SF Crimes Dashboard

sf_crimes_dashboard.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Dashboard of San Fransisco Crime Dataset with Mercury"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "import folium\n",
    "from folium import plugins\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.read_csv(\"./data/SF_crime.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "# those variables will be updated by Mercury framework\n",
    "# please keep all variables to be updated in one cell\n",
    "limit = 1000\n",
    "district = ['BAYVIEW', 'NORTHERN']\n",
    "category = ['VANDALISM', 'ASSAULT', 'ROBBERY']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# the code for plotting is based on https://github.com/marcellusruben/sf-crime-voila/blob/main/sf_crime.ipynb\n",
    "df = df.iloc[0:limit, :]\n",
    "\n",
    "latitude = 37.77\n",
    "longitude = -122.42\n",
    "\n",
    "df_dist = df.loc[df['PdDistrict'].isin(np.array(district))]\n",
    "df_category = df_dist.loc[df_dist['Category'].isin(np.array(category))]\n",
    "\n",
    "cat_unique = df_category['Category'].value_counts()\n",
    "cat_unique = cat_unique.reset_index()\n",
    "\n",
    "dist_unique = df_category['PdDistrict'].value_counts()\n",
    "dist_unique = dist_unique.reset_index()\n",
    "\n",
    "fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(20,10))\n",
    "\n",
    "# create map and display it\n",
    "sanfran_map = folium.Map(location=[latitude, longitude], zoom_start=12)\n",
    "\n",
    "\n",
    "incidents = plugins.MarkerCluster().add_to(sanfran_map)\n",
    "\n",
    "# loop through the dataframe and add each data point to the mark cluster\n",
    "for lat, lng, label, in zip(df_category.Y, df_category.X, df_category.Category):\n",
    "    folium.Marker(\n",
    "    location=[lat, lng],\n",
    "    icon=None,\n",
    "    popup=label,\n",
    "    ).add_to(incidents)\n",
    "# show map\n",
    "display(sanfran_map)\n",
    "\n",
    "ax1.bar(cat_unique['index'], cat_unique['Category'])\n",
    "ax1.set_title('Amount of Criminal Case Based on Category')\n",
    "ax2.bar(dist_unique['index'], dist_unique['PdDistrict'])\n",
    "ax2.set_title('Amount of Criminal Case in Selected District')\n",
    "\n",
    "plt.show()"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "dashenv",
   "language": "python",
   "name": "dashenv"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.10"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}