sthoumyre-ensae/Project_Carmignac
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
89c5d190e0
Project_Carmignac/data_1-Copy1.ipynb

1725 lines
370 KiB
Plaintext
Raw Normal View History

Téléverser les fichiers vers "/"
2026-02-01 23:12:11 +01:00
{
"cells": [
{
"cell_type": "markdown",
"id": "e637deae-9168-4fb2-b95f-4e42d8d72d9e",
"metadata": {},
"source": [
"# DATA COLLECTION "
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "f8508d94-74a7-4bb0-8b81-c2e06850c25f",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Agreement - Code</th>\n",
" <th>Company - Id</th>\n",
" <th>Company - Ultimate Parent Id</th>\n",
" <th>Registrar Account - ID</th>\n",
" <th>Registrar Account - Region</th>\n",
" <th>RegistrarAccount - Country</th>\n",
" <th>Product - Asset Type</th>\n",
" <th>Product - Strategy</th>\n",
" <th>Product - Legal Status</th>\n",
" <th>Product - Is Dedie ?</th>\n",
" <th>Product - Fund</th>\n",
" <th>Product - Shareclass Type</th>\n",
" <th>Product - Shareclass Currency</th>\n",
" <th>Product - Isin</th>\n",
" <th>Centralisation Date</th>\n",
" <th>Quantity - AUM</th>\n",
" <th>Value - AUM CCY</th>\n",
" <th>Value - AUM €</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>003</td>\n",
" <td>166</td>\n",
" <td>166</td>\n",
" <td>200000647</td>\n",
" <td>France</td>\n",
" <td>France</td>\n",
" <td>Diversified</td>\n",
" <td>Patrimoine</td>\n",
" <td>FCP</td>\n",
" <td>NO</td>\n",
" <td>Carmignac Patrimoine</td>\n",
" <td>A</td>\n",
" <td>EUR</td>\n",
" <td>FR0010135103</td>\n",
" <td>2015-03-31</td>\n",
" <td>35.368</td>\n",
" <td>2.464867e+04</td>\n",
" <td>2.464867e+04</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>003</td>\n",
" <td>166</td>\n",
" <td>166</td>\n",
" <td>200000647</td>\n",
" <td>France</td>\n",
" <td>France</td>\n",
" <td>Diversified</td>\n",
" <td>Patrimoine</td>\n",
" <td>FCP</td>\n",
" <td>NO</td>\n",
" <td>Carmignac Patrimoine</td>\n",
" <td>A</td>\n",
" <td>EUR</td>\n",
" <td>FR0010135103</td>\n",
" <td>2015-11-30</td>\n",
" <td>35.368</td>\n",
" <td>2.241306e+04</td>\n",
" <td>2.241306e+04</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>003</td>\n",
" <td>166</td>\n",
" <td>166</td>\n",
" <td>200000647</td>\n",
" <td>France</td>\n",
" <td>France</td>\n",
" <td>Diversified</td>\n",
" <td>Patrimoine</td>\n",
" <td>FCP</td>\n",
" <td>NO</td>\n",
" <td>Carmignac Patrimoine</td>\n",
" <td>A</td>\n",
" <td>EUR</td>\n",
" <td>FR0010135103</td>\n",
" <td>2015-12-31</td>\n",
" <td>35.368</td>\n",
" <td>2.205124e+04</td>\n",
" <td>2.205124e+04</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>003</td>\n",
" <td>166</td>\n",
" <td>166</td>\n",
" <td>200000647</td>\n",
" <td>France</td>\n",
" <td>France</td>\n",
" <td>Diversified</td>\n",
" <td>Patrimoine</td>\n",
" <td>FCP</td>\n",
" <td>NO</td>\n",
" <td>Carmignac Patrimoine</td>\n",
" <td>A</td>\n",
" <td>EUR</td>\n",
" <td>FR0010135103</td>\n",
" <td>2016-03-31</td>\n",
" <td>35.368</td>\n",
" <td>2.162612e+04</td>\n",
" <td>2.162612e+04</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>003</td>\n",
" <td>166</td>\n",
" <td>166</td>\n",
" <td>200000647</td>\n",
" <td>France</td>\n",
" <td>France</td>\n",
" <td>Diversified</td>\n",
" <td>Patrimoine</td>\n",
" <td>FCP</td>\n",
" <td>NO</td>\n",
" <td>Carmignac Patrimoine</td>\n",
" <td>A</td>\n",
" <td>EUR</td>\n",
" <td>FR0010135103</td>\n",
" <td>2016-11-30</td>\n",
" <td>35.368</td>\n",
" <td>2.248945e+04</td>\n",
" <td>2.248945e+04</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4880292</th>\n",
" <td>Private Client</td>\n",
" <td>Private Client</td>\n",
" <td>Private Client</td>\n",
" <td>Private Client</td>\n",
" <td>Switzerland</td>\n",
" <td>Switzerland</td>\n",
" <td>Fixed Income</td>\n",
" <td>Sécurité</td>\n",
" <td>SICAV</td>\n",
" <td>NO</td>\n",
" <td>Carmignac Portfolio Sécurité</td>\n",
" <td>AW &amp; AW-R</td>\n",
" <td>EUR</td>\n",
" <td>LU1299306321</td>\n",
" <td>2020-02-29</td>\n",
" <td>26801.000</td>\n",
" <td>2.740670e+06</td>\n",
" <td>2.740670e+06</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4880293</th>\n",
" <td>Private Client</td>\n",
" <td>Private Client</td>\n",
" <td>Private Client</td>\n",
" <td>Private Client</td>\n",
" <td>Switzerland</td>\n",
" <td>Switzerland</td>\n",
" <td>Fixed Income</td>\n",
" <td>Sécurité</td>\n",
" <td>SICAV</td>\n",
" <td>NO</td>\n",
" <td>Carmignac Portfolio Sécurité</td>\n",
" <td>AW &amp; AW-R</td>\n",
" <td>EUR</td>\n",
" <td>LU1299306321</td>\n",
" <td>2020-06-30</td>\n",
" <td>3099.000</td>\n",
" <td>3.122862e+05</td>\n",
" <td>3.122862e+05</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4880294</th>\n",
" <td>Private Client</td>\n",
" <td>Private Client</td>\n",
" <td>Private Client</td>\n",
" <td>Private Client</td>\n",
" <td>Switzerland</td>\n",
" <td>Switzerland</td>\n",
" <td>Fixed Income</td>\n",
" <td>Sécurité</td>\n",
" <td>SICAV</td>\n",
" <td>NO</td>\n",
" <td>Carmignac Portfolio Sécurité</td>\n",
" <td>AW &amp; AW-R</td>\n",
" <td>EUR</td>\n",
" <td>LU1299306321</td>\n",
" <td>2020-10-31</td>\n",
" <td>3099.000</td>\n",
" <td>3.184222e+05</td>\n",
" <td>3.184222e+05</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4880295</th>\n",
" <td>Private Client</td>\n",
" <td>Private Client</td>\n",
" <td>Private Client</td>\n",
" <td>Private Client</td>\n",
" <td>Switzerland</td>\n",
" <td>Switzerland</td>\n",
" <td>Fixed Income</td>\n",
" <td>Sécurité</td>\n",
" <td>SICAV</td>\n",
" <td>NO</td>\n",
" <td>Carmignac Portfolio Sécurité</td>\n",
" <td>AW &amp; AW-R</td>\n",
" <td>EUR</td>\n",
" <td>LU1299306321</td>\n",
" <td>2021-07-31</td>\n",
" <td>2835.000</td>\n",
" <td>2.976183e+05</td>\n",
" <td>2.976183e+05</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4880296</th>\n",
" <td>Private Client</td>\n",
" <td>Private Client</td>\n",
" <td>Private Client</td>\n",
" <td>Private Client</td>\n",
" <td>Switzerland</td>\n",
" <td>Switzerland</td>\n",
" <td>Fixed Income</td>\n",
" <td>Sécurité</td>\n",
" <td>SICAV</td>\n",
" <td>NO</td>\n",
" <td>Carmignac Portfolio Sécurité</td>\n",
" <td>FW &amp; FW-R</td>\n",
" <td>EUR</td>\n",
" <td>LU1792391911</td>\n",
" <td>2020-07-31</td>\n",
" <td>2916.394</td>\n",
" <td>2.874106e+05</td>\n",
" <td>2.874106e+05</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>4880297 rows × 18 columns</p>\n",
"</div>"
],
"text/plain": [
" Agreement - Code Company - Id Company - Ultimate Parent Id \\\n",
"0 003 166 166 \n",
"1 003 166 166 \n",
"2 003 166 166 \n",
"3 003 166 166 \n",
"4 003 166 166 \n",
"... ... ... ... \n",
"4880292 Private Client Private Client Private Client \n",
"4880293 Private Client Private Client Private Client \n",
"4880294 Private Client Private Client Private Client \n",
"4880295 Private Client Private Client Private Client \n",
"4880296 Private Client Private Client Private Client \n",
"\n",
" Registrar Account - ID Registrar Account - Region \\\n",
"0 200000647 France \n",
"1 200000647 France \n",
"2 200000647 France \n",
"3 200000647 France \n",
"4 200000647 France \n",
"... ... ... \n",
"4880292 Private Client Switzerland \n",
"4880293 Private Client Switzerland \n",
"4880294 Private Client Switzerland \n",
"4880295 Private Client Switzerland \n",
"4880296 Private Client Switzerland \n",
"\n",
" RegistrarAccount - Country Product - Asset Type Product - Strategy \\\n",
"0 France Diversified Patrimoine \n",
"1 France Diversified Patrimoine \n",
"2 France Diversified Patrimoine \n",
"3 France Diversified Patrimoine \n",
"4 France Diversified Patrimoine \n",
"... ... ... ... \n",
"4880292 Switzerland Fixed Income Sécurité \n",
"4880293 Switzerland Fixed Income Sécurité \n",
"4880294 Switzerland Fixed Income Sécurité \n",
"4880295 Switzerland Fixed Income Sécurité \n",
"4880296 Switzerland Fixed Income Sécurité \n",
"\n",
" Product - Legal Status Product - Is Dedie ? \\\n",
"0 FCP NO \n",
"1 FCP NO \n",
"2 FCP NO \n",
"3 FCP NO \n",
"4 FCP NO \n",
"... ... ... \n",
"4880292 SICAV NO \n",
"4880293 SICAV NO \n",
"4880294 SICAV NO \n",
"4880295 SICAV NO \n",
"4880296 SICAV NO \n",
"\n",
" Product - Fund Product - Shareclass Type \\\n",
"0 Carmignac Patrimoine A \n",
"1 Carmignac Patrimoine A \n",
"2 Carmignac Patrimoine A \n",
"3 Carmignac Patrimoine A \n",
"4 Carmignac Patrimoine A \n",
"... ... ... \n",
"4880292 Carmignac Portfolio Sécurité AW & AW-R \n",
"4880293 Carmignac Portfolio Sécurité AW & AW-R \n",
"4880294 Carmignac Portfolio Sécurité AW & AW-R \n",
"4880295 Carmignac Portfolio Sécurité AW & AW-R \n",
"4880296 Carmignac Portfolio Sécurité FW & FW-R \n",
"\n",
" Product - Shareclass Currency Product - Isin Centralisation Date \\\n",
"0 EUR FR0010135103 2015-03-31 \n",
"1 EUR FR0010135103 2015-11-30 \n",
"2 EUR FR0010135103 2015-12-31 \n",
"3 EUR FR0010135103 2016-03-31 \n",
"4 EUR FR0010135103 2016-11-30 \n",
"... ... ... ... \n",
"4880292 EUR LU1299306321 2020-02-29 \n",
"4880293 EUR LU1299306321 2020-06-30 \n",
"4880294 EUR LU1299306321 2020-10-31 \n",
"4880295 EUR LU1299306321 2021-07-31 \n",
"4880296 EUR LU1792391911 2020-07-31 \n",
"\n",
" Quantity - AUM Value - AUM CCY Value - AUM € \n",
"0 35.368 2.464867e+04 2.464867e+04 \n",
"1 35.368 2.241306e+04 2.241306e+04 \n",
"2 35.368 2.205124e+04 2.205124e+04 \n",
"3 35.368 2.162612e+04 2.162612e+04 \n",
"4 35.368 2.248945e+04 2.248945e+04 \n",
"... ... ... ... \n",
"4880292 26801.000 2.740670e+06 2.740670e+06 \n",
"4880293 3099.000 3.122862e+05 3.122862e+05 \n",
"4880294 3099.000 3.184222e+05 3.184222e+05 \n",
"4880295 2835.000 2.976183e+05 2.976183e+05 \n",
"4880296 2916.394 2.874106e+05 2.874106e+05 \n",
"\n",
"[4880297 rows x 18 columns]"
]
},
"execution_count": 1,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"import pandas as pd \n",
"chemin_fichier = \"s3://projet-bdc-data/carmignac/AUM ENSAE V2 -20251105.csv\"\n",
"df_aum2 = pd.read_csv(chemin_fichier, sep=';', engine='python')\n",
"df_aum2"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "4644da13-5aea-4ca0-9fcf-947324766292",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Agreement - Code</th>\n",
" <th>Company - Id</th>\n",
" <th>Company - Ultimate Parent Id</th>\n",
" <th>Registrar Account - ID</th>\n",
" <th>Registrar Account - Region</th>\n",
" <th>RegistrarAccount - Country</th>\n",
" <th>Product - Asset Type</th>\n",
" <th>Product - Strategy</th>\n",
" <th>Product - Legal Status</th>\n",
" <th>Product - Is Dedie ?</th>\n",
" <th>...</th>\n",
" <th>Centralisation Date</th>\n",
" <th>Quantity - Subscription</th>\n",
" <th>Quantity - Redemption</th>\n",
" <th>Quantity - NetFlows</th>\n",
" <th>Value Ccy - Subscription</th>\n",
" <th>Value Ccy - Redemption</th>\n",
" <th>Value Ccy - NetFlows</th>\n",
" <th>Value € - Subscription</th>\n",
" <th>Value € - Redemption</th>\n",
" <th>Value € - NetFlows</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>003</td>\n",
" <td>166</td>\n",
" <td>166</td>\n",
" <td>200127202</td>\n",
" <td>France</td>\n",
" <td>France</td>\n",
" <td>Equity</td>\n",
" <td>Investissement</td>\n",
" <td>SICAV</td>\n",
" <td>NO</td>\n",
" <td>...</td>\n",
" <td>2020-11-05</td>\n",
" <td>1636.000</td>\n",
" <td>0.000</td>\n",
" <td>1636.000</td>\n",
" <td>280983.00</td>\n",
" <td>0.00</td>\n",
" <td>280983.00</td>\n",
" <td>280983.00</td>\n",
" <td>0.00</td>\n",
" <td>280983.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>003</td>\n",
" <td>166</td>\n",
" <td>166</td>\n",
" <td>406533</td>\n",
" <td>France</td>\n",
" <td>France</td>\n",
" <td>Diversified</td>\n",
" <td>Patrimoine</td>\n",
" <td>FCP</td>\n",
" <td>NO</td>\n",
" <td>...</td>\n",
" <td>2015-03-09</td>\n",
" <td>144.690</td>\n",
" <td>0.000</td>\n",
" <td>144.690</td>\n",
" <td>99985.13</td>\n",
" <td>0.00</td>\n",
" <td>99985.13</td>\n",
" <td>99985.13</td>\n",
" <td>0.00</td>\n",
" <td>99985.13</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>003</td>\n",
" <td>166</td>\n",
" <td>166</td>\n",
" <td>406533</td>\n",
" <td>France</td>\n",
" <td>France</td>\n",
" <td>Equity</td>\n",
" <td>Investissement</td>\n",
" <td>FCP</td>\n",
" <td>NO</td>\n",
" <td>...</td>\n",
" <td>2016-10-26</td>\n",
" <td>0.000</td>\n",
" <td>-8.321</td>\n",
" <td>-8.321</td>\n",
" <td>0.00</td>\n",
" <td>-9384.76</td>\n",
" <td>-9384.76</td>\n",
" <td>0.00</td>\n",
" <td>-9384.76</td>\n",
" <td>-9384.76</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>003</td>\n",
" <td>166</td>\n",
" <td>166</td>\n",
" <td>406533</td>\n",
" <td>France</td>\n",
" <td>France</td>\n",
" <td>Equity</td>\n",
" <td>Investissement</td>\n",
" <td>FCP</td>\n",
" <td>NO</td>\n",
" <td>...</td>\n",
" <td>2018-10-18</td>\n",
" <td>0.000</td>\n",
" <td>-22.083</td>\n",
" <td>-22.083</td>\n",
" <td>0.00</td>\n",
" <td>-25227.40</td>\n",
" <td>-25227.40</td>\n",
" <td>0.00</td>\n",
" <td>-25227.40</td>\n",
" <td>-25227.40</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>003</td>\n",
" <td>166</td>\n",
" <td>166</td>\n",
" <td>406533</td>\n",
" <td>France</td>\n",
" <td>France</td>\n",
" <td>Equity</td>\n",
" <td>Investissement</td>\n",
" <td>FCP</td>\n",
" <td>NO</td>\n",
" <td>...</td>\n",
" <td>2019-04-08</td>\n",
" <td>0.000</td>\n",
" <td>-465.992</td>\n",
" <td>-465.992</td>\n",
" <td>0.00</td>\n",
" <td>-563775.76</td>\n",
" <td>-563775.76</td>\n",
" <td>0.00</td>\n",
" <td>-563775.76</td>\n",
" <td>-563775.76</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2574456</th>\n",
" <td>Private Client</td>\n",
" <td>Private Client</td>\n",
" <td>Private Client</td>\n",
" <td>Private Client</td>\n",
" <td>Luxembourg</td>\n",
" <td>Luxembourg</td>\n",
" <td>Fixed Income</td>\n",
" <td>Sécurité</td>\n",
" <td>FCP</td>\n",
" <td>NO</td>\n",
" <td>...</td>\n",
" <td>2015-06-12</td>\n",
" <td>0.000</td>\n",
" <td>-20.000</td>\n",
" <td>-20.000</td>\n",
" <td>0.00</td>\n",
" <td>-34294.40</td>\n",
" <td>-34294.40</td>\n",
" <td>0.00</td>\n",
" <td>-34294.40</td>\n",
" <td>-34294.40</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2574457</th>\n",
" <td>Private Client</td>\n",
" <td>Private Client</td>\n",
" <td>Private Client</td>\n",
" <td>Private Client</td>\n",
" <td>Luxembourg</td>\n",
" <td>Luxembourg</td>\n",
" <td>Fixed Income</td>\n",
" <td>Sécurité</td>\n",
" <td>FCP</td>\n",
" <td>NO</td>\n",
" <td>...</td>\n",
" <td>2015-09-18</td>\n",
" <td>328.726</td>\n",
" <td>0.000</td>\n",
" <td>328.726</td>\n",
" <td>564028.07</td>\n",
" <td>0.00</td>\n",
" <td>564028.07</td>\n",
" <td>564028.07</td>\n",
" <td>0.00</td>\n",
" <td>564028.07</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2574458</th>\n",
" <td>Private Client</td>\n",
" <td>Private Client</td>\n",
" <td>Private Client</td>\n",
" <td>Private Client</td>\n",
" <td>Luxembourg</td>\n",
" <td>Luxembourg</td>\n",
" <td>Fixed Income</td>\n",
" <td>Sécurité</td>\n",
" <td>FCP</td>\n",
" <td>NO</td>\n",
" <td>...</td>\n",
" <td>2015-09-25</td>\n",
" <td>4.443</td>\n",
" <td>0.000</td>\n",
" <td>4.443</td>\n",
" <td>7603.66</td>\n",
" <td>0.00</td>\n",
" <td>7603.66</td>\n",
" <td>7603.66</td>\n",
" <td>0.00</td>\n",
" <td>7603.66</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2574459</th>\n",
" <td>Private Client</td>\n",
" <td>Private Client</td>\n",
" <td>Private Client</td>\n",
" <td>Private Client</td>\n",
" <td>Luxembourg</td>\n",
" <td>Luxembourg</td>\n",
" <td>Fixed Income</td>\n",
" <td>Sécurité</td>\n",
" <td>FCP</td>\n",
" <td>NO</td>\n",
" <td>...</td>\n",
" <td>2015-11-09</td>\n",
" <td>0.000</td>\n",
" <td>-440.000</td>\n",
" <td>-440.000</td>\n",
" <td>0.00</td>\n",
" <td>-754696.80</td>\n",
" <td>-754696.80</td>\n",
" <td>0.00</td>\n",
" <td>-754696.80</td>\n",
" <td>-754696.80</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2574460</th>\n",
" <td>Private Client</td>\n",
" <td>Private Client</td>\n",
" <td>Private Client</td>\n",
" <td>Private Client</td>\n",
" <td>Luxembourg</td>\n",
" <td>Luxembourg</td>\n",
" <td>Fixed Income</td>\n",
" <td>Sécurité</td>\n",
" <td>SICAV</td>\n",
" <td>NO</td>\n",
" <td>...</td>\n",
" <td>2016-01-11</td>\n",
" <td>3595.000</td>\n",
" <td>0.000</td>\n",
" <td>3595.000</td>\n",
" <td>358385.55</td>\n",
" <td>0.00</td>\n",
" <td>358385.55</td>\n",
" <td>358385.55</td>\n",
" <td>0.00</td>\n",
" <td>358385.55</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>2574461 rows × 24 columns</p>\n",
"</div>"
],
"text/plain": [
" Agreement - Code Company - Id Company - Ultimate Parent Id \\\n",
"0 003 166 166 \n",
"1 003 166 166 \n",
"2 003 166 166 \n",
"3 003 166 166 \n",
"4 003 166 166 \n",
"... ... ... ... \n",
"2574456 Private Client Private Client Private Client \n",
"2574457 Private Client Private Client Private Client \n",
"2574458 Private Client Private Client Private Client \n",
"2574459 Private Client Private Client Private Client \n",
"2574460 Private Client Private Client Private Client \n",
"\n",
" Registrar Account - ID Registrar Account - Region \\\n",
"0 200127202 France \n",
"1 406533 France \n",
"2 406533 France \n",
"3 406533 France \n",
"4 406533 France \n",
"... ... ... \n",
"2574456 Private Client Luxembourg \n",
"2574457 Private Client Luxembourg \n",
"2574458 Private Client Luxembourg \n",
"2574459 Private Client Luxembourg \n",
"2574460 Private Client Luxembourg \n",
"\n",
" RegistrarAccount - Country Product - Asset Type Product - Strategy \\\n",
"0 France Equity Investissement \n",
"1 France Diversified Patrimoine \n",
"2 France Equity Investissement \n",
"3 France Equity Investissement \n",
"4 France Equity Investissement \n",
"... ... ... ... \n",
"2574456 Luxembourg Fixed Income Sécurité \n",
"2574457 Luxembourg Fixed Income Sécurité \n",
"2574458 Luxembourg Fixed Income Sécurité \n",
"2574459 Luxembourg Fixed Income Sécurité \n",
"2574460 Luxembourg Fixed Income Sécurité \n",
"\n",
" Product - Legal Status Product - Is Dedie ? ... Centralisation Date \\\n",
"0 SICAV NO ... 2020-11-05 \n",
"1 FCP NO ... 2015-03-09 \n",
"2 FCP NO ... 2016-10-26 \n",
"3 FCP NO ... 2018-10-18 \n",
"4 FCP NO ... 2019-04-08 \n",
"... ... ... ... ... \n",
"2574456 FCP NO ... 2015-06-12 \n",
"2574457 FCP NO ... 2015-09-18 \n",
"2574458 FCP NO ... 2015-09-25 \n",
"2574459 FCP NO ... 2015-11-09 \n",
"2574460 SICAV NO ... 2016-01-11 \n",
"\n",
" Quantity - Subscription Quantity - Redemption Quantity - NetFlows \\\n",
"0 1636.000 0.000 1636.000 \n",
"1 144.690 0.000 144.690 \n",
"2 0.000 -8.321 -8.321 \n",
"3 0.000 -22.083 -22.083 \n",
"4 0.000 -465.992 -465.992 \n",
"... ... ... ... \n",
"2574456 0.000 -20.000 -20.000 \n",
"2574457 328.726 0.000 328.726 \n",
"2574458 4.443 0.000 4.443 \n",
"2574459 0.000 -440.000 -440.000 \n",
"2574460 3595.000 0.000 3595.000 \n",
"\n",
" Value Ccy - Subscription Value Ccy - Redemption \\\n",
"0 280983.00 0.00 \n",
"1 99985.13 0.00 \n",
"2 0.00 -9384.76 \n",
"3 0.00 -25227.40 \n",
"4 0.00 -563775.76 \n",
"... ... ... \n",
"2574456 0.00 -34294.40 \n",
"2574457 564028.07 0.00 \n",
"2574458 7603.66 0.00 \n",
"2574459 0.00 -754696.80 \n",
"2574460 358385.55 0.00 \n",
"\n",
" Value Ccy - NetFlows Value € - Subscription Value € - Redemption \\\n",
"0 280983.00 280983.00 0.00 \n",
"1 99985.13 99985.13 0.00 \n",
"2 -9384.76 0.00 -9384.76 \n",
"3 -25227.40 0.00 -25227.40 \n",
"4 -563775.76 0.00 -563775.76 \n",
"... ... ... ... \n",
"2574456 -34294.40 0.00 -34294.40 \n",
"2574457 564028.07 564028.07 0.00 \n",
"2574458 7603.66 7603.66 0.00 \n",
"2574459 -754696.80 0.00 -754696.80 \n",
"2574460 358385.55 358385.55 0.00 \n",
"\n",
" Value € - NetFlows \n",
"0 280983.00 \n",
"1 99985.13 \n",
"2 -9384.76 \n",
"3 -25227.40 \n",
"4 -563775.76 \n",
"... ... \n",
"2574456 -34294.40 \n",
"2574457 564028.07 \n",
"2574458 7603.66 \n",
"2574459 -754696.80 \n",
"2574460 358385.55 \n",
"\n",
"[2574461 rows x 24 columns]"
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"chemin_fichier = \"s3://projet-bdc-data/carmignac/Flows ENSAE V2 -20251105.csv\"\n",
"df_flows2 = pd.read_csv(chemin_fichier, sep=';', engine='python')\n",
"df_flows2"
]
},
{
"cell_type": "markdown",
"id": "59d31eaf-c06c-4ebe-9f8c-cb9158a50976",
"metadata": {},
"source": [
"## DATA ANALYSIS"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "5773b911-6b84-448d-962f-8228eeac0250",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(4880297, 18)"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_aum2.shape"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "6f571810-c373-4d30-8ca5-c3a074b95b08",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Index(['Agreement - Code', 'Company - Id', 'Company - Ultimate Parent Id',\n",
" 'Registrar Account - ID', 'Registrar Account - Region',\n",
" 'RegistrarAccount - Country', 'Product - Asset Type',\n",
" 'Product - Strategy', 'Product - Legal Status', 'Product - Is Dedie ?',\n",
" 'Product - Fund', 'Product - Shareclass Type',\n",
" 'Product - Shareclass Currency', 'Product - Isin',\n",
" 'Centralisation Date', 'Quantity - AUM', 'Value - AUM CCY',\n",
" 'Value - AUM €'],\n",
" dtype='object')"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_aum2.columns"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "af25fd07-a613-4adc-b88b-93a8d300379c",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(2574461, 24)"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_flows2.shape"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "c6d0fe83-2957-430b-89cf-cd30833b7cab",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Index(['Agreement - Code', 'Company - Id', 'Company - Ultimate Parent Id',\n",
" 'Registrar Account - ID', 'Registrar Account - Region',\n",
" 'RegistrarAccount - Country', 'Product - Asset Type',\n",
" 'Product - Strategy', 'Product - Legal Status', 'Product - Is Dedie ?',\n",
" 'Product - Fund', 'Product - Shareclass Type',\n",
" 'Product - Shareclass Currency', 'Product - Isin',\n",
" 'Centralisation Date', 'Quantity - Subscription',\n",
" 'Quantity - Redemption', 'Quantity - NetFlows',\n",
" 'Value Ccy - Subscription', 'Value Ccy - Redemption',\n",
" 'Value Ccy - NetFlows', 'Value € - Subscription',\n",
" 'Value € - Redemption', 'Value € - NetFlows'],\n",
" dtype='object')"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_flows2.columns"
]
},
{
"cell_type": "markdown",
"id": "4ce2ad22-08e6-4e63-96b2-c2301172516e",
"metadata": {},
"source": [
"# ETUDE ET ANALYSE DES ANOMALIES"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "c883dfc2-b9b9-4d3e-80d3-0140cd222492",
"metadata": {},
"outputs": [],
"source": [
"df_aum2['Centralisation Date'] = pd.to_datetime(df_aum2['Centralisation Date'])\n",
"df_flows2['Centralisation Date'] = pd.to_datetime(df_flows2['Centralisation Date'])\n",
"\n",
"\n",
"key_cols = ['Registrar Account - ID', 'Product - Isin']"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "64ca9883-372b-4a5e-8fc1-10e5d835c411",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Doublons AUM: 250232\n",
"Doublons Flows: 4849\n"
]
}
],
"source": [
"# Vérifier doublons exacts\n",
"doublons_aum = df_aum2[df_aum2.duplicated(subset=key_cols + ['Centralisation Date'], keep=False)]\n",
"doublons_flows = df_flows2[df_flows2.duplicated(subset=key_cols + ['Centralisation Date'], keep=False)]\n",
"\n",
"print(\"Doublons AUM:\", doublons_aum.shape[0])\n",
"print(\"Doublons Flows:\", doublons_flows.shape[0])\n",
"\n",
"#same date, code isin du produit, et account ==> revoir les autres caracteristiques "
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "f47b276d-cce6-433c-87c5-860810d71d34",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" Cols: ['Company - Id', 'Company - Ultimate Parent Id', 'Registrar Account - ID', 'Registrar Account - Region', 'Product - Isin']\n",
"Doublons AUM: 26452\n",
"Doublons Flows: 0\n"
]
}
],
"source": [
"cols= ['Company - Id', 'Company - Ultimate Parent Id',\n",
" 'Registrar Account - ID', 'Registrar Account - Region','Product - Isin']\n",
"\n",
"doublons_aum2 = df_aum2[df_aum2.duplicated(subset=cols + ['Centralisation Date'], keep=False)]\n",
"doublons_flows2 = df_flows2[df_flows2.duplicated(subset=cols + ['Centralisation Date'], keep=False)]\n",
"\n",
"print(\" Cols: \", cols)\n",
"print(\"Doublons AUM:\", doublons_aum2.shape[0])\n",
"print(\"Doublons Flows:\", doublons_flows2.shape[0])"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "d2f355e6-30c5-420e-a3db-9095dd5e0147",
"metadata": {},
"outputs": [],
"source": [
"# # Comptes avec same flux et same product ISIN mais IDs différents ---> candidats pseudo-client\n",
"# #plusieurs comptes diff réalisent EXACTEMENT le même flux sur le même produit le même jour.\n",
"# #date?\n",
"\n",
"# pseudo_client_candidates = df_flows2.groupby(['Product - Isin','Centralisation Date', 'Quantity - NetFlows', 'Value € - NetFlows'])['Registrar Account - ID'].nunique()\n",
"# pseudo_client_candidates = pseudo_client_candidates[pseudo_client_candidates > 1]\n",
"# print(\"Comptes potentiels à fusionner:\")\n",
"# print(pseudo_client_candidates)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "8df98c34-b1f7-4fb9-bbc7-c9bbe762022a",
"metadata": {},
"outputs": [],
"source": [
"df = df_flows2.copy()\n",
"df[\"Date\"] = pd.to_datetime(df[\"Centralisation Date\"])\n",
"\n",
"# Groupby par ISIN et Date\n",
"grouped = df.groupby([\"Product - Isin\", \"Date\"])\n",
"\n",
"transfers = []\n",
"\n",
"for (isin, date), group in grouped:\n",
" # Sépare flux positifs et négatifs\n",
" entrants = group[group[\"Value € - NetFlows\"] > 0][[\"Registrar Account - ID\", \"Value € - NetFlows\"]]\n",
" sortants = group[group[\"Value € - NetFlows\"] < 0][[\"Registrar Account - ID\", \"Value € - NetFlows\"]]\n",
"\n",
" # On cherche des paires +M / -M\n",
" for _, row_sortie in sortants.iterrows():\n",
" montant_sortie = row_sortie[\"Value € - NetFlows\"]\n",
" compte_sortant = row_sortie[\"Registrar Account - ID\"]\n",
"\n",
" # Chercher un +M qui matche exactement le -M\n",
" match = entrants[entrants[\"Value € - NetFlows\"] == -montant_sortie]\n",
"\n",
" if len(match) > 0:\n",
" for _, row_entree in match.iterrows():\n",
" transfers.append({\n",
" \"ISIN\": isin,\n",
" \"Date\": date,\n",
" \"Compte sortant\": compte_sortant,\n",
" \"Montant sortie\": montant_sortie,\n",
" \"Compte entrant\": row_entree[\"Registrar Account - ID\"],\n",
" \"Montant entrée\": row_entree[\"Value € - NetFlows\"]\n",
" })\n",
"\n",
"\n",
"transf_compte = pd.DataFrame(transfers)\n",
"transf_compte"
]
},
{
"cell_type": "markdown",
"id": "c898b0c5-0a8e-4640-bc52-9490ee80e53d",
"metadata": {},
"source": [
"# MERGE AND ANALYSIS"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "ce33dbf8-1c59-416a-adc4-6eb7c1ea9d8e",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Merged dataset:\n"
]
}
],
"source": [
"import pandas as pd\n",
"import numpy as np\n",
"import matplotlib.pyplot as plt\n",
"\n",
"\n",
"df_aum2 = df_aum2.rename(columns={\n",
" \"Registrar Account - ID\": \"Account_ID\",\n",
" \"Product - Isin\": \"ISIN\",\n",
" \"Centralisation Date\": \"Date\",\n",
" \"Value - AUM €\": \"AUM_EUR\"\n",
"})\n",
"\n",
"df_flows2 = df_flows2.rename(columns={\n",
" \"Registrar Account - ID\": \"Account_ID\",\n",
" \"Product - Isin\": \"ISIN\",\n",
" \"Centralisation Date\": \"Date\",\n",
" \"Value € - NetFlows\": \"Flow_EUR\"\n",
"})\n",
"\n",
"\n",
"df_aum2[\"Date\"] = pd.to_datetime(df_aum2[\"Date\"])\n",
"df_flows2[\"Date\"] = pd.to_datetime(df_flows2[\"Date\"])\n",
"\n",
"df_aum2[\"Account_ID\"] = df_aum2[\"Account_ID\"].astype(str)\n",
"df_flows2[\"Account_ID\"] = df_flows2[\"Account_ID\"].astype(str)\n",
"\n",
"df_aum2[\"ISIN\"] = df_aum2[\"ISIN\"].str.upper()\n",
"df_flows2[\"ISIN\"] = df_flows2[\"ISIN\"].str.upper()\n",
"\n",
"\n",
"df_merged = pd.merge(\n",
" df_aum2[[\"Account_ID\", \"ISIN\", \"Date\", \"AUM_EUR\"]],\n",
" df_flows2[[\"Account_ID\", \"ISIN\", \"Date\", \"Flow_EUR\"]],\n",
" on=[\"Account_ID\", \"ISIN\", \"Date\"],\n",
" how=\"outer\"\n",
").sort_values([\"Account_ID\", \"ISIN\", \"Date\"])\n",
"\n",
"print(\"Merged dataset:\")"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "7e5d642e-5c16-4c78-8d83-075094902670",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Account_ID</th>\n",
" <th>ISIN</th>\n",
" <th>Date</th>\n",
" <th>AUM_EUR</th>\n",
" <th>Flow_EUR</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>100000014</td>\n",
" <td>LU0553415323</td>\n",
" <td>2015-01-31</td>\n",
" <td>0.000000e+00</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>100000014</td>\n",
" <td>LU0553415323</td>\n",
" <td>2015-02-28</td>\n",
" <td>0.000000e+00</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>100000014</td>\n",
" <td>LU0553415323</td>\n",
" <td>2015-03-31</td>\n",
" <td>0.000000e+00</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>100000014</td>\n",
" <td>LU0553415323</td>\n",
" <td>2015-04-30</td>\n",
" <td>0.000000e+00</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>100000014</td>\n",
" <td>LU0553415323</td>\n",
" <td>2015-05-31</td>\n",
" <td>0.000000e+00</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7369446</th>\n",
" <td>Private Client</td>\n",
" <td>LU2809794220</td>\n",
" <td>2025-10-30</td>\n",
" <td>NaN</td>\n",
" <td>-1623.71</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7369447</th>\n",
" <td>Private Client</td>\n",
" <td>LU2809794220</td>\n",
" <td>2025-10-31</td>\n",
" <td>4.438147e+06</td>\n",
" <td>4946.23</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7369448</th>\n",
" <td>Private Client</td>\n",
" <td>LU2809794576</td>\n",
" <td>2025-09-23</td>\n",
" <td>NaN</td>\n",
" <td>71660.14</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7369449</th>\n",
" <td>Private Client</td>\n",
" <td>LU2809794576</td>\n",
" <td>2025-09-30</td>\n",
" <td>7.094499e+04</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7369450</th>\n",
" <td>Private Client</td>\n",
" <td>LU2809794576</td>\n",
" <td>2025-10-31</td>\n",
" <td>7.871629e+04</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>7369451 rows × 5 columns</p>\n",
"</div>"
],
"text/plain": [
" Account_ID ISIN Date AUM_EUR Flow_EUR\n",
"0 100000014 LU0553415323 2015-01-31 0.000000e+00 NaN\n",
"1 100000014 LU0553415323 2015-02-28 0.000000e+00 NaN\n",
"2 100000014 LU0553415323 2015-03-31 0.000000e+00 NaN\n",
"3 100000014 LU0553415323 2015-04-30 0.000000e+00 NaN\n",
"4 100000014 LU0553415323 2015-05-31 0.000000e+00 NaN\n",
"... ... ... ... ... ...\n",
"7369446 Private Client LU2809794220 2025-10-30 NaN -1623.71\n",
"7369447 Private Client LU2809794220 2025-10-31 4.438147e+06 4946.23\n",
"7369448 Private Client LU2809794576 2025-09-23 NaN 71660.14\n",
"7369449 Private Client LU2809794576 2025-09-30 7.094499e+04 NaN\n",
"7369450 Private Client LU2809794576 2025-10-31 7.871629e+04 NaN\n",
"\n",
"[7369451 rows x 5 columns]"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_merged"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "e484a3df-260e-4532-850b-3917592fcfdf",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Date 2025-11-28\n",
"dtype: datetime64[ns]"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_merged[['Date']].max() #2015-01-02 jusuqua 2025-11-28"
]
},
{
"cell_type": "code",
"execution_count": 23,
"id": "ea14866a-1ce6-4b19-9225-d725304af8ec",
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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
"text/plain": [
"<Figure size 1000x600 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"# 2. HISTOGRAMME DES AUM (SANS ISIN)\n",
"\n",
"# We keep the mean AUM per Account \n",
"aum_by_account = (\n",
" df_merged.groupby(\"Account_ID\")[\"AUM_EUR\"]\n",
" .mean()\n",
" .dropna()\n",
")\n",
"\n",
"# plt.figure(figsize=(10,6))\n",
"# plt.hist(aum_by_account, bins=50)\n",
"# plt.xlabel(\"Mean AUM value (€)\")\n",
"# plt.ylabel(\"Number of client accounts\")\n",
"# plt.title(\"Distribution of client average AUM (one value per Account_ID)\")\n",
"# plt.grid(True)\n",
"# plt.show()\n",
"\n",
"plt.figure(figsize=(10,6))\n",
"plt.hist(aum_by_account, bins=100)\n",
"\n",
"# ZOOM sur les petits AUM (0 à 0.5M €)\n",
"plt.xlim(0, 0.5e7)\n",
"\n",
"plt.xlabel(\"Mean AUM value (€)\")\n",
"plt.ylabel(\"Number of client accounts\")\n",
"plt.title(\"Distribution of client average AUM \")\n",
"plt.show()\n"
]
},
{
"cell_type": "code",
"execution_count": 40,
"id": "8d0dec63-9b9a-47ea-90bd-ffe059bb232a",
"metadata": {},
"outputs": [
{
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAAA18AAAIjCAYAAAD80aFnAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjcsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvTLEjVAAAAAlwSFlzAAAPYQAAD2EBqD+naQAAacdJREFUeJzt3XlYVOX///HXoIIsgqICooi4i/uSivuCoqHmlkuWu6ahhksalWuWW5qWptUnRUtz66OV5kKuqZjlJ3I3dy1FXEFQUeH8/ujHfB1BZRCHwufjuua6mPvc5z7vMwwDL8459zEZhmEIAAAAAPBU2WV1AQAAAADwLCB8AQAAAIANEL4AAAAAwAYIXwAAAABgA4QvAAAAALABwhcAAAAA2ADhCwAAAABsgPAFAAAAADZA+AIAAAAAGyB8AVls3LhxMplMNtlWo0aN1KhRI/PzrVu3ymQyaeXKlTbZfs+ePVWsWDGbbCuj4uPj1bdvX3l5eclkMik0NPSJxnvwNT99+rRMJpPCw8OfaFwA/35Tp05V2bJllZycnNWlPLOuXLkiZ2dn/fDDD1ldCp4RhC8gE4WHh8tkMpkfuXPnlre3t4KCgvTRRx/pxo0bmbKd8+fPa9y4cYqKisqU8TLTP7m29Hj//fcVHh6ugQMH6ssvv9Qrr7yS1SVlyCeffELAe4pq1qwpk8mkuXPnprk85Z8qly9fTnN5hQoV0gzlJpNJEydOTHOdbt26yWQyycXF5YnrR+bKyOdeXFycpkyZolGjRsnO7u8/x65cuaJp06apQYMGKliwoPLmzavatWtr2bJlaY6RmJioUaNGydvbW46OjqpVq5YiIiIs+ty8eVNz5sxR8+bNVahQIeXJk0dVq1bV3LlzlZSUZNH3yJEjGjlypKpUqaI8efKoUKFCCg4O1q+//mrdC5KBsf766y916tRJefPmlaurq1544QWdPHnSos+5c+c0fvx41axZU/ny5VOBAgXUqFEj/fjjj6nGe/D38f2P6Ohoc7/8+fOrb9++Gj16tNX7CGSIASDTLFiwwJBkTJgwwfjyyy+N+fPnG++//77RvHlzw2QyGb6+vsbvv/9usc7du3eNW7duWbWdX375xZBkLFiwwKr1EhMTjcTERPPzLVu2GJKMFStWWDVORmu7c+eOcfv27Uzb1tNQq1Yto27dupk2XsOGDY2GDRuanycnJxu3bt0y7t27l2nbSEv58uUttovM88cffxiSjGLFij30vTJ27FhDknHp0qU0lz/4/Tl16pQhycidO7fh7++fqn98fLzh7Oxs5M6d23B2ds6U/UDmychn8ocffmi4urpafP5///33Rq5cuYwXXnjBmDlzpjF79myjcePGhiRjzJgxqcbo0qWLkTNnTmPEiBHGp59+agQEBBg5c+Y0fvrpJ3Of/fv3GyaTyQgMDDSmTp1qzJs3z2jXrp0hyejevbvFeMOHDzfy5s1r9OnTx/j000+NqVOnGiVKlDBy5MhhREREWPWaWDPWjRs3jFKlShkeHh7GlClTjBkzZhg+Pj5GkSJFjMuXL5v7ffzxx4ajo6PRtWtXY/bs2cbMmTONatWqGZKM+fPnW4z54O/j+x8P/s49dOiQIcnYtGmTVfsIZAThC8hEKR/2v/zyS6plmzZtMhwdHQ1fX1/j5s2bT7Qda3/RJyQkpNlu6/D1b+Dn52cEBwdn2ngPhi9b+beGr+Tk5Cf++XjaxowZY3h4eBjffPONYTKZjFOnTqXqk9Hw1b59e0OSERUVZdF/8eLFRq5cuYzWrVv/Y8LXv+F7ZSsZ+dyrVKmS8fLLL1u0nTx50jh9+rRFW3JystGkSRPDwcHBiI+PN7f//PPPhiRj2rRp5rZbt24ZJUqUMAICAsxtly5dMg4cOJBq+7169TIkGceOHTO3/frrr8aNGzcs+l2+fNkoWLCg1f+UsmasKVOmGJKMPXv2mNsOHz5s5MiRwwgLCzO3HThwINXP1O3bt42yZcsaRYoUsWh/1O/jtFSoUMF45ZVX0tUXeBKcdgjYSJMmTTR69GidOXNGX331lbk9rWu+IiIiVK9ePeXNm1cuLi4qU6aM3nrrLUl/X6f13HPPSZJ69eplPo0i5RSzRo0aqUKFCtq7d68aNGggJycn87oPXn+UIikpSW+99Za8vLzk7OysNm3a6Ny5cxZ9ihUrpp49e6Za9/4xH1dbWtd8JSQkaPjw4fLx8ZGDg4PKlCmjDz74QIZhWPQzmUwaNGiQVq9erQoVKsjBwUHly5fX+vXr037BHxATE6M+ffrI09NTuXPnVuXKlbVw4ULz8pTr306dOqW1a9eaaz99+vQjx/3qq69Us2ZNOTk5KV++fGrQoIE2btz40P4Pu+bryJEj6tixo9zd3ZU7d27VqFFD3333nUWflNNodu7cqWHDhqlgwYJydnZWu3btdOnSJXO/YsWK6eDBg9q2bZt5P9L6vt/vgw8+UJ06dZQ/f345OjqqevXqqa4FrFChgho3bpxq3eTkZBUuXFgdO3a0aJs5c6bKly+v3Llzy9PTU6+++qquXbtmsW6xYsXUqlUrbdiwQTVq1JCjo6M+/fRTSdKCBQvUpEkTeXh4yMHBQf7+/mme5pecnKxx48bJ29tbTk5Oaty4sQ4dOpTme/b69esKDQ01v99KliypKVOmWHXNzZIlS9SxY0e1atVKbm5uWrJkSbrXfZyAgAD5+fmlGnPx4sVq0aKF3N3d0zVOz5495eLiopMnTyooKEjOzs7y9vbWhAkTUv1sZcb3Ki0//fSTXnzxRRUtWlQODg7y8fHR0KFDdevWrVR9jxw5ok6dOqlgwYJydHRUmTJl9Pbbb1v0+euvv9SnTx95e3vLwcFBfn5+GjhwoO7cuWPuc/LkSb344otyd3eXk5OTateurbVr11qMk/Jz9ODPdspnwNatW81tKZ+nhw4dUuPGjeXk5KTChQtr6tSpFus96nMvLadOndK+ffsUGBho0e7n5ydfX1+LNpPJpLZt2yoxMdHiNLyVK1cqR44c6t+/v7ktd+7c6tOnjyIjI82f4QUKFFD58uVT1dCuXTtJ0uHDh81t1atXT3Vaa/78+VW/fn2LfulhzVgrV67Uc889Z34dJals2bJq2rSpli9fbm4rX768ChQoYLGug4ODnn/+ef35558PPbX/xo0bqU6xfFCzZs30/fffp/r5ADIb4QuwoZTrhx71x/nBgwfVqlUrJSYmasKECZo+fbratGmjnTt3SpLKlSunCRMmSJL69++vL7/8Ul9++aUaNGhgHuPKlStq2bKlqlSpopkzZ6b5B/P93nvvPa1du1ajRo3SkCFDFBERocDAwDT/SHqU9NR2P8Mw1KZNG3344Ydq0aKFZsyYoTJlyuiNN97QsGHDUvXfsWOHXnvtNXXp0kVTp07V7du31aFDB125cuWRdd26dUuNGjXSl19+qW7dumnatGlyc3NTz549NWvWLHPtX375pQoUKKAqVaqYay9YsOBDxx0/frxeeeUV5cqVSxMmTND48ePl4+OjzZs3p/clk/T397x27do6fPiw3nzzTU2fPl3Ozs5q27atVq1alar/4MGD9fvvv2vs2LEaOHCgvv/+ew0aNMi8fObMmSpSpIjKli1r3o8H/5B90KxZs1S1alVNmDBB77//vnLmzKkXX3zR4g/Xzp07a/v27RbXS0h/f1/Onz+vLl26mNteffVVvfHGG6pbt65mzZqlXr16afHixQoKCtLdu3ct1j969Ki6du2qZs2aadasWapSpYokae7cufL19dVbb72l6dOny8fHR6+99prmzJljsX5YWJjGjx+vGjVqaNq0aSpVqpSCgoKUkJBg0e/mzZtq2LChvvrqK3Xv3l0fffSR6tatq7CwsDTfb2n5+eefdfz4cXXt2lX29vZq3769Fi9enK5106tr165aunSp+Y/Ay5cva+PGjXrppZesGicpKUktWrSQp6enpk6dqurVq2vs2LEaO3asRb/M+F6lZcWKFbp586YGDhyojz/+WEFBQfr444/VvXt3i3779u1TrVq1tHnzZvXr10+zZs1S27Zt9f3335v7nD9
"text/plain": [
"<Figure size 1000x600 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"# 2. HISTOGRAMME DES AUM (SANS ISIN) POUR 2022+\n",
"df_filtered = df_merged[df_merged[\"Date\"].dt.year >= 2022]\n",
"\n",
"aum_by_account = (\n",
" df_filtered\n",
" .groupby(\"Account_ID\")[\"AUM_EUR\"]\n",
" .mean()\n",
" .dropna()\n",
")\n",
"\n",
"plt.figure(figsize=(10,6))\n",
"plt.hist(aum_by_account, bins=100)\n",
"\n",
"# ZOOM sur les petits AUM (0 à 5M €)\n",
"plt.xlim(0, 0.5e7)\n",
"\n",
"plt.xlabel(\"Mean AUM value (€)\")\n",
"plt.ylabel(\"Number of client accounts\")\n",
"plt.title(\"Distribution of client average AUM per account (2022–2025)\")\n",
"plt.show()\n"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "c79ae705-833e-420f-ab3e-51ccb2ae52c5",
"metadata": {},
"outputs": [],
"source": [
"# # 1) Créer une colonne Année-Mois\n",
"\n",
"# df_filtered = df_merged[df_merged[\"Date\"].dt.year >= 2022]\n",
"# df_filtered[\"YearMonth\"] = df_merged[\"Date\"].dt.to_period(\"M\")\n",
"\n",
"# # 2) AUM moyen par compte ET par mois\n",
"# aum_monthly = (\n",
"# df_merged.groupby([\"Account_ID\", \"YearMonth\"])[\"AUM_EUR\"]\n",
"# .mean()\n",
"# .reset_index()\n",
"# )\n",
"\n",
"# # 3) Pour chaque compte : moyenne des AUM mensuels sur toute la période\n",
"# aum_avg_over_time = (\n",
"# aum_monthly.groupby(\"Account_ID\")[\"AUM_EUR\"]\n",
"# .mean()\n",
"# .dropna()\n",
"# )\n",
"\n",
"# # 4) Histogramme des AUM mensuels moyens par compte (sur toute l’historique)\n",
"# plt.figure(figsize=(10,6))\n",
"# plt.hist(aum_avg_over_time, bins=100)\n",
"\n",
"# # Option : zoom sur les petits AUM (ex. 0 à 5M €)\n",
"# plt.xlim(0, 0.5e7)\n",
"\n",
"# plt.xlabel(\"Average monthly AUM per account (€)\")\n",
"# plt.ylabel(\"Number of client accounts\")\n",
"# plt.title(\"Distribution of average monthly AUM per account (full history)\")\n",
"# plt.grid(True)\n",
"# plt.show()\n"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "f13c213e-7f72-494a-bcf0-b4cd9feee55d",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Monthly flow summary:\n",
" n_positive_flows n_negative_flows\n",
"YearMonth \n",
"2015-01 10688 11779\n",
"2015-02 12905 10822\n",
"2015-03 15497 13207\n",
"2015-04 13838 11641\n",
"2015-05 11143 9065\n"
]
},
{
"data": {
"image/png": "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
"text/plain": [
"<Figure size 1400x600 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"###############################################################################\n",
"# 4. ANALYSE MENSUELLE DES FLOWS (ENTRANTS / SORTANTS)\n",
"\n",
"df_merged[\"YearMonth\"] = df_merged[\"Date\"].dt.to_period(\"M\")\n",
"\n",
"flows_monthly = df_merged.groupby(\"YearMonth\").agg(\n",
" n_positive_flows=(\"Flow_EUR\", lambda x: (x > 0).sum()),\n",
" n_negative_flows=(\"Flow_EUR\", lambda x: (x < 0).sum()),\n",
")\n",
"\n",
"print(\"Monthly flow summary:\")\n",
"print(flows_monthly.head())\n",
"\n",
"# ---- Plot bar chart ----\n",
"flows_monthly.index = flows_monthly.index.astype(str)\n",
"\n",
"plt.figure(figsize=(14,6))\n",
"plt.bar(flows_monthly.index, flows_monthly[\"n_positive_flows\"], label=\"Positive flows (inflows)\", alpha=0.7)\n",
"plt.bar(flows_monthly.index, flows_monthly[\"n_negative_flows\"], label=\"Negative flows (outflows)\", alpha=0.7)\n",
"plt.xticks(rotation=90)\n",
"plt.xlabel(\"Year-Month\")\n",
"plt.ylabel(\"Number of accounts with flows\")\n",
"plt.title(\"Monthly number of accounts with inflows vs outflows\")\n",
"plt.legend()\n",
"plt.tight_layout()\n",
"plt.show()\n"
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "4af0e205-a304-4b10-be1d-de69904aa0da",
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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
"text/plain": [
"<Figure size 1400x600 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"df_merged[\"YearMonth\"] = df_merged[\"Date\"].dt.to_period(\"M\")\n",
"\n",
"monthly_flow_amounts = df_merged.groupby(\"YearMonth\").agg(\n",
" avg_positive_flow=(\"Flow_EUR\", lambda x: x[x > 0].mean()),\n",
" avg_negative_flow=(\"Flow_EUR\", lambda x: x[x < 0].mean())\n",
")\n",
"\n",
"monthly_flow_amounts.index = monthly_flow_amounts.index.astype(str)\n",
"\n",
"plt.figure(figsize=(14,6))\n",
"plt.plot(monthly_flow_amounts.index, monthly_flow_amounts[\"avg_positive_flow\"], label=\"Average inflow (positive)\", marker=\"o\")\n",
"plt.plot(monthly_flow_amounts.index, monthly_flow_amounts[\"avg_negative_flow\"], label=\"Average outflow (negative)\", marker=\"o\")\n",
"plt.xticks(rotation=90)\n",
"plt.xlabel(\"Year-Month\")\n",
"plt.ylabel(\"Average flow (€)\")\n",
"plt.title(\"Monthly average inflows and outflows\")\n",
"plt.legend()\n",
"plt.tight_layout()\n",
"plt.show()\n"
]
},
{
"cell_type": "code",
"execution_count": 15,
"id": "2d548152-196f-456a-b21e-4d05e39d03c5",
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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
"text/plain": [
"<Figure size 1400x600 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"df = df_merged.copy()\n",
"df[\"YearMonth\"] = df[\"Date\"].dt.to_period(\"M\")\n",
"\n",
"# 1) Flow mensuel total par client\n",
"monthly_client_flow = (\n",
" df.groupby([\"Account_ID\", \"YearMonth\"])[\"Flow_EUR\"]\n",
" .sum()\n",
" .reset_index()\n",
")\n",
"\n",
"# 2) Calcul des seuils de quantiles (tu peux ajuster)\n",
"q1 = monthly_client_flow[\"Flow_EUR\"].quantile(0.33)\n",
"q2 = monthly_client_flow[\"Flow_EUR\"].quantile(0.66)\n",
"\n",
"# 3) Catégorisation des clients\n",
"def categorize(flow):\n",
" if flow <= q1:\n",
" return \"Petits flows\"\n",
" elif flow <= q2:\n",
" return \"Flows moyens\"\n",
" else:\n",
" return \"Grands flows\"\n",
"\n",
"monthly_client_flow[\"Flow_category\"] = monthly_client_flow[\"Flow_EUR\"].apply(categorize)\n",
"\n",
"# 4) Nombre de clients dans chaque catégorie par mois\n",
"category_counts = (\n",
" monthly_client_flow.groupby([\"YearMonth\", \"Flow_category\"])\n",
" .size()\n",
" .unstack(fill_value=0)\n",
")\n",
"\n",
"category_counts.index = category_counts.index.astype(str)\n",
"\n",
"# 5) Plot\n",
"category_counts.plot(kind=\"bar\", stacked=True, figsize=(14,6))\n",
"plt.title(\"Répartition des clients par niveau de flux mensuel\")\n",
"plt.xlabel(\"Mois\")\n",
"plt.ylabel(\"Nombre de clients\")\n",
"plt.xticks(rotation=90)\n",
"plt.tight_layout()\n",
"plt.show()\n"
]
},
{
"cell_type": "code",
"execution_count": 17,
"id": "2c5a83e0-1faf-4745-88b3-c0fb363317fc",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Répartition des comptes par catégorie :\n",
"Grands flows : YearMonth\n",
"2015-01 432\n",
"2015-02 499\n",
"2015-03 536\n",
"2015-04 530\n",
"2015-05 472\n",
" ... \n",
"2025-07 412\n",
"2025-08 388\n",
"2025-09 407\n",
"2025-10 418\n",
"2025-11 231\n",
"Name: Grands flows, Length: 131, dtype: int64 comptes\n",
"Petits flows : YearMonth\n",
"2015-01 7429\n",
"2015-02 7380\n",
"2015-03 7390\n",
"2015-04 7416\n",
"2015-05 7493\n",
" ... \n",
"2025-07 3474\n",
"2025-08 3507\n",
"2025-09 3509\n",
"2025-10 3529\n",
"2025-11 174\n",
"Name: Petits flows, Length: 131, dtype: int64 comptes\n"
]
}
],
"source": [
"print(\"Répartition des comptes par catégorie :\")\n",
"for cat, count in category_counts.items():\n",
" print(f\"{cat} : {count} comptes\")\n"
]
},
{
"cell_type": "code",
"execution_count": 18,
"id": "943b359e-b1c0-435e-943b-94167f8c566f",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Moyenne du nombre de comptes par catégorie (sur toute la période) :\n",
"Grands flows : 334 comptes en moyenne par mois\n",
"Petits flows : 6736 comptes en moyenne par mois\n"
]
}
],
"source": [
"# Nombre de comptes dans chaque catégorie par mois\n",
"category_counts_by_month = (\n",
" monthly_client_flow.groupby([\"YearMonth\", \"Flow_category\"])\n",
" .size()\n",
" .unstack(fill_value=0)\n",
")\n",
"\n",
"# Moyenne sur tous les mois\n",
"category_counts_mean = category_counts_by_month.mean()\n",
"\n",
"print(\"Moyenne du nombre de comptes par catégorie (sur toute la période) :\")\n",
"for cat, mean_val in category_counts_mean.items():\n",
" print(f\"{cat} : {mean_val:.0f} comptes en moyenne par mois\")\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "c6bb455c-91f9-4169-a179-273e98ef3ebd",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"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": "3.13.8"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
Reference in New Issue Copy Permalink