{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Tutorial 4: Trajectory aggregation (flow maps)\n",
    "\n",
    "<img align=\"right\" src=\"https://anitagraser.github.io/movingpandas/pics/movingpandas.png\">\n",
    "\n",
    "This tutorial covers trajectory generalization and aggregation using flow maps. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import urllib\n",
    "import os\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "from geopandas import GeoDataFrame, read_file\n",
    "from shapely.geometry import Point, LineString, Polygon, MultiPoint\n",
    "from datetime import datetime, timedelta\n",
    "\n",
    "import sys\n",
    "sys.path.append(\"..\")\n",
    "import movingpandas as mpd\n",
    "\n",
    "import warnings\n",
    "warnings.simplefilter(\"ignore\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Ship movements (AIS data)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = read_file('data/demodata_ais.gpkg')\n",
    "df['t'] = pd.to_datetime(df['Timestamp'], format='%d/%m/%Y %H:%M:%S')\n",
    "df = df.set_index('t')\n",
    "df = df[df.SOG>0]\n",
    "df.size"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "MIN_LENGTH = 100 # meters\n",
    "traj_collection = mpd.TrajectoryCollection(df, 'MMSI', min_length=MIN_LENGTH)\n",
    "print(\"Finished creating {} trajectories\".format(len(traj_collection)))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "trips = mpd.ObservationGapSplitter(traj_collection).split(gap=timedelta(minutes=5))\n",
    "print(\"Extracted {} individual trips from {} continuous vessel tracks\".format(len(trips), len(traj_collection)))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Generalizing the trip trajectories significantly speeds up the following aggregation step."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "%%time\n",
    "generalized = mpd.MinDistanceGeneralizer(trips).generalize(tolerance=100)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "%%time\n",
    "aggregator = mpd.TrajectoryCollectionAggregator(generalized, max_distance=1000, min_distance=100, min_stop_duration=timedelta(minutes=5))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "scrolled": false
   },
   "outputs": [],
   "source": [
    "pts = aggregator.get_significant_points_gdf()\n",
    "clusters = aggregator.get_clusters_gdf()\n",
    "( pts.hvplot(geo=True, tiles='OSM', frame_width=800) * \n",
    "  clusters.hvplot(geo=True, color='red') )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "scrolled": false
   },
   "outputs": [],
   "source": [
    "flows = aggregator.get_flows_gdf()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "( #trips.hvplot(color='gray')  *\n",
    "  flows.hvplot(geo=True, hover_cols=['weight'], line_width='weight', alpha=0.5, color='#1f77b3', tiles='OSM') * \n",
    "  clusters.hvplot(geo=True, color='red', size='n') )"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Comparison of generalized vs. original trajectories"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "%%time\n",
    "aggregator_original = mpd.TrajectoryCollectionAggregator(trips, max_distance=1000, min_distance=100, min_stop_duration=timedelta(minutes=5))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "( aggregator_original.get_flows_gdf().hvplot(title='Original', geo=True, tiles='OSM', hover_cols=['weight'], line_width='weight', alpha=0.5, color='#1f77b3', frame_height=400, frame_width=400) * \n",
    "  aggregator_original.get_clusters_gdf().hvplot(geo=True, color='red', size='n') +\n",
    "  flows.hvplot(title='Generalized', geo=True, tiles='OSM', hover_cols=['weight'], line_width='weight', alpha=0.5, color='#1f77b3', frame_height=400, frame_width=400) * \n",
    "  clusters.hvplot(geo=True, color='red', size='n') \n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Bird migration data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = read_file('data/demodata_gulls.gpkg')\n",
    "df['t'] = pd.to_datetime(df['timestamp'])\n",
    "df = df.set_index('t')\n",
    "df.size"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "traj_collection = mpd.TrajectoryCollection(df, 'individual-local-identifier', min_length=MIN_LENGTH)     \n",
    "print(\"Finished creating {} trajectories\".format(len(traj_collection)))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "trips = mpd.TemporalSplitter(traj_collection).split(mode='month')\n",
    "print(\"Extracted {} individual trips from {} continuous tracks\".format(len(trips), len(traj_collection)))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "generalized = mpd.MinTimeDeltaGeneralizer(trips).generalize(tolerance=timedelta(days=1))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "%%time\n",
    "aggregator = mpd.TrajectoryCollectionAggregator(generalized, max_distance=1000000, min_distance=100000, min_stop_duration=timedelta(minutes=5))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "flows = aggregator.get_flows_gdf()\n",
    "clusters = aggregator.get_clusters_gdf()\n",
    "\n",
    "( flows.hvplot(geo=True, hover_cols=['weight'], line_width='weight', alpha=0.5, color='#1f77b3', tiles='OSM') * \n",
    "  clusters.hvplot(geo=True, color='red', size='n') )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "%%time\n",
    "aggregator_original = mpd.TrajectoryCollectionAggregator(trips, max_distance=1000000, min_distance=100000, min_stop_duration=timedelta(minutes=5))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "( aggregator_original.get_flows_gdf().hvplot(title='Original', geo=True, tiles='OSM', hover_cols=['weight'], line_width='weight', alpha=0.5, color='#1f77b3', frame_height=600, frame_width=400) * \n",
    "  aggregator_original.get_clusters_gdf().hvplot(geo=True, color='red', size='n') +\n",
    "  flows.hvplot(title='Generalized', geo=True, tiles='OSM', hover_cols=['weight'], line_width='weight', alpha=0.5, color='#1f77b3', frame_height=600, frame_width=400) * \n",
    "  clusters.hvplot(geo=True, color='red', size='n') \n",
    ")"
   ]
  }
 ],
 "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": "3.7.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}