unir-metodologia/procesamiento_2017-2019.ipynb

940 lines
36 KiB
Plaintext
Raw Permalink Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "bcb2eb03-8273-46dd-ba20-f1817691fe42",
"metadata": {},
"outputs": [],
"source": [
"from functools import cache\n",
"import pandas as pd\n",
"\n",
"pd.set_option(\"display.max_columns\", None)"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "5b51e9a7-1dbd-4b86-8aad-109a2f4095cd",
"metadata": {},
"outputs": [],
"source": [
"columns_selected = [\n",
" \"edo_captura\",\n",
" \"edo_nac_madre\",\n",
" \"fecha_nac_madre\",\n",
" \"edad_madre\",\n",
" \"estado_conyugal\",\n",
" \"entidad_residencia_madre\",\n",
" \"numero_embarazos\",\n",
" \"hijos_nacidos_muertos\",\n",
" \"hijos_nacidos_vivos\",\n",
" \"hijos_sobrevivientes\",\n",
" \"el_hijo_anterior_nacio\",\n",
" \"vive_aun_hijo_anterior\",\n",
" \"orden_nacimiento\",\n",
" \"recibio_atencion_prenatal\",\n",
" \"trimestre_recibio_primera_consulta\",\n",
" \"total_consultas_recibidas\",\n",
" \"madre_sobrevivio_al_parto\",\n",
" \"escolaridad_madre\",\n",
" \"ocupacion_habitual_madre\",\n",
" \"trabaja_actualmente\",\n",
" \"fecha_nacimiento_nac_vivo\",\n",
" \"hora_nacimiento_nac_vivo\",\n",
" \"sexo_nac_vivo\",\n",
" \"semanas_gestacion_nac_vivo\",\n",
" \"talla_nac_vivo\",\n",
" \"peso_nac_vivo\",\n",
" \"valoracion_apgar_nac_vivo\",\n",
" \"valoracion_silverman_nac_vivo\",\n",
" \"producto_de_un_embarazo\",\n",
" \"entidad_certifico\",\n",
"]"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "2848508d-264a-487b-951f-99ef8483e3b1",
"metadata": {},
"outputs": [],
"source": [
"df_original = pd.read_csv(\"~/Downloads/out2.csv\", dtype=object)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "a6c8cc59-5461-4362-932f-0ddf8fbcb764",
"metadata": {},
"outputs": [],
"source": [
"# df_original.columns"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "f5641028-679f-473b-945d-5775d144dcf2",
"metadata": {},
"outputs": [],
"source": [
"df = df_original.copy()"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "b0362862-d25d-40a8-a4d7-95b1e337b955",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"{'entidad_residencia_madre.1', 'edo_captura.1', 'sexo_nacimiento_vivo.1', 'escolaridad_madre.1', 'edo_nac_madre.1', 'madre_sobrevivio_parto.1', 'recibio_atencion_prenatal.1', 'producto_de_un_embarazo.1', 'estado_conyugal'}\n"
]
}
],
"source": [
"df_cols = df.columns.to_list()\n",
"columnas_description = {x for x in df_cols if x[-2:] == \".1\"} | {\"estado_conyugal\"}\n",
"df_cols = [x for x in df_cols if x + \".1\" not in columnas_description]\n",
"print(columnas_description)\n",
"df = df[df_cols]"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "62f5a056-048a-4d5c-a28b-704cfcc44692",
"metadata": {},
"outputs": [],
"source": [
"df = df.rename(columns={x: x[:-2] for x in columnas_description})"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "57fab793-97b6-4189-b6e0-578062763b68",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Index(['Unnamed: 0', 'MPO_NACM', 'fecha_nac_madre', 'edad_madre', 'CON_INDM',\n",
" 'HABLA_INDM', 'CUAL_LENGM', 'estado_conyug', 'TIPOVIAL_RES',\n",
" 'TIPOASEN_RES', 'MPO_RES', 'LOC_RES', 'numeros_embarazos',\n",
" 'hijos_nacidos_muertos', 'hijos_nacidos_vivos', 'hijos_sobrevivientes',\n",
" 'hijo_anterior_nacio', 'VIVE_AUN', 'orden_nacimiento', 'TRIM_CONS',\n",
" 'total_consultas_recibidas', 'DERHAB', 'DERHAB2',\n",
" 'ocupacion_habitual_madre', 'CVEOCUPHAB', 'TRAB_ACT',\n",
" 'fecha_nacimiento_vivo', 'hora_nacimiento_vivo',\n",
" 'semanas_gestacion_vivo', 'talla_nacimiento_vivo', 'peso_nac_vivo',\n",
" 'valoracion_apgar_nac_vivo', 'valoracion_silverman_nac_vivo', 'BCG',\n",
" 'HEP_B', 'VIT_A', 'VIT_K', 'TAM_AUD', 'ACELRN', 'CVE_CIE', 'ACELRN2',\n",
" 'CVE_CIE2', 'PROCNAC', 'FORCEPS', 'ESPECIFIQUE', 'INST_NAC', 'UNIMED',\n",
" 'CLUES', 'ATENDIO', 'ATEN_OTRO', 'TIPOVIAL_NAC', 'TIPOASEN_NAC',\n",
" 'lugar_de_nacimiento', 'MPO_NAC', 'LOC_NAC', 'CERT_POR', 'OTROMEDICO',\n",
" 'UNIMED_33_1', 'CLUES_33_2', 'TIPOVIAL_CERT', 'TIPOASEN_CERT',\n",
" 'ENT_CERT', 'MPO_CERT', 'LOC_CERT', 'FECH_CERT', 'FECH_ALTA',\n",
" 'FECH_CAMB', 'IDCAPTURA', 'TIPO_FORMATO', 'edo_nac_madre',\n",
" 'edo_captura', 'el_hijo_anterior_nacio', 'entidad_certifico',\n",
" 'entidad_residencia_madre', 'escolaridad_madre', 'Descrip',\n",
" 'lugar_nacimiento', 'madre_sobrevivio_parto', 'producto_de_un_embarazo',\n",
" 'recibio_atencion_prenatal', 'sexo_nacimiento_vivo',\n",
" 'trabaja_actualmente', 'trimestre_recibio_primera_consulta',\n",
" 'vive_aun_hijo_anterior'],\n",
" dtype='object')"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.columns"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "3e3f76f5-2e5e-4ac6-a5c2-34cecdfa977b",
"metadata": {},
"outputs": [],
"source": [
"mapper = {\n",
" \"numeros_embarazos\": \"numero_embarazos\",\n",
" \"madre_sobrevivio_parto\": \"madre_sobrevivio_al_parto\",\n",
" \"fecha_nacimiento_vivo\": \"fecha_nacimiento_nac_vivo\",\n",
" \"hora_nacimiento_vivo\": \"hora_nacimiento_nac_vivo\",\n",
" \"sexo_nacimiento_vivo\": \"sexo_nac_vivo\",\n",
" \"semanas_gestacion_vivo\": \"semanas_gestacion_nac_vivo\",\n",
" \"talla_nacimiento_vivo\": \"talla_nac_vivo\",\n",
" \"Descrip\": \"estado_conyugal\",\n",
"}\n",
"df = df.rename(columns=mapper)"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "14f1b915-aa58-42c0-99f9-901ad56509c0",
"metadata": {},
"outputs": [],
"source": [
"# df_original.sample(n=10)[[\"estado_conyugal\"]]"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "0aa4b396-b901-441e-9f94-e6521e7146a9",
"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>edo_captura</th>\n",
" <th>edo_nac_madre</th>\n",
" <th>fecha_nac_madre</th>\n",
" <th>edad_madre</th>\n",
" <th>estado_conyugal</th>\n",
" <th>entidad_residencia_madre</th>\n",
" <th>numero_embarazos</th>\n",
" <th>hijos_nacidos_muertos</th>\n",
" <th>hijos_nacidos_vivos</th>\n",
" <th>hijos_sobrevivientes</th>\n",
" <th>el_hijo_anterior_nacio</th>\n",
" <th>vive_aun_hijo_anterior</th>\n",
" <th>orden_nacimiento</th>\n",
" <th>recibio_atencion_prenatal</th>\n",
" <th>trimestre_recibio_primera_consulta</th>\n",
" <th>total_consultas_recibidas</th>\n",
" <th>madre_sobrevivio_al_parto</th>\n",
" <th>escolaridad_madre</th>\n",
" <th>ocupacion_habitual_madre</th>\n",
" <th>trabaja_actualmente</th>\n",
" <th>fecha_nacimiento_nac_vivo</th>\n",
" <th>hora_nacimiento_nac_vivo</th>\n",
" <th>sexo_nac_vivo</th>\n",
" <th>semanas_gestacion_nac_vivo</th>\n",
" <th>talla_nac_vivo</th>\n",
" <th>peso_nac_vivo</th>\n",
" <th>valoracion_apgar_nac_vivo</th>\n",
" <th>valoracion_silverman_nac_vivo</th>\n",
" <th>producto_de_un_embarazo</th>\n",
" <th>entidad_certifico</th>\n",
" <th>CVE_CIE</th>\n",
" <th>CVE_CIE2</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>CHIAPAS</td>\n",
" <td>CHIAPAS</td>\n",
" <td>05/07/1980</td>\n",
" <td>36</td>\n",
" <td>UNIÓN LIBRE</td>\n",
" <td>CHIAPAS</td>\n",
" <td>9</td>\n",
" <td>1</td>\n",
" <td>8</td>\n",
" <td>8</td>\n",
" <td>VIVO</td>\n",
" <td>SI</td>\n",
" <td>9</td>\n",
" <td>SI</td>\n",
" <td>SEGUNDO</td>\n",
" <td>6</td>\n",
" <td>SI</td>\n",
" <td>NINGUNA</td>\n",
" <td>HOGAR</td>\n",
" <td>NaN</td>\n",
" <td>19/04/2017</td>\n",
" <td>02:00:00</td>\n",
" <td>MUJER</td>\n",
" <td>40</td>\n",
" <td>50</td>\n",
" <td>3100</td>\n",
" <td>8</td>\n",
" <td>0</td>\n",
" <td>ÚNICO</td>\n",
" <td>CHIAPAS</td>\n",
" <td>0000</td>\n",
" <td>0000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>CHIAPAS</td>\n",
" <td>CHIAPAS</td>\n",
" <td>17/05/1991</td>\n",
" <td>25</td>\n",
" <td>UNIÓN LIBRE</td>\n",
" <td>CHIAPAS</td>\n",
" <td>4</td>\n",
" <td>99</td>\n",
" <td>4</td>\n",
" <td>4</td>\n",
" <td>VIVO</td>\n",
" <td>SI</td>\n",
" <td>4</td>\n",
" <td>SI</td>\n",
" <td>SEGUNDO</td>\n",
" <td>4</td>\n",
" <td>SI</td>\n",
" <td>SECUNDARIA COMPLETA</td>\n",
" <td>HOGAR</td>\n",
" <td>NaN</td>\n",
" <td>11/01/2017</td>\n",
" <td>13:00:00</td>\n",
" <td>MUJER</td>\n",
" <td>39</td>\n",
" <td>50</td>\n",
" <td>3900</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>ÚNICO</td>\n",
" <td>CHIAPAS</td>\n",
" <td>0000</td>\n",
" <td>0000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>CHIAPAS</td>\n",
" <td>CHIAPAS</td>\n",
" <td>27/01/1982</td>\n",
" <td>35</td>\n",
" <td>CASADA</td>\n",
" <td>CHIAPAS</td>\n",
" <td>6</td>\n",
" <td>0</td>\n",
" <td>6</td>\n",
" <td>6</td>\n",
" <td>VIVO</td>\n",
" <td>SI</td>\n",
" <td>6</td>\n",
" <td>SI</td>\n",
" <td>PRIMERO</td>\n",
" <td>3</td>\n",
" <td>SI</td>\n",
" <td>PRIMARIA INCOMPLETA</td>\n",
" <td>AMA DE CASA</td>\n",
" <td>NaN</td>\n",
" <td>22/05/2017</td>\n",
" <td>12:23:00</td>\n",
" <td>MUJER</td>\n",
" <td>38</td>\n",
" <td>50</td>\n",
" <td>2960</td>\n",
" <td>9</td>\n",
" <td>0</td>\n",
" <td>ÚNICO</td>\n",
" <td>CHIAPAS</td>\n",
" <td>0000</td>\n",
" <td>0000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>CHIAPAS</td>\n",
" <td>CHIAPAS</td>\n",
" <td>16/11/1983</td>\n",
" <td>33</td>\n",
" <td>UNIÓN LIBRE</td>\n",
" <td>CHIAPAS</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>S.I.</td>\n",
" <td>NaN</td>\n",
" <td>1</td>\n",
" <td>SI</td>\n",
" <td>TERCERO</td>\n",
" <td>4</td>\n",
" <td>SI</td>\n",
" <td>PRIMARIA COMPLETA</td>\n",
" <td>AMA DE CASA</td>\n",
" <td>NaN</td>\n",
" <td>03/06/2017</td>\n",
" <td>10:35:00</td>\n",
" <td>MUJER</td>\n",
" <td>99</td>\n",
" <td>48</td>\n",
" <td>2900</td>\n",
" <td>99</td>\n",
" <td>99</td>\n",
" <td>ÚNICO</td>\n",
" <td>CHIAPAS</td>\n",
" <td>0000</td>\n",
" <td>0000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>CHIAPAS</td>\n",
" <td>CHIAPAS</td>\n",
" <td>22/11/1982</td>\n",
" <td>34</td>\n",
" <td>UNIÓN LIBRE</td>\n",
" <td>CHIAPAS</td>\n",
" <td>3</td>\n",
" <td>99</td>\n",
" <td>3</td>\n",
" <td>3</td>\n",
" <td>VIVO</td>\n",
" <td>SI</td>\n",
" <td>3</td>\n",
" <td>SI</td>\n",
" <td>PRIMERO</td>\n",
" <td>5</td>\n",
" <td>SI</td>\n",
" <td>NINGUNA</td>\n",
" <td>AMA DE CASA</td>\n",
" <td>NaN</td>\n",
" <td>29/04/2017</td>\n",
" <td>23:12:00</td>\n",
" <td>MUJER</td>\n",
" <td>39</td>\n",
" <td>51</td>\n",
" <td>3050</td>\n",
" <td>9</td>\n",
" <td>0</td>\n",
" <td>ÚNICO</td>\n",
" <td>CHIAPAS</td>\n",
" <td>0000</td>\n",
" <td>0000</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",
" </tr>\n",
" <tr>\n",
" <th>5873372</th>\n",
" <td>ZACATECAS</td>\n",
" <td>OTROS PAISES DE LATINOAMERICA</td>\n",
" <td>01/07/1987</td>\n",
" <td>31</td>\n",
" <td>CASADA</td>\n",
" <td>ZACATECAS</td>\n",
" <td>3</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>2</td>\n",
" <td>VIVO</td>\n",
" <td>SI</td>\n",
" <td>3</td>\n",
" <td>SI</td>\n",
" <td>PRIMERO</td>\n",
" <td>12</td>\n",
" <td>SI</td>\n",
" <td>PROFESIONAL</td>\n",
" <td>LIC. EN INFORMATICA</td>\n",
" <td>SI</td>\n",
" <td>23/05/2019</td>\n",
" <td>16:06:00</td>\n",
" <td>MUJER</td>\n",
" <td>39</td>\n",
" <td>49</td>\n",
" <td>2990</td>\n",
" <td>9</td>\n",
" <td>0</td>\n",
" <td>ÚNICO</td>\n",
" <td>ZACATECAS</td>\n",
" <td>0000</td>\n",
" <td>0000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5873373</th>\n",
" <td>ZACATECAS</td>\n",
" <td>ZACATECAS</td>\n",
" <td>17/07/1986</td>\n",
" <td>32</td>\n",
" <td>CASADA</td>\n",
" <td>ZACATECAS</td>\n",
" <td>3</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>3</td>\n",
" <td>VIVO</td>\n",
" <td>SI</td>\n",
" <td>3</td>\n",
" <td>SI</td>\n",
" <td>PRIMERO</td>\n",
" <td>5</td>\n",
" <td>SI</td>\n",
" <td>SECUNDARIA COMPLETA</td>\n",
" <td>HOGAR</td>\n",
" <td>NaN</td>\n",
" <td>24/05/2019</td>\n",
" <td>16:55:00</td>\n",
" <td>HOMBRE</td>\n",
" <td>37</td>\n",
" <td>50</td>\n",
" <td>3830</td>\n",
" <td>9</td>\n",
" <td>0</td>\n",
" <td>ÚNICO</td>\n",
" <td>ZACATECAS</td>\n",
" <td>0000</td>\n",
" <td>0000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5873374</th>\n",
" <td>ZACATECAS</td>\n",
" <td>ZACATECAS</td>\n",
" <td>16/01/2000</td>\n",
" <td>19</td>\n",
" <td>CASADA</td>\n",
" <td>ZACATECAS</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>NO HA TENIDO OTROS HIJOS(AS)</td>\n",
" <td>NaN</td>\n",
" <td>1</td>\n",
" <td>SI</td>\n",
" <td>PRIMERO</td>\n",
" <td>5</td>\n",
" <td>SI</td>\n",
" <td>SECUNDARIA COMPLETA</td>\n",
" <td>HOGAR</td>\n",
" <td>NaN</td>\n",
" <td>24/05/2019</td>\n",
" <td>23:13:00</td>\n",
" <td>HOMBRE</td>\n",
" <td>42</td>\n",
" <td>56</td>\n",
" <td>4460</td>\n",
" <td>9</td>\n",
" <td>0</td>\n",
" <td>ÚNICO</td>\n",
" <td>ZACATECAS</td>\n",
" <td>0000</td>\n",
" <td>0000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5873375</th>\n",
" <td>ZACATECAS</td>\n",
" <td>ZACATECAS</td>\n",
" <td>26/06/2000</td>\n",
" <td>18</td>\n",
" <td>UNIÓN LIBRE</td>\n",
" <td>ZACATECAS</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" <td>2</td>\n",
" <td>2</td>\n",
" <td>VIVO</td>\n",
" <td>SI</td>\n",
" <td>2</td>\n",
" <td>NO</td>\n",
" <td>NO RECIBIO</td>\n",
" <td>0</td>\n",
" <td>SI</td>\n",
" <td>BACHILLERATO O PREPARATORIA INCOMPLETA</td>\n",
" <td>HOGAR</td>\n",
" <td>NaN</td>\n",
" <td>25/05/2019</td>\n",
" <td>01:47:00</td>\n",
" <td>HOMBRE</td>\n",
" <td>39</td>\n",
" <td>49</td>\n",
" <td>3090</td>\n",
" <td>9</td>\n",
" <td>0</td>\n",
" <td>ÚNICO</td>\n",
" <td>ZACATECAS</td>\n",
" <td>0000</td>\n",
" <td>0000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5873376</th>\n",
" <td>ZACATECAS</td>\n",
" <td>ZACATECAS</td>\n",
" <td>24/09/2002</td>\n",
" <td>16</td>\n",
" <td>UNIÓN LIBRE</td>\n",
" <td>SAN LUIS POTOSI</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>NO HA TENIDO OTROS HIJOS(AS)</td>\n",
" <td>NaN</td>\n",
" <td>1</td>\n",
" <td>SI</td>\n",
" <td>PRIMERO</td>\n",
" <td>9</td>\n",
" <td>SI</td>\n",
" <td>SECUNDARIA INCOMPLETA</td>\n",
" <td>HOGAR</td>\n",
" <td>NaN</td>\n",
" <td>25/05/2019</td>\n",
" <td>08:53:00</td>\n",
" <td>MUJER</td>\n",
" <td>40</td>\n",
" <td>54</td>\n",
" <td>3300</td>\n",
" <td>9</td>\n",
" <td>0</td>\n",
" <td>ÚNICO</td>\n",
" <td>ZACATECAS</td>\n",
" <td>0000</td>\n",
" <td>0000</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5873377 rows × 32 columns</p>\n",
"</div>"
],
"text/plain": [
" edo_captura edo_nac_madre fecha_nac_madre edad_madre \\\n",
"0 CHIAPAS CHIAPAS 05/07/1980 36 \n",
"1 CHIAPAS CHIAPAS 17/05/1991 25 \n",
"2 CHIAPAS CHIAPAS 27/01/1982 35 \n",
"3 CHIAPAS CHIAPAS 16/11/1983 33 \n",
"4 CHIAPAS CHIAPAS 22/11/1982 34 \n",
"... ... ... ... ... \n",
"5873372 ZACATECAS OTROS PAISES DE LATINOAMERICA 01/07/1987 31 \n",
"5873373 ZACATECAS ZACATECAS 17/07/1986 32 \n",
"5873374 ZACATECAS ZACATECAS 16/01/2000 19 \n",
"5873375 ZACATECAS ZACATECAS 26/06/2000 18 \n",
"5873376 ZACATECAS ZACATECAS 24/09/2002 16 \n",
"\n",
" estado_conyugal entidad_residencia_madre numero_embarazos \\\n",
"0 UNIÓN LIBRE CHIAPAS 9 \n",
"1 UNIÓN LIBRE CHIAPAS 4 \n",
"2 CASADA CHIAPAS 6 \n",
"3 UNIÓN LIBRE CHIAPAS 1 \n",
"4 UNIÓN LIBRE CHIAPAS 3 \n",
"... ... ... ... \n",
"5873372 CASADA ZACATECAS 3 \n",
"5873373 CASADA ZACATECAS 3 \n",
"5873374 CASADA ZACATECAS 1 \n",
"5873375 UNIÓN LIBRE ZACATECAS 2 \n",
"5873376 UNIÓN LIBRE SAN LUIS POTOSI 1 \n",
"\n",
" hijos_nacidos_muertos hijos_nacidos_vivos hijos_sobrevivientes \\\n",
"0 1 8 8 \n",
"1 99 4 4 \n",
"2 0 6 6 \n",
"3 0 1 1 \n",
"4 99 3 3 \n",
"... ... ... ... \n",
"5873372 1 2 2 \n",
"5873373 0 3 3 \n",
"5873374 0 1 1 \n",
"5873375 0 2 2 \n",
"5873376 0 1 1 \n",
"\n",
" el_hijo_anterior_nacio vive_aun_hijo_anterior orden_nacimiento \\\n",
"0 VIVO SI 9 \n",
"1 VIVO SI 4 \n",
"2 VIVO SI 6 \n",
"3 S.I. NaN 1 \n",
"4 VIVO SI 3 \n",
"... ... ... ... \n",
"5873372 VIVO SI 3 \n",
"5873373 VIVO SI 3 \n",
"5873374 NO HA TENIDO OTROS HIJOS(AS) NaN 1 \n",
"5873375 VIVO SI 2 \n",
"5873376 NO HA TENIDO OTROS HIJOS(AS) NaN 1 \n",
"\n",
" recibio_atencion_prenatal trimestre_recibio_primera_consulta \\\n",
"0 SI SEGUNDO \n",
"1 SI SEGUNDO \n",
"2 SI PRIMERO \n",
"3 SI TERCERO \n",
"4 SI PRIMERO \n",
"... ... ... \n",
"5873372 SI PRIMERO \n",
"5873373 SI PRIMERO \n",
"5873374 SI PRIMERO \n",
"5873375 NO NO RECIBIO \n",
"5873376 SI PRIMERO \n",
"\n",
" total_consultas_recibidas madre_sobrevivio_al_parto \\\n",
"0 6 SI \n",
"1 4 SI \n",
"2 3 SI \n",
"3 4 SI \n",
"4 5 SI \n",
"... ... ... \n",
"5873372 12 SI \n",
"5873373 5 SI \n",
"5873374 5 SI \n",
"5873375 0 SI \n",
"5873376 9 SI \n",
"\n",
" escolaridad_madre ocupacion_habitual_madre \\\n",
"0 NINGUNA HOGAR \n",
"1 SECUNDARIA COMPLETA HOGAR \n",
"2 PRIMARIA INCOMPLETA AMA DE CASA \n",
"3 PRIMARIA COMPLETA AMA DE CASA \n",
"4 NINGUNA AMA DE CASA \n",
"... ... ... \n",
"5873372 PROFESIONAL LIC. EN INFORMATICA \n",
"5873373 SECUNDARIA COMPLETA HOGAR \n",
"5873374 SECUNDARIA COMPLETA HOGAR \n",
"5873375 BACHILLERATO O PREPARATORIA INCOMPLETA HOGAR \n",
"5873376 SECUNDARIA INCOMPLETA HOGAR \n",
"\n",
" trabaja_actualmente fecha_nacimiento_nac_vivo \\\n",
"0 NaN 19/04/2017 \n",
"1 NaN 11/01/2017 \n",
"2 NaN 22/05/2017 \n",
"3 NaN 03/06/2017 \n",
"4 NaN 29/04/2017 \n",
"... ... ... \n",
"5873372 SI 23/05/2019 \n",
"5873373 NaN 24/05/2019 \n",
"5873374 NaN 24/05/2019 \n",
"5873375 NaN 25/05/2019 \n",
"5873376 NaN 25/05/2019 \n",
"\n",
" hora_nacimiento_nac_vivo sexo_nac_vivo semanas_gestacion_nac_vivo \\\n",
"0 02:00:00 MUJER 40 \n",
"1 13:00:00 MUJER 39 \n",
"2 12:23:00 MUJER 38 \n",
"3 10:35:00 MUJER 99 \n",
"4 23:12:00 MUJER 39 \n",
"... ... ... ... \n",
"5873372 16:06:00 MUJER 39 \n",
"5873373 16:55:00 HOMBRE 37 \n",
"5873374 23:13:00 HOMBRE 42 \n",
"5873375 01:47:00 HOMBRE 39 \n",
"5873376 08:53:00 MUJER 40 \n",
"\n",
" talla_nac_vivo peso_nac_vivo valoracion_apgar_nac_vivo \\\n",
"0 50 3100 8 \n",
"1 50 3900 0 \n",
"2 50 2960 9 \n",
"3 48 2900 99 \n",
"4 51 3050 9 \n",
"... ... ... ... \n",
"5873372 49 2990 9 \n",
"5873373 50 3830 9 \n",
"5873374 56 4460 9 \n",
"5873375 49 3090 9 \n",
"5873376 54 3300 9 \n",
"\n",
" valoracion_silverman_nac_vivo producto_de_un_embarazo \\\n",
"0 0 ÚNICO \n",
"1 0 ÚNICO \n",
"2 0 ÚNICO \n",
"3 99 ÚNICO \n",
"4 0 ÚNICO \n",
"... ... ... \n",
"5873372 0 ÚNICO \n",
"5873373 0 ÚNICO \n",
"5873374 0 ÚNICO \n",
"5873375 0 ÚNICO \n",
"5873376 0 ÚNICO \n",
"\n",
" entidad_certifico CVE_CIE CVE_CIE2 \n",
"0 CHIAPAS 0000 0000 \n",
"1 CHIAPAS 0000 0000 \n",
"2 CHIAPAS 0000 0000 \n",
"3 CHIAPAS 0000 0000 \n",
"4 CHIAPAS 0000 0000 \n",
"... ... ... ... \n",
"5873372 ZACATECAS 0000 0000 \n",
"5873373 ZACATECAS 0000 0000 \n",
"5873374 ZACATECAS 0000 0000 \n",
"5873375 ZACATECAS 0000 0000 \n",
"5873376 ZACATECAS 0000 0000 \n",
"\n",
"[5873377 rows x 32 columns]"
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df[columns_selected + [\"CVE_CIE\", \"CVE_CIE2\"]]"
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "7aaf8aac-3785-4704-b3e2-214a9234602b",
"metadata": {},
"outputs": [],
"source": [
"def _codigo_de_anomalia(x):\n",
" return \",\".join([str(x[\"CVE_CIE\"]), str(x[\"CVE_CIE2\"])])\n",
"\n",
"\n",
"df[\"codigo_anomalia\"] = df[[\"CVE_CIE\", \"CVE_CIE2\"]].apply(_codigo_de_anomalia, axis=1)"
]
},
{
"cell_type": "code",
"execution_count": 16,
"id": "f69b89af-239a-4270-818c-89f25f4b2f88",
"metadata": {},
"outputs": [],
"source": [
"df = df[columns_selected + [\"codigo_anomalia\"]]"
]
},
{
"cell_type": "code",
"execution_count": 17,
"id": "904449a1-3e85-4837-ae7c-8e1ee6f3dee9",
"metadata": {},
"outputs": [],
"source": [
"def _ano_nacimiento_vivo_func(str_date):\n",
" try:\n",
" return str_date.split(\"/\")[-1]\n",
" except:\n",
" return \"\"\n",
"\n",
"\n",
"df[\"año_de_nacimiento_vivo\"] = df[\"fecha_nacimiento_nac_vivo\"].apply(\n",
" _ano_nacimiento_vivo_func\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 21,
"id": "f08a323d-4570-404f-8d11-7288e3973ee7",
"metadata": {},
"outputs": [],
"source": [
"columnas_finales = [\n",
" \"edo_captura\",\n",
" \"edo_nac_madre\",\n",
" \"fecha_nac_madre\",\n",
" \"edad_madre\",\n",
" \"estado_conyugal\",\n",
" \"entidad_residencia_madre\",\n",
" \"numero_embarazos\",\n",
" \"hijos_nacidos_muertos\",\n",
" \"hijos_nacidos_vivos\",\n",
" \"hijos_sobrevivientes\",\n",
" \"el_hijo_anterior_nacio\",\n",
" \"vive_aun_hijo_anterior\",\n",
" \"orden_nacimiento\",\n",
" \"recibio_atencion_prenatal\",\n",
" \"trimestre_recibio_primera_consulta\",\n",
" \"total_consultas_recibidas\",\n",
" \"madre_sobrevivio_al_parto\",\n",
" \"escolaridad_madre\",\n",
" \"ocupacion_habitual_madre\",\n",
" \"trabaja_actualmente\",\n",
" \"fecha_nacimiento_nac_vivo\",\n",
" \"hora_nacimiento_nac_vivo\",\n",
" \"sexo_nac_vivo\",\n",
" \"semanas_gestacion_nac_vivo\",\n",
" \"talla_nac_vivo\",\n",
" \"peso_nac_vivo\",\n",
" \"valoracion_apgar_nac_vivo\",\n",
" \"valoracion_silverman_nac_vivo\",\n",
" \"producto_de_un_embarazo\",\n",
" \"codigo_anomalia\",\n",
" \"entidad_certifico\",\n",
"]"
]
},
{
"cell_type": "code",
"execution_count": 23,
"id": "010aaf2a-4098-4609-b110-9761902d1118",
"metadata": {},
"outputs": [],
"source": [
"df[columnas_finales].to_csv(\"2017-2019.csv\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "d61bb185-91fa-4872-a2f8-1638c1abc3c4",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.6"
}
},
"nbformat": 4,
"nbformat_minor": 5
}