{ "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", " | Product - Asset Type | \n", "Total AUM (€) | \n", "
|---|---|---|
| 0 | \n", "Diversified | \n", "2.249487e+12 | \n", "
| 1 | \n", "Fixed Income | \n", "1.901982e+12 | \n", "
| 2 | \n", "Equity | \n", "9.811712e+11 | \n", "
| 3 | \n", "Alternative | \n", "1.208047e+11 | \n", "
| 4 | \n", "NaN | \n", "1.786480e+10 | \n", "
| 5 | \n", "Private Assets | \n", "2.205183e+09 | \n", "