Fixing NA miss-imputation

0_Preprocessing.ipynb

@@ -39,7 +39,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -49,7 +49,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -67,7 +67,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -84,7 +84,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 23,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -112,7 +112,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 24,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -123,7 +123,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 25,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -136,7 +136,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 26,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -153,7 +153,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 27,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -171,7 +171,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 28,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -190,7 +190,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 29,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -200,7 +200,7 @@
     "    left_on=\"stay_id\",\n",
     "    right_on=\"stay_id\",\n",
     "    how=\"left\"\n",
-    ").fillna(0)\n",
+    ")\n",
     "\n",
     "stays_atc_2 = pd.merge(\n",
     "    stays,\n",
@@ -208,26 +208,17 @@
     "    left_on=\"stay_id\",\n",
     "    right_on=\"stay_id\",\n",
     "    how=\"left\"\n",
-    ").fillna(0)"
+    ")\n",
+    "\n",
+    "stays_atc_4[atc_stays_pivoted_4.columns[1:]] = stays_atc_4[atc_stays_pivoted_4.columns[1:]].fillna(0)\n",
+    "stays_atc_2[atc_stays_pivoted_2.columns[1:]] = stays_atc_2[atc_stays_pivoted_2.columns[1:]].fillna(0)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 39,
    "metadata": {},
-   "outputs": [
-    {
-     "ename": "NameError",
-     "evalue": "name 'stays_atc_2' is not defined",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[1;31mNameError\u001b[0m                                 Traceback (most recent call last)",
-      "\u001b[1;32m~\\AppData\\Local\\Temp/ipykernel_10104/535576780.py\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[0;32m      2\u001b[0m \u001b[1;31m# On écrit en parquet pour optimiser le stockage et les temps d'io\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m      3\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 4\u001b[1;33m \u001b[0mstays_atc_2\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msort_values\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m\"stay_id\"\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mreset_index\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdrop\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mTrue\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mto_parquet\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m\"./data/features_atc2.parquet\"\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mengine\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;34m\"pyarrow\"\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mindex\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mFalse\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m      5\u001b[0m \u001b[0mstays_atc_4\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msort_values\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m\"stay_id\"\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mreset_index\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdrop\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mTrue\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mto_parquet\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m\"./data/features_atc4.parquet\"\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mengine\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;34m\"pyarrow\"\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mindex\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mFalse\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
-      "\u001b[1;31mNameError\u001b[0m: name 'stays_atc_2' is not defined"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "# Ecriture du featues dataset\n",
     "# On écrit en parquet pour optimiser le stockage et les temps d'io\n",
@@ -245,7 +236,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 12,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -263,7 +254,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 13,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -279,7 +270,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 14,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -293,7 +284,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 15,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -305,7 +296,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 16,
    "metadata": {},
    "outputs": [],
    "source": [