diff --git a/Clustering.ipynb b/Clustering.ipynb
index 705951e..0e3aca7 100644
--- a/Clustering.ipynb
+++ b/Clustering.ipynb
@@ -1806,10 +1806,179 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 240,
    "id": "c697888b-cb72-4a98-86af-56647f5a5161",
    "metadata": {},
-   "outputs": [],
+   "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>log_aum_qty_mean</th>\n",
+       "      <th>log_gross_flow_qty_mean</th>\n",
+       "      <th>frequency</th>\n",
+       "      <th>rel_intensity_total</th>\n",
+       "      <th>net_flow_qty_vol</th>\n",
+       "      <th>n_tx_total</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>409</th>\n",
+       "      <td>12.907910</td>\n",
+       "      <td>10.377945</td>\n",
+       "      <td>0.984615</td>\n",
+       "      <td>10.355747</td>\n",
+       "      <td>25238.018408</td>\n",
+       "      <td>38671</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>381</th>\n",
+       "      <td>14.850749</td>\n",
+       "      <td>11.109940</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>3.085492</td>\n",
+       "      <td>39047.638017</td>\n",
+       "      <td>36949</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>399</th>\n",
+       "      <td>14.329599</td>\n",
+       "      <td>10.848036</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>3.998634</td>\n",
+       "      <td>32239.885939</td>\n",
+       "      <td>36456</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>418</th>\n",
+       "      <td>14.247808</td>\n",
+       "      <td>11.848117</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>11.796898</td>\n",
+       "      <td>99058.868316</td>\n",
+       "      <td>28497</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>419</th>\n",
+       "      <td>14.627385</td>\n",
+       "      <td>11.110770</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>1.484969</td>\n",
+       "      <td>30763.896059</td>\n",
+       "      <td>27296</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",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>314</th>\n",
+       "      <td>11.077486</td>\n",
+       "      <td>7.942331</td>\n",
+       "      <td>0.043478</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>13490.257463</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>238</th>\n",
+       "      <td>9.093884</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>198</th>\n",
+       "      <td>10.191618</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>266</th>\n",
+       "      <td>8.939081</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>328</th>\n",
+       "      <td>12.580429</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>421 rows × 6 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "     log_aum_qty_mean  log_gross_flow_qty_mean  frequency  \\\n",
+       "409         12.907910                10.377945   0.984615   \n",
+       "381         14.850749                11.109940   1.000000   \n",
+       "399         14.329599                10.848036   1.000000   \n",
+       "418         14.247808                11.848117   1.000000   \n",
+       "419         14.627385                11.110770   1.000000   \n",
+       "..                ...                      ...        ...   \n",
+       "314         11.077486                 7.942331   0.043478   \n",
+       "238          9.093884                 0.000000   0.000000   \n",
+       "198         10.191618                 0.000000   0.000000   \n",
+       "266          8.939081                 0.000000   0.000000   \n",
+       "328         12.580429                 0.000000   0.000000   \n",
+       "\n",
+       "     rel_intensity_total  net_flow_qty_vol  n_tx_total  \n",
+       "409            10.355747      25238.018408       38671  \n",
+       "381             3.085492      39047.638017       36949  \n",
+       "399             3.998634      32239.885939       36456  \n",
+       "418            11.796898      99058.868316       28497  \n",
+       "419             1.484969      30763.896059       27296  \n",
+       "..                   ...               ...         ...  \n",
+       "314             1.000000      13490.257463           1  \n",
+       "238             0.000000          0.000000           0  \n",
+       "198             0.000000          0.000000           0  \n",
+       "266             0.000000          0.000000           0  \n",
+       "328             0.000000          0.000000           0  \n",
+       "\n",
+       "[421 rows x 6 columns]"
+      ]
+     },
+     "execution_count": 240,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
     "X_sorted = X.sort_values(by=\"n_tx_total\", ascending=False)\n",
     "X_sorted"
@@ -3208,7 +3377,6 @@
     "\n",
     "for start, end in windows:\n",
     "    # FILTRAGE : On recalcule les variables sur la période (simulation)\n",
-    "    # Note : Tu dois adapter cette partie à tes données brutes par date\n",
     "    df_period = df_month[(df_month['month'] > start) & (df_month['month'] <= end)].copy()\n",
     "\n",
     "    eps = 1e-9  \n",
@@ -3513,6 +3681,84 @@
     "df_evo.groupby([\"cluster_2016\", \"cluster_2019\"]).size().unstack()"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 212,
+   "id": "40cf3d1e-e53c-4a13-acba-c9d6cebfcca0",
+   "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>cluster_2019</th>\n",
+       "      <th>1</th>\n",
+       "      <th>2</th>\n",
+       "      <th>3</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>cluster_2016</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>8.0</td>\n",
+       "      <td>2.0</td>\n",
+       "      <td>10.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>1.0</td>\n",
+       "      <td>38.0</td>\n",
+       "      <td>5.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>NaN</td>\n",
+       "      <td>5.0</td>\n",
+       "      <td>82.0</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "cluster_2019    1     2     3\n",
+       "cluster_2016                 \n",
+       "1             8.0   2.0  10.0\n",
+       "2             1.0  38.0   5.0\n",
+       "3             NaN   5.0  82.0"
+      ]
+     },
+     "execution_count": 212,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df_evo.groupby([\"cluster_2016\", \"cluster_2019\"]).size().unstack()"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 213,
diff --git a/clustering_avril.ipynb b/clustering_avril.ipynb
index 595eccc..8818101 100644
--- a/clustering_avril.ipynb
+++ b/clustering_avril.ipynb
@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 290,
+   "execution_count": 322,
    "id": "2fee3a54-847b-432f-bda5-3d6a9aa9020c",
    "metadata": {},
    "outputs": [],
@@ -33,7 +33,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 291,
+   "execution_count": 323,
    "id": "1f95b6b6-03b8-4f23-b236-5c71beedea04",
    "metadata": {},
    "outputs": [],
@@ -44,7 +44,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 292,
+   "execution_count": 324,
    "id": "cab4432f-d7e5-4c18-ab86-19fe6759eed6",
    "metadata": {},
    "outputs": [
@@ -251,7 +251,7 @@
        "4          2016-11-30          35.368       22489.4502     22489.4502  "
       ]
      },
-     "execution_count": 292,
+     "execution_count": 324,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -303,7 +303,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 293,
+   "execution_count": 325,
    "id": "232e399b-64dc-4943-9c15-793a268ee896",
    "metadata": {},
    "outputs": [
@@ -559,7 +559,7 @@
        "4                    0.00            -563775.76          -563775.76  "
       ]
      },
-     "execution_count": 293,
+     "execution_count": 325,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -570,7 +570,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 294,
+   "execution_count": 326,
    "id": "e19e970c-d1dc-4608-9f6f-73dd3e282ba6",
    "metadata": {},
    "outputs": [],
@@ -589,7 +589,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 295,
+   "execution_count": 327,
    "id": "79c732d4-8d4d-4f7d-9a46-2e89cf2b213d",
    "metadata": {},
    "outputs": [],
@@ -608,7 +608,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 296,
+   "execution_count": 328,
    "id": "f7f7242c-051e-4d7d-9a76-b46523089e49",
    "metadata": {},
    "outputs": [],
@@ -635,7 +635,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 297,
+   "execution_count": 329,
    "id": "91ea0342-607a-420e-af0d-178d063da761",
    "metadata": {},
    "outputs": [
@@ -741,7 +741,7 @@
        "4    24  "
       ]
      },
-     "execution_count": 297,
+     "execution_count": 329,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -801,315 +801,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 33,
-   "id": "aa176fed-7867-4fb7-9d27-991eeaafaae1",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "eps = 1e-9  \n",
-    "\n",
-    "# 1) Active month indicator: did the client trade this month?\n",
-    "df_month0[\"active_month\"] = (df_month0[\"gross_flow_qty\"] > 0).astype(int)\n",
-    "\n",
-    "#client avec beaucoup de mois à 0 → “stable / dormant”\n",
-    "#client actif presque tous les mois → “rebalancer / institutionnel actif”\n",
-    "\n",
-    "\n",
-    "# 2) Monthly relative intensity (turnover proxy in quantity terms) : Mesurer l’intensité de trading relativement à la taille et pouvoir ocmparer client petit avec client plus gros\n",
-    "df_month0[\"rel_intensity_m\"] = df_month0[\"gross_flow_qty\"] / (df_month0[\"aum_qty\"].abs() + eps)\n",
-    "\n",
-    "# 3) Monthly net flow ratio (directional change): sert a Capturer la direction de la dynamique\n",
-    "df_month0[\"netflow_to_aum_m\"] = df_month0[\"net_flow_qty\"] / (df_month0[\"aum_qty\"].abs() + eps)\n",
-    "\n",
-    "# 4) Aggregate to client-level features (1 row per client)\n",
-    "df_client_feat0 = (\n",
-    "    df_month0.groupby(ID_COL, as_index=False)\n",
-    "            .agg(\n",
-    "                # Coverage / activity\n",
-    "                n_months=(\"month\", \"nunique\"),\n",
-    "                n_active_months=(\"active_month\", \"sum\"),\n",
-    "                flow_freq=(\"active_month\", \"mean\"),\n",
-    "\n",
-    "                # Size in quantity terms\n",
-    "                aum_qty_mean=(\"aum_qty\", \"mean\"),\n",
-    "                aum_qty_median=(\"aum_qty\", \"median\"),\n",
-    "\n",
-    "                # Flows in quantity terms\n",
-    "                net_flow_qty_sum=(\"net_flow_qty\", \"sum\"),\n",
-    "                gross_flow_qty_sum=(\"gross_flow_qty\", \"sum\"),\n",
-    "                gross_flow_qty_mean=(\"gross_flow_qty\", \"mean\"),\n",
-    "\n",
-    "                # Dispersion / volatility proxy\n",
-    "                net_flow_qty_vol=(\"net_flow_qty\", \"std\"),\n",
-    "                rel_intensity=(\"rel_intensity_m\", \"mean\"),\n",
-    "                netflow_to_aum=(\"netflow_to_aum_m\", \"mean\"),\n",
-    "\n",
-    "                # Trading frequency proxy\n",
-    "                n_tx_total=(\"n_tx\", \"sum\"),\n",
-    "            )\n",
-    ")\n",
-    "\n",
-    "# 5) Clean NaNs due to std on constant series\n",
-    "df_client_feat0[\"net_flow_qty_vol\"] = df_client_feat0[\"net_flow_qty_vol\"].fillna(0.0)\n",
-    "\n",
-    "# 6) Log transforms (useful because distributions are heavy-tailed)\n",
-    "df_client_feat0[\"log_aum_qty_mean\"] = np.log1p(df_client_feat0[\"aum_qty_mean\"].clip(lower=0))\n",
-    "df_client_feat0[\"log_gross_flow_qty_mean\"] = np.log1p(df_client_feat0[\"gross_flow_qty_mean\"].clip(lower=0))\n",
-    "\n",
-    "# 7) Global turnover proxy\n",
-    "df_client_feat0[\"gross_flow_to_aum\"] = df_client_feat0[\"gross_flow_qty_sum\"] / (df_client_feat0[\"aum_qty_mean\"].abs() + eps)\n",
-    "\n",
-    "dfc0 = df_client_feat0.copy()\n",
-    "\n",
-    "# Minimal filters (adjust if needed)\n",
-    "dfc0 = dfc0[(dfc0[\"n_months\"] >= 6)]                  # at least 6 observed months\n",
-    "dfc0 = dfc0[(dfc0[\"aum_qty_mean\"].abs() > 0)]         # avoid zero holdings\n",
-    "\n",
-    "dfc0[\"frequency\"] = dfc0[\"flow_freq\"]\n",
-    "dfc0[\"rel_intensity_total\"] = dfc0[\"gross_flow_to_aum\"]\n",
-    "\n",
-    "# Choose a compact, interpretable feature set (quantity-based)\n",
-    "features0 = [\n",
-    "    \"log_aum_qty_mean\",            # size (log)\n",
-    "    \"log_gross_flow_qty_mean\",     # activity intensity (log)\n",
-    "    \"frequency\",                   # activity frequency\n",
-    "    \"rel_intensity_total\",         # turnover proxy\n",
-    "    \"net_flow_qty_vol\",            # volatility of net flows\n",
-    "    \"n_tx_total\",                  # total number of transactions\n",
-    "]\n",
-    "\n",
-    "# Build X (drop NaNs/Infs)\n",
-    "X0 = (dfc0[features0]\n",
-    "     .replace([np.inf, -np.inf], np.nan)\n",
-    "     .dropna()\n",
-    "     .copy())\n",
-    "\n",
-    "# Keep IDs aligned\n",
-    "ids = dfc0.loc[X0.index, ID_COL].copy()\n",
-    "\n",
-    "# Standardize (critical for distance-based clustering)\n",
-    "scaler = StandardScaler()\n",
-    "X_scaled0 = scaler.fit_transform(X0)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 34,
-   "id": "1c616e7c-a1c3-4b9a-9e06-8b942f837266",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "image/png": "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",
-      "text/plain": [
-       "<Figure size 640x480 with 1 Axes>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "image/png": "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",
-      "text/plain": [
-       "<Figure size 640x480 with 1 Axes>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Best K by silhouette: 5\n"
-     ]
-    }
-   ],
-   "source": [
-    "# 1er clustering\n",
-    "\n",
-    "k_range = range(2, 21)\n",
-    "inertias = []\n",
-    "silhouettes = []\n",
-    "\n",
-    "for k in k_range:\n",
-    "    km = KMeans(n_clusters=k, n_init=30, random_state=42)\n",
-    "    labels = km.fit_predict(X_scaled0)\n",
-    "    inertias.append(km.inertia_)\n",
-    "    silhouettes.append(silhouette_score(X_scaled0, labels))\n",
-    "\n",
-    "# Elbow plot\n",
-    "plt.figure()\n",
-    "plt.plot(list(k_range), inertias, marker=\"o\")\n",
-    "plt.xlabel(\"Number of clusters K\")\n",
-    "plt.ylabel(\"Inertia (within-cluster SSE)\")\n",
-    "plt.title(\"Elbow curve for K-means\")\n",
-    "plt.show()\n",
-    "\n",
-    "# Silhouette plot\n",
-    "plt.figure()\n",
-    "plt.plot(list(k_range), silhouettes, marker=\"o\")\n",
-    "plt.xlabel(\"Number of clusters K\")\n",
-    "plt.ylabel(\"Silhouette score\")\n",
-    "plt.title(\"Silhouette score for K-means\")\n",
-    "plt.show()\n",
-    "\n",
-    "best_k = list(k_range)[int(np.argmax(silhouettes))]\n",
-    "print(\"Best K by silhouette:\", best_k)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 35,
-   "id": "8f52f288-17fe-4f70-9703-d24e50b6a7a1",
-   "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>n_clients</th>\n",
-       "      <th>aum_qty_med</th>\n",
-       "      <th>freq_med</th>\n",
-       "      <th>rel_int_med</th>\n",
-       "      <th>gross_flow_med</th>\n",
-       "      <th>n_tx_med</th>\n",
-       "      <th>vol_med</th>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>cluster_kmeans</th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>1.0</th>\n",
-       "      <td>242</td>\n",
-       "      <td>2.464422e+04</td>\n",
-       "      <td>0.953846</td>\n",
-       "      <td>8.355143</td>\n",
-       "      <td>2.813915e+03</td>\n",
-       "      <td>1210.0</td>\n",
-       "      <td>3.297591e+03</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2.0</th>\n",
-       "      <td>102</td>\n",
-       "      <td>2.360580e+04</td>\n",
-       "      <td>0.059419</td>\n",
-       "      <td>0.465813</td>\n",
-       "      <td>1.149596e+02</td>\n",
-       "      <td>4.0</td>\n",
-       "      <td>3.228290e+02</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>0.0</th>\n",
-       "      <td>48</td>\n",
-       "      <td>3.351804e+05</td>\n",
-       "      <td>1.000000</td>\n",
-       "      <td>10.719448</td>\n",
-       "      <td>4.247979e+04</td>\n",
-       "      <td>11538.0</td>\n",
-       "      <td>3.695062e+04</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>3.0</th>\n",
-       "      <td>12</td>\n",
-       "      <td>8.769226e+03</td>\n",
-       "      <td>0.968254</td>\n",
-       "      <td>127.337410</td>\n",
-       "      <td>1.484639e+04</td>\n",
-       "      <td>2458.0</td>\n",
-       "      <td>1.675758e+04</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>4.0</th>\n",
-       "      <td>1</td>\n",
-       "      <td>2.559419e+07</td>\n",
-       "      <td>1.000000</td>\n",
-       "      <td>2.433395</td>\n",
-       "      <td>1.112157e+06</td>\n",
-       "      <td>4410.0</td>\n",
-       "      <td>4.349047e+06</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "                n_clients   aum_qty_med  freq_med  rel_int_med  \\\n",
-       "cluster_kmeans                                                   \n",
-       "1.0                   242  2.464422e+04  0.953846     8.355143   \n",
-       "2.0                   102  2.360580e+04  0.059419     0.465813   \n",
-       "0.0                    48  3.351804e+05  1.000000    10.719448   \n",
-       "3.0                    12  8.769226e+03  0.968254   127.337410   \n",
-       "4.0                     1  2.559419e+07  1.000000     2.433395   \n",
-       "\n",
-       "                gross_flow_med  n_tx_med       vol_med  \n",
-       "cluster_kmeans                                          \n",
-       "1.0               2.813915e+03    1210.0  3.297591e+03  \n",
-       "2.0               1.149596e+02       4.0  3.228290e+02  \n",
-       "0.0               4.247979e+04   11538.0  3.695062e+04  \n",
-       "3.0               1.484639e+04    2458.0  1.675758e+04  \n",
-       "4.0               1.112157e+06    4410.0  4.349047e+06  "
-      ]
-     },
-     "execution_count": 35,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "km = KMeans(n_clusters=5, n_init=50, random_state=42)\n",
-    "labels_km = km.fit_predict(X_scaled0)\n",
-    "\n",
-    "dfc0.loc[X0.index, \"cluster_kmeans\"] = labels_km\n",
-    "\n",
-    "# Profiling table (medians = robust to outliers)\n",
-    "k_profile = (\n",
-    "    dfc0.loc[X0.index]\n",
-    "      .groupby(\"cluster_kmeans\")\n",
-    "      .agg(n_clients=(ID_COL, \"count\"),\n",
-    "          aum_qty_med=(\"aum_qty_mean\", \"median\"),\n",
-    "          freq_med=(\"frequency\", \"median\"),\n",
-    "          rel_int_med=(\"rel_intensity_total\", \"median\"),\n",
-    "          gross_flow_med=(\"gross_flow_qty_mean\", \"median\"),\n",
-    "          n_tx_med=(\"n_tx_total\", \"median\"),\n",
-    "          vol_med=(\"net_flow_qty_vol\", \"median\"),\n",
-    "          )\n",
-    "      .sort_values(\"n_clients\", ascending=False)\n",
-    ")\n",
-    "\n",
-    "k_profile"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 298,
+   "execution_count": 330,
    "id": "8caa4710-c7d5-4397-9d90-82f756499016",
    "metadata": {},
    "outputs": [],
@@ -1155,7 +847,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 299,
+   "execution_count": 331,
    "id": "fe081e43-092b-4429-813a-67417e39fd07",
    "metadata": {},
    "outputs": [],
@@ -1187,7 +879,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 300,
+   "execution_count": 332,
    "id": "b2a1cdce-1b1c-45d9-9c74-93f826bd65fd",
    "metadata": {},
    "outputs": [],
@@ -1224,7 +916,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 301,
+   "execution_count": 333,
    "id": "e10eb2ef-04cd-4186-b188-72d760b4d778",
    "metadata": {},
    "outputs": [
@@ -1416,7 +1108,7 @@
        "4     2.253872e-03  9.853705e-03  "
       ]
      },
-     "execution_count": 301,
+     "execution_count": 333,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1482,7 +1174,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 302,
+   "execution_count": 334,
    "id": "321b09ab-90f0-4add-a670-0d8c74046e03",
    "metadata": {},
    "outputs": [
@@ -1698,7 +1390,7 @@
        "4        -0.053  "
       ]
      },
-     "execution_count": 302,
+     "execution_count": 334,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1756,7 +1448,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 303,
+   "execution_count": 335,
    "id": "614bf72b-7afa-4633-ba09-22540a441459",
    "metadata": {},
    "outputs": [
@@ -1985,7 +1677,7 @@
        "4         75567.276  1.332268e-14  "
       ]
      },
-     "execution_count": 303,
+     "execution_count": 335,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -2052,7 +1744,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 304,
+   "execution_count": 336,
    "id": "2e01fa4f-ba89-4c8a-8cbb-528d89bc811c",
    "metadata": {},
    "outputs": [
@@ -2194,7 +1886,7 @@
        "4         6.316077e+11     152.0                   14               15  "
       ]
      },
-     "execution_count": 304,
+     "execution_count": 336,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -2227,7 +1919,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 305,
+   "execution_count": 337,
    "id": "2d81b4fd-f82d-42f1-ba03-8460706fea0d",
    "metadata": {},
    "outputs": [
@@ -2600,7 +2292,7 @@
        "4                   NaN            -0.204637            -0.109646  "
       ]
      },
-     "execution_count": 305,
+     "execution_count": 337,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -2711,7 +2403,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 306,
+   "execution_count": 338,
    "id": "8c1a0491-a0bb-4165-b073-41f81637466b",
    "metadata": {},
    "outputs": [
@@ -3115,7 +2807,7 @@
        "4    1.129487e+00    2098.385472           -0.012011 -2.472128e+00  "
       ]
      },
-     "execution_count": 306,
+     "execution_count": 338,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -3169,7 +2861,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 307,
+   "execution_count": 339,
    "id": "4e4ea46f-5c3d-4a4a-b79c-ff5ae8973bad",
    "metadata": {},
    "outputs": [
@@ -3215,7 +2907,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 308,
+   "execution_count": 340,
    "id": "09943df7-8c78-4c51-b387-866c5cddd392",
    "metadata": {},
    "outputs": [
@@ -3249,7 +2941,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 309,
+   "execution_count": 366,
    "id": "9eb5fbb8-1a7b-434c-ba36-3c2a560b4cb1",
    "metadata": {},
    "outputs": [
@@ -3341,7 +3033,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 310,
+   "execution_count": 364,
    "id": "5f006fc0-d0e7-47b2-94f0-7e3bbdf91097",
    "metadata": {},
    "outputs": [
@@ -3533,7 +3225,7 @@
        "18  20  2348.022385    0.134130        1.432542"
       ]
      },
-     "execution_count": 310,
+     "execution_count": 364,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -3565,7 +3257,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 311,
+   "execution_count": 343,
    "id": "0198c399-f532-44c5-91a7-d4e0a27887ec",
    "metadata": {},
    "outputs": [
@@ -3601,7 +3293,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 312,
+   "execution_count": 344,
    "id": "5ba1f3bf-7fd7-49aa-8b28-0ca0f2658bf0",
    "metadata": {},
    "outputs": [
@@ -3636,7 +3328,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 313,
+   "execution_count": 345,
    "id": "0052976f-e30f-4f84-b720-6fa4a9078aba",
    "metadata": {},
    "outputs": [
@@ -4359,7 +4051,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 314,
+   "execution_count": 346,
    "id": "4d04e670-51ae-482d-a5c5-93fe8263cfeb",
    "metadata": {},
    "outputs": [],
@@ -4376,7 +4068,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 315,
+   "execution_count": 347,
    "id": "6ebe0025-0532-4e51-acb2-81aa786a164b",
    "metadata": {},
    "outputs": [
@@ -4440,7 +4132,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 316,
+   "execution_count": 348,
    "id": "5b3c5228-c176-4f1c-8edb-5b5d093df8a9",
    "metadata": {},
    "outputs": [
@@ -4478,7 +4170,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 317,
+   "execution_count": 349,
    "id": "5071c36c-0176-460c-aeb7-ed7c4fb35ce5",
    "metadata": {},
    "outputs": [
@@ -4522,7 +4214,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 318,
+   "execution_count": 350,
    "id": "72393182-7c5b-4484-b0e0-770bff771d4c",
    "metadata": {},
    "outputs": [
@@ -4604,7 +4296,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 319,
+   "execution_count": 351,
    "id": "a5f006c5-55a8-475f-b58d-fc26886c0aba",
    "metadata": {},
    "outputs": [
@@ -4813,20 +4505,10 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 320,
+   "execution_count": 352,
    "id": "b8b4940e-4ab5-4123-a59a-e99d5f1fc5b6",
    "metadata": {},
    "outputs": [
-    {
-     "data": {
-      "image/png": "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",
-      "text/plain": [
-       "<Figure size 800x400 with 1 Axes>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
     {
      "data": {
       "image/png": "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",
@@ -4839,7 +4521,7 @@
     }
    ],
    "source": [
-    "for k in [2, 5]:\n",
+    "for k in [5]:\n",
     "    tmp = (\n",
     "        dfc.groupby(f\"cluster_k{k}\")\n",
     "        .agg(\n",
@@ -4859,9 +4541,2882 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 356,
    "id": "a0370454-561e-48c5-ad3b-28a356a2abac",
    "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Filtered clients: (246, 55)\n",
+      "Filtered clients: (317, 55)\n",
+      "Filtered clients: (317, 55)\n",
+      "Filtered clients: (327, 55)\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Analyse temporelle\n",
+    "\n",
+    "def corr_lag(x, y, lag):\n",
+    "    x = np.asarray(x, dtype=float)\n",
+    "    y = np.asarray(y, dtype=float)\n",
+    "    \n",
+    "    mask = np.isfinite(x) & np.isfinite(y)\n",
+    "    x, y = x[mask], y[mask]\n",
+    "    \n",
+    "    if len(x) <= lag + 3:\n",
+    "        return np.nan\n",
+    "    \n",
+    "    return pd.Series(x[lag:]).corr(pd.Series(y[:-lag]))\n",
+    "\n",
+    "# 1. Définir les fenêtres temporelles (ex: 2 ans glissants)\n",
+    "windows = [\n",
+    "    (\"2017-10-31\", \"2019-10-31\"),\n",
+    "    (\"2019-10-31\", \"2021-10-31\"),\n",
+    "    (\"2021-10-31\", \"2023-10-31\"),\n",
+    "    (\"2023-10-31\", \"2025-10-31\")\n",
+    "]\n",
+    "\n",
+    "for start, end in windows:\n",
+    "    # FILTRAGE : On recalcule les variables sur la période (simulation)\n",
+    "    df_month_copy = df_month[(df_month['month'] > start) & (df_month['month'] <= end)].copy()\n",
+    "    df_rel_m_copy = df_rel_m[(df_rel_m['month'] > start) & (df_rel_m['month'] <= end)].copy()\n",
+    "    \n",
+    "    tmp_copy = df_rel_m_copy.sort_values([ID_COL, ISIN_COL, \"month\"]).copy()\n",
+    "    tmp_copy[\"prev_aum\"] = tmp_copy.groupby([ID_COL, ISIN_COL])[\"aum_qty\"].shift(1)\n",
+    "    tmp_copy[\"full_exit_event\"] = ((tmp_copy[\"prev_aum\"] > 0) & (tmp_copy[\"aum_qty\"] <= 0)).astype(int)\n",
+    "    tmp_copy[\"entry_event\"] = ((tmp_copy[\"prev_aum\"].fillna(0) <= 0) & (tmp_copy[\"aum_qty\"] > 0)).astype(int)\n",
+    "\n",
+    "    df_rel_feat_copy = (\n",
+    "        tmp_copy.groupby([ID_COL, ISIN_COL], as_index=False)\n",
+    "        .agg(\n",
+    "        rel_n_months=(\"month\", \"nunique\"),\n",
+    "        rel_active_months=(\"active_rel_month\", \"sum\"),\n",
+    "        rel_holding_months=(\"holding_rel_month\", \"sum\"),\n",
+    "        rel_aum_mean=(\"aum_qty\", \"mean\"),\n",
+    "        rel_turnover_mean=(\"turnover_rel\", \"mean\"),\n",
+    "        rel_turnover_vol=(\"turnover_rel\", \"std\"),\n",
+    "        rel_flow_to_aum_vol=(\"flow_to_aum_rel\", \"std\"),\n",
+    "        rel_n_tx=(\"n_tx\", \"sum\"),\n",
+    "        rel_full_exit_count=(\"full_exit_event\", \"sum\"),\n",
+    "        rel_entry_count=(\"entry_event\", \"sum\")\n",
+    "        )\n",
+    "    )\n",
+    "\n",
+    "    df_rel_client_copy = (\n",
+    "    df_rel_feat_copy\n",
+    "    .groupby(ID_COL, as_index=False)\n",
+    "    .agg(\n",
+    "        n_isin_total=(ISIN_COL, \"nunique\"),\n",
+    "        rel_turnover_mean_avg=(\"rel_turnover_mean\", \"mean\"),\n",
+    "        rel_turnover_vol_avg=(\"rel_turnover_vol\", \"mean\"),\n",
+    "        rel_flow_to_aum_vol_avg=(\"rel_flow_to_aum_vol\", \"mean\"),\n",
+    "        full_exit_count=(\"rel_full_exit_count\", \"sum\"),\n",
+    "        entry_count=(\"rel_entry_count\", \"sum\"),\n",
+    "        avg_holding_months_per_isin=(\"rel_holding_months\", \"mean\"),\n",
+    "        max_holding_months_per_isin=(\"rel_holding_months\", \"max\")\n",
+    "        )\n",
+    "    )\n",
+    "\n",
+    "    df_client_copy = (\n",
+    "    df_month_copy\n",
+    "    .groupby(ID_COL, as_index=False)\n",
+    "    .agg(\n",
+    "        n_months=(\"month\", \"nunique\"),\n",
+    "        n_active_months=(\"active_month\", \"sum\"),\n",
+    "        flow_freq=(\"active_month\", \"mean\"),\n",
+    "\n",
+    "        aum_qty_mean=(\"aum_qty\", \"mean\"),\n",
+    "        aum_qty_median=(\"aum_qty\", \"median\"),\n",
+    "        aum_qty_max=(\"aum_qty\", \"max\"),\n",
+    "        aum_qty_last=(\"aum_qty\", \"last\"),\n",
+    "\n",
+    "        net_flow_qty_sum=(\"net_flow_qty\", \"sum\"),\n",
+    "        gross_flow_qty_sum=(\"gross_flow_qty\", \"sum\"),\n",
+    "        gross_flow_qty_mean=(\"gross_flow_qty\", \"mean\"),\n",
+    "        n_tx_total=(\"n_tx\", \"sum\"),\n",
+    "\n",
+    "        net_flow_vol=(\"net_flow_qty\", \"std\"),\n",
+    "        turnover_mean=(\"turnover_m\", \"mean\"),\n",
+    "        turnover_vol=(\"turnover_m\", \"std\"),\n",
+    "        flow_to_aum_mean=(\"flow_to_aum_m\", \"mean\"),\n",
+    "        flow_to_aum_vol=(\"flow_to_aum_m\", \"std\"),\n",
+    "\n",
+    "        avg_n_isin_held=(\"n_isin_held\", \"mean\"),\n",
+    "        max_n_isin_held=(\"n_isin_held\", \"max\"),\n",
+    "\n",
+    "        sub_share_mean=(\"sub_share_m\", \"mean\"),\n",
+    "        red_share_mean=(\"red_share_m\", \"mean\"),\n",
+    "\n",
+    "        delta_rate_mean=(\"delta_rate_m\", \"mean\"),\n",
+    "        aum_drawdown_last=(\"aum_drawdown\", \"last\"),\n",
+    "        aum_drawdown_max=(\"aum_drawdown\", \"max\"),\n",
+    "\n",
+    "        region=(\"region\", \"last\"),\n",
+    "        country=(\"country\", \"last\")\n",
+    "        )\n",
+    "    )\n",
+    "\n",
+    "    df_client_copy = df_client_copy.merge(df_rel_client_copy, on=ID_COL, how=\"left\")\n",
+    "\n",
+    "    #Variables de corrélations entre performance et flux\n",
+    "\n",
+    "    rows = []\n",
+    "\n",
+    "    for acc, g in df_month_copy.groupby(ID_COL):\n",
+    "        g = g.sort_values(\"month\")\n",
+    "    \n",
+    "        flow = g[\"flow_to_aum_m\"].values\n",
+    "        ret_fund = g[\"ret_fund_m\"].values\n",
+    "        ret_bench = g[\"ret_bench_m\"].values\n",
+    "        rate = g[\"delta_rate_m\"].values\n",
+    "    \n",
+    "        rows.append({\n",
+    "        ID_COL: acc,\n",
+    "        \n",
+    "        # 👇 Corrélations perf vs flux\n",
+    "        \"corr_flow_fund_lag3\": corr_lag(flow, ret_fund, 3),\n",
+    "        \"corr_flow_fund_lag6\": corr_lag(flow, ret_fund, 6),\n",
+    "        \n",
+    "        \"corr_flow_bench_lag3\": corr_lag(flow, ret_bench, 3),\n",
+    "        \"corr_flow_bench_lag6\": corr_lag(flow, ret_bench, 6),\n",
+    "        \n",
+    "        # 👇 Corrélation taux vs flux\n",
+    "        \"corr_flow_rate_lag3\": corr_lag(flow, rate, 3),\n",
+    "        \"corr_flow_rate_lag6\": corr_lag(flow, rate, 6),\n",
+    "        })\n",
+    "\n",
+    "    df_corr_copy = pd.DataFrame(rows)\n",
+    "\n",
+    "    df_client_copy = df_client_copy.merge(df_corr_copy, on=ID_COL, how=\"left\")\n",
+    "\n",
+    "    dfc_copy = df_client_copy.copy()\n",
+    "\n",
+    "    dfc_copy[\"gross_flow_to_aum\"] = dfc_copy[\"gross_flow_qty_sum\"] / (dfc_copy[\"aum_qty_mean\"].abs() + EPS)\n",
+    "    dfc_copy[\"avg_ticket\"] = dfc_copy[\"gross_flow_qty_sum\"] / (dfc_copy[\"n_tx_total\"] + EPS)\n",
+    "    dfc_copy[\"flow_direction_balance\"] = dfc_copy[\"net_flow_qty_sum\"] / (dfc_copy[\"gross_flow_qty_sum\"] + EPS)\n",
+    "    dfc_copy[\"redemption_bias\"] = dfc_copy[\"red_share_mean\"] - dfc_copy[\"sub_share_mean\"]\n",
+    "    dfc_copy[\"activity_intensity\"] = dfc_copy[\"n_tx_total\"] / (dfc_copy[\"n_months\"] + EPS)\n",
+    "    dfc_copy[\"exit_rate_per_isin\"] = dfc_copy[\"full_exit_count\"] / (dfc_copy[\"n_isin_total\"] + EPS)\n",
+    "    dfc_copy[\"entry_rate_per_isin\"] = dfc_copy[\"entry_count\"] / (dfc_copy[\"n_isin_total\"] + EPS)\n",
+    "    dfc_copy[\"aum_final_to_peak\"] = dfc_copy[\"aum_qty_last\"] / (dfc_copy[\"aum_qty_max\"] + EPS)\n",
+    "\n",
+    "    for col in [\"aum_qty_mean\", \"gross_flow_qty_sum\", \"n_tx_total\", \"avg_ticket\", \"gross_flow_qty_mean\"]:\n",
+    "        dfc_copy[f\"log_{col}\"] = np.log1p(dfc_copy[col].clip(lower=0))\n",
+    "\n",
+    "        dfc_copy = dfc_copy[(dfc_copy[\"n_months\"] >= 6) & (dfc_copy[\"aum_qty_mean\"] > 0)].copy()\n",
+    "\n",
+    "        top_countries = dfc_copy[\"country\"].fillna(\"Unknown\").value_counts().head(10).index\n",
+    "        top_regions = dfc_copy[\"region\"].fillna(\"Unknown\").value_counts().head(10).index\n",
+    "\n",
+    "        dfc_copy[\"country_grp\"] = np.where(dfc_copy[\"country\"].isin(top_countries), dfc_copy[\"country\"], \"Other\")\n",
+    "        dfc_copy[\"region_grp\"] = np.where(dfc_copy[\"region\"].isin(top_regions), dfc_copy[\"region\"], \"Other\")\n",
+    "\n",
+    "    \n",
+    "    if start == \"2017-10-31\":\n",
+    "        df_2017 = dfc_copy.copy()\n",
+    "    if start == \"2019-10-31\":\n",
+    "        df_2019 = dfc_copy.copy()\n",
+    "    if start == \"2021-10-31\":\n",
+    "        df_2021 = dfc_copy.copy()\n",
+    "    if start == \"2023-10-31\":\n",
+    "        df_2023 = dfc_copy.copy()\n",
+    "    print(\"Filtered clients:\", dfc_copy.shape)\n",
+    "\n",
+    "# Moins de codes à mesure que l'on remonte dans le temps"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 367,
+   "id": "d4a05629-4dac-48a2-bd7f-b7a885d7e47a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "base_features = [\n",
+    "    \"log_aum_qty_mean\",\n",
+    "    \"flow_freq\",\n",
+    "    \"gross_flow_to_aum\",\n",
+    "    #\"turnover_vol\",\n",
+    "    \"flow_to_aum_vol\",\n",
+    "    \"activity_intensity\",\n",
+    "    \"n_tx_total\",\n",
+    "    \"avg_n_isin_held\",\n",
+    "    \"n_isin_total\",\n",
+    "    \"avg_holding_months_per_isin\",\n",
+    "    \"exit_rate_per_isin\",\n",
+    "    \"flow_direction_balance\",\n",
+    "    #\"redemption_bias\",\n",
+    "    \"aum_drawdown_last\",\n",
+    "    \"corr_flow_fund_lag3\",\n",
+    "    \"corr_flow_fund_lag6\",\n",
+    "    \"corr_flow_rate_lag3\",\n",
+    "    #\"corr_flow_rate_lag6\",\n",
+    "    #\"corr_flow_bench_lag3\",\n",
+    "    #\"corr_flow_bench_lag6\"\n",
+    "    \n",
+    "]\n",
+    "\n",
+    "base_features2 = [\n",
+    "    \"log_aum_qty_mean\",\n",
+    "    \"log_gross_flow_qty_mean\",\n",
+    "    \"n_tx_total\",\n",
+    "    \"flow_freq\",\n",
+    "    \"gross_flow_to_aum\",\n",
+    "    \"net_flow_vol\",\n",
+    "    #\"avg_n_isin_held\",\n",
+    "    #\"flow_direction_balance\",\n",
+    "]\n",
+    "\n",
+    "windows = [\n",
+    "    (\"2017-10-31\", \"2019-10-31\"),\n",
+    "    (\"2019-10-31\", \"2021-10-31\"),\n",
+    "    (\"2021-10-31\", \"2023-10-31\"),\n",
+    "    (\"2023-10-31\", \"2025-10-31\")\n",
+    "]\n",
+    "\n",
+    "stability_results = []\n",
+    "\n",
+    "X_temp_2017 = df_2017[base_features].replace([np.inf, -np.inf], np.nan).fillna(df_2017[base_features].median())\n",
+    "X_temp_2019 = df_2019[base_features].replace([np.inf, -np.inf], np.nan).fillna(df_2019[base_features].median())\n",
+    "X_temp_2021 = df_2021[base_features].replace([np.inf, -np.inf], np.nan).fillna(df_2021[base_features].median())\n",
+    "X_temp_2023 = df_2023[base_features].replace([np.inf, -np.inf], np.nan).fillna(df_2023[base_features].median())\n",
+    "\n",
+    "X_temp_2017_scaled = scaler.transform(X_temp_2017)\n",
+    "X_temp_2019_scaled = scaler.transform(X_temp_2019)\n",
+    "X_temp_2021_scaled = scaler.transform(X_temp_2021)\n",
+    "X_temp_2023_scaled = scaler.transform(X_temp_2023)\n",
+    "\n",
+    "km = RESULTS[5][\"model\"]\n",
+    "\n",
+    "labels_2017 = km.predict(X_temp_2017_scaled)\n",
+    "labels_2019 = km.predict(X_temp_2019_scaled)\n",
+    "labels_2021 = km.predict(X_temp_2021_scaled)\n",
+    "labels_2023 = km.predict(X_temp_2023_scaled)\n",
+    "\n",
+    "df_2017[\"cluster_kmeans\"] = labels_2017\n",
+    "df_2019[\"cluster_kmeans\"] = labels_2019\n",
+    "df_2021[\"cluster_kmeans\"] = labels_2021\n",
+    "df_2023[\"cluster_kmeans\"] = labels_2023\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 368,
+   "id": "79428e73-9401-4d39-9fad-20d06a4d1f2b",
+   "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>Registrar Account - ID</th>\n",
+       "      <th>n_months</th>\n",
+       "      <th>n_active_months</th>\n",
+       "      <th>flow_freq</th>\n",
+       "      <th>aum_qty_mean</th>\n",
+       "      <th>aum_qty_median</th>\n",
+       "      <th>aum_qty_max</th>\n",
+       "      <th>aum_qty_last</th>\n",
+       "      <th>net_flow_qty_sum</th>\n",
+       "      <th>gross_flow_qty_sum</th>\n",
+       "      <th>gross_flow_qty_mean</th>\n",
+       "      <th>n_tx_total</th>\n",
+       "      <th>net_flow_vol</th>\n",
+       "      <th>turnover_mean</th>\n",
+       "      <th>turnover_vol</th>\n",
+       "      <th>flow_to_aum_mean</th>\n",
+       "      <th>flow_to_aum_vol</th>\n",
+       "      <th>avg_n_isin_held</th>\n",
+       "      <th>max_n_isin_held</th>\n",
+       "      <th>sub_share_mean</th>\n",
+       "      <th>red_share_mean</th>\n",
+       "      <th>delta_rate_mean</th>\n",
+       "      <th>aum_drawdown_last</th>\n",
+       "      <th>aum_drawdown_max</th>\n",
+       "      <th>region</th>\n",
+       "      <th>country</th>\n",
+       "      <th>n_isin_total</th>\n",
+       "      <th>rel_turnover_mean_avg</th>\n",
+       "      <th>rel_turnover_vol_avg</th>\n",
+       "      <th>rel_flow_to_aum_vol_avg</th>\n",
+       "      <th>full_exit_count</th>\n",
+       "      <th>entry_count</th>\n",
+       "      <th>avg_holding_months_per_isin</th>\n",
+       "      <th>max_holding_months_per_isin</th>\n",
+       "      <th>corr_flow_fund_lag3</th>\n",
+       "      <th>corr_flow_fund_lag6</th>\n",
+       "      <th>corr_flow_bench_lag3</th>\n",
+       "      <th>corr_flow_bench_lag6</th>\n",
+       "      <th>corr_flow_rate_lag3</th>\n",
+       "      <th>corr_flow_rate_lag6</th>\n",
+       "      <th>gross_flow_to_aum</th>\n",
+       "      <th>avg_ticket</th>\n",
+       "      <th>flow_direction_balance</th>\n",
+       "      <th>redemption_bias</th>\n",
+       "      <th>activity_intensity</th>\n",
+       "      <th>exit_rate_per_isin</th>\n",
+       "      <th>entry_rate_per_isin</th>\n",
+       "      <th>aum_final_to_peak</th>\n",
+       "      <th>log_aum_qty_mean</th>\n",
+       "      <th>country_grp</th>\n",
+       "      <th>region_grp</th>\n",
+       "      <th>log_gross_flow_qty_sum</th>\n",
+       "      <th>log_n_tx_total</th>\n",
+       "      <th>log_avg_ticket</th>\n",
+       "      <th>log_gross_flow_qty_mean</th>\n",
+       "      <th>cluster_kmeans</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>18872</td>\n",
+       "      <td>24</td>\n",
+       "      <td>24</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>13099.683542</td>\n",
+       "      <td>12313.2330</td>\n",
+       "      <td>39201.929</td>\n",
+       "      <td>15362.431</td>\n",
+       "      <td>-86610.542</td>\n",
+       "      <td>145870.662</td>\n",
+       "      <td>6077.944250</td>\n",
+       "      <td>347.0</td>\n",
+       "      <td>4405.421469</td>\n",
+       "      <td>6.866620e-01</td>\n",
+       "      <td>6.476563e-01</td>\n",
+       "      <td>-4.346513e-01</td>\n",
+       "      <td>4.760756e-01</td>\n",
+       "      <td>5.666667</td>\n",
+       "      <td>9</td>\n",
+       "      <td>0.182835</td>\n",
+       "      <td>-0.820120</td>\n",
+       "      <td>-0.004667</td>\n",
+       "      <td>0.796705</td>\n",
+       "      <td>0.965250</td>\n",
+       "      <td>Switzerland</td>\n",
+       "      <td>Switzerland</td>\n",
+       "      <td>70</td>\n",
+       "      <td>2.868232e+11</td>\n",
+       "      <td>4.008490e+11</td>\n",
+       "      <td>4.992860e+11</td>\n",
+       "      <td>50</td>\n",
+       "      <td>71</td>\n",
+       "      <td>1.942857</td>\n",
+       "      <td>7</td>\n",
+       "      <td>-0.098882</td>\n",
+       "      <td>0.103718</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0.621462</td>\n",
+       "      <td>0.312713</td>\n",
+       "      <td>11.135434</td>\n",
+       "      <td>420.376548</td>\n",
+       "      <td>-0.593749</td>\n",
+       "      <td>-1.002955</td>\n",
+       "      <td>14.458333</td>\n",
+       "      <td>0.714286</td>\n",
+       "      <td>1.014286</td>\n",
+       "      <td>0.391879</td>\n",
+       "      <td>9.480420</td>\n",
+       "      <td>Switzerland</td>\n",
+       "      <td>Switzerland</td>\n",
+       "      <td>11.890482</td>\n",
+       "      <td>5.852202</td>\n",
+       "      <td>6.043527</td>\n",
+       "      <td>8.712586</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>200000076</td>\n",
+       "      <td>24</td>\n",
+       "      <td>23</td>\n",
+       "      <td>0.958333</td>\n",
+       "      <td>19721.920083</td>\n",
+       "      <td>9272.4710</td>\n",
+       "      <td>46591.535</td>\n",
+       "      <td>5705.213</td>\n",
+       "      <td>-958.588</td>\n",
+       "      <td>79325.796</td>\n",
+       "      <td>3305.241500</td>\n",
+       "      <td>131.0</td>\n",
+       "      <td>4205.535841</td>\n",
+       "      <td>2.448698e-01</td>\n",
+       "      <td>4.034074e-01</td>\n",
+       "      <td>-1.119577e-01</td>\n",
+       "      <td>4.487544e-01</td>\n",
+       "      <td>3.750000</td>\n",
+       "      <td>7</td>\n",
+       "      <td>0.408252</td>\n",
+       "      <td>-0.556621</td>\n",
+       "      <td>-0.004667</td>\n",
+       "      <td>0.877548</td>\n",
+       "      <td>0.911153</td>\n",
+       "      <td>Spain</td>\n",
+       "      <td>Spain</td>\n",
+       "      <td>10</td>\n",
+       "      <td>7.402653e+10</td>\n",
+       "      <td>1.892627e+11</td>\n",
+       "      <td>1.897906e+11</td>\n",
+       "      <td>11</td>\n",
+       "      <td>16</td>\n",
+       "      <td>9.000000</td>\n",
+       "      <td>16</td>\n",
+       "      <td>0.079104</td>\n",
+       "      <td>-0.154260</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0.154608</td>\n",
+       "      <td>-0.043408</td>\n",
+       "      <td>4.022215</td>\n",
+       "      <td>605.540427</td>\n",
+       "      <td>-0.012084</td>\n",
+       "      <td>-0.964873</td>\n",
+       "      <td>5.458333</td>\n",
+       "      <td>1.100000</td>\n",
+       "      <td>1.600000</td>\n",
+       "      <td>0.122452</td>\n",
+       "      <td>9.889537</td>\n",
+       "      <td>Spain</td>\n",
+       "      <td>Spain</td>\n",
+       "      <td>11.281331</td>\n",
+       "      <td>4.882802</td>\n",
+       "      <td>6.407771</td>\n",
+       "      <td>8.103567</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>200000082</td>\n",
+       "      <td>9</td>\n",
+       "      <td>9</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>94110.153222</td>\n",
+       "      <td>9912.7690</td>\n",
+       "      <td>316149.358</td>\n",
+       "      <td>168684.609</td>\n",
+       "      <td>-54092.803</td>\n",
+       "      <td>170248.173</td>\n",
+       "      <td>18916.463667</td>\n",
+       "      <td>334.0</td>\n",
+       "      <td>15896.897315</td>\n",
+       "      <td>1.676878e+01</td>\n",
+       "      <td>4.067557e+01</td>\n",
+       "      <td>-1.331691e+01</td>\n",
+       "      <td>3.939035e+01</td>\n",
+       "      <td>1.333333</td>\n",
+       "      <td>2</td>\n",
+       "      <td>0.322361</td>\n",
+       "      <td>-0.688804</td>\n",
+       "      <td>-0.021889</td>\n",
+       "      <td>0.466440</td>\n",
+       "      <td>0.999064</td>\n",
+       "      <td>Italy</td>\n",
+       "      <td>Italy</td>\n",
+       "      <td>5</td>\n",
+       "      <td>3.729108e+12</td>\n",
+       "      <td>2.856665e+12</td>\n",
+       "      <td>3.471936e+12</td>\n",
+       "      <td>11</td>\n",
+       "      <td>11</td>\n",
+       "      <td>2.400000</td>\n",
+       "      <td>4</td>\n",
+       "      <td>-0.202170</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>-0.207860</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1.809031</td>\n",
+       "      <td>509.725069</td>\n",
+       "      <td>-0.317729</td>\n",
+       "      <td>-1.011165</td>\n",
+       "      <td>37.111111</td>\n",
+       "      <td>2.200000</td>\n",
+       "      <td>2.200000</td>\n",
+       "      <td>0.533560</td>\n",
+       "      <td>11.452232</td>\n",
+       "      <td>Italy</td>\n",
+       "      <td>Italy</td>\n",
+       "      <td>12.045018</td>\n",
+       "      <td>5.814131</td>\n",
+       "      <td>6.235831</td>\n",
+       "      <td>9.847841</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>200000146</td>\n",
+       "      <td>24</td>\n",
+       "      <td>24</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>74707.740583</td>\n",
+       "      <td>106267.2235</td>\n",
+       "      <td>196139.292</td>\n",
+       "      <td>196139.292</td>\n",
+       "      <td>-59221.624</td>\n",
+       "      <td>211436.064</td>\n",
+       "      <td>8809.836000</td>\n",
+       "      <td>1132.0</td>\n",
+       "      <td>5513.516693</td>\n",
+       "      <td>1.256966e+00</td>\n",
+       "      <td>2.328463e+00</td>\n",
+       "      <td>-1.348461e-01</td>\n",
+       "      <td>4.600613e-01</td>\n",
+       "      <td>5.458333</td>\n",
+       "      <td>9</td>\n",
+       "      <td>0.382985</td>\n",
+       "      <td>-0.717218</td>\n",
+       "      <td>-0.004667</td>\n",
+       "      <td>0.074580</td>\n",
+       "      <td>0.996116</td>\n",
+       "      <td>Italy</td>\n",
+       "      <td>Italy</td>\n",
+       "      <td>20</td>\n",
+       "      <td>3.031166e+11</td>\n",
+       "      <td>2.822949e+11</td>\n",
+       "      <td>2.429317e+11</td>\n",
+       "      <td>42</td>\n",
+       "      <td>53</td>\n",
+       "      <td>6.550000</td>\n",
+       "      <td>11</td>\n",
+       "      <td>0.279563</td>\n",
+       "      <td>0.344789</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>-0.141305</td>\n",
+       "      <td>0.256302</td>\n",
+       "      <td>2.830176</td>\n",
+       "      <td>186.780975</td>\n",
+       "      <td>-0.280092</td>\n",
+       "      <td>-1.100203</td>\n",
+       "      <td>47.166667</td>\n",
+       "      <td>2.100000</td>\n",
+       "      <td>2.650000</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>11.221352</td>\n",
+       "      <td>Italy</td>\n",
+       "      <td>Italy</td>\n",
+       "      <td>12.261683</td>\n",
+       "      <td>7.032624</td>\n",
+       "      <td>5.235276</td>\n",
+       "      <td>9.083738</td>\n",
+       "      <td>4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>200000147</td>\n",
+       "      <td>24</td>\n",
+       "      <td>24</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>26636.948500</td>\n",
+       "      <td>29692.2925</td>\n",
+       "      <td>48287.032</td>\n",
+       "      <td>7512.370</td>\n",
+       "      <td>-7789.010</td>\n",
+       "      <td>45214.622</td>\n",
+       "      <td>1883.942583</td>\n",
+       "      <td>826.0</td>\n",
+       "      <td>1158.765419</td>\n",
+       "      <td>8.937726e-02</td>\n",
+       "      <td>6.399876e-02</td>\n",
+       "      <td>-2.717045e-02</td>\n",
+       "      <td>6.214485e-02</td>\n",
+       "      <td>19.000000</td>\n",
+       "      <td>24</td>\n",
+       "      <td>0.375099</td>\n",
+       "      <td>-0.637097</td>\n",
+       "      <td>-0.004667</td>\n",
+       "      <td>0.956999</td>\n",
+       "      <td>0.956999</td>\n",
+       "      <td>Italy</td>\n",
+       "      <td>Italy</td>\n",
+       "      <td>60</td>\n",
+       "      <td>2.801077e+10</td>\n",
+       "      <td>6.331226e+10</td>\n",
+       "      <td>6.213826e+10</td>\n",
+       "      <td>107</td>\n",
+       "      <td>138</td>\n",
+       "      <td>7.600000</td>\n",
+       "      <td>17</td>\n",
+       "      <td>0.215711</td>\n",
+       "      <td>0.376121</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>-0.130792</td>\n",
+       "      <td>0.108078</td>\n",
+       "      <td>1.697440</td>\n",
+       "      <td>54.739252</td>\n",
+       "      <td>-0.172268</td>\n",
+       "      <td>-1.012196</td>\n",
+       "      <td>34.416667</td>\n",
+       "      <td>1.783333</td>\n",
+       "      <td>2.300000</td>\n",
+       "      <td>0.155577</td>\n",
+       "      <td>10.190092</td>\n",
+       "      <td>Italy</td>\n",
+       "      <td>Italy</td>\n",
+       "      <td>10.719198</td>\n",
+       "      <td>6.717805</td>\n",
+       "      <td>4.020685</td>\n",
+       "      <td>7.541653</td>\n",
+       "      <td>1</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",
+       "      <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",
+       "      <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>266</th>\n",
+       "      <td>422444</td>\n",
+       "      <td>24</td>\n",
+       "      <td>24</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>12267.997958</td>\n",
+       "      <td>9950.5330</td>\n",
+       "      <td>32977.443</td>\n",
+       "      <td>4877.824</td>\n",
+       "      <td>-15441.419</td>\n",
+       "      <td>32108.803</td>\n",
+       "      <td>1337.866792</td>\n",
+       "      <td>631.0</td>\n",
+       "      <td>1041.528882</td>\n",
+       "      <td>2.150940e-01</td>\n",
+       "      <td>2.769692e-01</td>\n",
+       "      <td>-1.143586e-01</td>\n",
+       "      <td>2.638958e-01</td>\n",
+       "      <td>11.166667</td>\n",
+       "      <td>15</td>\n",
+       "      <td>0.320475</td>\n",
+       "      <td>-0.697638</td>\n",
+       "      <td>-0.004667</td>\n",
+       "      <td>0.856627</td>\n",
+       "      <td>0.947579</td>\n",
+       "      <td>Italy</td>\n",
+       "      <td>Italy</td>\n",
+       "      <td>34</td>\n",
+       "      <td>3.093744e+10</td>\n",
+       "      <td>6.664333e+10</td>\n",
+       "      <td>6.710298e+10</td>\n",
+       "      <td>71</td>\n",
+       "      <td>89</td>\n",
+       "      <td>7.882353</td>\n",
+       "      <td>14</td>\n",
+       "      <td>-0.065606</td>\n",
+       "      <td>-0.151279</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>-0.097411</td>\n",
+       "      <td>-0.114743</td>\n",
+       "      <td>2.617281</td>\n",
+       "      <td>50.885583</td>\n",
+       "      <td>-0.480909</td>\n",
+       "      <td>-1.018113</td>\n",
+       "      <td>26.291667</td>\n",
+       "      <td>2.088235</td>\n",
+       "      <td>2.617647</td>\n",
+       "      <td>0.147914</td>\n",
+       "      <td>9.414831</td>\n",
+       "      <td>Italy</td>\n",
+       "      <td>Italy</td>\n",
+       "      <td>10.376917</td>\n",
+       "      <td>6.448889</td>\n",
+       "      <td>3.949041</td>\n",
+       "      <td>7.199579</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>267</th>\n",
+       "      <td>422445</td>\n",
+       "      <td>24</td>\n",
+       "      <td>24</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>69421.793833</td>\n",
+       "      <td>55546.6050</td>\n",
+       "      <td>163966.050</td>\n",
+       "      <td>14277.014</td>\n",
+       "      <td>-251075.901</td>\n",
+       "      <td>347147.887</td>\n",
+       "      <td>14464.495292</td>\n",
+       "      <td>685.0</td>\n",
+       "      <td>17441.410733</td>\n",
+       "      <td>3.217610e-01</td>\n",
+       "      <td>4.302206e-01</td>\n",
+       "      <td>-2.075494e-01</td>\n",
+       "      <td>3.112958e-01</td>\n",
+       "      <td>10.375000</td>\n",
+       "      <td>14</td>\n",
+       "      <td>0.137291</td>\n",
+       "      <td>-0.873971</td>\n",
+       "      <td>-0.004667</td>\n",
+       "      <td>0.938989</td>\n",
+       "      <td>0.948780</td>\n",
+       "      <td>United Kingdom</td>\n",
+       "      <td>United Kingdom</td>\n",
+       "      <td>37</td>\n",
+       "      <td>2.100063e+11</td>\n",
+       "      <td>4.459683e+11</td>\n",
+       "      <td>3.365609e+11</td>\n",
+       "      <td>59</td>\n",
+       "      <td>74</td>\n",
+       "      <td>6.729730</td>\n",
+       "      <td>17</td>\n",
+       "      <td>0.059350</td>\n",
+       "      <td>0.090918</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0.165629</td>\n",
+       "      <td>-0.029560</td>\n",
+       "      <td>5.000561</td>\n",
+       "      <td>506.785236</td>\n",
+       "      <td>-0.723253</td>\n",
+       "      <td>-1.011262</td>\n",
+       "      <td>28.541667</td>\n",
+       "      <td>1.594595</td>\n",
+       "      <td>2.000000</td>\n",
+       "      <td>0.087073</td>\n",
+       "      <td>11.147971</td>\n",
+       "      <td>United Kingdom</td>\n",
+       "      <td>United Kingdom</td>\n",
+       "      <td>12.757509</td>\n",
+       "      <td>6.530878</td>\n",
+       "      <td>6.230059</td>\n",
+       "      <td>9.579521</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>268</th>\n",
+       "      <td>422554</td>\n",
+       "      <td>24</td>\n",
+       "      <td>6</td>\n",
+       "      <td>0.250000</td>\n",
+       "      <td>1789.997458</td>\n",
+       "      <td>2021.5270</td>\n",
+       "      <td>2518.899</td>\n",
+       "      <td>554.000</td>\n",
+       "      <td>-2115.826</td>\n",
+       "      <td>2115.826</td>\n",
+       "      <td>88.159417</td>\n",
+       "      <td>9.0</td>\n",
+       "      <td>296.399564</td>\n",
+       "      <td>1.193556e-01</td>\n",
+       "      <td>5.157004e-01</td>\n",
+       "      <td>-1.193556e-01</td>\n",
+       "      <td>5.157004e-01</td>\n",
+       "      <td>5.333333</td>\n",
+       "      <td>6</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>-0.250000</td>\n",
+       "      <td>-0.004667</td>\n",
+       "      <td>0.795396</td>\n",
+       "      <td>0.795396</td>\n",
+       "      <td>Spain</td>\n",
+       "      <td>Portugal</td>\n",
+       "      <td>8</td>\n",
+       "      <td>2.166681e+09</td>\n",
+       "      <td>1.061451e+10</td>\n",
+       "      <td>1.061451e+10</td>\n",
+       "      <td>3</td>\n",
+       "      <td>6</td>\n",
+       "      <td>16.000000</td>\n",
+       "      <td>24</td>\n",
+       "      <td>-0.032409</td>\n",
+       "      <td>0.252735</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0.002680</td>\n",
+       "      <td>-0.019555</td>\n",
+       "      <td>1.182027</td>\n",
+       "      <td>235.091778</td>\n",
+       "      <td>-1.000000</td>\n",
+       "      <td>-0.250000</td>\n",
+       "      <td>0.375000</td>\n",
+       "      <td>0.375000</td>\n",
+       "      <td>0.750000</td>\n",
+       "      <td>0.219937</td>\n",
+       "      <td>7.490528</td>\n",
+       "      <td>Other</td>\n",
+       "      <td>Spain</td>\n",
+       "      <td>7.657673</td>\n",
+       "      <td>2.302585</td>\n",
+       "      <td>5.464221</td>\n",
+       "      <td>4.490426</td>\n",
+       "      <td>3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>269</th>\n",
+       "      <td>422691</td>\n",
+       "      <td>24</td>\n",
+       "      <td>24</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>39831.571833</td>\n",
+       "      <td>34980.0330</td>\n",
+       "      <td>84299.823</td>\n",
+       "      <td>36354.458</td>\n",
+       "      <td>-38718.541</td>\n",
+       "      <td>77652.421</td>\n",
+       "      <td>3235.517542</td>\n",
+       "      <td>324.0</td>\n",
+       "      <td>2235.473089</td>\n",
+       "      <td>8.638039e-02</td>\n",
+       "      <td>8.322480e-02</td>\n",
+       "      <td>-3.706567e-02</td>\n",
+       "      <td>6.696282e-02</td>\n",
+       "      <td>14.041667</td>\n",
+       "      <td>18</td>\n",
+       "      <td>0.308259</td>\n",
+       "      <td>-0.719980</td>\n",
+       "      <td>-0.004667</td>\n",
+       "      <td>0.568748</td>\n",
+       "      <td>0.864511</td>\n",
+       "      <td>Spain</td>\n",
+       "      <td>Spain</td>\n",
+       "      <td>42</td>\n",
+       "      <td>4.960864e+10</td>\n",
+       "      <td>1.547882e+11</td>\n",
+       "      <td>1.513444e+11</td>\n",
+       "      <td>40</td>\n",
+       "      <td>57</td>\n",
+       "      <td>8.023810</td>\n",
+       "      <td>19</td>\n",
+       "      <td>0.302523</td>\n",
+       "      <td>-0.131632</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0.015668</td>\n",
+       "      <td>-0.430534</td>\n",
+       "      <td>1.949519</td>\n",
+       "      <td>239.667966</td>\n",
+       "      <td>-0.498613</td>\n",
+       "      <td>-1.028239</td>\n",
+       "      <td>13.500000</td>\n",
+       "      <td>0.952381</td>\n",
+       "      <td>1.357143</td>\n",
+       "      <td>0.431252</td>\n",
+       "      <td>10.592440</td>\n",
+       "      <td>Spain</td>\n",
+       "      <td>Spain</td>\n",
+       "      <td>11.260011</td>\n",
+       "      <td>5.783825</td>\n",
+       "      <td>5.483418</td>\n",
+       "      <td>8.082253</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>270</th>\n",
+       "      <td>422874</td>\n",
+       "      <td>24</td>\n",
+       "      <td>24</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>2136.818542</td>\n",
+       "      <td>727.0000</td>\n",
+       "      <td>9560.044</td>\n",
+       "      <td>612.299</td>\n",
+       "      <td>-3167.353</td>\n",
+       "      <td>85045.949</td>\n",
+       "      <td>3543.581208</td>\n",
+       "      <td>321.0</td>\n",
+       "      <td>4353.942068</td>\n",
+       "      <td>2.763833e+11</td>\n",
+       "      <td>1.157257e+12</td>\n",
+       "      <td>-8.166042e+09</td>\n",
+       "      <td>3.001015e+10</td>\n",
+       "      <td>1.666667</td>\n",
+       "      <td>4</td>\n",
+       "      <td>0.411331</td>\n",
+       "      <td>-0.611609</td>\n",
+       "      <td>-0.004667</td>\n",
+       "      <td>0.967122</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>Spain</td>\n",
+       "      <td>Spain</td>\n",
+       "      <td>26</td>\n",
+       "      <td>3.481410e+11</td>\n",
+       "      <td>5.321386e+11</td>\n",
+       "      <td>5.878530e+11</td>\n",
+       "      <td>14</td>\n",
+       "      <td>23</td>\n",
+       "      <td>1.538462</td>\n",
+       "      <td>5</td>\n",
+       "      <td>0.021567</td>\n",
+       "      <td>-0.332525</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0.046606</td>\n",
+       "      <td>0.015242</td>\n",
+       "      <td>39.800267</td>\n",
+       "      <td>264.940651</td>\n",
+       "      <td>-0.037243</td>\n",
+       "      <td>-1.022940</td>\n",
+       "      <td>13.375000</td>\n",
+       "      <td>0.538462</td>\n",
+       "      <td>0.884615</td>\n",
+       "      <td>0.064048</td>\n",
+       "      <td>7.667541</td>\n",
+       "      <td>Spain</td>\n",
+       "      <td>Spain</td>\n",
+       "      <td>11.350959</td>\n",
+       "      <td>5.774552</td>\n",
+       "      <td>5.583273</td>\n",
+       "      <td>8.173175</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>246 rows × 56 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "    Registrar Account - ID  n_months  n_active_months  flow_freq  \\\n",
+       "0                    18872        24               24   1.000000   \n",
+       "1                200000076        24               23   0.958333   \n",
+       "2                200000082         9                9   1.000000   \n",
+       "3                200000146        24               24   1.000000   \n",
+       "4                200000147        24               24   1.000000   \n",
+       "..                     ...       ...              ...        ...   \n",
+       "266                 422444        24               24   1.000000   \n",
+       "267                 422445        24               24   1.000000   \n",
+       "268                 422554        24                6   0.250000   \n",
+       "269                 422691        24               24   1.000000   \n",
+       "270                 422874        24               24   1.000000   \n",
+       "\n",
+       "     aum_qty_mean  aum_qty_median  aum_qty_max  aum_qty_last  \\\n",
+       "0    13099.683542      12313.2330    39201.929     15362.431   \n",
+       "1    19721.920083       9272.4710    46591.535      5705.213   \n",
+       "2    94110.153222       9912.7690   316149.358    168684.609   \n",
+       "3    74707.740583     106267.2235   196139.292    196139.292   \n",
+       "4    26636.948500      29692.2925    48287.032      7512.370   \n",
+       "..            ...             ...          ...           ...   \n",
+       "266  12267.997958       9950.5330    32977.443      4877.824   \n",
+       "267  69421.793833      55546.6050   163966.050     14277.014   \n",
+       "268   1789.997458       2021.5270     2518.899       554.000   \n",
+       "269  39831.571833      34980.0330    84299.823     36354.458   \n",
+       "270   2136.818542        727.0000     9560.044       612.299   \n",
+       "\n",
+       "     net_flow_qty_sum  gross_flow_qty_sum  gross_flow_qty_mean  n_tx_total  \\\n",
+       "0          -86610.542          145870.662          6077.944250       347.0   \n",
+       "1            -958.588           79325.796          3305.241500       131.0   \n",
+       "2          -54092.803          170248.173         18916.463667       334.0   \n",
+       "3          -59221.624          211436.064          8809.836000      1132.0   \n",
+       "4           -7789.010           45214.622          1883.942583       826.0   \n",
+       "..                ...                 ...                  ...         ...   \n",
+       "266        -15441.419           32108.803          1337.866792       631.0   \n",
+       "267       -251075.901          347147.887         14464.495292       685.0   \n",
+       "268         -2115.826            2115.826            88.159417         9.0   \n",
+       "269        -38718.541           77652.421          3235.517542       324.0   \n",
+       "270         -3167.353           85045.949          3543.581208       321.0   \n",
+       "\n",
+       "     net_flow_vol  turnover_mean  turnover_vol  flow_to_aum_mean  \\\n",
+       "0     4405.421469   6.866620e-01  6.476563e-01     -4.346513e-01   \n",
+       "1     4205.535841   2.448698e-01  4.034074e-01     -1.119577e-01   \n",
+       "2    15896.897315   1.676878e+01  4.067557e+01     -1.331691e+01   \n",
+       "3     5513.516693   1.256966e+00  2.328463e+00     -1.348461e-01   \n",
+       "4     1158.765419   8.937726e-02  6.399876e-02     -2.717045e-02   \n",
+       "..            ...            ...           ...               ...   \n",
+       "266   1041.528882   2.150940e-01  2.769692e-01     -1.143586e-01   \n",
+       "267  17441.410733   3.217610e-01  4.302206e-01     -2.075494e-01   \n",
+       "268    296.399564   1.193556e-01  5.157004e-01     -1.193556e-01   \n",
+       "269   2235.473089   8.638039e-02  8.322480e-02     -3.706567e-02   \n",
+       "270   4353.942068   2.763833e+11  1.157257e+12     -8.166042e+09   \n",
+       "\n",
+       "     flow_to_aum_vol  avg_n_isin_held  max_n_isin_held  sub_share_mean  \\\n",
+       "0       4.760756e-01         5.666667                9        0.182835   \n",
+       "1       4.487544e-01         3.750000                7        0.408252   \n",
+       "2       3.939035e+01         1.333333                2        0.322361   \n",
+       "3       4.600613e-01         5.458333                9        0.382985   \n",
+       "4       6.214485e-02        19.000000               24        0.375099   \n",
+       "..               ...              ...              ...             ...   \n",
+       "266     2.638958e-01        11.166667               15        0.320475   \n",
+       "267     3.112958e-01        10.375000               14        0.137291   \n",
+       "268     5.157004e-01         5.333333                6        0.000000   \n",
+       "269     6.696282e-02        14.041667               18        0.308259   \n",
+       "270     3.001015e+10         1.666667                4        0.411331   \n",
+       "\n",
+       "     red_share_mean  delta_rate_mean  aum_drawdown_last  aum_drawdown_max  \\\n",
+       "0         -0.820120        -0.004667           0.796705          0.965250   \n",
+       "1         -0.556621        -0.004667           0.877548          0.911153   \n",
+       "2         -0.688804        -0.021889           0.466440          0.999064   \n",
+       "3         -0.717218        -0.004667           0.074580          0.996116   \n",
+       "4         -0.637097        -0.004667           0.956999          0.956999   \n",
+       "..              ...              ...                ...               ...   \n",
+       "266       -0.697638        -0.004667           0.856627          0.947579   \n",
+       "267       -0.873971        -0.004667           0.938989          0.948780   \n",
+       "268       -0.250000        -0.004667           0.795396          0.795396   \n",
+       "269       -0.719980        -0.004667           0.568748          0.864511   \n",
+       "270       -0.611609        -0.004667           0.967122          1.000000   \n",
+       "\n",
+       "             region         country  n_isin_total  rel_turnover_mean_avg  \\\n",
+       "0       Switzerland     Switzerland            70           2.868232e+11   \n",
+       "1             Spain           Spain            10           7.402653e+10   \n",
+       "2             Italy           Italy             5           3.729108e+12   \n",
+       "3             Italy           Italy            20           3.031166e+11   \n",
+       "4             Italy           Italy            60           2.801077e+10   \n",
+       "..              ...             ...           ...                    ...   \n",
+       "266           Italy           Italy            34           3.093744e+10   \n",
+       "267  United Kingdom  United Kingdom            37           2.100063e+11   \n",
+       "268           Spain        Portugal             8           2.166681e+09   \n",
+       "269           Spain           Spain            42           4.960864e+10   \n",
+       "270           Spain           Spain            26           3.481410e+11   \n",
+       "\n",
+       "     rel_turnover_vol_avg  rel_flow_to_aum_vol_avg  full_exit_count  \\\n",
+       "0            4.008490e+11             4.992860e+11               50   \n",
+       "1            1.892627e+11             1.897906e+11               11   \n",
+       "2            2.856665e+12             3.471936e+12               11   \n",
+       "3            2.822949e+11             2.429317e+11               42   \n",
+       "4            6.331226e+10             6.213826e+10              107   \n",
+       "..                    ...                      ...              ...   \n",
+       "266          6.664333e+10             6.710298e+10               71   \n",
+       "267          4.459683e+11             3.365609e+11               59   \n",
+       "268          1.061451e+10             1.061451e+10                3   \n",
+       "269          1.547882e+11             1.513444e+11               40   \n",
+       "270          5.321386e+11             5.878530e+11               14   \n",
+       "\n",
+       "     entry_count  avg_holding_months_per_isin  max_holding_months_per_isin  \\\n",
+       "0             71                     1.942857                            7   \n",
+       "1             16                     9.000000                           16   \n",
+       "2             11                     2.400000                            4   \n",
+       "3             53                     6.550000                           11   \n",
+       "4            138                     7.600000                           17   \n",
+       "..           ...                          ...                          ...   \n",
+       "266           89                     7.882353                           14   \n",
+       "267           74                     6.729730                           17   \n",
+       "268            6                    16.000000                           24   \n",
+       "269           57                     8.023810                           19   \n",
+       "270           23                     1.538462                            5   \n",
+       "\n",
+       "     corr_flow_fund_lag3  corr_flow_fund_lag6  corr_flow_bench_lag3  \\\n",
+       "0              -0.098882             0.103718                   NaN   \n",
+       "1               0.079104            -0.154260                   NaN   \n",
+       "2              -0.202170                  NaN                   NaN   \n",
+       "3               0.279563             0.344789                   NaN   \n",
+       "4               0.215711             0.376121                   NaN   \n",
+       "..                   ...                  ...                   ...   \n",
+       "266            -0.065606            -0.151279                   NaN   \n",
+       "267             0.059350             0.090918                   NaN   \n",
+       "268            -0.032409             0.252735                   NaN   \n",
+       "269             0.302523            -0.131632                   NaN   \n",
+       "270             0.021567            -0.332525                   NaN   \n",
+       "\n",
+       "     corr_flow_bench_lag6  corr_flow_rate_lag3  corr_flow_rate_lag6  \\\n",
+       "0                     NaN             0.621462             0.312713   \n",
+       "1                     NaN             0.154608            -0.043408   \n",
+       "2                     NaN            -0.207860                  NaN   \n",
+       "3                     NaN            -0.141305             0.256302   \n",
+       "4                     NaN            -0.130792             0.108078   \n",
+       "..                    ...                  ...                  ...   \n",
+       "266                   NaN            -0.097411            -0.114743   \n",
+       "267                   NaN             0.165629            -0.029560   \n",
+       "268                   NaN             0.002680            -0.019555   \n",
+       "269                   NaN             0.015668            -0.430534   \n",
+       "270                   NaN             0.046606             0.015242   \n",
+       "\n",
+       "     gross_flow_to_aum  avg_ticket  flow_direction_balance  redemption_bias  \\\n",
+       "0            11.135434  420.376548               -0.593749        -1.002955   \n",
+       "1             4.022215  605.540427               -0.012084        -0.964873   \n",
+       "2             1.809031  509.725069               -0.317729        -1.011165   \n",
+       "3             2.830176  186.780975               -0.280092        -1.100203   \n",
+       "4             1.697440   54.739252               -0.172268        -1.012196   \n",
+       "..                 ...         ...                     ...              ...   \n",
+       "266           2.617281   50.885583               -0.480909        -1.018113   \n",
+       "267           5.000561  506.785236               -0.723253        -1.011262   \n",
+       "268           1.182027  235.091778               -1.000000        -0.250000   \n",
+       "269           1.949519  239.667966               -0.498613        -1.028239   \n",
+       "270          39.800267  264.940651               -0.037243        -1.022940   \n",
+       "\n",
+       "     activity_intensity  exit_rate_per_isin  entry_rate_per_isin  \\\n",
+       "0             14.458333            0.714286             1.014286   \n",
+       "1              5.458333            1.100000             1.600000   \n",
+       "2             37.111111            2.200000             2.200000   \n",
+       "3             47.166667            2.100000             2.650000   \n",
+       "4             34.416667            1.783333             2.300000   \n",
+       "..                  ...                 ...                  ...   \n",
+       "266           26.291667            2.088235             2.617647   \n",
+       "267           28.541667            1.594595             2.000000   \n",
+       "268            0.375000            0.375000             0.750000   \n",
+       "269           13.500000            0.952381             1.357143   \n",
+       "270           13.375000            0.538462             0.884615   \n",
+       "\n",
+       "     aum_final_to_peak  log_aum_qty_mean     country_grp      region_grp  \\\n",
+       "0             0.391879          9.480420     Switzerland     Switzerland   \n",
+       "1             0.122452          9.889537           Spain           Spain   \n",
+       "2             0.533560         11.452232           Italy           Italy   \n",
+       "3             1.000000         11.221352           Italy           Italy   \n",
+       "4             0.155577         10.190092           Italy           Italy   \n",
+       "..                 ...               ...             ...             ...   \n",
+       "266           0.147914          9.414831           Italy           Italy   \n",
+       "267           0.087073         11.147971  United Kingdom  United Kingdom   \n",
+       "268           0.219937          7.490528           Other           Spain   \n",
+       "269           0.431252         10.592440           Spain           Spain   \n",
+       "270           0.064048          7.667541           Spain           Spain   \n",
+       "\n",
+       "     log_gross_flow_qty_sum  log_n_tx_total  log_avg_ticket  \\\n",
+       "0                 11.890482        5.852202        6.043527   \n",
+       "1                 11.281331        4.882802        6.407771   \n",
+       "2                 12.045018        5.814131        6.235831   \n",
+       "3                 12.261683        7.032624        5.235276   \n",
+       "4                 10.719198        6.717805        4.020685   \n",
+       "..                      ...             ...             ...   \n",
+       "266               10.376917        6.448889        3.949041   \n",
+       "267               12.757509        6.530878        6.230059   \n",
+       "268                7.657673        2.302585        5.464221   \n",
+       "269               11.260011        5.783825        5.483418   \n",
+       "270               11.350959        5.774552        5.583273   \n",
+       "\n",
+       "     log_gross_flow_qty_mean  cluster_kmeans  \n",
+       "0                   8.712586               1  \n",
+       "1                   8.103567               1  \n",
+       "2                   9.847841               1  \n",
+       "3                   9.083738               4  \n",
+       "4                   7.541653               1  \n",
+       "..                       ...             ...  \n",
+       "266                 7.199579               1  \n",
+       "267                 9.579521               1  \n",
+       "268                 4.490426               3  \n",
+       "269                 8.082253               1  \n",
+       "270                 8.173175               1  \n",
+       "\n",
+       "[246 rows x 56 columns]"
+      ]
+     },
+     "execution_count": 368,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df_2017"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 379,
+   "id": "80300015-8c96-4c68-8572-b005fe3008cb",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "===== K=5 (2017) =====\n"
+     ]
+    },
+    {
+     "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>n_clients</th>\n",
+       "      <th>aum_qty_mean_med</th>\n",
+       "      <th>gross_flow_to_aum_med</th>\n",
+       "      <th>flow_freq_med</th>\n",
+       "      <th>n_tx_total_med</th>\n",
+       "      <th>avg_n_isin_held_med</th>\n",
+       "      <th>n_isin_total_med</th>\n",
+       "      <th>avg_holding_months_per_isin_med</th>\n",
+       "      <th>exit_rate_per_isin_med</th>\n",
+       "      <th>flow_direction_balance_med</th>\n",
+       "      <th>redemption_bias_med</th>\n",
+       "      <th>aum_drawdown_last_med</th>\n",
+       "      <th>aum_final_to_peak_med</th>\n",
+       "      <th>corr_flow_fund_lag3_med</th>\n",
+       "      <th>corr_flow_fund_lag6_med</th>\n",
+       "      <th>corr_flow_rate_lag3_med</th>\n",
+       "      <th>corr_flow_rate_lag6_med</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>cluster_kmeans</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>111</td>\n",
+       "      <td>16968.521150</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>2.291667</td>\n",
+       "      <td>15.0</td>\n",
+       "      <td>3.800000</td>\n",
+       "      <td>0.083333</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.920330</td>\n",
+       "      <td>0.112701</td>\n",
+       "      <td>0.029610</td>\n",
+       "      <td>-0.028331</td>\n",
+       "      <td>0.026860</td>\n",
+       "      <td>0.009551</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>91</td>\n",
+       "      <td>15224.049625</td>\n",
+       "      <td>4.040687</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>347.0</td>\n",
+       "      <td>2.772727</td>\n",
+       "      <td>19.0</td>\n",
+       "      <td>4.000000</td>\n",
+       "      <td>1.175000</td>\n",
+       "      <td>-0.326316</td>\n",
+       "      <td>-1.013060</td>\n",
+       "      <td>0.919243</td>\n",
+       "      <td>0.111327</td>\n",
+       "      <td>0.028616</td>\n",
+       "      <td>-0.021581</td>\n",
+       "      <td>-0.000388</td>\n",
+       "      <td>-0.003074</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>27</td>\n",
+       "      <td>88889.763125</td>\n",
+       "      <td>1.307204</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>1132.0</td>\n",
+       "      <td>14.666667</td>\n",
+       "      <td>32.0</td>\n",
+       "      <td>15.380952</td>\n",
+       "      <td>0.196429</td>\n",
+       "      <td>-0.290942</td>\n",
+       "      <td>-1.051078</td>\n",
+       "      <td>0.322512</td>\n",
+       "      <td>0.677488</td>\n",
+       "      <td>0.186117</td>\n",
+       "      <td>0.079017</td>\n",
+       "      <td>-0.033758</td>\n",
+       "      <td>0.104930</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>12</td>\n",
+       "      <td>536154.854937</td>\n",
+       "      <td>2.704868</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>4320.0</td>\n",
+       "      <td>22.479167</td>\n",
+       "      <td>54.0</td>\n",
+       "      <td>8.628205</td>\n",
+       "      <td>2.010311</td>\n",
+       "      <td>-0.483334</td>\n",
+       "      <td>-1.148256</td>\n",
+       "      <td>0.655400</td>\n",
+       "      <td>0.411812</td>\n",
+       "      <td>0.150284</td>\n",
+       "      <td>0.115993</td>\n",
+       "      <td>0.067313</td>\n",
+       "      <td>0.094253</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>5</td>\n",
+       "      <td>72055.041304</td>\n",
+       "      <td>12.515495</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>347.0</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>10.0</td>\n",
+       "      <td>1.916667</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>-1.251187</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.054633</td>\n",
+       "      <td>-0.100003</td>\n",
+       "      <td>0.002018</td>\n",
+       "      <td>0.026134</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                n_clients  aum_qty_mean_med  gross_flow_to_aum_med  \\\n",
+       "cluster_kmeans                                                       \n",
+       "3                     111      16968.521150               0.000000   \n",
+       "1                      91      15224.049625               4.040687   \n",
+       "4                      27      88889.763125               1.307204   \n",
+       "0                      12     536154.854937               2.704868   \n",
+       "2                       5      72055.041304              12.515495   \n",
+       "\n",
+       "                flow_freq_med  n_tx_total_med  avg_n_isin_held_med  \\\n",
+       "cluster_kmeans                                                       \n",
+       "3                         0.0             0.0             2.291667   \n",
+       "1                         1.0           347.0             2.772727   \n",
+       "4                         1.0          1132.0            14.666667   \n",
+       "0                         1.0          4320.0            22.479167   \n",
+       "2                         1.0           347.0             1.000000   \n",
+       "\n",
+       "                n_isin_total_med  avg_holding_months_per_isin_med  \\\n",
+       "cluster_kmeans                                                      \n",
+       "3                           15.0                         3.800000   \n",
+       "1                           19.0                         4.000000   \n",
+       "4                           32.0                        15.380952   \n",
+       "0                           54.0                         8.628205   \n",
+       "2                           10.0                         1.916667   \n",
+       "\n",
+       "                exit_rate_per_isin_med  flow_direction_balance_med  \\\n",
+       "cluster_kmeans                                                       \n",
+       "3                             0.083333                    0.000000   \n",
+       "1                             1.175000                   -0.326316   \n",
+       "4                             0.196429                   -0.290942   \n",
+       "0                             2.010311                   -0.483334   \n",
+       "2                             1.000000                    0.000000   \n",
+       "\n",
+       "                redemption_bias_med  aum_drawdown_last_med  \\\n",
+       "cluster_kmeans                                               \n",
+       "3                          0.000000               0.920330   \n",
+       "1                         -1.013060               0.919243   \n",
+       "4                         -1.051078               0.322512   \n",
+       "0                         -1.148256               0.655400   \n",
+       "2                         -1.251187               1.000000   \n",
+       "\n",
+       "                aum_final_to_peak_med  corr_flow_fund_lag3_med  \\\n",
+       "cluster_kmeans                                                   \n",
+       "3                            0.112701                 0.029610   \n",
+       "1                            0.111327                 0.028616   \n",
+       "4                            0.677488                 0.186117   \n",
+       "0                            0.411812                 0.150284   \n",
+       "2                            0.000000                 0.054633   \n",
+       "\n",
+       "                corr_flow_fund_lag6_med  corr_flow_rate_lag3_med  \\\n",
+       "cluster_kmeans                                                     \n",
+       "3                             -0.028331                 0.026860   \n",
+       "1                             -0.021581                -0.000388   \n",
+       "4                              0.079017                -0.033758   \n",
+       "0                              0.115993                 0.067313   \n",
+       "2                             -0.100003                 0.002018   \n",
+       "\n",
+       "                corr_flow_rate_lag6_med  \n",
+       "cluster_kmeans                           \n",
+       "3                              0.009551  \n",
+       "1                             -0.003074  \n",
+       "4                              0.104930  \n",
+       "0                              0.094253  \n",
+       "2                              0.026134  "
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "===== K=5 (2019) =====\n"
+     ]
+    },
+    {
+     "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>n_clients</th>\n",
+       "      <th>aum_qty_mean_med</th>\n",
+       "      <th>gross_flow_to_aum_med</th>\n",
+       "      <th>flow_freq_med</th>\n",
+       "      <th>n_tx_total_med</th>\n",
+       "      <th>avg_n_isin_held_med</th>\n",
+       "      <th>n_isin_total_med</th>\n",
+       "      <th>avg_holding_months_per_isin_med</th>\n",
+       "      <th>exit_rate_per_isin_med</th>\n",
+       "      <th>flow_direction_balance_med</th>\n",
+       "      <th>redemption_bias_med</th>\n",
+       "      <th>aum_drawdown_last_med</th>\n",
+       "      <th>aum_final_to_peak_med</th>\n",
+       "      <th>corr_flow_fund_lag3_med</th>\n",
+       "      <th>corr_flow_fund_lag6_med</th>\n",
+       "      <th>corr_flow_rate_lag3_med</th>\n",
+       "      <th>corr_flow_rate_lag6_med</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>cluster_kmeans</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>158</td>\n",
+       "      <td>9633.246229</td>\n",
+       "      <td>4.266741</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>329.5</td>\n",
+       "      <td>2.638587</td>\n",
+       "      <td>20.0</td>\n",
+       "      <td>2.923188</td>\n",
+       "      <td>1.066964</td>\n",
+       "      <td>0.034443</td>\n",
+       "      <td>-1.006633</td>\n",
+       "      <td>0.876492</td>\n",
+       "      <td>0.221628</td>\n",
+       "      <td>-0.009886</td>\n",
+       "      <td>-0.002589</td>\n",
+       "      <td>-0.021260</td>\n",
+       "      <td>0.004922</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>74</td>\n",
+       "      <td>17463.171534</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>1.764493</td>\n",
+       "      <td>11.0</td>\n",
+       "      <td>3.765625</td>\n",
+       "      <td>0.119658</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.730164</td>\n",
+       "      <td>0.486056</td>\n",
+       "      <td>-0.015831</td>\n",
+       "      <td>-0.054000</td>\n",
+       "      <td>0.029791</td>\n",
+       "      <td>0.012218</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>68</td>\n",
+       "      <td>61413.995862</td>\n",
+       "      <td>1.242228</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>512.5</td>\n",
+       "      <td>10.750000</td>\n",
+       "      <td>19.0</td>\n",
+       "      <td>14.662500</td>\n",
+       "      <td>0.084118</td>\n",
+       "      <td>0.284410</td>\n",
+       "      <td>-1.022922</td>\n",
+       "      <td>0.024953</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>0.036290</td>\n",
+       "      <td>0.005350</td>\n",
+       "      <td>-0.063025</td>\n",
+       "      <td>-0.070005</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>15</td>\n",
+       "      <td>315716.091250</td>\n",
+       "      <td>4.836881</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>4596.0</td>\n",
+       "      <td>13.250000</td>\n",
+       "      <td>62.0</td>\n",
+       "      <td>5.065217</td>\n",
+       "      <td>1.952381</td>\n",
+       "      <td>0.114974</td>\n",
+       "      <td>-1.104636</td>\n",
+       "      <td>0.767660</td>\n",
+       "      <td>0.442852</td>\n",
+       "      <td>0.024923</td>\n",
+       "      <td>0.080512</td>\n",
+       "      <td>0.001555</td>\n",
+       "      <td>-0.089721</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>2</td>\n",
+       "      <td>77921.342500</td>\n",
+       "      <td>4.689483</td>\n",
+       "      <td>0.666667</td>\n",
+       "      <td>3060.0</td>\n",
+       "      <td>2.583333</td>\n",
+       "      <td>32.5</td>\n",
+       "      <td>1.420635</td>\n",
+       "      <td>0.250000</td>\n",
+       "      <td>0.610875</td>\n",
+       "      <td>-0.710315</td>\n",
+       "      <td>0.000641</td>\n",
+       "      <td>0.999359</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0.048991</td>\n",
+       "      <td>0.069475</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                n_clients  aum_qty_mean_med  gross_flow_to_aum_med  \\\n",
+       "cluster_kmeans                                                       \n",
+       "1                     158       9633.246229               4.266741   \n",
+       "3                      74      17463.171534               0.000000   \n",
+       "4                      68      61413.995862               1.242228   \n",
+       "0                      15     315716.091250               4.836881   \n",
+       "2                       2      77921.342500               4.689483   \n",
+       "\n",
+       "                flow_freq_med  n_tx_total_med  avg_n_isin_held_med  \\\n",
+       "cluster_kmeans                                                       \n",
+       "1                    1.000000           329.5             2.638587   \n",
+       "3                    0.000000             0.0             1.764493   \n",
+       "4                    1.000000           512.5            10.750000   \n",
+       "0                    1.000000          4596.0            13.250000   \n",
+       "2                    0.666667          3060.0             2.583333   \n",
+       "\n",
+       "                n_isin_total_med  avg_holding_months_per_isin_med  \\\n",
+       "cluster_kmeans                                                      \n",
+       "1                           20.0                         2.923188   \n",
+       "3                           11.0                         3.765625   \n",
+       "4                           19.0                        14.662500   \n",
+       "0                           62.0                         5.065217   \n",
+       "2                           32.5                         1.420635   \n",
+       "\n",
+       "                exit_rate_per_isin_med  flow_direction_balance_med  \\\n",
+       "cluster_kmeans                                                       \n",
+       "1                             1.066964                    0.034443   \n",
+       "3                             0.119658                    0.000000   \n",
+       "4                             0.084118                    0.284410   \n",
+       "0                             1.952381                    0.114974   \n",
+       "2                             0.250000                    0.610875   \n",
+       "\n",
+       "                redemption_bias_med  aum_drawdown_last_med  \\\n",
+       "cluster_kmeans                                               \n",
+       "1                         -1.006633               0.876492   \n",
+       "3                          0.000000               0.730164   \n",
+       "4                         -1.022922               0.024953   \n",
+       "0                         -1.104636               0.767660   \n",
+       "2                         -0.710315               0.000641   \n",
+       "\n",
+       "                aum_final_to_peak_med  corr_flow_fund_lag3_med  \\\n",
+       "cluster_kmeans                                                   \n",
+       "1                            0.221628                -0.009886   \n",
+       "3                            0.486056                -0.015831   \n",
+       "4                            1.000000                 0.036290   \n",
+       "0                            0.442852                 0.024923   \n",
+       "2                            0.999359                      NaN   \n",
+       "\n",
+       "                corr_flow_fund_lag6_med  corr_flow_rate_lag3_med  \\\n",
+       "cluster_kmeans                                                     \n",
+       "1                             -0.002589                -0.021260   \n",
+       "3                             -0.054000                 0.029791   \n",
+       "4                              0.005350                -0.063025   \n",
+       "0                              0.080512                 0.001555   \n",
+       "2                                   NaN                 0.048991   \n",
+       "\n",
+       "                corr_flow_rate_lag6_med  \n",
+       "cluster_kmeans                           \n",
+       "1                              0.004922  \n",
+       "3                              0.012218  \n",
+       "4                             -0.070005  \n",
+       "0                             -0.089721  \n",
+       "2                              0.069475  "
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "===== K=5 (2021) =====\n"
+     ]
+    },
+    {
+     "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>n_clients</th>\n",
+       "      <th>aum_qty_mean_med</th>\n",
+       "      <th>gross_flow_to_aum_med</th>\n",
+       "      <th>flow_freq_med</th>\n",
+       "      <th>n_tx_total_med</th>\n",
+       "      <th>avg_n_isin_held_med</th>\n",
+       "      <th>n_isin_total_med</th>\n",
+       "      <th>avg_holding_months_per_isin_med</th>\n",
+       "      <th>exit_rate_per_isin_med</th>\n",
+       "      <th>flow_direction_balance_med</th>\n",
+       "      <th>redemption_bias_med</th>\n",
+       "      <th>aum_drawdown_last_med</th>\n",
+       "      <th>aum_final_to_peak_med</th>\n",
+       "      <th>corr_flow_fund_lag3_med</th>\n",
+       "      <th>corr_flow_fund_lag6_med</th>\n",
+       "      <th>corr_flow_rate_lag3_med</th>\n",
+       "      <th>corr_flow_rate_lag6_med</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>cluster_kmeans</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>176</td>\n",
+       "      <td>13730.289442</td>\n",
+       "      <td>3.314366</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>303.5</td>\n",
+       "      <td>3.260870</td>\n",
+       "      <td>20.0</td>\n",
+       "      <td>3.661905</td>\n",
+       "      <td>1.242647</td>\n",
+       "      <td>-0.321897</td>\n",
+       "      <td>-1.013108</td>\n",
+       "      <td>0.889758</td>\n",
+       "      <td>0.203476</td>\n",
+       "      <td>-0.055453</td>\n",
+       "      <td>-0.035168</td>\n",
+       "      <td>0.034440</td>\n",
+       "      <td>0.061284</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>65</td>\n",
+       "      <td>32116.345125</td>\n",
+       "      <td>0.349545</td>\n",
+       "      <td>0.125000</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>1.666667</td>\n",
+       "      <td>7.0</td>\n",
+       "      <td>5.500000</td>\n",
+       "      <td>0.272727</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>-0.125000</td>\n",
+       "      <td>0.517941</td>\n",
+       "      <td>0.565745</td>\n",
+       "      <td>-0.023467</td>\n",
+       "      <td>-0.004682</td>\n",
+       "      <td>0.159795</td>\n",
+       "      <td>0.081149</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>61</td>\n",
+       "      <td>113501.940000</td>\n",
+       "      <td>0.950099</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>907.0</td>\n",
+       "      <td>14.833333</td>\n",
+       "      <td>20.0</td>\n",
+       "      <td>19.128205</td>\n",
+       "      <td>0.166667</td>\n",
+       "      <td>-0.125148</td>\n",
+       "      <td>-1.024417</td>\n",
+       "      <td>0.214815</td>\n",
+       "      <td>0.805057</td>\n",
+       "      <td>-0.017808</td>\n",
+       "      <td>0.013349</td>\n",
+       "      <td>0.020689</td>\n",
+       "      <td>0.045295</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>14</td>\n",
+       "      <td>432637.663188</td>\n",
+       "      <td>4.529472</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>4802.0</td>\n",
+       "      <td>21.062500</td>\n",
+       "      <td>65.0</td>\n",
+       "      <td>7.035629</td>\n",
+       "      <td>1.286394</td>\n",
+       "      <td>-0.114398</td>\n",
+       "      <td>-1.076190</td>\n",
+       "      <td>0.649860</td>\n",
+       "      <td>0.405715</td>\n",
+       "      <td>0.071547</td>\n",
+       "      <td>0.023572</td>\n",
+       "      <td>0.175785</td>\n",
+       "      <td>0.120807</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>1</td>\n",
+       "      <td>502831.492923</td>\n",
+       "      <td>1.175835</td>\n",
+       "      <td>0.923077</td>\n",
+       "      <td>31.0</td>\n",
+       "      <td>0.692308</td>\n",
+       "      <td>4.0</td>\n",
+       "      <td>2.250000</td>\n",
+       "      <td>0.500000</td>\n",
+       "      <td>-0.075935</td>\n",
+       "      <td>-0.923077</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>-0.239729</td>\n",
+       "      <td>-0.165593</td>\n",
+       "      <td>-0.603793</td>\n",
+       "      <td>0.022203</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                n_clients  aum_qty_mean_med  gross_flow_to_aum_med  \\\n",
+       "cluster_kmeans                                                       \n",
+       "1                     176      13730.289442               3.314366   \n",
+       "3                      65      32116.345125               0.349545   \n",
+       "4                      61     113501.940000               0.950099   \n",
+       "0                      14     432637.663188               4.529472   \n",
+       "2                       1     502831.492923               1.175835   \n",
+       "\n",
+       "                flow_freq_med  n_tx_total_med  avg_n_isin_held_med  \\\n",
+       "cluster_kmeans                                                       \n",
+       "1                    1.000000           303.5             3.260870   \n",
+       "3                    0.125000             1.0             1.666667   \n",
+       "4                    1.000000           907.0            14.833333   \n",
+       "0                    1.000000          4802.0            21.062500   \n",
+       "2                    0.923077            31.0             0.692308   \n",
+       "\n",
+       "                n_isin_total_med  avg_holding_months_per_isin_med  \\\n",
+       "cluster_kmeans                                                      \n",
+       "1                           20.0                         3.661905   \n",
+       "3                            7.0                         5.500000   \n",
+       "4                           20.0                        19.128205   \n",
+       "0                           65.0                         7.035629   \n",
+       "2                            4.0                         2.250000   \n",
+       "\n",
+       "                exit_rate_per_isin_med  flow_direction_balance_med  \\\n",
+       "cluster_kmeans                                                       \n",
+       "1                             1.242647                   -0.321897   \n",
+       "3                             0.272727                    0.000000   \n",
+       "4                             0.166667                   -0.125148   \n",
+       "0                             1.286394                   -0.114398   \n",
+       "2                             0.500000                   -0.075935   \n",
+       "\n",
+       "                redemption_bias_med  aum_drawdown_last_med  \\\n",
+       "cluster_kmeans                                               \n",
+       "1                         -1.013108               0.889758   \n",
+       "3                         -0.125000               0.517941   \n",
+       "4                         -1.024417               0.214815   \n",
+       "0                         -1.076190               0.649860   \n",
+       "2                         -0.923077               1.000000   \n",
+       "\n",
+       "                aum_final_to_peak_med  corr_flow_fund_lag3_med  \\\n",
+       "cluster_kmeans                                                   \n",
+       "1                            0.203476                -0.055453   \n",
+       "3                            0.565745                -0.023467   \n",
+       "4                            0.805057                -0.017808   \n",
+       "0                            0.405715                 0.071547   \n",
+       "2                            0.000000                -0.239729   \n",
+       "\n",
+       "                corr_flow_fund_lag6_med  corr_flow_rate_lag3_med  \\\n",
+       "cluster_kmeans                                                     \n",
+       "1                             -0.035168                 0.034440   \n",
+       "3                             -0.004682                 0.159795   \n",
+       "4                              0.013349                 0.020689   \n",
+       "0                              0.023572                 0.175785   \n",
+       "2                             -0.165593                -0.603793   \n",
+       "\n",
+       "                corr_flow_rate_lag6_med  \n",
+       "cluster_kmeans                           \n",
+       "1                              0.061284  \n",
+       "3                              0.081149  \n",
+       "4                              0.045295  \n",
+       "0                              0.120807  \n",
+       "2                              0.022203  "
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "===== K=5 (2023) =====\n"
+     ]
+    },
+    {
+     "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>n_clients</th>\n",
+       "      <th>aum_qty_mean_med</th>\n",
+       "      <th>gross_flow_to_aum_med</th>\n",
+       "      <th>flow_freq_med</th>\n",
+       "      <th>n_tx_total_med</th>\n",
+       "      <th>avg_n_isin_held_med</th>\n",
+       "      <th>n_isin_total_med</th>\n",
+       "      <th>avg_holding_months_per_isin_med</th>\n",
+       "      <th>exit_rate_per_isin_med</th>\n",
+       "      <th>flow_direction_balance_med</th>\n",
+       "      <th>redemption_bias_med</th>\n",
+       "      <th>aum_drawdown_last_med</th>\n",
+       "      <th>aum_final_to_peak_med</th>\n",
+       "      <th>corr_flow_fund_lag3_med</th>\n",
+       "      <th>corr_flow_fund_lag6_med</th>\n",
+       "      <th>corr_flow_rate_lag3_med</th>\n",
+       "      <th>corr_flow_rate_lag6_med</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>cluster_kmeans</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>172</td>\n",
+       "      <td>1.357394e+04</td>\n",
+       "      <td>4.150092</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>310.0</td>\n",
+       "      <td>2.848485</td>\n",
+       "      <td>20.0</td>\n",
+       "      <td>3.227273</td>\n",
+       "      <td>1.108732</td>\n",
+       "      <td>0.130341</td>\n",
+       "      <td>-1.011453</td>\n",
+       "      <td>0.906305</td>\n",
+       "      <td>0.246636</td>\n",
+       "      <td>-0.021698</td>\n",
+       "      <td>-0.048594</td>\n",
+       "      <td>-0.010974</td>\n",
+       "      <td>-0.042960</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>82</td>\n",
+       "      <td>8.636871e+04</td>\n",
+       "      <td>1.389136</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>770.5</td>\n",
+       "      <td>12.895833</td>\n",
+       "      <td>27.0</td>\n",
+       "      <td>14.025264</td>\n",
+       "      <td>0.275518</td>\n",
+       "      <td>0.237140</td>\n",
+       "      <td>-1.024236</td>\n",
+       "      <td>0.125418</td>\n",
+       "      <td>0.953249</td>\n",
+       "      <td>-0.000646</td>\n",
+       "      <td>0.010373</td>\n",
+       "      <td>-0.102000</td>\n",
+       "      <td>0.070727</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>55</td>\n",
+       "      <td>6.469700e+04</td>\n",
+       "      <td>0.486343</td>\n",
+       "      <td>0.125000</td>\n",
+       "      <td>4.0</td>\n",
+       "      <td>1.041667</td>\n",
+       "      <td>3.0</td>\n",
+       "      <td>8.000000</td>\n",
+       "      <td>0.222222</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>-0.132403</td>\n",
+       "      <td>0.355167</td>\n",
+       "      <td>0.812196</td>\n",
+       "      <td>0.048014</td>\n",
+       "      <td>-0.013428</td>\n",
+       "      <td>0.146384</td>\n",
+       "      <td>0.189835</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>16</td>\n",
+       "      <td>5.487127e+05</td>\n",
+       "      <td>3.956302</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>5915.5</td>\n",
+       "      <td>21.229167</td>\n",
+       "      <td>68.5</td>\n",
+       "      <td>6.473287</td>\n",
+       "      <td>1.152933</td>\n",
+       "      <td>0.407132</td>\n",
+       "      <td>-1.158641</td>\n",
+       "      <td>0.487722</td>\n",
+       "      <td>0.921376</td>\n",
+       "      <td>-0.063857</td>\n",
+       "      <td>0.034445</td>\n",
+       "      <td>-0.126342</td>\n",
+       "      <td>-0.203116</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>2</td>\n",
+       "      <td>1.312765e+06</td>\n",
+       "      <td>6.604496</td>\n",
+       "      <td>0.708333</td>\n",
+       "      <td>314.0</td>\n",
+       "      <td>1.267857</td>\n",
+       "      <td>8.0</td>\n",
+       "      <td>2.375000</td>\n",
+       "      <td>1.541667</td>\n",
+       "      <td>-0.426440</td>\n",
+       "      <td>-0.843028</td>\n",
+       "      <td>0.995909</td>\n",
+       "      <td>0.010642</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0.206573</td>\n",
+       "      <td>0.199750</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                n_clients  aum_qty_mean_med  gross_flow_to_aum_med  \\\n",
+       "cluster_kmeans                                                       \n",
+       "1                     172      1.357394e+04               4.150092   \n",
+       "4                      82      8.636871e+04               1.389136   \n",
+       "3                      55      6.469700e+04               0.486343   \n",
+       "0                      16      5.487127e+05               3.956302   \n",
+       "2                       2      1.312765e+06               6.604496   \n",
+       "\n",
+       "                flow_freq_med  n_tx_total_med  avg_n_isin_held_med  \\\n",
+       "cluster_kmeans                                                       \n",
+       "1                    1.000000           310.0             2.848485   \n",
+       "4                    1.000000           770.5            12.895833   \n",
+       "3                    0.125000             4.0             1.041667   \n",
+       "0                    1.000000          5915.5            21.229167   \n",
+       "2                    0.708333           314.0             1.267857   \n",
+       "\n",
+       "                n_isin_total_med  avg_holding_months_per_isin_med  \\\n",
+       "cluster_kmeans                                                      \n",
+       "1                           20.0                         3.227273   \n",
+       "4                           27.0                        14.025264   \n",
+       "3                            3.0                         8.000000   \n",
+       "0                           68.5                         6.473287   \n",
+       "2                            8.0                         2.375000   \n",
+       "\n",
+       "                exit_rate_per_isin_med  flow_direction_balance_med  \\\n",
+       "cluster_kmeans                                                       \n",
+       "1                             1.108732                    0.130341   \n",
+       "4                             0.275518                    0.237140   \n",
+       "3                             0.222222                    0.000000   \n",
+       "0                             1.152933                    0.407132   \n",
+       "2                             1.541667                   -0.426440   \n",
+       "\n",
+       "                redemption_bias_med  aum_drawdown_last_med  \\\n",
+       "cluster_kmeans                                               \n",
+       "1                         -1.011453               0.906305   \n",
+       "4                         -1.024236               0.125418   \n",
+       "3                         -0.132403               0.355167   \n",
+       "0                         -1.158641               0.487722   \n",
+       "2                         -0.843028               0.995909   \n",
+       "\n",
+       "                aum_final_to_peak_med  corr_flow_fund_lag3_med  \\\n",
+       "cluster_kmeans                                                   \n",
+       "1                            0.246636                -0.021698   \n",
+       "4                            0.953249                -0.000646   \n",
+       "3                            0.812196                 0.048014   \n",
+       "0                            0.921376                -0.063857   \n",
+       "2                            0.010642                      NaN   \n",
+       "\n",
+       "                corr_flow_fund_lag6_med  corr_flow_rate_lag3_med  \\\n",
+       "cluster_kmeans                                                     \n",
+       "1                             -0.048594                -0.010974   \n",
+       "4                              0.010373                -0.102000   \n",
+       "3                             -0.013428                 0.146384   \n",
+       "0                              0.034445                -0.126342   \n",
+       "2                                   NaN                 0.206573   \n",
+       "\n",
+       "                corr_flow_rate_lag6_med  \n",
+       "cluster_kmeans                           \n",
+       "1                             -0.042960  \n",
+       "4                              0.070727  \n",
+       "3                              0.189835  \n",
+       "0                             -0.203116  \n",
+       "2                              0.199750  "
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "print(f\"\\n===== K=5 (2017) =====\")\n",
+    "prof = (\n",
+    "    df_2017.groupby(f\"cluster_kmeans\")\n",
+    "        .agg(\n",
+    "            n_clients=(ID_COL, \"count\"),\n",
+    "            **{f\"{c}_med\": (c, \"median\") for c in profile_vars}\n",
+    "        )\n",
+    "        .sort_values(\"n_clients\", ascending=False)\n",
+    "    )\n",
+    "display(prof)\n",
+    "\n",
+    "print(f\"\\n===== K=5 (2019) =====\")\n",
+    "\n",
+    "prof = (\n",
+    "    df_2019.groupby(f\"cluster_kmeans\")\n",
+    "        .agg(\n",
+    "            n_clients=(ID_COL, \"count\"),\n",
+    "            **{f\"{c}_med\": (c, \"median\") for c in profile_vars}\n",
+    "        )\n",
+    "        .sort_values(\"n_clients\", ascending=False)\n",
+    "    )\n",
+    "display(prof)\n",
+    "\n",
+    "print(f\"\\n===== K=5 (2021) =====\")\n",
+    "\n",
+    "prof = (\n",
+    "    df_2021.groupby(f\"cluster_kmeans\")\n",
+    "        .agg(\n",
+    "            n_clients=(ID_COL, \"count\"),\n",
+    "            **{f\"{c}_med\": (c, \"median\") for c in profile_vars}\n",
+    "        )\n",
+    "        .sort_values(\"n_clients\", ascending=False)\n",
+    "    )\n",
+    "display(prof)\n",
+    "\n",
+    "print(f\"\\n===== K=5 (2023) =====\")\n",
+    "\n",
+    "prof = (\n",
+    "    df_2023.groupby(f\"cluster_kmeans\")\n",
+    "        .agg(\n",
+    "            n_clients=(ID_COL, \"count\"),\n",
+    "            **{f\"{c}_med\": (c, \"median\") for c in profile_vars}\n",
+    "        )\n",
+    "        .sort_values(\"n_clients\", ascending=False)\n",
+    "    )\n",
+    "display(prof)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2895cf20-79e0-4b98-b0c2-107425f99b60",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "labels_map = {\n",
+    "    0: \"Cluster 0 (30): Large and highly active movers\",\n",
+    "    1: \"Cluster 1 (168): Occasional large movers\",\n",
+    "    3: \"Cluster 3 (111): Dormant profiles\",\n",
+    "    4: \"Cluster 4 (90): Loyal clients\"\n",
+    "}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 381,
+   "id": "0040629e-2d5a-4e61-ba50-a1e1cce790e1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Merge\n",
+    "\n",
+    "df_evo = (\n",
+    "    df_2017[[ID_COL, \"cluster_kmeans\"]]\n",
+    "    .rename(columns={\"cluster_kmeans\": \"cluster_2017\"})\n",
+    "    .merge(\n",
+    "        df_2019[[ID_COL, \"cluster_kmeans\"]]\n",
+    "        .rename(columns={\"cluster_kmeans\": \"cluster_2019\"}),\n",
+    "        on=ID_COL\n",
+    "    )\n",
+    "    .merge(\n",
+    "        df_2021[[ID_COL, \"cluster_kmeans\"]]\n",
+    "        .rename(columns={\"cluster_kmeans\": \"cluster_2021\"}),\n",
+    "        on=ID_COL\n",
+    "    )\n",
+    "    .merge(\n",
+    "        df_2023[[ID_COL, \"cluster_kmeans\"]]\n",
+    "        .rename(columns={\"cluster_kmeans\": \"cluster_2023\"}),\n",
+    "        on=ID_COL\n",
+    "    )\n",
+    ")\n",
+    "\n",
+    "df_evo = df_evo.isin(clusters_keep = [1, 2, 3])\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 382,
+   "id": "6fb52dd0-e5ee-443f-a155-913caaf4bbe1",
+   "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>cluster_2019</th>\n",
+       "      <th>0</th>\n",
+       "      <th>1</th>\n",
+       "      <th>3</th>\n",
+       "      <th>4</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>cluster_2017</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>9.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>NaN</td>\n",
+       "      <td>64.0</td>\n",
+       "      <td>3.0</td>\n",
+       "      <td>8.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>NaN</td>\n",
+       "      <td>3.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>2.0</td>\n",
+       "      <td>30.0</td>\n",
+       "      <td>31.0</td>\n",
+       "      <td>5.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>1.0</td>\n",
+       "      <td>5.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>19.0</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "cluster_2019    0     1     3     4\n",
+       "cluster_2017                       \n",
+       "0             9.0   NaN   NaN   1.0\n",
+       "1             NaN  64.0   3.0   8.0\n",
+       "2             NaN   3.0   1.0   NaN\n",
+       "3             2.0  30.0  31.0   5.0\n",
+       "4             1.0   5.0   1.0  19.0"
+      ]
+     },
+     "execution_count": 382,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df_evo.groupby([\"cluster_2017\", \"cluster_2019\"]).size().unstack()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 383,
+   "id": "7bad62fa-d161-4c6e-ad80-d0c8a75c06c2",
+   "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>cluster_2021</th>\n",
+       "      <th>0</th>\n",
+       "      <th>1</th>\n",
+       "      <th>2</th>\n",
+       "      <th>3</th>\n",
+       "      <th>4</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>cluster_2019</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>9.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>1.0</td>\n",
+       "      <td>96.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2.0</td>\n",
+       "      <td>3.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>NaN</td>\n",
+       "      <td>12.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>22.0</td>\n",
+       "      <td>1.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>1.0</td>\n",
+       "      <td>9.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>22.0</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "cluster_2021    0     1    2     3     4\n",
+       "cluster_2019                            \n",
+       "0             9.0   1.0  NaN   NaN   2.0\n",
+       "1             1.0  96.0  NaN   2.0   3.0\n",
+       "3             NaN  12.0  1.0  22.0   1.0\n",
+       "4             1.0   9.0  NaN   1.0  22.0"
+      ]
+     },
+     "execution_count": 383,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df_evo.groupby([\"cluster_2019\", \"cluster_2021\"]).size().unstack()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 384,
+   "id": "8f135625-24b3-417e-9414-d2cd0dc32cfe",
+   "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>cluster_2023</th>\n",
+       "      <th>0</th>\n",
+       "      <th>1</th>\n",
+       "      <th>2</th>\n",
+       "      <th>3</th>\n",
+       "      <th>4</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>cluster_2021</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>11.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>1.0</td>\n",
+       "      <td>97.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2.0</td>\n",
+       "      <td>18.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>NaN</td>\n",
+       "      <td>13.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>12.0</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>2.0</td>\n",
+       "      <td>4.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>22.0</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "cluster_2023     0     1    2     3     4\n",
+       "cluster_2021                             \n",
+       "0             11.0   NaN  NaN   NaN   NaN\n",
+       "1              1.0  97.0  NaN   2.0  18.0\n",
+       "2              NaN   NaN  1.0   NaN   NaN\n",
+       "3              NaN  13.0  NaN  12.0   NaN\n",
+       "4              2.0   4.0  NaN   NaN  22.0"
+      ]
+     },
+     "execution_count": 384,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df_evo.groupby([\"cluster_2021\", \"cluster_2023\"]).size().unstack()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 391,
+   "id": "73db7626-a489-49f1-9c3b-bfde6001e193",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 800x600 with 2 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "import seaborn as sns\n",
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "df_filtered = df_evo[\n",
+    "    (df_evo[\"cluster_2017\"] != 2) & \n",
+    "    (df_evo[\"cluster_2019\"] != 2) &\n",
+    "    (df_evo[\"cluster_2021\"] != 2) &\n",
+    "    (df_evo[\"cluster_2023\"] != 2)\n",
+    "]\n",
+    "\n",
+    "# matrice de transition\n",
+    "transition1 = df_filtered.groupby([\"cluster_2017\", \"cluster_2019\"]).size().unstack(fill_value=0)\n",
+    "transition2 = df_filtered.groupby([\"cluster_2019\", \"cluster_2021\"]).size().unstack(fill_value=0)\n",
+    "transition3 = df_filtered.groupby([\"cluster_2021\", \"cluster_2023\"]).size().unstack(fill_value=0)\n",
+    "\n",
+    "transition_pct1 = transition1.div(transition1.sum(axis=1), axis=0)\n",
+    "transition_pct2 = transition2.div(transition2.sum(axis=1), axis=0)\n",
+    "transition_pct3 = transition3.div(transition3.sum(axis=1), axis=0)\n",
+    "\n",
+    "plt.figure(figsize=(8,6))\n",
+    "#sns.heatmap(transition1, annot=True, fmt=\"d\", cmap=\"Blues\")\n",
+    "sns.heatmap(transition_pct1, annot=True, fmt=\".2f\", cmap=\"Blues\")\n",
+    "\n",
+    "plt.ylabel(\"Cluster 2016-2019\")\n",
+    "plt.xlabel(\"Cluster 2019-2022\")\n",
+    "plt.title(\"Matrice de transition des clusters (2016 → 2019)\")\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 393,
+   "id": "47edb04f-e57c-48de-8696-af968b5614d7",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 1400x600 with 4 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "fig, axes = plt.subplots(1, 2, figsize=(14,6), sharey=True)\n",
+    "\n",
+    "# --- Heatmap 1 : 2017 → 2019 ---\n",
+    "sns.heatmap(\n",
+    "    transition_pct1,\n",
+    "    annot=True,\n",
+    "    fmt=\".2f\",\n",
+    "    cmap=\"Blues\",\n",
+    "    ax=axes[0]\n",
+    ")\n",
+    "\n",
+    "axes[0].set_xlabel(\"Cluster 2019-2021\")\n",
+    "axes[0].set_ylabel(\"Cluster 2017-2019\")\n",
+    "axes[0].set_title(\"Transition des clusters (2017-2019 → 2019-2021)\")\n",
+    "\n",
+    "# --- Heatmap 2 : 2019 → 2021 ---\n",
+    "sns.heatmap(\n",
+    "    transition_pct2,\n",
+    "    annot=True,\n",
+    "    fmt=\".2f\",\n",
+    "    cmap=\"Blues\",\n",
+    "    ax=axes[1]\n",
+    ")\n",
+    "\n",
+    "axes[1].set_xlabel(\"Cluster 2021-2023\")\n",
+    "axes[1].set_ylabel(\"Cluster 2019-2021\")\n",
+    "axes[1].set_title(\"Transition des clusters (2019-2021 → 2021-2023)\")\n",
+    "\n",
+    "plt.tight_layout()\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 394,
+   "id": "24ff33bb-3658-4c36-bcd8-0a0982577314",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 1800x600 with 6 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "fig, axes = plt.subplots(1, 3, figsize=(18,6), sharey=True)\n",
+    "\n",
+    "# --- Heatmap 1 : \n",
+    "sns.heatmap(\n",
+    "    transition_pct1,\n",
+    "    annot=True,\n",
+    "    fmt=\".2f\",\n",
+    "    cmap=\"Blues\",\n",
+    "    ax=axes[0]\n",
+    ")\n",
+    "\n",
+    "axes[0].set_xlabel(\"Cluster 2019-2021\")\n",
+    "axes[0].set_ylabel(\"Cluster 2017-2019\")\n",
+    "axes[0].set_title(\"Transition (2017-2019 → 2019-2021)\")\n",
+    "\n",
+    "# --- Heatmap 2 : \n",
+    "sns.heatmap(\n",
+    "    transition_pct2,\n",
+    "    annot=True,\n",
+    "    fmt=\".2f\",\n",
+    "    cmap=\"Blues\",\n",
+    "    ax=axes[1]\n",
+    ")\n",
+    "\n",
+    "axes[1].set_xlabel(\"Cluster 2021-2023\")\n",
+    "axes[1].set_ylabel(\"Cluster 2019-2021\")\n",
+    "axes[1].set_title(\"Transition (2019-2021 → 2021-2023)\")\n",
+    "\n",
+    "# --- Heatmap 3 : \n",
+    "sns.heatmap(\n",
+    "    transition_pct3,\n",
+    "    annot=True,\n",
+    "    fmt=\".2f\",\n",
+    "    cmap=\"Blues\",\n",
+    "    ax=axes[2]\n",
+    ")\n",
+    "\n",
+    "axes[2].set_xlabel(\"Cluster 2023-2025\")\n",
+    "axes[2].set_ylabel(\"Cluster 2021-2023\")\n",
+    "axes[2].set_title(\"Transition (2021-2023 → 2023-2025)\")\n",
+    "\n",
+    "plt.tight_layout()\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 410,
+   "id": "f50429f5-12ea-4056-8568-d27d005835ca",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 1000x600 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 1000x600 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "import pandas as pd\n",
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "labels_map_new = {\n",
+    "    0: \"Cluster 0: Large and highly active movers\",\n",
+    "    1: \"Cluster 1: Occasional large movers\",\n",
+    "    2: \"Cluster 2: Extreme\",\n",
+    "    3: \"Cluster 3: Dormant profiles\",\n",
+    "    4: \"Cluster 4: Loyal clients\"\n",
+    "}\n",
+    "\n",
+    "colors_map = {\n",
+    "    \"Cluster 0: Large and highly active movers\" : \"#0000FF\", #bleu\n",
+    "    \"Cluster 1: Occasional large movers\": \"#FFA500\", #orange\n",
+    "    \"Cluster 2: Extreme\": \"#800080\", #violet\n",
+    "    \"Cluster 3: Dormant profiles\": \"#008000\", #vert\n",
+    "    \"Cluster 4: Loyal clients\": \"#FF0000\" #rouge\n",
+    "}\n",
+    "\n",
+    "# --- 1. Construction du dataset long ---\n",
+    "df_long = pd.concat([\n",
+    "    df_2017.assign(period=\"2017-2019\"),\n",
+    "    df_2019.assign(period=\"2019-2021\"),\n",
+    "    df_2021.assign(period=\"2021-2023\"),\n",
+    "    df_2023.assign(period=\"2023-2025\")\n",
+    "])\n",
+    "\n",
+    "# --- 2. Comptage par cluster et période ---\n",
+    "counts = (\n",
+    "    df_long.groupby([\"period\", \"cluster_kmeans\"])\n",
+    "    .size()\n",
+    "    .unstack(fill_value=0)\n",
+    ")\n",
+    "\n",
+    "# --- 3. Passage en proportions ---\n",
+    "props = counts.div(counts.sum(axis=1), axis=0)\n",
+    "\n",
+    "\n",
+    "props = props.sort_index(axis=1)\n",
+    "props.columns = [labels_map_new.get(int(c), f\"Cluster {int(c)}\") for c in props.columns]\n",
+    "\n",
+    "# =========================\n",
+    "# 🔹 Graphique 1 : AREA\n",
+    "# =========================\n",
+    "plt.figure(figsize=(10,6))\n",
+    "\n",
+    "props.plot(\n",
+    "    kind=\"area\",\n",
+    "    stacked=True,\n",
+    "    ax=plt.gca()\n",
+    ")\n",
+    "\n",
+    "plt.ylabel(\"Proportion of clients\")\n",
+    "plt.xlabel(\"Period\")\n",
+    "plt.title(\"Evolution of cluster proportions over time\")\n",
+    "plt.ylim(0, 1)\n",
+    "plt.legend(title=\"Cluster\", loc=\"upper left\")\n",
+    "\n",
+    "plt.tight_layout()\n",
+    "plt.show()\n",
+    "\n",
+    "# =========================\n",
+    "# 🔹 Graphique 2 : BAR\n",
+    "# =========================\n",
+    "\n",
+    "colors_list = [colors_map[c] for c in props.columns]\n",
+    "\n",
+    "plt.figure(figsize=(10,6))\n",
+    "\n",
+    "props.plot(\n",
+    "    kind=\"bar\",\n",
+    "    stacked=True,\n",
+    "    ax=plt.gca(),\n",
+    "    color=colors_list\n",
+    ")\n",
+    "\n",
+    "plt.xticks(rotation=45, ha=\"right\")\n",
+    "\n",
+    "plt.ylabel(\"Proportion of clients\")\n",
+    "plt.xlabel(\"Period\")\n",
+    "plt.title(\"Cluster distribution by period\")\n",
+    "plt.ylim(0, 1)\n",
+    "plt.legend(title=\"Cluster\", bbox_to_anchor=(1.05, 1), loc=\"upper left\")\n",
+    "\n",
+    "plt.tight_layout()\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2f8e871a-1cb7-499d-b45f-de714b15cd15",
+   "metadata": {},
    "outputs": [],
    "source": []
   }