Challenge 7 (sort of) upload 1

DataHackathon2019/Challenge_7_sort_of/Accidents and Lethal Accidents - Geographical Analysis.ipynb

@@ -0,0 +1,329 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Accidents and Lethal Accidents - Geographical Analysis\n",
+    "Ori Moisis, Tal Peleg, Aviram Stern, Noam Hershtig & Moran Neuhof"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "toc": true
+   },
+   "source": [
+    "<h1>Table of Contents<span class=\"tocSkip\"></span></h1>\n",
+    "<div class=\"toc\"><ul class=\"toc-item\"><li><span><a href=\"#Accidents-and-Lethal-Accidents---Geographical-Analysis\" data-toc-modified-id=\"Accidents-and-Lethal-Accidents---Geographical-Analysis-1\"><span class=\"toc-item-num\">1&nbsp;&nbsp;</span>Accidents and Lethal Accidents - Geographical Analysis</a></span><ul class=\"toc-item\"><li><span><a href=\"#Looking-at-lethal-accidents\" data-toc-modified-id=\"Looking-at-lethal-accidents-1.1\"><span class=\"toc-item-num\">1.1&nbsp;&nbsp;</span>Looking at lethal accidents</a></span><ul class=\"toc-item\"><li><span><a href=\"#Accidents-geographical-distribution---by-year\" data-toc-modified-id=\"Accidents-geographical-distribution---by-year-1.1.1\"><span class=\"toc-item-num\">1.1.1&nbsp;&nbsp;</span>Accidents geographical distribution - by year</a></span></li><li><span><a href=\"#Accidents-geographical-distribution---by-hour\" data-toc-modified-id=\"Accidents-geographical-distribution---by-hour-1.1.2\"><span class=\"toc-item-num\">1.1.2&nbsp;&nbsp;</span>Accidents geographical distribution - by hour</a></span></li></ul></li><li><span><a href=\"#Looking-at-all-accidents\" data-toc-modified-id=\"Looking-at-all-accidents-1.2\"><span class=\"toc-item-num\">1.2&nbsp;&nbsp;</span>Looking at all accidents</a></span><ul class=\"toc-item\"><li><span><a href=\"#Accidents-geographical-distribution---by-year\" data-toc-modified-id=\"Accidents-geographical-distribution---by-year-1.2.1\"><span class=\"toc-item-num\">1.2.1&nbsp;&nbsp;</span>Accidents geographical distribution - by year</a></span></li><li><span><a href=\"#Accidents-geographical-distribution---by-hour\" data-toc-modified-id=\"Accidents-geographical-distribution---by-hour-1.2.2\"><span class=\"toc-item-num\">1.2.2&nbsp;&nbsp;</span>Accidents geographical distribution - by hour</a></span></li></ul></li><li><span><a href=\"#Binned-coordinates\" data-toc-modified-id=\"Binned-coordinates-1.3\"><span class=\"toc-item-num\">1.3&nbsp;&nbsp;</span>Binned coordinates</a></span><ul class=\"toc-item\"><li><span><a href=\"#Binning-coordinated\" data-toc-modified-id=\"Binning-coordinated-1.3.1\"><span class=\"toc-item-num\">1.3.1&nbsp;&nbsp;</span>Binning coordinated</a></span></li><li><span><a href=\"#Accidents-geographical-distribution---by-year-(binned)\" data-toc-modified-id=\"Accidents-geographical-distribution---by-year-(binned)-1.3.2\"><span class=\"toc-item-num\">1.3.2&nbsp;&nbsp;</span>Accidents geographical distribution - by year (binned)</a></span></li><li><span><a href=\"#Accidents-geographical-distribution---by-hour-(binned)\" data-toc-modified-id=\"Accidents-geographical-distribution---by-hour-(binned)-1.3.3\"><span class=\"toc-item-num\">1.3.3&nbsp;&nbsp;</span>Accidents geographical distribution - by hour (binned)</a></span></li></ul></li></ul></li></ul></div>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Imports\n",
+    "import numpy as np\n",
+    "import matplotlib.pyplot as plt\n",
+    "import seaborn as sns\n",
+    "import pandas as pd\n",
+    "import os\n",
+    "import geopandas\n",
+    "from shapely.geometry import Point\n",
+    "\n",
+    "%matplotlib inline"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Load file\n",
+    "df = pd.read_csv('anyway_tables_csv_updated/involved_markers_hebrew.csv')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "## Preparing coordinates in dataframe\n",
+    "df['Coordinates'] = list(zip(df.longitude, df.latitude))\n",
+    "df['Coordinates'] = df['Coordinates'].apply(Point)\n",
+    "world = geopandas.read_file(geopandas.datasets.get_path('naturalearth_lowres'))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Looking at lethal accidents"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Subsetting only lethal accidents\n",
+    "lethal_df = df[df['accident_severity']==1].reset_index().drop_duplicates('provider_and_id').reset_index()\n",
+    "lethal_gdf = geopandas.GeoDataFrame(lethal_df, geometry='Coordinates')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Accidents geographical distribution - by year"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for i, year in enumerate(range(2008, 2019)):\n",
+    "    ax = world[world.name == 'Israel'].plot(color='white', edgecolor='black', figsize=(16,9))\n",
+    "    lethal_df_year = lethal_gdf[lethal_gdf['accident_year'] == year]\n",
+    "    lethal_df_year.plot(ax=ax, color='red',alpha=0.3)\n",
+    "    plt.title(year)\n",
+    "    plt.savefig(f\"{year}.png\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Accidents geographical distribution - by hour"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for i, hour in enumerate(range(0, 24)):\n",
+    "    ax = world[world.name == 'Israel'].plot(color='white', edgecolor='black', figsize=(16,9))\n",
+    "    lethal_gdf_hour = lethal_gdf[lethal_gdf['accident_hour'] == hour]\n",
+    "    lethal_gdf_hour.plot(ax=ax, color='red',alpha=0.3)\n",
+    "    plt.title(hour)\n",
+    "    plt.savefig(f\"hour_of_day{hour}.png\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Looking at all accidents"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "gdf = geopandas.GeoDataFrame(df, geometry='Coordinates')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Accidents geographical distribution - by year"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for i, year in enumerate(range(2008, 2019)):\n",
+    "    ax = world[world.name == 'Israel'].plot(color='white', edgecolor='black', figsize=(16,9))\n",
+    "    gdf_year = gdf[gdf['accident_year'] == year]\n",
+    "    gdf_year.plot(ax=ax, color='red',alpha=0.3)\n",
+    "    plt.title(year)\n",
+    "    plt.savefig(f\"all_accidents_year_{year}.png\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Accidents geographical distribution - by hour"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for i, hour in enumerate(range(0, 24)):\n",
+    "    ax = world[world.name == 'Israel'].plot(color='white', edgecolor='black', figsize=(16,9))\n",
+    "    gdf_hour = gdf[gdf['accident_hour'] == hour]\n",
+    "    gdf_hour.plot(ax=ax, color='red',alpha=0.3)\n",
+    "    plt.title(hour)\n",
+    "    plt.savefig(f\"all_accidents_hour_of_day{hour}.png\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Binned coordinates"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Binning coordinated"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Binned distributions\n",
+    "# Accurate DF (with accuracy filter)\n",
+    "accurate_df = df[df['location_accuracy'] == 1].reset_index().drop_duplicates('provider_and_id').reset_index()\n",
+    "\n",
+    "lat_cut = pd.cut(accurate_df.latitude, np.linspace(min(accurate_df.latitude), max(accurate_df.latitude), 30), right=True).apply(lambda x: x.mid)\n",
+    "lon_cut = pd.cut(accurate_df.longitude, np.linspace(min(accurate_df.longitude), max(accurate_df.longitude), 20), right=True).apply(lambda x: x.mid)\n",
+    "\n",
+    "accurate_df['lon_cut'] = lon_cut\n",
+    "accurate_df['lat_cut'] = lat_cut\n",
+    "\n",
+    "accurate_df['Binned_Coordinates'] = list(zip(accurate_df.lon_cut, accurate_df.lat_cut))\n",
+    "accurate_df['Binned_Coordinates'] = accurate_df['Binned_Coordinates'].apply(Point)\n",
+    "# Creating GDF\n",
+    "accurate_gdf = geopandas.GeoDataFrame(accurate_df, geometry='Binned_Coordinates')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Accidents geographical distribution - by year (binned)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Binned\n",
+    "for i, year in enumerate(range(2008, 2019)):\n",
+    "    ax = world[world.name == 'Israel'].plot(color='white', edgecolor='black', figsize=(16,9))\n",
+    "    gdf_year = accurate_gdf[accurate_gdf['accident_year'] == year]\n",
+    "    gdf_year.plot(ax=ax, color='red',alpha=0.3)\n",
+    "    plt.title(year)\n",
+    "    plt.savefig(f\"all_accidents_year_{year}.png\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Accidents geographical distribution - by hour (binned)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for i, hour in enumerate(range(0, 24)):\n",
+    "    ax = world[world.name == 'Israel'].plot(color='white', edgecolor='black', figsize=(16,9))\n",
+    "    gdf_hour = accurate_gdf[accurate_gdf['accident_hour'] == hour]\n",
+    "    gdf_hour.plot(ax=ax, color='red',alpha=0.3)\n",
+    "    plt.title(hour)\n",
+    "    plt.savefig(f\"all_accidents_hour_of_day{hour}.png\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "The same can be done for lethal accidents only (by repeating the filter in 1.1)"
+   ]
+  }
+ ],
+ "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": "3.6.8"
+  },
+  "toc": {
+   "base_numbering": 1,
+   "nav_menu": {},
+   "number_sections": true,
+   "sideBar": true,
+   "skip_h1_title": false,
+   "title_cell": "Table of Contents",
+   "title_sidebar": "Contents",
+   "toc_cell": true,
+   "toc_position": {},
+   "toc_section_display": true,
+   "toc_window_display": false
+  },
+  "varInspector": {
+   "cols": {
+    "lenName": 16,
+    "lenType": 16,
+    "lenVar": 40
+   },
+   "kernels_config": {
+    "python": {
+     "delete_cmd_postfix": "",
+     "delete_cmd_prefix": "del ",
+     "library": "var_list.py",
+     "varRefreshCmd": "print(var_dic_list())"
+    },
+    "r": {
+     "delete_cmd_postfix": ") ",
+     "delete_cmd_prefix": "rm(",
+     "library": "var_list.r",
+     "varRefreshCmd": "cat(var_dic_list()) "
+    }
+   },
+   "types_to_exclude": [
+    "module",
+    "function",
+    "builtin_function_or_method",
+    "instance",
+    "_Feature"
+   ],
+   "window_display": false
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}