Cambio de formato de sinadef y otros

SINADEF/Bot-Tweet-covid.2.0.ipynb

@@ -0,0 +1,147 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Requirement already satisfied: seaborn in c:\\users\\user\\appdata\\local\\programs\\python\\python38\\lib\\site-packages (0.11.1)\n",
+      "Requirement already satisfied: matplotlib>=2.2 in c:\\users\\user\\appdata\\local\\programs\\python\\python38\\lib\\site-packages (from seaborn) (3.2.1)\n",
+      "Requirement already satisfied: scipy>=1.0 in c:\\users\\user\\appdata\\local\\programs\\python\\python38\\lib\\site-packages (from seaborn) (1.4.1)\n",
+      "Requirement already satisfied: numpy>=1.15 in c:\\users\\user\\appdata\\local\\programs\\python\\python38\\lib\\site-packages (from seaborn) (1.19.5)\n",
+      "Requirement already satisfied: pandas>=0.23 in c:\\users\\user\\appdata\\local\\programs\\python\\python38\\lib\\site-packages (from seaborn) (1.2.0)\n",
+      "Requirement already satisfied: cycler>=0.10 in c:\\users\\user\\appdata\\local\\programs\\python\\python38\\lib\\site-packages (from matplotlib>=2.2->seaborn) (0.10.0)\n",
+      "Requirement already satisfied: pyparsing!=2.0.4,!=2.1.2,!=2.1.6,>=2.0.1 in c:\\users\\user\\appdata\\local\\programs\\python\\python38\\lib\\site-packages (from matplotlib>=2.2->seaborn) (2.4.7)\n",
+      "Requirement already satisfied: kiwisolver>=1.0.1 in c:\\users\\user\\appdata\\local\\programs\\python\\python38\\lib\\site-packages (from matplotlib>=2.2->seaborn) (1.2.0)\n",
+      "Requirement already satisfied: python-dateutil>=2.1 in c:\\users\\user\\appdata\\local\\programs\\python\\python38\\lib\\site-packages (from matplotlib>=2.2->seaborn) (2.8.1)\n",
+      "Requirement already satisfied: six in c:\\users\\user\\appdata\\local\\programs\\python\\python38\\lib\\site-packages (from cycler>=0.10->matplotlib>=2.2->seaborn) (1.15.0)\n",
+      "Requirement already satisfied: pytz>=2017.3 in c:\\users\\user\\appdata\\local\\programs\\python\\python38\\lib\\site-packages (from pandas>=0.23->seaborn) (2020.1)\n"
+     ]
+    }
+   ],
+   "source": [
+    "!pip install seaborn --upgrade\n",
+    "# Trabajarlos como semanas."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 100,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "## Sinadef\n",
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import datetime\n",
+    "import matplotlib.pyplot as plt\n",
+    "import seaborn as sns\n",
+    "import math\n",
+    "from datetime import timedelta\n",
+    "import os\n",
+    "%matplotlib inline\n",
+    "pd.set_option('display.max_columns', None)\n",
+    "import time"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 105,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Tomó 2.09 segundos procesar los datos. \n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "t0 = time.time()\n",
+    "name_file = 'fallecidos_covid.csv'\n",
+    "df_c = pd.read_csv(name_file, sep=';' , encoding='latin-1')\n",
+    "df = df_c.copy()\n",
+    "bins = [-1, 0, 10, 20, 30, 40, 50, 60, 70, 80, 90, float(\"inf\")]\n",
+    "df['FECHA_FALLECIMIENTO'] = df['FECHA_FALLECIMIENTO'].apply(lambda x: datetime.datetime.strptime(str(x), '%Y%m%d').date())\n",
+    "# 0 -> 0 ,1 -> 1 - 10, 2 -> 11 - 20, 3 -> 21- 30, 4 -> 31 - 40\n",
+    "# 5 -> 41 - 50, 6 -> 51 - 60, 7 -> 61 - 70, 8 -> 71 - 80, 9 -> 81 - 90, 10 -> 91+\n",
+    "df['Edad_fallecimiento'] = pd.cut(df['EDAD_DECLARADA'], bins)\n",
+    "df['Edad_fallecimiento'] = df['Edad_fallecimiento'].cat.codes\n",
+    "\n",
+    "# AGRUPAR DATOS POR FECHAS:\n",
+    "# SEXO\n",
+    "# EDAD_fallecimiento (por grupos)\n",
+    "# DEPARTAMENTO\n",
+    "\n",
+    "def df_por_dia(df, columna):\n",
+    "    df_counts = pd.pivot_table(df , index = ['FECHA_FALLECIMIENTO'], columns = columna, aggfunc = 'size')\n",
+    "    df_counts = df_counts[:-1]\n",
+    "    df_counts = df_counts.fillna(0)\n",
+    "    return df_counts\n",
+    "\n",
+    "def df_por_semana(df, columna):\n",
+    "    df_aux = df.copy()\n",
+    "    df_aux.loc[: , ('SEMANA_DEL_AÑO')] = df_aux['FECHA_FALLECIMIENTO'].apply(lambda x: (x.isocalendar()[:2]))\n",
+    "    df_return = pd.pivot_table(df_aux, index = ['SEMANA_DEL_AÑO'],columns = columna, aggfunc = 'size')\n",
+    "    df_return = df_return.fillna(0)\n",
+    "    return df_return\n",
+    "\n",
+    "lista = ['SEXO', 'Edad_fallecimiento', 'DEPARTAMENTO']\n",
+    "\n",
+    "directory = os.path.join(os.getcwd(), 'results')\n",
+    "if not os.path.exists(directory):\n",
+    "    os.mkdir(directory)\n",
+    "\n",
+    "for columna in lista:\n",
+    "    data_frame = df_por_dia(df, columna)\n",
+    "    data_frame.to_csv(directory + '//Por_dia_' + columna + '.csv')\n",
+    "    data_frame_semana = df_por_semana(df, columna)\n",
+    "    data_frame_semana.to_csv(directory + '//Por_semana_' + columna + '.csv')\n",
+    "    \n",
+    "t1 = time.time()\n",
+    "print('Tomó {} segundos procesar los datos. \\n'.format(round(t1 - t0, 2)))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "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": "3.8.3rc1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}