Documentation (#25)

* wip(documentaion): in this commit the documentation for the scripts and fucntion is added· * wip(notebooks): in this commit the notebooks added * Revisando código * Remove .py files * Renombrando carpetas * Moviendo archivo analisis * Agregar carpeta normzalización y modificar readme de la app * Agregar README * Actualizar README Co-authored-by: Ivan Galaviz <ivan.galaviz@wizeline.com>
saturdaysai-gdl2-plata · Jul 4, 2020 · 8803b97 · 8803b97
1 parent dfd8cd5
commit 8803b97
Show file tree

Hide file tree

Showing 18 changed files with 1,770 additions and 1,024 deletions.
diff --git a/.DS_Store b/.DS_Store
diff --git a/.gitignore b/.gitignore
@@ -1 +1,2 @@
 .vscode
+.DS_Store
diff --git a/0. Normalizing datasets/FilterCrimesJalisco18_19.ipynb b/0. Normalizing datasets/FilterCrimesJalisco18_19.ipynb
@@ -0,0 +1,52 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "name": "FilterCrimesJalisco18-19.ipynb",
+      "provenance": [],
+      "collapsed_sections": []
+    },
+    "kernelspec": {
+      "name": "python3",
+      "display_name": "Python 3"
+    }
+  },
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "LFnIwgj4YAjs",
+        "colab_type": "text"
+      },
+      "source": [
+        "# Dataset incidencia criminal\n",
+        "\n",
+        "Los datos que utilizamos para nuestro análisis se pueden encontrar [aquí](https://iieg.gob.mx/ns/wp-content/uploads/2020/04/marzo20.rar).\n",
+        "\n",
+        "Lamentablemente no existe una ruta directa al .csv."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "W7qRThDmPFUC",
+        "colab_type": "code",
+        "colab": {}
+      },
+      "source": [
+        "import pandas as pd\n",
+        "\n",
+        "df = pd.read_csv('marzo20.csv')\n",
+        "\n",
+        "years = [2018, 2019]\n",
+        "\n",
+        "filtered = df[(df['Año'].isin(years))]\n",
+        "\n",
+        "filtered.to_csv('incidencia_delictiva_jalisco18-19_filter.csv', index=False)"
+      ],
+      "execution_count": null,
+      "outputs": []
+    }
+  ]
+}
diff --git a/0. Normalizing datasets/MiBici.ipynb b/0. Normalizing datasets/MiBici.ipynb
@@ -0,0 +1,82 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "name": "Saturdays.IA MiBici.ipynb",
+      "provenance": [],
+      "collapsed_sections": []
+    },
+    "kernelspec": {
+      "name": "python3",
+      "display_name": "Python 3"
+    }
+  },
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "JvqasNWf3N6L",
+        "colab_type": "text"
+      },
+      "source": [
+        "## Downloading datasets"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "uw9yCw5mKEKw",
+        "colab_type": "code",
+        "colab": {}
+      },
+      "source": [
+        "urls = [\n",
+        "    \"https://www.mibici.net/site/assets/files/1200/datos_abiertos_2018_01.csv\",\n",
+        "    \"https://www.mibici.net/site/assets/files/1201/datos_abiertos_2018_02.csv\",\n",
+        "    \"https://www.mibici.net/site/assets/files/1202/datos_abiertos_2018_03.csv\",\n",
+        "    \"https://www.mibici.net/site/assets/files/1203/datos_abiertos_2018_04.csv\",\n",
+        "    \"https://www.mibici.net/site/assets/files/1204/datos_abiertos_2018_05.csv\",\n",
+        "    \"https://www.mibici.net/site/assets/files/1205/datos_abiertos_2018_06.csv\",\n",
+        "    \"https://www.mibici.net/site/assets/files/1206/datos_abiertos_2018_07.csv\",\n",
+        "    \"https://www.mibici.net/site/assets/files/1207/datos_abiertos_2018_08.csv\",\n",
+        "    \"https://www.mibici.net/site/assets/files/1208/datos_abiertos_2018_09.csv\",\n",
+        "    \"https://www.mibici.net/site/assets/files/1209/datos_abiertos_2018_10.csv\",\n",
+        "    \"https://www.mibici.net/site/assets/files/1210/datos_abiertos_2018_11.csv\",\n",
+        "    \"https://www.mibici.net/site/assets/files/1211/datos_abiertos_2018_12.csv\",\n",
+        "    \"https://www.mibici.net/site/assets/files/1214/datos_abiertos_2019_01.csv\",\n",
+        "    \"https://www.mibici.net/site/assets/files/1217/datos_abiertos_2019_02.csv\",\n",
+        "    \"https://www.mibici.net/site/assets/files/1218/datos_abiertos_2019_03.csv\",\n",
+        "    \"https://www.mibici.net/site/assets/files/1219/datos_abiertos_2019_04.csv\",\n",
+        "    \"https://www.mibici.net/site/assets/files/1220/datos_abiertos_2019_05.csv\",\n",
+        "    \"https://www.mibici.net/site/assets/files/1221/datos_abiertos_2019_06.csv\",\n",
+        "    \"https://www.mibici.net/site/assets/files/1222/datos_abiertos_2019_07.csv\",\n",
+        "    \"https://www.mibici.net/site/assets/files/1223/datos_abiertos_2019_08.csv\",\n",
+        "    \"https://www.mibici.net/site/assets/files/1224/datos_abiertos_2019_09.csv\",\n",
+        "    \"https://www.mibici.net/site/assets/files/1225/datos_abiertos_2019_10.csv\",\n",
+        "    \"https://www.mibici.net/site/assets/files/1227/datos_abiertos_2019_11.csv\",\n",
+        "    \"https://www.mibici.net/site/assets/files/1228/datos_abiertos_2019_12.csv\"\n",
+        "]\n",
+        "\n",
+        "for url in urls:\n",
+        "    !curl -O \"$url\"\n",
+        "\n",
+        "import glob\n",
+        "filenames = glob.glob(\"*.csv\")\n",
+        "\n",
+        "import pandas as pd\n",
+        "combined_csv = pd.concat([pd.read_csv(f, engine=\"python\") for f in filenames])\n",
+        "combined_csv.to_csv(\"datos.csv\", index=False)\n",
+        "\n",
+        "import os\n",
+        "for f in filenames:\n",
+        "    os.remove(f)\n",
+        "\n",
+        "df = pd.read_csv('datos.csv')\n",
+        "df = df.rename(columns={\"A�o_de_nacimiento\": \"Anio_de_nacimiento\"})"
+      ],
+      "execution_count": null,
+      "outputs": []
+    }
+  ]
+}