{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "# AUM Analysis\n", "\n", "This notebook sums the **Value - AUM €** by **Product - Asset Type** and by **Product - Fund** from the AUM sample data." ] }, { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Collecting openpyxl\n", " Downloading openpyxl-3.1.5-py2.py3-none-any.whl.metadata (2.5 kB)\n", "Collecting et-xmlfile (from openpyxl)\n", " Downloading et_xmlfile-2.0.0-py3-none-any.whl.metadata (2.7 kB)\n", "Downloading openpyxl-3.1.5-py2.py3-none-any.whl (250 kB)\n", "Downloading et_xmlfile-2.0.0-py3-none-any.whl (18 kB)\n", "Installing collected packages: et-xmlfile, openpyxl\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2/2\u001b[0m [openpyxl]1/2\u001b[0m [openpyxl]\n", "\u001b[1A\u001b[2KSuccessfully installed et-xmlfile-2.0.0 openpyxl-3.1.5\n" ] } ], "source": [ "import pandas as pd\n", "import numpy as np\n", "import matplotlib.pyplot as plt\n", "!pip install openpyxl\n", "import os\n", "import s3fs\n", "import seaborn as sns\n", "import plotly.express as px" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [], "source": [ "fs = s3fs.S3FileSystem(\n", " client_kwargs={'endpoint_url': 'https://'+'minio-simple.lab.groupe-genes.fr'},\n", " key = os.environ[\"AWS_ACCESS_KEY_ID\"], \n", " secret = os.environ[\"AWS_SECRET_ACCESS_KEY\"], \n", " token = os.environ[\"AWS_SESSION_TOKEN\"])" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "/tmp/ipykernel_8794/3768862044.py:5: DtypeWarning: Columns (0,1,2,3) have mixed types. Specify dtype option on import or set low_memory=False.\n", " stocks = pd.read_csv(f, sep=\";\")\n" ] } ], "source": [ "#with fs.open('projet-bdc-data//carmignac/Flows ENSAE V2 -20251105.csv', 'rb') as f:\n", " #flows = pd.read_csv(f, sep=\";\")\n", "\n", "with fs.open('projet-bdc-data//carmignac/AUM ENSAE V2 -20251105.csv', 'rb') as f:\n", " stocks = pd.read_csv(f, sep=\";\")\n", "\n", "#with fs.open('projet-bdc-data/carmignac/Monthly AUM and NAV since 2010.xlsx', 'rb') as f:#\n", " #nav_raw = pd.read_excel(f, header=None, engine=\"openpyxl\")\n", "\n", "#nav = nav_raw[0].str.split(\",\", expand=True)\n", "#nav.columns = nav.iloc[0]\n", "#nav = nav[1:].reset_index(drop=True)" ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Date conversion done.\n" ] } ], "source": [ "stocks[\"Centralisation Date\"] = pd.to_datetime(stocks[\"Centralisation Date\"], errors=\"coerce\")\n", "#flows[\"Centralisation Date\"] = pd.to_datetime(flows[\"Centralisation Date\"], errors=\"coerce\")\n", "#nav[\"NavDate\"] = pd.to_datetime(nav[\"NavDate\"], format=\"%d/%m/%Y\", errors=\"coerce\")\n", "\n", "print(\"Date conversion done.\")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Sum of AUM by Product - Asset Type" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "AUM (€) by Product - Asset Type:\n", "Product - Asset Type\n", "Diversified 2.249487e+12\n", "Fixed Income 1.901982e+12\n", "Equity 9.811712e+11\n", "Alternative 1.208047e+11\n", "NaN 1.786480e+10\n", "Private Assets 2.205183e+09\n" ] }, { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
Product - Asset TypeTotal AUM (€)
0Diversified2.249487e+12
1Fixed Income1.901982e+12
2Equity9.811712e+11
3Alternative1.208047e+11
4NaN1.786480e+10
5Private Assets2.205183e+09
\n", "
" ], "text/plain": [ " Product - Asset Type Total AUM (€)\n", "0 Diversified 2.249487e+12\n", "1 Fixed Income 1.901982e+12\n", "2 Equity 9.811712e+11\n", "3 Alternative 1.208047e+11\n", "4 NaN 1.786480e+10\n", "5 Private Assets 2.205183e+09" ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Sum Value - AUM € per Product - Asset Type\n", "aum_by_asset_type = stocks.groupby('Product - Asset Type', dropna=False)['Value - AUM €'].sum().sort_values(ascending=False)\n", "\n", "print(\"AUM (€) by Product - Asset Type:\")\n", "print(aum_by_asset_type.to_string())\n", "\n", "# Display as DataFrame for nicer formatting\n", "aum_by_asset_type_df = aum_by_asset_type.reset_index()\n", "aum_by_asset_type_df.columns = ['Product - Asset Type', 'Total AUM (€)']\n", "aum_by_asset_type_df" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Sum of AUM by Product - Fund" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "# Sum Value - AUM € per Product - Fund\n", "aum_by_fund = stocks.groupby('Product - Fund', dropna=False)['Value - AUM €'].sum().sort_values(ascending=False)\n", "\n", "print(\"AUM (€) by Product - Fund:\")\n", "print(aum_by_fund.to_string())\n", "\n", "# Display as DataFrame for nicer formatting\n", "aum_by_fund_df = aum_by_fund.reset_index()\n", "aum_by_fund_df.columns = ['Product - Fund', 'Total AUM (€)']\n", "aum_by_fund_df" ] } ], "metadata": { "kernelspec": { "display_name": "Python 3", "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": "3.13.12" } }, "nbformat": 4, "nbformat_minor": 4 }