part 3 of ass 8

#979
alexanderquispe · Feb 15, 2024 · c9100dc · c9100dc
1 parent b6d92db
commit c9100dc
Showing 1 changed file with 136 additions and 7 deletions.
diff --git a/Lecture_10/Assignment_8/group_1_ass_8_2024.ipynb b/Lecture_10/Assignment_8/group_1_ass_8_2024.ipynb
@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": null,
    "id": "10b9d7f6",
    "metadata": {},
    "outputs": [],
@@ -24,7 +24,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": null,
    "id": "ab8d0d69",
    "metadata": {},
    "outputs": [],
@@ -42,7 +42,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": null,
    "id": "3ca29162",
    "metadata": {},
    "outputs": [],
@@ -55,7 +55,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": null,
    "id": "9a8e5168",
    "metadata": {},
    "outputs": [],
@@ -76,7 +76,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": null,
+   "id": "a1061972",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "base_Distrito"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
    "id": "07d1243d",
    "metadata": {},
    "outputs": [],
@@ -87,7 +97,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": null,
    "id": "e29feb17",
    "metadata": {},
    "outputs": [],
@@ -116,13 +126,132 @@
     "3. Use geopandas to plot the number of cases in 2021 by the district using a continuous legend. Do not forget to indicate the color of NA values. Use this shapefile."
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "45ec5dbe",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#Usamos la base filtrando el año 2021 y la renombramos\n",
+    "\n",
+    "base_Distrito_2021 = base_Distrito[base_Distrito[\"Año\"] == 2021]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6e34df96",
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [],
+   "source": [
+    "#Checamos que los valores en las columnas Ubigeo_Distrito son únicas para ambas bases\n",
+    "\n",
+    "maps_DIST.Ubigeo_Distrito.is_unique\n",
+    "base_Distrito_2021.Ubigeo_Distrito.is_unique"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7a3d4b9e",
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [],
+   "source": [
+    "#Checamos que tipos de datos son los valores en ambas bases, con énfasis en Ubigeo_Distrito para hacer el merge\n",
+    "\n",
+    "maps_DIST.dtypes\n",
+    "base_Distrito_2021.dtypes"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "38ce8fb0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#Convertimos los valores de la columna Ubigeo_Distrito en la base_Distrito_2021 a string\n",
+    "\n",
+    "base_Distrito_2021.loc[:, 'Ubigeo_Distrito'] = base_Distrito_2021['Ubigeo_Distrito'].astype(str)"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
    "id": "603ea155",
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [],
+   "source": [
+    "#Relizamos el merge, dejando todas las observaciones de la base maps_DIST, lo que nos genera valores NaN.\n",
+    "\n",
+    "dataset = pd.merge(maps_DIST, base_Distrito_2021, how = \"left\", on = \"Ubigeo_Distrito\" )"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "aafaf7da",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#Para poder observar los distintos valores únicos en la columna Casos se realiza una tabla de frecuencias\n",
+    "\n",
+    "tabla_frecuencias_casos = dataset['Casos'].value_counts().reset_index()\n",
+    "tabla_frecuencias_casos.columns = ['Número de Casos', 'Frecuencia']\n",
+    "tabla_frecuencias_casos = tabla_frecuencias_casos.sort_values(by='Número de Casos')\n",
+    "\n",
+    "tabla_frecuencias_casos"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c1658b99",
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [],
+   "source": [
+    "!pip install --upgrade mapclassify"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9dd96f04",
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [
+    "#Se hace el mapeo considerando un colo diferente para los valores NaN\n",
+    "\n",
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "fig, ax = plt.subplots(figsize=(20, 20))\n",
+    "dataset.plot(ax = ax, \n",
+    "        column='Casos', \n",
+    "         cmap= 'Reds', \n",
+    "         figsize=(20, 20), \n",
+    "         linestyle='--',\n",
+    "         edgecolor='black', \n",
+    "         legend = True,  \n",
+    "         scheme = \"User_Defined\", \n",
+    "         missing_kwds= dict(color = \"#DADADB\",), \n",
+    "         classification_kwds = dict( bins = [ 100, 200, 300, 400, 500, 1000, 1500, 2000,  2500, 3000 ] ), \n",
+    "         legend_kwds=dict(  loc='upper left',\n",
+    "                            bbox_to_anchor=(1.01, 1),\n",
+    "                            fontsize='x-large',\n",
+    "                            title= \"Número de casos por Distrito\", \n",
+    "                            title_fontsize = 'x-large', \n",
+    "                            frameon= False )\n",
+    "            )"
+   ]
   }
  ],
  "metadata": {