Features renamed

EDA/EDA.ipynb

@@ -552,7 +552,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -629,7 +629,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -643,7 +643,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -651,16 +651,6 @@
     "no_redef_cols = ['Structural_conflic', 'Age', 'NumHijos', 'Años_consumo_droga', 'Adherencia_tto_recalc']"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# res_vars = ['Tiempo_tx', 'Readmisiones_estudios', 'Periodos_COVID', 'Pandemia_inicio_fin_tratamiento', \n",
-    "#            'Nreadmision', 'Readmisiones_PRECOVID', 'Readmisiones_COVID']"
-   ]
-  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -670,7 +660,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -705,7 +695,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -743,15 +733,89 @@
     "corr_cols = soc_vars_enc + ind_vars_enc"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "###### Excluding unknown columns and renaming"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Drop unknown columns\n",
+    "corr_cols = [corr_col for corr_col in corr_cols if corr_col not in ['Ed_Unknowledge', 'JobIn_unkwnodledge', 'Hous_unknowledge', 'Frec30_Desconocido']]\n",
+    "soc_vars_enc = [corr_col for corr_col in soc_vars_enc if corr_col not in ['Ed_Unknowledge', 'JobIn_unkwnodledge', 'Hous_unknowledge', 'Frec30_Desconocido']]\n",
+    "ind_vars_enc = [corr_col for corr_col in soc_vars_enc if ind_vars_enc not in ['Ed_Unknowledge', 'JobIn_unkwnodledge', 'Hous_unknowledge', 'Frec30_Desconocido']]"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
-    "# Export column names for future programs\n",
+    "name_mapping = {\n",
+    "    'Ed_Not Complete primary school': 'Ed_Not_Complete_Primary',\n",
+    "    'Ed_Primary education': 'Ed_Primary',\n",
+    "    'Ed_Secondary Education': 'Ed_Secondary',\n",
+    "    'Ed_Secondary more technical education': 'Ed_Secondary_Technical',\n",
+    "    'Ed_Tertiary': 'Ed_Tertiary',\n",
+    "    'Social_protection_REDEF': 'Social_Protection',\n",
+    "    'JobIn_Non-stable': 'JobIn_Unstable',\n",
+    "    'JobIn_Stable': 'JobIn_Stable',\n",
+    "    'JobIn_Unemployed': 'JobIn_Unemployed',\n",
+    "    'Hous_Institutional': 'Hous_Institutional',\n",
+    "    'Hous_Stable': 'Hous_Stable',\n",
+    "    'Hous_Unstable': 'Hous_Unstable',\n",
+    "    'Alterations_early_childhood_develop_REDEF': 'Early_Alterations',\n",
+    "    'SocInc_Live with families or friends': 'SocInc_Family_Friends',\n",
+    "    'SocInc_live alone': 'SocInc_Alone',\n",
+    "    'SocInc_live in institutions': 'SocInc_Instit',\n",
+    "    'Risk_stigma_REDEF': 'Risk_Stigma',\n",
+    "    'Structural_conflic': 'Structural_Conflict',\n",
+    "    'Age': 'Age',\n",
+    "    'Sex_REDEF': 'Sex',\n",
+    "    'NumHijos': 'Num_Children',\n",
+    "    'Smoking_REDEF': 'Smoking',\n",
+    "    'Biological_vulnerability_REDEF': 'Bio_Vulner',\n",
+    "    'Opiaceos_DxCIE_REDEF': 'Opiods_DXCIE',\n",
+    "    'Cannabis_DXCIE_REDEF': 'Cannabis_DXCIE',\n",
+    "    'BZD_DxCIE_REDEF': 'BZD_DXCIE',\n",
+    "    'Cocaina_DxCIE_REDEF': 'Cocaine_DXCIE',\n",
+    "    'Alucinogenos_DXCIE_REDEF': 'Hallucin_DXCIE',\n",
+    "    'Tabaco_DXCIE_REDEF': 'Tobacco_DXCIE',\n",
+    "    'Frec30_1 día/semana': 'Freq_1dpw',\n",
+    "    'Frec30_2-3 días\\u200e/semana': 'Freq_2-3dpw',\n",
+    "    'Frec30_4-6 días/semana': 'Freq_4-6dpw',\n",
+    "    'Frec30_Menos de 1 día\\u200e/semana': 'Freq_l1dpw',\n",
+    "    'Frec30_No consumio': 'Freq_None',\n",
+    "    'Frec30_Todos los días': 'Freq_Everyday',\n",
+    "    'Años_consumo_droga': 'Years_Drug_Use',\n",
+    "    'OtrosDx_Psiquiatrico_REDEF': 'Other_Psychiatric_DX',\n",
+    "    'Tx_previos_REDEF': 'Previous_Treatments',\n",
+    "    'Adherencia_tto_recalc': 'Treatment_Adherence'\n",
+    "}\n",
+    "\n",
+    "# Update lists of feature names\n",
+    "corr_cols = [name_mapping[corr_col] for corr_col in corr_cols]\n",
+    "soc_vars_enc = [name_mapping[col] for col in soc_vars_enc]\n",
+    "ind_vars_enc = [name_mapping[col] for col in ind_vars_enc]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 37,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Export feature names\n",
+    "np.save('./output/feature_names.npy', corr_cols)\n",
     "np.save('./output/soc_vars_names.npy', soc_vars_enc)\n",
-    "np.save('./output/ind_vars_names.npy', soc_vars_enc)"
+    "np.save('./output/ind_vars_names.npy', ind_vars_enc)"
    ]
   },
   {

gen_train_data/gen_train_data.ipynb

@@ -53,7 +53,21 @@
       "(10677, 39)\n",
       "(22861,)\n",
       "(10677,)\n",
-      "39\n"
+      "['Ed_Not Complete primary school' 'Ed_Primary education'\n",
+      " 'Ed_Secondary Education' 'Ed_Secondary more technical education'\n",
+      " 'Ed_Tertiary' 'Social_protection_REDEF' 'JobIn_Non-stable' 'JobIn_Stable'\n",
+      " 'JobIn_Unemployed' 'Hous_Institutional' 'Hous_Stable' 'Hous_Unstable'\n",
+      " 'Alterations_early_childhood_develop_REDEF'\n",
+      " 'SocInc_Live with families or friends' 'SocInc_live alone'\n",
+      " 'SocInc_live in institutions' 'Risk_stigma_REDEF' 'Structural_conflic'\n",
+      " 'Age' 'Sex_REDEF' 'NumHijos' 'Smoking_REDEF'\n",
+      " 'Biological_vulnerability_REDEF' 'Opiaceos_DxCIE_REDEF'\n",
+      " 'Cannabis_DXCIE_REDEF' 'BZD_DxCIE_REDEF' 'Cocaina_DxCIE_REDEF'\n",
+      " 'Alucinogenos_DXCIE_REDEF' 'Tabaco_DXCIE_REDEF' 'Frec30_1 día/semana'\n",
+      " 'Frec30_2-3 días\\u200e/semana' 'Frec30_4-6 días/semana'\n",
+      " 'Frec30_Menos de 1 día\\u200e/semana' 'Frec30_No consumio'\n",
+      " 'Frec30_Todos los días' 'Años_consumo_droga' 'OtrosDx_Psiquiatrico_REDEF'\n",
+      " 'Tx_previos_REDEF' 'Adherencia_tto_recalc']\n"
      ]
     }
    ],
@@ -67,7 +81,7 @@
     "print(X_post.shape)\n",
     "print(y_pre.shape)\n",
     "print(y_post.shape)\n",
-    "print(len(feat))"
+    "print((feat))"
    ]
   },
   {