Stats descriptives

.ipynb_checkpoints/Stats_descriptives-checkpoint.ipynb

@@ -0,0 +1,33 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5e49fa70-05e3-4d9a-82db-e36ab3c993c7",
+   "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
+}

.ipynb_checkpoints/detection_rupture-checkpoint.py

@@ -0,0 +1,86 @@
+import pandas as pd
+
+def detect_ruptures(df, epsilon=0.05):
+    # Colonnes clés pour identifier les comptes
+    key_cols = [
+        'Agreement - Code',
+        'Company - Id',
+        'Company - Ultimate Parent Id',
+        'Registrar Account - Region',
+        'RegistrarAccount - Country',
+        'Registrar Account - ID'
+    ]
+    
+    # Travailler sur une copie
+    df_temp = df.copy()
+
+    # Colonnes de dates
+    df_temp['Centralisation Date'] = pd.to_datetime(df_temp['Centralisation Date'])
+
+    # Dates distinctes
+    full_dates = (
+        pd.Series(df_temp['Centralisation Date'].unique())
+        .sort_values()
+        .reset_index(drop=True)
+    )
+
+    # Combinaisons comptes × dates
+    accounts = df_temp[key_cols].drop_duplicates()
+    full_index = accounts.merge(
+        pd.DataFrame({'Centralisation Date': full_dates}), 
+        how='cross'
+    )
+
+    # Agréger les AUM par clé
+    agg_cols = key_cols + ['Centralisation Date']
+    df_agg = (
+        df_temp.groupby(agg_cols)['Value - AUM €']
+        .sum()
+        .reset_index()
+    )
+
+    # Merge sur toutes les combinaisons
+    df_full = pd.merge(full_index, df_agg, on=agg_cols, how='left')
+
+    # Remplissage des trous par 0
+    df_full['Value - AUM €'] = df_full['Value - AUM €'].fillna(0)
+
+    # Tri
+    df_full = df_full.sort_values(key_cols + ['Centralisation Date'])
+
+    # Variation et valeur précédente
+    df_full['AUM_diff'] = df_full.groupby(key_cols)['Value - AUM €'].diff().fillna(0)
+    df_full['prev_value'] = df_full.groupby(key_cols)['Value - AUM €'].shift(1).fillna(0)
+
+    # Comptes qui perdent tout
+    df_zero = df_full[(df_full['AUM_diff'] < 0) & (df_full['Value - AUM €'] == 0)].copy()
+
+    # Comptes qui partent de 0
+    df_from_zero = df_full[(df_full['AUM_diff'] > 0) & (df_full['prev_value'] == 0)].copy()
+
+    # Colonnes pour le merge (sans ID)
+    merge_cols = [
+        'Centralisation Date',
+        'Agreement - Code',
+        'Company - Id',
+        'Company - Ultimate Parent Id',
+        'Registrar Account - Region',
+        'RegistrarAccount - Country'
+    ]
+
+    # Détection des ruptures
+    ruptures = pd.merge(df_zero, df_from_zero, on=merge_cols, suffixes=('_old','_new'))
+
+    # Calcul de la différence relative selon epsilon
+    ruptures['diff_rel'] = abs(ruptures['AUM_diff_old'] + ruptures['AUM_diff_new']) / (
+        (abs(ruptures['AUM_diff_old']) + abs(ruptures['AUM_diff_new'])) / 2
+    )
+
+    # Filtrage avec epsilon
+    ruptures = ruptures[ruptures['diff_rel'] <= epsilon].drop(columns=['diff_rel'])
+
+    # Colonnes finales
+    ruptures_df = ruptures[['Centralisation Date','Registrar Account - ID_old','Registrar Account - ID_new','AUM_diff_new']]
+    ruptures_df.columns = ['date','old_account','new_account','value']
+
+    return ruptures_df

.ipynb_checkpoints/function-checkpoint.py

@@ -0,0 +1,72 @@
+import matplotlib.pyplot as plt
+import pandas as pd
+
+def evolution_2_comptes(df, id1, id2):
+    def prepare_df(id):
+        df_id = df[df['Registrar Account - ID'] == id].copy()
+        df_id['Centralisation Date'] = pd.to_datetime(df_id['Centralisation Date'])
+        df_agg = (
+            df_id
+            .groupby('Centralisation Date')['Quantity - AUM']
+            .sum()
+            .reset_index()
+            .sort_values('Centralisation Date')
+        )
+        return df_agg
+
+    df1 = prepare_df(id1)
+    df2 = prepare_df(id2)
+
+    plt.figure(figsize=(12, 6))
+
+    # Courbe du premier compte
+    plt.plot(df1['Centralisation Date'], df1['Quantity - AUM'],
+             marker='.', linestyle='-', label=f'Account {id1}')
+
+    # Courbe du second compte
+    plt.plot(df2['Centralisation Date'], df2['Quantity - AUM'],
+             marker='.', linestyle='-', label=f'Account {id2}')
+
+    plt.title("Évolution des AUM pour deux comptes")
+    plt.xlabel("Date")
+    plt.ylabel("Quantity - AUM")
+    plt.grid(True)
+    plt.legend()           # <- important pour distinguer les comptes
+    plt.tight_layout()
+    plt.show()
+
+def evolution_3_comptes(df, id1, id2, id3):
+    def prepare_df(id):
+        df_id = df[df['Registrar Account - ID'] == id].copy()
+        df_id['Centralisation Date'] = pd.to_datetime(df_id['Centralisation Date'])
+        df_agg = (
+            df_id
+            .groupby('Centralisation Date')['Quantity - AUM']
+            .sum()
+            .reset_index()
+            .sort_values('Centralisation Date')
+        )
+        return df_agg
+
+    df1 = prepare_df(id1)
+    df2 = prepare_df(id2)
+    df3 = prepare_df(id3)
+
+    plt.figure(figsize=(12, 6))
+
+    plt.plot(df1['Centralisation Date'], df1['Quantity - AUM'],
+             marker='.', linestyle='-', label=f'Account {id1}')
+
+    plt.plot(df2['Centralisation Date'], df2['Quantity - AUM'],
+             marker='.', linestyle='-', label=f'Account {id2}')
+
+    plt.plot(df3['Centralisation Date'], df3['Quantity - AUM'],
+             marker='.', linestyle='-', label=f'Account {id3}')
+
+    plt.title("Évolution des AUM pour trois comptes")
+    plt.xlabel("Date")
+    plt.ylabel("Quantity - AUM")
+    plt.grid(True)
+    plt.legend()
+    plt.tight_layout()
+    plt.show()

.ipynb_checkpoints/rupture-checkpoint.ipynb

@@ -0,0 +1,58 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "132a1aa1-4cb9-49e7-9f45-c09dd8fd57c1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "import s3fs\n",
+    "import pandas as pd\n",
+    "\n",
+    "s3_ENDPOINT_URL = \"https://\" + os.environ[\"AWS_S3_ENDPOINT\"]\n",
+    "\n",
+    "fs = s3fs.S3FileSystem(client_kwargs={'endpoint_url': s3_ENDPOINT_URL})\n",
+    "\n",
+    "BUCKET = \"projet-bdc-data\"\n",
+    "carmignac_path = \"projet-bdc-data/carmignac\"\n",
+    "\n",
+    "# Liste des fichiers AUM\n",
+    "all_files = fs.ls(carmignac_path)\n",
+    "aum_files = [f for f in all_files if \"AUM\" in f and f.endswith(\".csv\")]\n",
+    "print(\"Fichiers AUM :\", aum_files)\n",
+    "\n",
+    "# Lire tous les fichiers dans un dictionnaire\n",
+    "aum_data = {}\n",
+    "for file_path in aum_files:\n",
+    "    with fs.open(file_path, 'r') as f:\n",
+    "        df = pd.read_csv(f, sep=';',low_memory=False)\n",
+    "        aum_data[os.path.basename(file_path)] = df\n",
+    "\n",
+    "df = aum_data['AUM ENSAE V2 -20251105.csv']"
+   ]
+  }
+ ],
+ "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
+}

detection_rupture.py

@@ -0,0 +1,86 @@
+import pandas as pd
+
+def detect_ruptures(df, epsilon=0.05):
+    # Colonnes clés pour identifier les comptes
+    key_cols = [
+        'Agreement - Code',
+        'Company - Id',
+        'Company - Ultimate Parent Id',
+        'Registrar Account - Region',
+        'RegistrarAccount - Country',
+        'Registrar Account - ID'
+    ]
+    
+    # Travailler sur une copie
+    df_temp = df.copy()
+
+    # Colonnes de dates
+    df_temp['Centralisation Date'] = pd.to_datetime(df_temp['Centralisation Date'])
+
+    # Dates distinctes
+    full_dates = (
+        pd.Series(df_temp['Centralisation Date'].unique())
+        .sort_values()
+        .reset_index(drop=True)
+    )
+
+    # Combinaisons comptes × dates
+    accounts = df_temp[key_cols].drop_duplicates()
+    full_index = accounts.merge(
+        pd.DataFrame({'Centralisation Date': full_dates}), 
+        how='cross'
+    )
+
+    # Agréger les AUM par clé
+    agg_cols = key_cols + ['Centralisation Date']
+    df_agg = (
+        df_temp.groupby(agg_cols)['Value - AUM €']
+        .sum()
+        .reset_index()
+    )
+
+    # Merge sur toutes les combinaisons
+    df_full = pd.merge(full_index, df_agg, on=agg_cols, how='left')
+
+    # Remplissage des trous par 0
+    df_full['Value - AUM €'] = df_full['Value - AUM €'].fillna(0)
+
+    # Tri
+    df_full = df_full.sort_values(key_cols + ['Centralisation Date'])
+
+    # Variation et valeur précédente
+    df_full['AUM_diff'] = df_full.groupby(key_cols)['Value - AUM €'].diff().fillna(0)
+    df_full['prev_value'] = df_full.groupby(key_cols)['Value - AUM €'].shift(1).fillna(0)
+
+    # Comptes qui perdent tout
+    df_zero = df_full[(df_full['AUM_diff'] < 0) & (df_full['Value - AUM €'] == 0)].copy()
+
+    # Comptes qui partent de 0
+    df_from_zero = df_full[(df_full['AUM_diff'] > 0) & (df_full['prev_value'] == 0)].copy()
+
+    # Colonnes pour le merge (sans ID)
+    merge_cols = [
+        'Centralisation Date',
+        'Agreement - Code',
+        'Company - Id',
+        'Company - Ultimate Parent Id',
+        'Registrar Account - Region',
+        'RegistrarAccount - Country'
+    ]
+
+    # Détection des ruptures
+    ruptures = pd.merge(df_zero, df_from_zero, on=merge_cols, suffixes=('_old','_new'))
+
+    # Calcul de la différence relative selon epsilon
+    ruptures['diff_rel'] = abs(ruptures['AUM_diff_old'] + ruptures['AUM_diff_new']) / (
+        (abs(ruptures['AUM_diff_old']) + abs(ruptures['AUM_diff_new'])) / 2
+    )
+
+    # Filtrage avec epsilon
+    ruptures = ruptures[ruptures['diff_rel'] <= epsilon].drop(columns=['diff_rel'])
+
+    # Colonnes finales
+    ruptures_df = ruptures[['Centralisation Date','Registrar Account - ID_old','Registrar Account - ID_new','AUM_diff_new']]
+    ruptures_df.columns = ['date','old_account','new_account','value']
+
+    return ruptures_df

function.py

@@ -0,0 +1,73 @@
+import matplotlib.pyplot as plt
+import pandas as pd
+
+def evolution_2_comptes(df, id1, id2):
+    def prepare_df(id):
+        df_id = df[df['Registrar Account - ID'] == id].copy()
+        df_id['Centralisation Date'] = pd.to_datetime(df_id['Centralisation Date'])
+        df_agg = (
+            df_id
+            .groupby('Centralisation Date')['Quantity - AUM']
+            .sum()
+            .reset_index()
+            .sort_values('Centralisation Date')
+        )
+        return df_agg
+
+    df1 = prepare_df(id1)
+    df2 = prepare_df(id2)
+
+    plt.figure(figsize=(12, 6))
+
+    # Courbe du premier compte
+    plt.plot(df1['Centralisation Date'], df1['Quantity - AUM'],
+             marker='.', linestyle='-', label=f'Account {id1}')
+
+    # Courbe du second compte
+    plt.plot(df2['Centralisation Date'], df2['Quantity - AUM'],
+             marker='.', linestyle='-', label=f'Account {id2}')
+
+    plt.title("Évolution des AUM pour deux comptes")
+    plt.xlabel("Date")
+    plt.ylabel("Quantity - AUM")
+    plt.grid(True)
+    plt.legend()           # <- important pour distinguer les comptes
+    plt.tight_layout()
+    plt.show()
+
+
+def evolution_3_comptes(df, id1, id2, id3):
+    def prepare_df(id):
+        df_id = df[df['Registrar Account - ID'] == id].copy()
+        df_id['Centralisation Date'] = pd.to_datetime(df_id['Centralisation Date'])
+        df_agg = (
+            df_id
+            .groupby('Centralisation Date')['Quantity - AUM']
+            .sum()
+            .reset_index()
+            .sort_values('Centralisation Date')
+        )
+        return df_agg
+
+    df1 = prepare_df(id1)
+    df2 = prepare_df(id2)
+    df3 = prepare_df(id3)
+
+    plt.figure(figsize=(12, 6))
+
+    plt.plot(df1['Centralisation Date'], df1['Quantity - AUM'],
+             marker='.', linestyle='-', label=f'Account {id1}')
+
+    plt.plot(df2['Centralisation Date'], df2['Quantity - AUM'],
+             marker='.', linestyle='-', label=f'Account {id2}')
+
+    plt.plot(df3['Centralisation Date'], df3['Quantity - AUM'],
+             marker='.', linestyle='-', label=f'Account {id3}')
+
+    plt.title("Évolution des AUM pour trois comptes")
+    plt.xlabel("Date")
+    plt.ylabel("Quantity - AUM")
+    plt.grid(True)
+    plt.legend()
+    plt.tight_layout()
+    plt.show()