Completed comments

gen_train_data/gen_train_data.ipynb

@@ -17,7 +17,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -31,7 +31,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -42,30 +42,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "(22861, 39)\n",
-      "(10677, 39)\n",
-      "(22861,)\n",
-      "(10677,)\n",
-      "['Ed_Not_Complete_Primary' 'Ed_Primary' 'Ed_Secondary'\n",
-      " 'Ed_Secondary_Technical' 'Ed_Tertiary' 'Social_Protection'\n",
-      " 'JobIn_Unstable' 'JobIn_Stable' 'JobIn_Unemployed' 'Hous_Institutional'\n",
-      " 'Hous_Stable' 'Hous_Unstable' 'Early_Alterations' 'SocInc_Family_Friends'\n",
-      " 'SocInc_Alone' 'SocInc_Instit' 'Risk_Stigma' 'Structural_Conflict' 'Age'\n",
-      " 'Sex' 'Num_Children' 'Smoking' 'Bio_Vulner' 'Opiods_DXCIE'\n",
-      " 'Cannabis_DXCIE' 'BZD_DXCIE' 'Cocaine_DXCIE' 'Hallucin_DXCIE'\n",
-      " 'Tobacco_DXCIE' 'Freq_1dpw' 'Freq_2-3dpw' 'Freq_4-6dpw' 'Freq_l1dpw'\n",
-      " 'Freq_None' 'Freq_Everyday' 'Years_Drug_Use' 'Other_Psychiatric_DX'\n",
-      " 'Previous_Treatments' 'Treatment_Adherence']\n"
-     ]
-    }
-   ],
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
    "source": [
     "# Creating a numpy matrix (X) without the target variable and a list with the target variable (y) \n",
     "X_pre, y_pre = df_pre.loc[:, df_pre.columns != \"Treatment_Outcome\"].to_numpy(), df_pre.Treatment_Outcome\n",
@@ -162,6 +141,13 @@
     "np.save('./output/post/y_train_over_post.npy', y_train_over_post)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Pipeline 4: UNDER"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,