From ed4734d07ffce840cfd0d03a77a2e61fcae149c5 Mon Sep 17 00:00:00 2001
From: Francois Caud <frcaud@gmail.com>
Date: Fri, 22 Dec 2023 18:28:12 +0100
Subject: [PATCH] update starting_kit script in notebook

---
 tephra_starting_kit.ipynb | 131 +++++++++++++++++++-------------------
 1 file changed, 67 insertions(+), 64 deletions(-)

diff --git a/tephra_starting_kit.ipynb b/tephra_starting_kit.ipynb
index c42d884..4f4fed7 100644
--- a/tephra_starting_kit.ipynb
+++ b/tephra_starting_kit.ipynb
@@ -120,7 +120,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 46,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -189,7 +189,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [
     {
@@ -588,7 +588,7 @@
        "[6220 rows x 95 columns]"
       ]
      },
-     "execution_count": 12,
+     "execution_count": 2,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -600,7 +600,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [
     {
@@ -999,7 +999,7 @@
        "[839 rows x 95 columns]"
       ]
      },
-     "execution_count": 13,
+     "execution_count": 3,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1011,7 +1011,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [
     {
@@ -1038,7 +1038,7 @@
        "      dtype='object')"
       ]
      },
-     "execution_count": 15,
+     "execution_count": 4,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1049,7 +1049,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [
     {
@@ -1058,7 +1058,7 @@
        "<AxesSubplot:>"
       ]
      },
-     "execution_count": 17,
+     "execution_count": 5,
      "metadata": {},
      "output_type": "execute_result"
     },
@@ -1091,7 +1091,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 39,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [
     {
@@ -1106,7 +1106,7 @@
        "       dtype=object))"
       ]
      },
-     "execution_count": 39,
+     "execution_count": 6,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1124,7 +1124,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [
     {
@@ -1163,7 +1163,7 @@
        "Name: Event, dtype: int64"
       ]
      },
-     "execution_count": 22,
+     "execution_count": 7,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1174,7 +1174,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 23,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [
     {
@@ -1210,7 +1210,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 40,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [
     {
@@ -2176,7 +2176,7 @@
        "[30 rows x 455 columns]"
       ]
      },
-     "execution_count": 40,
+     "execution_count": 9,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -2189,7 +2189,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 42,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [
     {
@@ -2231,7 +2231,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 26,
+   "execution_count": 11,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2253,7 +2253,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 31,
+   "execution_count": 12,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2264,7 +2264,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 32,
+   "execution_count": 13,
    "metadata": {},
    "outputs": [
     {
@@ -2637,7 +2637,7 @@
        "[6220 rows x 35 columns]"
       ]
      },
-     "execution_count": 32,
+     "execution_count": 13,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -2648,7 +2648,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 33,
+   "execution_count": 14,
    "metadata": {},
    "outputs": [
     {
@@ -2657,7 +2657,7 @@
        "<AxesSubplot:>"
       ]
      },
-     "execution_count": 33,
+     "execution_count": 14,
      "metadata": {},
      "output_type": "execute_result"
     },
@@ -2687,7 +2687,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 34,
+   "execution_count": 15,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2698,7 +2698,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 35,
+   "execution_count": 16,
    "metadata": {},
    "outputs": [
     {
@@ -3071,7 +3071,7 @@
        "[839 rows x 35 columns]"
       ]
      },
-     "execution_count": 35,
+     "execution_count": 16,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -3082,7 +3082,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 36,
+   "execution_count": 17,
    "metadata": {},
    "outputs": [
     {
@@ -3091,7 +3091,7 @@
        "<AxesSubplot:>"
       ]
      },
-     "execution_count": 36,
+     "execution_count": 17,
      "metadata": {},
      "output_type": "execute_result"
     },
@@ -3121,7 +3121,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 30,
+   "execution_count": 18,
    "metadata": {},
    "outputs": [
     {
@@ -3142,7 +3142,7 @@
        "         4.26585366,  0.99751983]])"
       ]
      },
-     "execution_count": 30,
+     "execution_count": 18,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -3154,7 +3154,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 37,
+   "execution_count": 19,
    "metadata": {},
    "outputs": [
     {
@@ -3175,7 +3175,7 @@
        "                nan,         nan]])"
       ]
      },
-     "execution_count": 37,
+     "execution_count": 19,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -3195,7 +3195,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 43,
+   "execution_count": 20,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3238,7 +3238,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 45,
+   "execution_count": 21,
    "metadata": {},
    "outputs": [
     {
@@ -3247,7 +3247,7 @@
        "(array([19, 19, 19, ..., 28, 28,  8], dtype=int8), (6220,))"
       ]
      },
-     "execution_count": 45,
+     "execution_count": 21,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -3259,7 +3259,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 47,
+   "execution_count": 22,
    "metadata": {},
    "outputs": [
     {
@@ -3318,7 +3318,7 @@
        " (839,))"
       ]
      },
-     "execution_count": 47,
+     "execution_count": 22,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -3337,7 +3337,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 48,
+   "execution_count": 23,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3355,7 +3355,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 49,
+   "execution_count": 24,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3373,20 +3373,20 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 51,
+   "execution_count": 25,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/html": [
-       "<style>#sk-container-id-2 {color: black;background-color: white;}#sk-container-id-2 pre{padding: 0;}#sk-container-id-2 div.sk-toggleable {background-color: white;}#sk-container-id-2 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-2 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-2 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-2 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-2 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-2 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-2 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-2 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-2 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-2 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-2 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-2 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-2 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-2 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-2 div.sk-item {position: relative;z-index: 1;}#sk-container-id-2 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-2 div.sk-item::before, #sk-container-id-2 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-2 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-2 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-2 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-2 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-2 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-2 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-2 div.sk-label-container {text-align: center;}#sk-container-id-2 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-2 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-2\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>Pipeline(steps=[(&#x27;transformer&#x27;,\n",
+       "<style>#sk-container-id-1 {color: black;background-color: white;}#sk-container-id-1 pre{padding: 0;}#sk-container-id-1 div.sk-toggleable {background-color: white;}#sk-container-id-1 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-1 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-1 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-1 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-1 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-1 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-1 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-1 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-1 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-1 div.sk-item {position: relative;z-index: 1;}#sk-container-id-1 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-1 div.sk-item::before, #sk-container-id-1 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-1 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-1 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-1 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-1 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-1 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-1 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-1 div.sk-label-container {text-align: center;}#sk-container-id-1 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-1 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>Pipeline(steps=[(&#x27;transformer&#x27;,\n",
        "                 Pipeline(steps=[(&#x27;imputer&#x27;, SimpleImputer(strategy=&#x27;median&#x27;)),\n",
        "                                 (&#x27;scaler&#x27;, StandardScaler())])),\n",
-       "                (&#x27;classifier&#x27;, LogisticRegression(max_iter=500))])</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-6\" type=\"checkbox\" ><label for=\"sk-estimator-id-6\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">Pipeline</label><div class=\"sk-toggleable__content\"><pre>Pipeline(steps=[(&#x27;transformer&#x27;,\n",
+       "                (&#x27;classifier&#x27;, LogisticRegression(max_iter=500))])</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" ><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">Pipeline</label><div class=\"sk-toggleable__content\"><pre>Pipeline(steps=[(&#x27;transformer&#x27;,\n",
        "                 Pipeline(steps=[(&#x27;imputer&#x27;, SimpleImputer(strategy=&#x27;median&#x27;)),\n",
        "                                 (&#x27;scaler&#x27;, StandardScaler())])),\n",
-       "                (&#x27;classifier&#x27;, LogisticRegression(max_iter=500))])</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-7\" type=\"checkbox\" ><label for=\"sk-estimator-id-7\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">transformer: Pipeline</label><div class=\"sk-toggleable__content\"><pre>Pipeline(steps=[(&#x27;imputer&#x27;, SimpleImputer(strategy=&#x27;median&#x27;)),\n",
-       "                (&#x27;scaler&#x27;, StandardScaler())])</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-8\" type=\"checkbox\" ><label for=\"sk-estimator-id-8\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">SimpleImputer</label><div class=\"sk-toggleable__content\"><pre>SimpleImputer(strategy=&#x27;median&#x27;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-9\" type=\"checkbox\" ><label for=\"sk-estimator-id-9\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">StandardScaler</label><div class=\"sk-toggleable__content\"><pre>StandardScaler()</pre></div></div></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-10\" type=\"checkbox\" ><label for=\"sk-estimator-id-10\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">LogisticRegression</label><div class=\"sk-toggleable__content\"><pre>LogisticRegression(max_iter=500)</pre></div></div></div></div></div></div></div>"
+       "                (&#x27;classifier&#x27;, LogisticRegression(max_iter=500))])</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-2\" type=\"checkbox\" ><label for=\"sk-estimator-id-2\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">transformer: Pipeline</label><div class=\"sk-toggleable__content\"><pre>Pipeline(steps=[(&#x27;imputer&#x27;, SimpleImputer(strategy=&#x27;median&#x27;)),\n",
+       "                (&#x27;scaler&#x27;, StandardScaler())])</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-3\" type=\"checkbox\" ><label for=\"sk-estimator-id-3\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">SimpleImputer</label><div class=\"sk-toggleable__content\"><pre>SimpleImputer(strategy=&#x27;median&#x27;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-4\" type=\"checkbox\" ><label for=\"sk-estimator-id-4\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">StandardScaler</label><div class=\"sk-toggleable__content\"><pre>StandardScaler()</pre></div></div></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-5\" type=\"checkbox\" ><label for=\"sk-estimator-id-5\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">LogisticRegression</label><div class=\"sk-toggleable__content\"><pre>LogisticRegression(max_iter=500)</pre></div></div></div></div></div></div></div>"
       ],
       "text/plain": [
        "Pipeline(steps=[('transformer',\n",
@@ -3395,7 +3395,7 @@
        "                ('classifier', LogisticRegression(max_iter=500))])"
       ]
      },
-     "execution_count": 51,
+     "execution_count": 25,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -3414,7 +3414,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 52,
+   "execution_count": 26,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3423,7 +3423,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 53,
+   "execution_count": 27,
    "metadata": {},
    "outputs": [
     {
@@ -3432,7 +3432,7 @@
        "(839,)"
       ]
      },
-     "execution_count": 53,
+     "execution_count": 27,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -3450,7 +3450,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 54,
+   "execution_count": 28,
    "metadata": {},
    "outputs": [
     {
@@ -3459,7 +3459,7 @@
        "0.7377830750893921"
       ]
      },
-     "execution_count": 54,
+     "execution_count": 28,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -3470,7 +3470,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 55,
+   "execution_count": 29,
    "metadata": {},
    "outputs": [
     {
@@ -3530,7 +3530,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 57,
+   "execution_count": 30,
    "metadata": {},
    "outputs": [
     {
@@ -3562,7 +3562,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 56,
+   "execution_count": 31,
    "metadata": {},
    "outputs": [
     {
@@ -3571,7 +3571,7 @@
        "0.7158235028382088"
       ]
      },
-     "execution_count": 56,
+     "execution_count": 31,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -3614,7 +3614,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 34,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3637,12 +3637,15 @@
     "        self.pipe = make_pipeline(self.transformer, self.model)\n",
     "\n",
     "    def fit(self, X, y):\n",
+    "        X = X.drop([\"groups\"], axis=1)\n",
     "        self.pipe.fit(X, y)\n",
     "\n",
     "    def predict(self, X):\n",
+    "        X = X.drop([\"groups\"], axis=1)\n",
     "        return self.pipe.predict(X)\n",
     "\n",
     "    def predict_proba(self, X):\n",
+    "        X = X.drop([\"groups\"], axis=1)\n",
     "        return self.pipe.predict_proba(X)"
    ]
   },
@@ -3656,7 +3659,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 25,
+   "execution_count": 33,
    "metadata": {},
    "outputs": [
     {
@@ -3669,20 +3672,20 @@
       "\u001b[38;5;178m\u001b[1mTraining submissions/starting_kit ...\u001b[0m\n",
       "\u001b[38;5;178m\u001b[1mCV fold 0\u001b[0m\n",
       "\t\u001b[38;5;178m\u001b[1mscore  bal_acc    acc      time\u001b[0m\n",
-      "\t\u001b[38;5;10m\u001b[1mtrain\u001b[0m    \u001b[38;5;10m\u001b[1m0.833\u001b[0m  \u001b[38;5;150m0.864\u001b[0m  \u001b[38;5;150m1.809391\u001b[0m\n",
-      "\t\u001b[38;5;12m\u001b[1mvalid\u001b[0m    \u001b[38;5;12m\u001b[1m0.682\u001b[0m  \u001b[38;5;105m0.713\u001b[0m  \u001b[38;5;105m0.008721\u001b[0m\n",
-      "\t\u001b[38;5;1m\u001b[1mtest\u001b[0m     \u001b[38;5;1m\u001b[1m0.635\u001b[0m  \u001b[38;5;218m0.695\u001b[0m  \u001b[38;5;218m0.001404\u001b[0m\n",
+      "\t\u001b[38;5;10m\u001b[1mtrain\u001b[0m    \u001b[38;5;10m\u001b[1m0.833\u001b[0m  \u001b[38;5;150m0.864\u001b[0m  \u001b[38;5;150m1.835487\u001b[0m\n",
+      "\t\u001b[38;5;12m\u001b[1mvalid\u001b[0m    \u001b[38;5;12m\u001b[1m0.682\u001b[0m  \u001b[38;5;105m0.713\u001b[0m  \u001b[38;5;105m0.020979\u001b[0m\n",
+      "\t\u001b[38;5;1m\u001b[1mtest\u001b[0m     \u001b[38;5;1m\u001b[1m0.635\u001b[0m  \u001b[38;5;218m0.695\u001b[0m  \u001b[38;5;218m0.005458\u001b[0m\n",
       "\u001b[38;5;178m\u001b[1mCV fold 1\u001b[0m\n",
       "\t\u001b[38;5;178m\u001b[1mscore  bal_acc    acc      time\u001b[0m\n",
-      "\t\u001b[38;5;10m\u001b[1mtrain\u001b[0m    \u001b[38;5;10m\u001b[1m0.826\u001b[0m  \u001b[38;5;150m0.879\u001b[0m  \u001b[38;5;150m1.175791\u001b[0m\n",
-      "\t\u001b[38;5;12m\u001b[1mvalid\u001b[0m    \u001b[38;5;12m\u001b[1m0.671\u001b[0m  \u001b[38;5;105m0.692\u001b[0m  \u001b[38;5;105m0.012650\u001b[0m\n",
-      "\t\u001b[38;5;1m\u001b[1mtest\u001b[0m     \u001b[38;5;1m\u001b[1m0.609\u001b[0m  \u001b[38;5;218m0.648\u001b[0m  \u001b[38;5;218m0.001484\u001b[0m\n",
+      "\t\u001b[38;5;10m\u001b[1mtrain\u001b[0m    \u001b[38;5;10m\u001b[1m0.826\u001b[0m  \u001b[38;5;150m0.879\u001b[0m  \u001b[38;5;150m1.536761\u001b[0m\n",
+      "\t\u001b[38;5;12m\u001b[1mvalid\u001b[0m    \u001b[38;5;12m\u001b[1m0.670\u001b[0m  \u001b[38;5;105m0.692\u001b[0m  \u001b[38;5;105m0.013410\u001b[0m\n",
+      "\t\u001b[38;5;1m\u001b[1mtest\u001b[0m     \u001b[38;5;1m\u001b[1m0.609\u001b[0m  \u001b[38;5;218m0.648\u001b[0m  \u001b[38;5;218m0.004637\u001b[0m\n",
       "\u001b[38;5;178m\u001b[1m----------------------------\u001b[0m\n",
       "\u001b[38;5;178m\u001b[1mMean CV scores\u001b[0m\n",
       "\u001b[38;5;178m\u001b[1m----------------------------\u001b[0m\n",
       "\t\u001b[38;5;178m\u001b[1mscore         bal_acc             acc        time\u001b[0m\n",
-      "\t\u001b[38;5;10m\u001b[1mtrain\u001b[0m  \u001b[38;5;10m\u001b[1m0.829\u001b[0m \u001b[38;5;150m\u001b[38;5;150m\u001b[38;5;150m±\u001b[0m\u001b[0m\u001b[0m \u001b[38;5;150m0.0035\u001b[0m  \u001b[38;5;150m0.871\u001b[0m \u001b[38;5;150m\u001b[38;5;150m\u001b[38;5;150m±\u001b[0m\u001b[0m\u001b[0m \u001b[38;5;150m0.0076\u001b[0m  \u001b[38;5;150m1.5\u001b[0m \u001b[38;5;150m\u001b[38;5;150m\u001b[38;5;150m±\u001b[0m\u001b[0m\u001b[0m \u001b[38;5;150m0.32\u001b[0m\n",
-      "\t\u001b[38;5;12m\u001b[1mvalid\u001b[0m  \u001b[38;5;12m\u001b[1m0.676\u001b[0m \u001b[38;5;105m\u001b[38;5;105m\u001b[38;5;105m±\u001b[0m\u001b[0m\u001b[0m \u001b[38;5;105m\u001b[38;5;105m\u001b[38;5;105m0.0\u001b[0m\u001b[0m055\u001b[0m  \u001b[38;5;105m0.703\u001b[0m \u001b[38;5;105m\u001b[38;5;105m\u001b[38;5;105m±\u001b[0m\u001b[0m\u001b[0m \u001b[38;5;105m\u001b[38;5;105m\u001b[38;5;105m0.0\u001b[0m\u001b[0m103\u001b[0m   \u001b[38;5;105m\u001b[38;5;105m0.0\u001b[0m\u001b[0m \u001b[38;5;105m\u001b[38;5;105m\u001b[38;5;105m±\u001b[0m\u001b[0m\u001b[0m \u001b[38;5;105m\u001b[38;5;105m0.0\u001b[0m\u001b[0m\n",
+      "\t\u001b[38;5;10m\u001b[1mtrain\u001b[0m  \u001b[38;5;10m\u001b[1m0.829\u001b[0m \u001b[38;5;150m\u001b[38;5;150m\u001b[38;5;150m±\u001b[0m\u001b[0m\u001b[0m \u001b[38;5;150m0.0035\u001b[0m  \u001b[38;5;150m0.871\u001b[0m \u001b[38;5;150m\u001b[38;5;150m\u001b[38;5;150m±\u001b[0m\u001b[0m\u001b[0m \u001b[38;5;150m0.0076\u001b[0m  \u001b[38;5;150m1.7\u001b[0m \u001b[38;5;150m\u001b[38;5;150m\u001b[38;5;150m±\u001b[0m\u001b[0m\u001b[0m \u001b[38;5;150m0.15\u001b[0m\n",
+      "\t\u001b[38;5;12m\u001b[1mvalid\u001b[0m  \u001b[38;5;12m\u001b[1m0.676\u001b[0m \u001b[38;5;105m\u001b[38;5;105m\u001b[38;5;105m±\u001b[0m\u001b[0m\u001b[0m \u001b[38;5;105m\u001b[38;5;105m\u001b[38;5;105m0.0\u001b[0m\u001b[0m056\u001b[0m  \u001b[38;5;105m0.703\u001b[0m \u001b[38;5;105m\u001b[38;5;105m\u001b[38;5;105m±\u001b[0m\u001b[0m\u001b[0m \u001b[38;5;105m\u001b[38;5;105m\u001b[38;5;105m0.0\u001b[0m\u001b[0m103\u001b[0m   \u001b[38;5;105m\u001b[38;5;105m0.0\u001b[0m\u001b[0m \u001b[38;5;105m\u001b[38;5;105m\u001b[38;5;105m±\u001b[0m\u001b[0m\u001b[0m \u001b[38;5;105m\u001b[38;5;105m0.0\u001b[0m\u001b[0m\n",
       "\t\u001b[38;5;1m\u001b[1mtest\u001b[0m   \u001b[38;5;1m\u001b[1m0.622\u001b[0m \u001b[38;5;218m\u001b[38;5;218m\u001b[38;5;218m±\u001b[0m\u001b[0m\u001b[0m \u001b[38;5;218m\u001b[38;5;218m\u001b[38;5;218m0.0\u001b[0m\u001b[0m129\u001b[0m  \u001b[38;5;218m0.672\u001b[0m \u001b[38;5;218m\u001b[38;5;218m\u001b[38;5;218m±\u001b[0m\u001b[0m\u001b[0m \u001b[38;5;218m\u001b[38;5;218m\u001b[38;5;218m0.0\u001b[0m\u001b[0m232\u001b[0m   \u001b[38;5;218m\u001b[38;5;218m0.0\u001b[0m\u001b[0m \u001b[38;5;218m\u001b[38;5;218m\u001b[38;5;218m±\u001b[0m\u001b[0m\u001b[0m \u001b[38;5;218m\u001b[38;5;218m0.0\u001b[0m\u001b[0m\n",
       "\u001b[38;5;178m\u001b[1m----------------------------\u001b[0m\n",
       "\u001b[38;5;178m\u001b[1mBagged scores\u001b[0m\n",