python working with notebook!

2025-08-20 04:20:00 +00:00 · 2024-11-17 23:58:47 +00:00 · 2024-11-17 23:58:47 +00:00 · bba5acd724
commit bba5acd724
parent 09f74916e8
13 changed files with 586 additions and 79 deletions
--- a/Cargo.toml
+++ b/Cargo.toml
@ -31,8 +31,8 @@ futures = "0.3"
 # pyo3 = { version = "0.23.1", features = ["extension-module"] }
 # pyo3 = { version = "0.21.2", features = ["extension-module"] }
 # pyo3 = { version = "*", features = ["abi3-py38"] }
-pyo3 = { version = "*", features = ["extension-module"] }
-pyo3-polars = { version = "0.18.0" }
+pyo3 = { version = "*", features = ["extension-module", "abi3-py37"] }
+pyo3-polars = { version = "*" }
 polars = { version = "*", features = [
    "lazy",
    "temporal",
@ -40,6 +40,7 @@ polars = { version = "*", features = [
    "json",
    "parquet",
    "dtype-datetime",
+    # "dtype-categorical",
    "strings",
    "timezones",
    "ndarray",
--- a/README.md
+++ b/README.md
@ -2,33 +2,30 @@

 A Rust implementation of the [Macrosynergy Python Package](https://github.com/macrosynergy/macrosynergy).

-## Running Notebook
+## Build and install the Python package

 ```bash
-cargo install evcxr_jupyter
-evcxr_jupyter --install
-pip install jupyterlab
-jupyter lab
+python -m venv .venv
+# source .venv/bin/activate
+./.venv/Scripts/activate
+pip install maturin
+maturin develop --release
 ```

-Or try following this guide here: [DataCrayon - Setup Jupyter with Rust](https://datacrayon.com/data-analysis-with-rust-notebooks/setup-anaconda-jupyter-and-rust/)
-
 ## Status

- Download
+- [x] Download

-  - [x] Get Catalogue
-  - [x] Get Generic DQ Time Series
-  - [x] Get JPMaQS Indicators as Polars DataFrame
-  - [ ] Save to disk functionality
-    - [x] Hacky iterative method
-    - [ ] Non-hacky way to save to disk
+  - [ ] Pending: Optimize thread pool

 - Utils

-  - [ ] Reduce DF
+  - [ ] QDF
+    - [x] Read QDF
+    - [x] Reduce DF
+    - [x] Update DF
+    - [ ] Get Blacklist
    - [ ] Apply Blacklist
-  - [ ] Update DF

 - Panel
  - [ ] Historic Volatility
--- a/notebooks/python-notebook.ipynb
+++ b/notebooks/python-notebook.ipynb
@ -0,0 +1,364 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Build and 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\n",
+    "\n",
+    "maturin develop --release\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "e:\\Work\\ruzt\\msyrs\\.venv\\Lib\\site-packages\\tqdm\\auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
+      "  from .autonotebook import tqdm as notebook_tqdm\n"
+     ]
+    }
+   ],
+   "source": [
+    "import macrosynergy\n",
+    "import pandas as pd\n",
+    "import numpy as np\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import msyrs\n",
+    "import polars as pl"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "DATA_FOLDER_PATH = \"E:/Work/jpmaqs-data\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "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: (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>&quot;USD&quot;</td><td>&quot;ADPEMPL_SA_P1M1ML1&quot;</td><td>-0.173806</td><td>3.0</td><td>3</td><td>33</td></tr><tr><td>2010-03-04</td><td>&quot;USD&quot;</td><td>&quot;ADPEMPL_SA_P1M1ML1&quot;</td><td>-0.173806</td><td>3.0</td><td>4</td><td>34</td></tr><tr><td>2010-03-05</td><td>&quot;USD&quot;</td><td>&quot;ADPEMPL_SA_P1M1ML1&quot;</td><td>-0.173806</td><td>3.0</td><td>5</td><td>35</td></tr><tr><td>2010-03-08</td><td>&quot;USD&quot;</td><td>&quot;ADPEMPL_SA_P1M1ML1&quot;</td><td>-0.173806</td><td>3.0</td><td>8</td><td>38</td></tr><tr><td>2010-03-09</td><td>&quot;USD&quot;</td><td>&quot;ADPEMPL_SA_P1M1ML1&quot;</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": 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",
+    "[\"CPIC\", \"CPIH\", \"INFTEFF\", \"INTRGDP\", \"INTRGDPv5Y\", \"PCREDITGDP\", \"RGDP\", \"RYLDIRS\", \"PCREDITBN\"]\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": [
+    {
+     "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>&quot;AUD&quot;</td><td>&quot;CPIC_SA_P1M1ML12&quot;</td><td>6.434599</td><td>2.0</td><td>26</td><td>223</td></tr><tr><td>1990-04-27</td><td>&quot;AUD&quot;</td><td>&quot;CPIC_SA_P1M1ML12&quot;</td><td>6.434599</td><td>2.0</td><td>27</td><td>224</td></tr><tr><td>1990-04-30</td><td>&quot;AUD&quot;</td><td>&quot;CPIC_SA_P1M1ML12&quot;</td><td>6.434599</td><td>2.0</td><td>30</td><td>227</td></tr><tr><td>1990-05-01</td><td>&quot;AUD&quot;</td><td>&quot;CPIC_SA_P1M1ML12&quot;</td><td>6.434599</td><td>2.0</td><td>31</td><td>228</td></tr><tr><td>1990-05-02</td><td>&quot;AUD&quot;</td><td>&quot;CPIC_SA_P1M1ML12&quot;</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": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "big_df: pl.DataFrame = msyrs.qdf.load_qdf_from_download_bank(\n",
+    "    folder_path=DATA_FOLDER_PATH, tickers=tickers\n",
+    ")\n",
+    "big_df.head(5)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "sel_cids = [\"USD\", \"EUR\", \"GBP\", \"AUD\", \"CAD\"]\n",
+    "start = \"2024-11-14\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "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: (20, 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>2024-11-14</td><td>&quot;AUD&quot;</td><td>&quot;EQXR_NSA&quot;</td><td>0.329188</td><td>1.0</td><td>0</td><td>0</td></tr><tr><td>2024-11-15</td><td>&quot;AUD&quot;</td><td>&quot;EQXR_NSA&quot;</td><td>0.826346</td><td>1.0</td><td>0</td><td>0</td></tr><tr><td>2024-11-14</td><td>&quot;CAD&quot;</td><td>&quot;EQXR_NSA&quot;</td><td>0.199402</td><td>1.0</td><td>0</td><td>0</td></tr><tr><td>2024-11-15</td><td>&quot;CAD&quot;</td><td>&quot;EQXR_NSA&quot;</td><td>-0.696517</td><td>1.0</td><td>0</td><td>0</td></tr><tr><td>2024-11-14</td><td>&quot;EUR&quot;</td><td>&quot;EQXR_NSA&quot;</td><td>2.024889</td><td>1.0</td><td>0</td><td>0</td></tr><tr><td>&hellip;</td><td>&hellip;</td><td>&hellip;</td><td>&hellip;</td><td>&hellip;</td><td>&hellip;</td><td>&hellip;</td></tr><tr><td>2024-11-15</td><td>&quot;EUR&quot;</td><td>&quot;EQXR_VT10&quot;</td><td>-0.477901</td><td>1.0</td><td>0</td><td>0</td></tr><tr><td>2024-11-14</td><td>&quot;GBP&quot;</td><td>&quot;EQXR_VT10&quot;</td><td>0.664208</td><td>1.0</td><td>0</td><td>0</td></tr><tr><td>2024-11-15</td><td>&quot;GBP&quot;</td><td>&quot;EQXR_VT10&quot;</td><td>-0.068778</td><td>1.0</td><td>0</td><td>0</td></tr><tr><td>2024-11-14</td><td>&quot;USD&quot;</td><td>&quot;EQXR_VT10&quot;</td><td>-0.549983</td><td>1.0</td><td>0</td><td>0</td></tr><tr><td>2024-11-15</td><td>&quot;USD&quot;</td><td>&quot;EQXR_VT10&quot;</td><td>-1.198544</td><td>1.0</td><td>0</td><td>0</td></tr></tbody></table></div>"
+      ],
+      "text/plain": [
+       "shape: (20, 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",
+       "│ 2024-11-14 ┆ CAD ┆ EQXR_NSA  ┆ 0.199402  ┆ 1.0     ┆ 0       ┆ 0       │\n",
+       "│ 2024-11-15 ┆ CAD ┆ EQXR_NSA  ┆ -0.696517 ┆ 1.0     ┆ 0       ┆ 0       │\n",
+       "│ 2024-11-14 ┆ EUR ┆ EQXR_NSA  ┆ 2.024889  ┆ 1.0     ┆ 0       ┆ 0       │\n",
+       "│ …          ┆ …   ┆ …         ┆ …         ┆ …       ┆ …       ┆ …       │\n",
+       "│ 2024-11-15 ┆ EUR ┆ EQXR_VT10 ┆ -0.477901 ┆ 1.0     ┆ 0       ┆ 0       │\n",
+       "│ 2024-11-14 ┆ GBP ┆ EQXR_VT10 ┆ 0.664208  ┆ 1.0     ┆ 0       ┆ 0       │\n",
+       "│ 2024-11-15 ┆ GBP ┆ EQXR_VT10 ┆ -0.068778 ┆ 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",
+       "└────────────┴─────┴───────────┴───────────┴─────────┴─────────┴─────────┘"
+      ]
+     },
+     "execution_count": 8,
+     "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": 9,
+   "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": 10,
+   "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>2024-11-14</td><td>&quot;AUD&quot;</td><td>&quot;EQXR_NSA&quot;</td><td>0.329188</td><td>1.0</td><td>0</td><td>0</td></tr><tr><td>2024-11-15</td><td>&quot;AUD&quot;</td><td>&quot;EQXR_NSA&quot;</td><td>0.826346</td><td>1.0</td><td>0</td><td>0</td></tr><tr><td>2024-11-14</td><td>&quot;CAD&quot;</td><td>&quot;EQXR_NSA&quot;</td><td>0.199402</td><td>1.0</td><td>0</td><td>0</td></tr><tr><td>2024-11-15</td><td>&quot;CAD&quot;</td><td>&quot;EQXR_NSA&quot;</td><td>-0.696517</td><td>1.0</td><td>0</td><td>0</td></tr><tr><td>2024-11-14</td><td>&quot;EUR&quot;</td><td>&quot;EQXR_NSA&quot;</td><td>2.024889</td><td>1.0</td><td>0</td><td>0</td></tr><tr><td>2024-11-15</td><td>&quot;EUR&quot;</td><td>&quot;EQXR_NSA&quot;</td><td>-0.661567</td><td>1.0</td><td>0</td><td>0</td></tr><tr><td>2024-11-14</td><td>&quot;GBP&quot;</td><td>&quot;EQXR_NSA&quot;</td><td>0.596533</td><td>1.0</td><td>0</td><td>0</td></tr><tr><td>2024-11-15</td><td>&quot;GBP&quot;</td><td>&quot;EQXR_NSA&quot;</td><td>-0.06177</td><td>1.0</td><td>0</td><td>0</td></tr><tr><td>2024-11-14</td><td>&quot;USD&quot;</td><td>&quot;EQXR_NSA&quot;</td><td>-0.627493</td><td>1.0</td><td>0</td><td>0</td></tr><tr><td>2024-11-15</td><td>&quot;USD&quot;</td><td>&quot;EQXR_NSA&quot;</td><td>-1.367457</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",
+       "│ 2024-11-14 ┆ AUD ┆ EQXR_NSA ┆ 0.329188  ┆ 1.0     ┆ 0       ┆ 0       │\n",
+       "│ 2024-11-15 ┆ AUD ┆ EQXR_NSA ┆ 0.826346  ┆ 1.0     ┆ 0       ┆ 0       │\n",
+       "│ 2024-11-14 ┆ CAD ┆ EQXR_NSA ┆ 0.199402  ┆ 1.0     ┆ 0       ┆ 0       │\n",
+       "│ 2024-11-15 ┆ CAD ┆ EQXR_NSA ┆ -0.696517 ┆ 1.0     ┆ 0       ┆ 0       │\n",
+       "│ 2024-11-14 ┆ EUR ┆ EQXR_NSA ┆ 2.024889  ┆ 1.0     ┆ 0       ┆ 0       │\n",
+       "│ 2024-11-15 ┆ EUR ┆ EQXR_NSA ┆ -0.661567 ┆ 1.0     ┆ 0       ┆ 0       │\n",
+       "│ 2024-11-14 ┆ GBP ┆ EQXR_NSA ┆ 0.596533  ┆ 1.0     ┆ 0       ┆ 0       │\n",
+       "│ 2024-11-15 ┆ GBP ┆ EQXR_NSA ┆ -0.06177  ┆ 1.0     ┆ 0       ┆ 0       │\n",
+       "│ 2024-11-14 ┆ USD ┆ EQXR_NSA ┆ -0.627493 ┆ 1.0     ┆ 0       ┆ 0       │\n",
+       "│ 2024-11-15 ┆ USD ┆ EQXR_NSA ┆ -1.367457 ┆ 1.0     ┆ 0       ┆ 0       │\n",
+       "└────────────┴─────┴──────────┴───────────┴─────────┴─────────┴─────────┘"
+      ]
+     },
+     "execution_count": 10,
+     "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": 11,
+   "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>2024-11-14</td><td>&quot;GBP&quot;</td><td>&quot;FXXR_NSA&quot;</td><td>-0.067809</td><td>1.0</td><td>0</td><td>0</td></tr><tr><td>2024-11-15</td><td>&quot;GBP&quot;</td><td>&quot;FXXR_NSA&quot;</td><td>-0.430055</td><td>1.0</td><td>0</td><td>0</td></tr><tr><td>2024-11-14</td><td>&quot;AUD&quot;</td><td>&quot;FXXR_VT10&quot;</td><td>-0.4294</td><td>1.0</td><td>0</td><td>0</td></tr><tr><td>2024-11-15</td><td>&quot;AUD&quot;</td><td>&quot;FXXR_VT10&quot;</td><td>-0.452535</td><td>1.0</td><td>0</td><td>0</td></tr><tr><td>2024-11-14</td><td>&quot;CAD&quot;</td><td>&quot;FXXR_VT10&quot;</td><td>-1.132314</td><td>1.0</td><td>0</td><td>0</td></tr><tr><td>2024-11-15</td><td>&quot;CAD&quot;</td><td>&quot;FXXR_VT10&quot;</td><td>-1.755605</td><td>1.0</td><td>0</td><td>0</td></tr><tr><td>2024-11-14</td><td>&quot;EUR&quot;</td><td>&quot;FXXR_VT10&quot;</td><td>-0.292422</td><td>1.0</td><td>0</td><td>0</td></tr><tr><td>2024-11-15</td><td>&quot;EUR&quot;</td><td>&quot;FXXR_VT10&quot;</td><td>-0.855108</td><td>1.0</td><td>0</td><td>0</td></tr><tr><td>2024-11-14</td><td>&quot;GBP&quot;</td><td>&quot;FXXR_VT10&quot;</td><td>-0.110526</td><td>1.0</td><td>0</td><td>0</td></tr><tr><td>2024-11-15</td><td>&quot;GBP&quot;</td><td>&quot;FXXR_VT10&quot;</td><td>-0.700977</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",
+       "│ 2024-11-14 ┆ GBP ┆ FXXR_NSA  ┆ -0.067809 ┆ 1.0     ┆ 0       ┆ 0       │\n",
+       "│ 2024-11-15 ┆ GBP ┆ FXXR_NSA  ┆ -0.430055 ┆ 1.0     ┆ 0       ┆ 0       │\n",
+       "│ 2024-11-14 ┆ AUD ┆ FXXR_VT10 ┆ -0.4294   ┆ 1.0     ┆ 0       ┆ 0       │\n",
+       "│ 2024-11-15 ┆ AUD ┆ FXXR_VT10 ┆ -0.452535 ┆ 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",
+       "│ 2024-11-14 ┆ EUR ┆ FXXR_VT10 ┆ -0.292422 ┆ 1.0     ┆ 0       ┆ 0       │\n",
+       "│ 2024-11-15 ┆ EUR ┆ FXXR_VT10 ┆ -0.855108 ┆ 1.0     ┆ 0       ┆ 0       │\n",
+       "│ 2024-11-14 ┆ GBP ┆ FXXR_VT10 ┆ -0.110526 ┆ 1.0     ┆ 0       ┆ 0       │\n",
+       "│ 2024-11-15 ┆ GBP ┆ FXXR_VT10 ┆ -0.700977 ┆ 1.0     ┆ 0       ┆ 0       │\n",
+       "└────────────┴─────┴───────────┴───────────┴─────────┴─────────┴─────────┘"
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "new_df.tail(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": "3.12.7"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
--- a/notebooks/rust-notebook.ipynb
+++ b/notebooks/rust-notebook.ipynb
@ -1,5 +1,32 @@
 {
 "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "31d0d7e3",
+   "metadata": {},
+   "source": [
+    "# Running this noteboook\n",
+    "\n",
+    "Create a new Python Venv using:\n",
+    "\n",
+    "```bash\n",
+    "python -m venv .venv\n",
+    "# source .venv/bin/activate\n",
+    "./.venv/Scripts/activate\n",
+    "```\n",
+    "\n",
+    "Install `evcxr_jupyter` and `jupyterlab` using:\n",
+    "\n",
+    "```bash\n",
+    "cargo install evcxr_jupyter\n",
+    "evcxr_jupyter --install\n",
+    "pip install jupyterlab\n",
+    "jupyter lab\n",
+    "```\n",
+    "\n",
+    "Or try following this guide here: [DataCrayon - Setup Jupyter with Rust](https://datacrayon.com/data-analysis-with-rust-notebooks/setup-anaconda-jupyter-and-rust/)"
+   ]
+  },
  {
   "cell_type": "markdown",
   "id": "8d04a212-4025-41d7-809e-864649b08ab5",
@ -21,7 +48,7 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": null,
   "id": "22e1ae9e-14b8-4be4-b852-8f0fb420eaca",
   "metadata": {},
   "outputs": [],
@ -399,7 +426,7 @@
   "mimetype": "text/rust",
   "name": "rust",
   "pygment_lexer": "rust",
-   "version": ""
+   "version": "3.12.7"
  }
 },
 "nbformat": 4,
--- a/notebooks/test.py
+++ b/notebooks/test.py
@ -0,0 +1,44 @@
+import msyrs
+import datetime
+
+# "E:\Work\jpmaqs-data\data\ADPEMPL_SA_P1M1ML1\USD_ADPEMPL_SA_P1M1ML1.csv"
+
+DATA_FOLDER_PATH = "E:/Work/jpmaqs-data"
+
+dfpath = f"{DATA_FOLDER_PATH}/data/ADPEMPL_SA_P1M1ML1/USD_ADPEMPL_SA_P1M1ML1.csv"
+
+print(msyrs.qdf.load_qdf(dfpath))
+
+cids_dm = "AUD.CAD.CHF.EUR.GBP.JPY.NOK.NZD.SEK.USD".split(".")
+cids_em = "CLP.COP.CZK.HUF.IDR.ILS.INR.KRW.MXN.PLN.THB.TRY.TWD.ZAR".split(".")
+cids = cids_dm + cids_em
+cids_dux = list(set(cids) - set(["IDR", "NZD"]))
+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(
+    "."
+)
+mkts = "DU02YXR_NSA.DU05YXR_NSA.DU02YXR_VT10.DU05YXR_VT10.EQXR_NSA.EQXR_VT10.FXXR_NSA.FXXR_VT10.FXCRR_NSA.FXTARGETED_NSA.FXUNTRADABLE_NSA".split(
+    "."
+)
+xcats = ecos + mkts
+
+tickers = [f"{c}_{x}" for c in cids for x in xcats]
+
+
+# load_qdf_from_download_bank
+
+df = msyrs.qdf.load_qdf_from_download_bank(
+    folder_path=DATA_FOLDER_PATH, tickers=tickers
+)
+print(df)
+
+start_date = (datetime.datetime.now() - datetime.timedelta(days=5)).strftime("%Y-%m-%d")
+
+sel_cids = ["AUD", "USD", "GBP", "CAD", "JPY", "EUR"]
+df_eq = msyrs.qdf.reduce_dataframe(
+    df=df, cids=["AUD"], xcats=["EQXR_NSA"], start=start_date
+)
+print(df_eq)
+
+fx_xcats = [xc for xc in xcats if xc.startswith("FX")]
+df_fx = msyrs.qdf.reduce_dataframe(df=df, xcats=fx_xcats, intersect=True)
+print(df_fx)
--- a/pyproject.toml
+++ b/pyproject.toml
@ -0,0 +1,7 @@
+[build-system]
+requires = ["maturin>=1.0,<2.0"]
+build-backend = "maturin"
+
+[tool.maturin]
+# "extension-module" tells pyo3 we want to build an extension module (skips linking against libpython.so)
+features = ["pyo3/extension-module"]
--- a/src/lib.rs
+++ b/src/lib.rs
@ -1,30 +1,14 @@
 #![doc = include_str!("../README.md")]

+/// Documentation for the `msyrs` Python API.
+pub mod py;
+
+/// Documentation for the Rust API.
+
+
+/// Documentation for the `download` module.
 pub mod download;
 pub mod utils;

-use pyo3::{prelude::*, wrap_pymodule};
-use pyo3_polars::PyDataFrame;

-#[pyfunction]
-pub fn load_qdf(file_path: &str) -> PyResult<PyDataFrame> {
-    Ok(PyDataFrame(
-        utils::qdf::load_quantamental_dataframe(file_path).unwrap(),
-    ))
-}
-
-// ignore deprecated warning
-#[allow(deprecated)]
-#[pymodule]
-pub fn qdf(_py: Python, m: &PyModule) -> PyResult<()> {
-    m.add_function(wrap_pyfunction!(load_qdf, m)?)?;
-    Ok(())
-}
-
-#[allow(deprecated)]
-#[pymodule]
-pub fn msyrs(_py: Python, m: &PyModule) -> PyResult<()> {
-// add qdf as a submodule
-    m.add_wrapped(wrap_pymodule!(qdf))?;
-    Ok(())
-}
+pub use py::msyrs;
--- a/src/py/mod.rs
+++ b/src/py/mod.rs
@ -0,0 +1,12 @@
+
+/// Python API for [`crate::utils::qdf`].
+pub mod qdf;
+use pyo3::{prelude::*, wrap_pymodule};
+// use pyo3_polars::PyDataFrame;
+
+#[allow(deprecated)]
+#[pymodule]
+pub fn msyrs(_py: Python, m: &PyModule) -> PyResult<()> {
+    m.add_wrapped(wrap_pymodule!(qdf::qdf))?;
+    Ok(())
+}
--- a/src/py/qdf.rs
+++ b/src/py/qdf.rs
@ -0,0 +1,78 @@
+use pyo3::prelude::*;
+use pyo3_polars::PyDataFrame;
+
+/// Python wrapper for [`crate::utils::qdf`] module.
+#[allow(deprecated)]
+#[pymodule]
+pub fn qdf(_py: Python, m: &PyModule) -> PyResult<()> {
+    m.add_function(wrap_pyfunction!(load_qdf, m)?)?;
+    m.add_function(wrap_pyfunction!(load_qdf_from_download_bank, m)?)?;
+    m.add_function(wrap_pyfunction!(reduce_dataframe, m)?)?;
+    m.add_function(wrap_pyfunction!(update_dataframe, m)?)?;
+    Ok(())
+}
+
+/// Python wrapper for loading a Quantamental DataFrame from a CSV file.
+/// See [`crate::utils::qdf::load_quantamental_dataframe`] for full documentation.
+#[pyfunction]
+pub fn load_qdf(file_path: String) -> PyResult<PyDataFrame> {
+    Ok(PyDataFrame(
+        crate::utils::qdf::load_quantamental_dataframe(file_path).unwrap(),
+    ))
+}
+
+/// Python wrapper for loading a Quantamental DataFrame from a download bank.
+/// See [`crate::utils::qdf::load::load_qdf_from_download_bank`] for full documentation.
+#[pyfunction]
+pub fn load_qdf_from_download_bank(
+    folder_path: String,
+    cids: Option<Vec<String>>,
+    xcats: Option<Vec<String>>,
+    tickers: Option<Vec<String>>,
+) -> PyResult<PyDataFrame> {
+    Ok(PyDataFrame(
+        crate::utils::qdf::load::load_qdf_from_download_bank(folder_path, cids, xcats, tickers)
+            .unwrap(),
+    ))
+}
+
+/// Python wrapper for reduce_dataframe
+/// See [`crate::utils::qdf::reduce_df::reduce_dataframe`] for full documentation.
+#[pyfunction]
+pub fn reduce_dataframe(
+    df: PyDataFrame,
+    cids: Option<Vec<String>>,
+    xcats: Option<Vec<String>>,
+    metrics: Option<Vec<String>>,
+    start: Option<String>,
+    end: Option<String>,
+    intersect: Option<bool>,
+) -> PyResult<PyDataFrame> {
+    Ok(PyDataFrame(
+        crate::utils::qdf::reduce_df::reduce_dataframe(
+            df.into(),
+            cids,
+            xcats,
+            metrics,
+            start,
+            end,
+            intersect.unwrap_or(false),
+        )
+        .unwrap(),
+    ))
+}
+
+/// Python wrapper for update_dataframe
+/// See [`crate::utils::qdf::update_df::update_dataframe`] for full documentation.
+#[pyfunction]
+pub fn update_dataframe(
+    df: PyDataFrame,
+    df_add: PyDataFrame,
+    xcat_replace: Option<bool>,
+) -> PyResult<PyDataFrame> {
+    let xcat_replace = xcat_replace.unwrap_or(false);
+    Ok(PyDataFrame(
+        crate::utils::qdf::update_df::update_dataframe(&df.into(), &df_add.into(), xcat_replace)
+            .unwrap(),
+    ))
+}
--- a/src/utils/qdf/load.rs
+++ b/src/utils/qdf/load.rs
@ -23,10 +23,10 @@ fn _file_base_name(file_path: String) -> String {
 /// The CSV must be named in the format `cid_xcat.csv` (`ticker.csv`).
 /// The DataFrame must have a `real_date` column along with additional value columns.
 pub fn load_quantamental_dataframe(
-    file_path: &str,
+    file_path: String,
 ) -> Result<DataFrame, Box<dyn std::error::Error>> {
    // get the file base name
-    let base_file_name = _file_base_name(file_path.into());
+    let base_file_name = _file_base_name(file_path.clone().into());

    // if filename does not have _ then it is not a Quantamental DataFrame
    if !base_file_name.contains('_') {
@ -37,7 +37,7 @@ pub fn load_quantamental_dataframe(
    let (cid, xcat) = split_ticker(ticker.to_string())?;

    let mut df = CsvReadOptions::default()
-        .try_into_reader_with_file_path(Some(file_path.into()))
+        .try_into_reader_with_file_path(Some(file_path.to_string().into()))
        .unwrap()
        .finish()
        .unwrap();
@ -99,7 +99,7 @@ fn collect_paths_recursively<P: AsRef<std::path::Path>>(path: P) -> std::io::Res
 }

 fn _load_qdf_thread_safe(file_path: &str) -> Result<DataFrame, Box<dyn Error + Send + Sync>> {
-    let res = load_quantamental_dataframe(file_path);
+    let res = load_quantamental_dataframe(file_path.to_string());
    res.map_err(|e| {
        anyhow::Error::msg(e.to_string())
            .context("Failed to load quantamental dataframe")
@ -107,10 +107,10 @@ fn _load_qdf_thread_safe(file_path: &str) -> Result<DataFrame, Box<dyn Error + S
    })
 }
 pub fn load_qdf_from_download_bank(
-    folder_path: &str,
-    cids: Option<Vec<&str>>,
-    xcats: Option<Vec<&str>>,
-    tickers: Option<Vec<&str>>,
+    folder_path: String,
+    cids: Option<Vec<String>>,
+    xcats: Option<Vec<String>>,
+    tickers: Option<Vec<String>>,
 ) -> Result<DataFrame, Box<dyn std::error::Error>> {
    let rcids = cids.unwrap_or_else(|| Vec::new());
    let rxcats = xcats.unwrap_or_else(|| Vec::new());
@ -145,9 +145,9 @@ pub fn load_qdf_from_download_bank(
    let load_files = rel_files
        .iter()
        .filter(|(_, cid, xcat)| {
-            let f1 = rcids.len() > 0 && rcids.contains(&cid.as_str());
-            let f2 = rxcats.len() > 0 && rxcats.contains(&xcat.as_str());
-            let f3 = rtickers.len() > 0 && rtickers.contains(&create_ticker(cid, xcat).as_str());
+            let f1 = rcids.len() > 0 && rcids.contains(&cid);
+            let f2 = rxcats.len() > 0 && rxcats.contains(&xcat);
+            let f3 = rtickers.len() > 0 && rtickers.contains(&create_ticker(cid, xcat));
            f1 | f2 | f3
        })
        .map(|(file, _, _)| *file)
@ -160,7 +160,7 @@ pub fn load_qdf_from_download_bank(
        return Err("No files to load".into());
    }
    if load_files.len() == 1 {
-        let dfx = load_quantamental_dataframe(load_files[0]).unwrap();
+        let dfx = load_quantamental_dataframe(load_files[0].to_string()).unwrap();
        return Ok(dfx);
    }

--- a/src/utils/qdf/reduce_df.rs
+++ b/src/utils/qdf/reduce_df.rs
@ -17,11 +17,11 @@ const QDF_INDEX_COLUMNS: [&str; 3] = ["real_date", "cid", "xcat"];
 /// If no filters are provided, the original DataFrame is returned.
 pub fn reduce_dataframe(
    df: DataFrame,
-    cids: Option<Vec<&str>>,
-    xcats: Option<Vec<&str>>,
+    cids: Option<Vec<String>>,
+    xcats: Option<Vec<String>>,
    metrics: Option<Vec<String>>,
-    start: Option<&str>,
-    end: Option<&str>,
+    start: Option<String>,
+    end: Option<String>,
    intersect: bool,
 ) -> Result<DataFrame, Box<dyn Error>> {
    check_quantamental_dataframe(&df)?;
@ -36,10 +36,10 @@ pub fn reduce_dataframe(
    let u_xcats: Vec<String> = get_unique_xcats(&new_df)?;
    let u_tickers: Vec<String> = _get_unique_strs_from_str_column_object(&ticker_col)?;

-    let specified_cids: Vec<&str> =
-        cids.unwrap_or_else(|| u_cids.iter().map(AsRef::as_ref).collect());
-    let specified_xcats: Vec<&str> =
-        xcats.unwrap_or_else(|| u_xcats.iter().map(AsRef::as_ref).collect());
+    let cids_vec = cids.unwrap_or_else(|| u_cids.clone());
+    let specified_cids: Vec<&str> = cids_vec.iter().map(AsRef::as_ref).collect();
+    let xcats_vec = xcats.unwrap_or_else(|| u_xcats.clone());
+    let specified_xcats: Vec<&str> = xcats_vec.iter().map(AsRef::as_ref).collect();

    let non_idx_cols: Vec<String> = new_df
        .get_column_names()
@ -107,7 +107,7 @@ pub fn reduce_dataframe(
    // Apply date filtering if `start` or `end` is provided

    if let Some(start) = start {
-        let start_date = chrono::NaiveDate::parse_from_str(start, "%Y-%m-%d")?;
+        let start_date = chrono::NaiveDate::parse_from_str(&start, "%Y-%m-%d")?;
        new_df = new_df
            .lazy()
            .filter(
@ -120,7 +120,7 @@ pub fn reduce_dataframe(
    }

    if let Some(end) = end {
-        let end_date = chrono::NaiveDate::parse_from_str(end, "%Y-%m-%d")?;
+        let end_date = chrono::NaiveDate::parse_from_str(&end, "%Y-%m-%d")?;
        new_df = new_df
            .lazy()
            .filter(
--- a/src/utils/qdf/update_df.rs
+++ b/src/utils/qdf/update_df.rs
@ -11,7 +11,7 @@ const QDF_INDEX_COLUMNS: [&str; 3] = ["real_date", "cid", "xcat"];
 pub fn update_dataframe(
    df: &DataFrame,
    df_add: &DataFrame,
-    // xcat_replace: Option<&str>,
+    xcat_replace: bool,
 ) -> Result<DataFrame, Box<dyn Error>> {
    check_quantamental_dataframe(df)?;
    check_quantamental_dataframe(df_add)?;
@ -20,7 +20,10 @@ pub fn update_dataframe(
    } else if df_add.is_empty() {
        return Ok(df.clone());
    };
-
+    println!(
+        "xcat_replace not implemented yet (passed value: {})",
+        xcat_replace
+    );
    // vstack and drop duplicates keeping last
    let mut new_df = df.vstack(df_add)?;
    // help?
--- a/test.py
+++ b/test.py
@ -1,10 +0,0 @@
-import msyrs
-
-# "E:\Work\jpmaqs-data\data\ADPEMPL_SA_P1M1ML1\USD_ADPEMPL_SA_P1M1ML1.csv"
-
-dfpath = "E:/Work/jpmaqs-data/data/ADPEMPL_SA_P1M1ML1/USD_ADPEMPL_SA_P1M1ML1.csv"
-
-print(msyrs.qdf.load_qdf(dfpath))
-
-
-