>0</td><td>0</td></tr><tr><td>2024-11-12</td><td>"GBP"</td><td>"FXXR_VT10"</td><td>-1.083137</td><td>1.0</td><td>0</td><td>0</td></tr><tr><td>2024-11-13</td><td>"GBP"</td><td>"FXXR_VT10"</td><td>-0.328958</td><td>1.0</td><td>0</td><td>0</td></tr><tr><td>2024-11-14</td><td>"GBP"</td><td>"FXXR_VT10"</td><td>-0.110526</td><td>1.0</td><td>0</td><td>0</td></tr><tr><td>2024-11-15</td><td>"GBP"</td><td>"FXXR_VT10"</td><td>-0.700977</td><td>1.0</td><td>0</td><td>0</td></tr><tr><td>2024-11-18</td><td>"GBP"</td><td>"FXXR_VT10"</td><td>-0.140805</td><td>1.0</td><td>0</td><td>0</td></tr><tr><td>2024-11-19</td><td>"GBP"</td><td>"FXXR_VT10"</td><td>0.223372</td><td>1.0</td><td>0</td><td>0</td></tr><tr><td>2024-11-20</td><td>"GBP"</td><td>"FXXR_VT10"</td><td>0.361783</td><td>1.0</td><td>0</td><td>0</td></tr><tr><td>2024-11-21</td><td>"GBP"</td><td>"FXXR_VT10"</td><td>-0.375365</td><td>1.0</td><td>0</td><td>0</td></tr></tbody></table></div>"
|
|
],
|
|
"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",
|
|
"│ 2024-11-07 ┆ GBP ┆ FXXR_VT10 ┆ 0.806682 ┆ 1.0 ┆ 0 ┆ 0 │\n",
|
|
"│ 2024-11-08 ┆ GBP ┆ FXXR_VT10 ┆ -0.247346 ┆ 1.0 ┆ 0 ┆ 0 │\n",
|
|
"│ 2024-11-12 ┆ GBP ┆ FXXR_VT10 ┆ -1.083137 ┆ 1.0 ┆ 0 ┆ 0 │\n",
|
|
"│ 2024-11-13 ┆ GBP ┆ FXXR_VT10 ┆ -0.328958 ┆ 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",
|
|
"│ 2024-11-19 ┆ GBP ┆ FXXR_VT10 ┆ 0.223372 ┆ 1.0 ┆ 0 ┆ 0 │\n",
|
|
"│ 2024-11-20 ┆ GBP ┆ FXXR_VT10 ┆ 0.361783 ┆ 1.0 ┆ 0 ┆ 0 │\n",
|
|
"│ 2024-11-21 ┆ GBP ┆ FXXR_VT10 ┆ -0.375365 ┆ 1.0 ┆ 0 ┆ 0 │\n",
|
|
"└────────────┴─────┴───────────┴───────────┴─────────┴─────────┴─────────┘"
|
|
]
|
|
},
|
|
"execution_count": 20,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"new_df.tail(10)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 21,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Time taken: 0.0014519691467285156\n",
|
|
"Time taken: 0.0\n"
|
|
]
|
|
}
|
|
],
|
|
"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=252,\n",
|
|
" lback_method=\"calendar\",\n",
|
|
" half_life=None,\n",
|
|
" start=None,\n",
|
|
" end=None,\n",
|
|
" est_freq=None,\n",
|
|
" remove_zeros=None,\n",
|
|
" postfix=\"_HV\",\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)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 22,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Time taken: 0.054981231689453125\n"
|
|
]
|
|
}
|
|
],
|
|
"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": 23,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"new_pd_df = macrosynergy.management.types.QuantamentalDataFrame(new_pd_df)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 24,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Time taken: 2.785749673843384\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"starttime = time.time()\n",
|
|
"new_pd_df.to_wide()\n",
|
|
"print(\"Time taken: \", time.time() - starttime)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 25,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Time taken: 58.54259753227234 seconds\n"
|
|
]
|
|
}
|
|
],
|
|
"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": "3.11.0"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 4
|
|
}
|