ohsome_green_region.ipynb 146 KB
Newer Older
Sarah Heidekorn's avatar
Sarah Heidekorn committed
1
2
3
4
5
6
7
8
9
{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "inside-matthew",
   "metadata": {},
   "source": [
    "# ohsome green regions (via tree related tags)\n",
    "\n",
10
    "Welcome back to the ohsome Region of the month format where you can learn and get inspiration about potential applications of the [ohsome API](https://docs.ohsome.org/ohsome-api/v1/). This time we looked at trees, more precisely forests, in four different canadian regions (Edmonton, Halifax, Ottawa and Vancouver) looking for the green region of the month, which means there will be a winner announced at the end of this blogpost. \n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
11
    "This time, the analysis will be done via jupyter notebook using the python programming language."
Sarah Heidekorn's avatar
Sarah Heidekorn committed
12
13
14
15
16
17
18
   ]
  },
  {
   "cell_type": "markdown",
   "id": "appropriate-balloon",
   "metadata": {},
   "source": [
19
    "### **1. Data** \n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
20
    "\n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
21
    "As always there is no request without input information and, concerning the boundaries of the request, you can get a GeoJSON with region boundaries [here](https://osm-boundaries.com). This file will be used as spatial input to add the information of the boundaries of your request.\n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
22
23
    "\n",
    "\n",
24
    "### **2: Import of libraries**\n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
25
    "\n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
26
    "At first you'll have to import libraries that help you handling the data later on. This includes a range of things, being it sending the get/post request itself or plotting the output data.\n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
27
28
29
30
31
32
    "\n",
    "_e.g.: numpy for stats, pandas for analytics or json for simply handling json-files as you will see further down in the code_"
   ]
  },
  {
   "cell_type": "code",
33
   "execution_count": 11,
Sarah Heidekorn's avatar
Sarah Heidekorn committed
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
   "id": "overall-iraqi",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "        <script type=\"text/javascript\">\n",
       "        window.PlotlyConfig = {MathJaxConfig: 'local'};\n",
       "        if (window.MathJax) {MathJax.Hub.Config({SVG: {font: \"STIX-Web\"}});}\n",
       "        if (typeof require !== 'undefined') {\n",
       "        require.undef(\"plotly\");\n",
       "        requirejs.config({\n",
       "            paths: {\n",
       "                'plotly': ['https://cdn.plot.ly/plotly-latest.min']\n",
       "            }\n",
       "        });\n",
       "        require(['plotly'], function(Plotly) {\n",
       "            window._Plotly = Plotly;\n",
       "        });\n",
       "        }\n",
       "        </script>\n",
       "        "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# import of useful libraries for the analysis (e.g. pandas -> analysis, \n",
    "# json -> for handling json responses)\n",
    "\n",
    "import pandas as pd\n",
    "import geopandas as gpd\n",
    "import numpy as np\n",
    "import json\n",
    "import geojson\n",
    "import requests\n",
    "import plotly\n",
    "import IPython\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "\n",
    "# for generating interactive graphs\n",
    "import plotly.graph_objs as go\n",
    "\n",
    "from IPython.display import *\n",
    "from geojson import MultiPolygon\n",
    "\n",
    "plotly.offline.init_notebook_mode(connected=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "silent-medicare",
   "metadata": {},
   "source": [
91
    "### **3: Defining a function and the spatial & temporal boundaries**\n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
92
    "\n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
93
    "Then you'll have to define the spatial and temporal boundaries of the request you intend to send. Begin by defining a variable for the ohsome API as well as a function to help building your request.\n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
94
95
96
97
98
    "Below you will realize that two functions have been defined as there will be two different types of requests, quite similar to the ones sent in the [ohsome street network analysis](http://k1z.blog.uni-heidelberg.de/2021/01/18/ohsome-street-network-analysis-part-1/). But more information is to be found in the next step of this blogpost."
   ]
  },
  {
   "cell_type": "code",
99
   "execution_count": 12,
Sarah Heidekorn's avatar
Sarah Heidekorn committed
100
101
102
103
   "id": "specialized-henry",
   "metadata": {},
   "outputs": [],
   "source": [
104
105
    "#set a variable for the API\n",
    "ohsome_api = \"https://api.ohsome.org/v1\"         \n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
106
    "\n",
107
    "# define a functions for the filters\n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
108
    "def elements(agg,**params):\n",
109
    "    return requests.post(ohsome_api+\"/elements\"+agg,params)\n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
110
111
    "\n",
    "def users(agg,**params):\n",
112
    "    return requests.post(ohsome_api+\"/users\"+agg,params)\n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
113
    "\n",
114
    "#define the spatial boundaries/set the path to your file:\n",
115
    "with open(\"yourpath/marchregions.geojson\") as f: \n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
116
117
118
    "    regions = json.load(f)\n",
    "    regions = json.dumps(regions)\n",
    "\n",
119
    "#define time intervals\n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
120
    "t_mon = \"2008-01-01/2021-02-01/P1M\"\n",
121
    "filter_req = '(landuse=forest or natural=wood) and geometry:polygon'\n"
Sarah Heidekorn's avatar
Sarah Heidekorn committed
122
123
124
125
126
127
128
   ]
  },
  {
   "cell_type": "markdown",
   "id": "secret-salmon",
   "metadata": {},
   "source": [
129
    "### **4: Requests**\n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
130
    "\n",
131
    "The code below is dealing with how you can phrase your exact request. To keep it simple and get a first look at the data the request only asks for the overall density of wood/forest in the regions of interest.\n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
    "\n",
    "\n",
    "For this months analysis you can request the data by using the following conditions:\n",
    "\n",
    "For the forest dataset:\n",
    "\n",
    "_endpoint\t->\t/elements/area/density/groupBy/boundary_\n",
    "\n",
    "_timestamp  \t->\t2008-01-01/2021-02-01/P1M_\n",
    "\n",
    "_filter\t\t->\t(landuse=forest or nature=wood) and geometry:polygon_\n",
    "\n",
    "\n",
    "For the user dataset:\n",
    "\n",
    "_endpoint\t\t->\t/users/groupBy/boundary_\n",
    "\n",
    "_timestamp\t\t->\t2008-01-01/2021-02-01/P1M_\n",
    "\n",
151
    "_filter\t\t    ->\t(landuse=forest or nature=wood) and geometry:polygon_\n",
152
153
154
    "\n",
    "\n",
    "\n",
155
    "_-> You might wonder why there was only made use of tree-RELATED tags instead of the tree key itself for this analysis. The problem was that said key wasn’t used because over the whole time span there was zero tree information given, yet, **BUT** at least for Ottawa a tree import has been [proposed in 2017](https://wiki.openstreetmap.org/wiki/Ottawa/Import/Trees) so there might be data for Ottawa soon! <-_"
156
157
158
159
   ]
  },
  {
   "cell_type": "markdown",
160
   "id": "loving-bulgaria",
161
162
163
   "metadata": {},
   "source": [
    "## **Analysis Part 1 - Density**"
Sarah Heidekorn's avatar
Sarah Heidekorn committed
164
165
166
167
   ]
  },
  {
   "cell_type": "code",
168
   "execution_count": 13,
Sarah Heidekorn's avatar
Sarah Heidekorn committed
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
   "id": "greater-eligibility",
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'https://api.ohsome.org/v1/elements/area/density/groupBy/boundary'"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
184
185
186
187
188
189
     "ename": "KeyError",
     "evalue": "'groupByResult'",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mKeyError\u001b[0m                                  Traceback (most recent call last)",
190
191
      "\u001b[0;32m<ipython-input-13-580d2314b820>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m     16\u001b[0m     \u001b[0mdensity\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mround\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdf\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;36m2\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     17\u001b[0m     \u001b[0mdensity\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mplot\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfigsize\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;36m9\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;36m7\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfontsize\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m11\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 18\u001b[0;31m \u001b[0marea\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[0;32m<ipython-input-13-580d2314b820>\u001b[0m in \u001b[0;36marea\u001b[0;34m()\u001b[0m\n\u001b[1;32m      9\u001b[0m \u001b[0;31m#turn output into DataFrame-format:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     10\u001b[0m     \u001b[0mdf\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mpd\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mDataFrame\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 11\u001b[0;31m     \u001b[0;32mfor\u001b[0m \u001b[0mgroupBy\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mgreen\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'groupByResult'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     12\u001b[0m         \u001b[0mseries\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mpd\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mSeries\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m{\u001b[0m\u001b[0mrow\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'timestamp'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0mrow\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'value'\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mrow\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mgroupBy\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'result'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m}\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     13\u001b[0m         \u001b[0mdf\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mgroupBy\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'groupByObject'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mseries\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
192
193
      "\u001b[0;31mKeyError\u001b[0m: 'groupByResult'"
     ]
Sarah Heidekorn's avatar
Sarah Heidekorn committed
194
195
196
    }
   ],
   "source": [
197
    "# define and plot request/path\n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
198
    "def area():   \n",
199
    "    res = elements(\"/area/density/groupBy/boundary\"                 \n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
200
    "         ,filter=filter_req\n",
201
202
    "         ,bpolys=regions                                            \n",
    "         ,time=t_mon)                                                \n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
203
204
    "    display(res.url)\n",
    "    green = res.json()\n",
205
206
    "#turn output into DataFrame-format:\n",
    "    df = pd.DataFrame()                                             \n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
207
208
209
210
    "    for groupBy in green['groupByResult']:\n",
    "        series = pd.Series({row['timestamp']:row['value'] for row in groupBy['result']})\n",
    "        df[groupBy['groupByObject']] = series\n",
    "    df.set_index(pd.to_datetime(df.index),inplace=True)\n",
211
    "    df.to_pickle(\"./df_density.pkl\")                                \n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
212
    "    density = round(df, 2)\n",
213
    "    density.plot(figsize=(9,7), fontsize=11)                            \n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
214
215
216
    "area()"
   ]
  },
217
218
  {
   "cell_type": "markdown",
219
   "id": "terminal-treasury",
220
221
   "metadata": {},
   "source": [
Sarah Heidekorn's avatar
Sarah Heidekorn committed
222
    "#### In the graphic above you can see the development of the density of natural=wood as well as landuse=forest information"
223
224
   ]
  },
Sarah Heidekorn's avatar
Sarah Heidekorn committed
225
226
227
228
229
230
231
  {
   "cell_type": "markdown",
   "id": "editorial-scotland",
   "metadata": {},
   "source": [
    "When looking at the plot of the output dataset it is pretty safe to say that Edmonton has the lowest density of forest/wood information given when comparing it to the other regions. Although this might be part of low mapping activities too, it might as well be related to local oil and gas production areas or farmland which reduced the amount of forest. Another factor could be the general geographic connection to the Prairies Ecozone.\n",
    "\n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
232
233
    "Furthermore, it is worth mentioning that all cities, but Vancouver, only really added their forest information around 2010 and 2011. \n",
    "Interestingly the density values for Vancouver only cross parts with the Ottawa- and Halifax-values around 2017. Additionally there is a strong increase in density in the early 2013 months. During that same year the Open Data Hackathon took place on Feb 23rd.\n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
234
    "\n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
235
    "Ottawa and Halifax both begin to have increasing information starting around the same period in 2010 and cross each other several times until Ottawa finally takes its place at the top in 2018. Densitywise Ottawa is the winner looking at the overall development of density throughout the years. \n",
236
    "\n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
237
    "[Canvec imports](https://wiki.openstreetmap.org/wiki/CanVec) between 2010-2012 are might be related to the strong increases during that time period as the tag _natural=wood_ was part of the data given (-> CanVec Vegetation (VE)). Another related import might be one of [Canadian Protected Areas](https://wiki.openstreetmap.org/wiki/Import/Catalogue#One-Time_Imports) which has been in progress since 2009 ([from geogratis](http://geogratis.gc.ca)) but that is only an assumption."
Sarah Heidekorn's avatar
Sarah Heidekorn committed
238
239
240
241
   ]
  },
  {
   "cell_type": "code",
242
   "execution_count": 12,
Sarah Heidekorn's avatar
Sarah Heidekorn committed
243
244
245
246
   "id": "potential-intent",
   "metadata": {},
   "outputs": [
    {
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>region</th>\n",
       "      <th>mean</th>\n",
       "      <th>median</th>\n",
       "      <th>min</th>\n",
       "      <th>max</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Vancouver</td>\n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
278
279
       "      <td>204006.88</td>\n",
       "      <td>260064.90</td>\n",
280
281
282
283
284
285
       "      <td>614.07</td>\n",
       "      <td>319494.75</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Halifax</td>\n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
286
287
       "      <td>223159.97</td>\n",
       "      <td>296758.98</td>\n",
288
289
290
291
292
293
       "      <td>0.00</td>\n",
       "      <td>324080.16</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Edmonton</td>\n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
294
295
       "      <td>28518.29</td>\n",
       "      <td>32828.07</td>\n",
296
297
298
299
300
301
       "      <td>0.00</td>\n",
       "      <td>49962.98</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Ottawa</td>\n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
302
303
       "      <td>234835.11</td>\n",
       "      <td>316338.05</td>\n",
304
305
306
307
308
309
310
311
       "      <td>1942.07</td>\n",
       "      <td>330267.47</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
Sarah Heidekorn's avatar
Sarah Heidekorn committed
312
313
314
315
316
       "      region       mean     median      min        max\n",
       "0  Vancouver  204006.88  260064.90   614.07  319494.75\n",
       "1    Halifax  223159.97  296758.98     0.00  324080.16\n",
       "2   Edmonton   28518.29   32828.07     0.00   49962.98\n",
       "3     Ottawa  234835.11  316338.05  1942.07  330267.47"
317
318
319
320
321
322
323
324
325
326
327
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:ylabel='region'>"
      ]
     },
328
     "execution_count": 12,
329
330
331
332
333
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
334
      "image/png": "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\n",
335
      "text/plain": [
336
       "<Figure size 576x576 with 1 Axes>"
337
338
339
340
341
342
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
Sarah Heidekorn's avatar
Sarah Heidekorn committed
343
344
345
    }
   ],
   "source": [
346
347
    "#read the pickle file which was saved earlier:\n",
    "df_density = pd.read_pickle(\"./df_density.pkl\")          \n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
348
349
    "\n",
    "val = {'region':['Vancouver', 'Halifax', 'Edmonton', 'Ottawa'], \n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
350
351
    "       'mean': [204006.88, 223159.97, 28518.29, 234835.11], \n",
    "       'median': [260064.90, 296758.98, 32828.07, 316338.05], 'min':[614.07, 0.0, 0.0, 1942.07], \n",
352
    "       'max':[319494.75, 324080.16, 49962.98, 330267.47]}\n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
353
354
355
    "val_density = pd.DataFrame(val)\n",
    "\n",
    "display (val_density)\n",
356
    "val_density.plot.barh(0, figsize=(8,8))\n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
357
358
359
360
361
362
363
364
365
    "\n",
    "#The table was created by searching for the mean, median, minimum and maximum values of each region.\n",
    "#You can do it with numpy, like so:\n",
    "#Ottawa, Ontario:\n",
    "#Oarray = df_density['Ottawa']\n",
    "#OttMean = np.mean(Oarray)\n",
    "#OttMedian = np.median(Oarray)\n",
    "#OttMin = np.min(Oarray)\n",
    "#OttMax = np.max(Oarray)\n",
366
    "#display(OttMean, OttMedian, OttMin, OttMax) -> to look at the values"
Sarah Heidekorn's avatar
Sarah Heidekorn committed
367
368
   ]
  },
369
370
  {
   "cell_type": "markdown",
371
   "id": "formed-morning",
372
373
   "metadata": {},
   "source": [
Sarah Heidekorn's avatar
Sarah Heidekorn committed
374
    "#### Above you can see the output DataFrame 'val_density' with some statistics for the density dataset, below that it was visualized in a barchart."
375
376
377
378
   ]
  },
  {
   "cell_type": "markdown",
379
   "id": "golden-soviet",
380
381
   "metadata": {},
   "source": [
382
    "Apart from Ottawa there is no display of a minimum value in the barchart above. This is due to the fact that Edmonton and Halifax both started at zero in the beginning of the examined timespan but also because the initial value of Metro Vancouver was probably too small to be visible in the graphic.\n",
383
    "\n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
384
385
    "When looking at the chart one can once more see that Ottawa has the overall highest density values when taking e.g. the mean or maximum values into account, but even more so, it also has the highest initial (minimum) values!\n",
    "It is followed by Halifax & Vancouver. Edmonton comes last with the smallest overall values."
386
387
   ]
  },
388
389
  {
   "cell_type": "code",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
390
391
   "execution_count": 5,
   "id": "developmental-russian",
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>region</th>\n",
       "      <th>Δ density</th>\n",
417
       "      <th>percent</th>\n",
418
419
420
421
422
423
424
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Vancouver</td>\n",
       "      <td>316130.09</td>\n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
425
       "      <td>0.998</td>\n",
426
427
428
429
430
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Halifax</td>\n",
       "      <td>299203.41</td>\n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
431
       "      <td>1.000</td>\n",
432
433
434
435
436
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Edmonton</td>\n",
       "      <td>49647.97</td>\n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
437
       "      <td>1.000</td>\n",
438
439
440
441
442
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Ottawa</td>\n",
       "      <td>322071.36</td>\n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
443
       "      <td>0.991</td>\n",
444
445
446
447
448
449
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
Sarah Heidekorn's avatar
Sarah Heidekorn committed
450
451
452
453
454
       "      region  Δ density  percent\n",
       "0  Vancouver  316130.09    0.998\n",
       "1    Halifax  299203.41    1.000\n",
       "2   Edmonton   49647.97    1.000\n",
       "3     Ottawa  322071.36    0.991"
455
456
457
458
459
460
461
462
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
Sarah Heidekorn's avatar
Sarah Heidekorn committed
463
       "<BarContainer object of 4 artists>"
464
465
      ]
     },
Sarah Heidekorn's avatar
Sarah Heidekorn committed
466
     "execution_count": 5,
467
468
469
470
471
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
Sarah Heidekorn's avatar
Sarah Heidekorn committed
472
      "image/png": "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\n",
473
      "text/plain": [
Sarah Heidekorn's avatar
Sarah Heidekorn committed
474
       "<Figure size 432x288 with 1 Axes>"
475
476
477
478
479
480
481
482
483
484
485
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "devdens = {'region':['Vancouver', 'Halifax', 'Edmonton', 'Ottawa'],\n",
    "           'Δ density': [316130.09, 299203.41, 49647.97, 322071.36],\n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
486
    "           'percent': [0.998, 1.0, 1.0, 0.991]}\n",
487
488
489
    "dev_density = pd.DataFrame(devdens)\n",
    "\n",
    "display (dev_density)\n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
490
491
492
493
494
    "\n",
    "plt.figure()\n",
    "x = dev_density['region']\n",
    "y = dev_density['Δ density']\n",
    "plt.bar(x,y)\n",
495
496
497
498
499
500
501
502
    "\n",
    "#one way to calculate these values is:\n",
    "#display(df_density)\n",
    "#EdDiff = 49647.97 -  0.00\n",
    "#EdPerc = EdDiff/49647.97\n",
    "#display(EdDiff, EdPerc)"
   ]
  },
503
504
  {
   "cell_type": "markdown",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
505
   "id": "coated-acrylic",
506
507
   "metadata": {},
   "source": [
Sarah Heidekorn's avatar
Sarah Heidekorn committed
508
    "#### Above you can see the Δ density and percentual-values in numbers as well as figures. You can notice that the development for ALL regions was very good as the minimum percentuage of growth in density is in Ottawa with 99.143%.\n",
509
    "\n",
510
    "As usual Edmonton shows the lowest values and Ottawa the highest. This is due to their overall development, yet it should be noted that the Δ density-values for Vancouver get really close to those of Ottawa and the starting values weren't much lower either which implies a very similar development over the whole timespan.\n",
511
512
513
514
515
516
517
518
    "\n",
    "**Δ Density Ranking:**\n",
    "1. Ottawa\n",
    "2. Vancouver\n",
    "3. Halifax\n",
    "4. Edmonton\n",
    "\n",
    "_side note: The percentage-values aren't shown in a figure as they are all very similar and differences were hard to make out with the eyes only_"
519
520
   ]
  },
Sarah Heidekorn's avatar
Sarah Heidekorn committed
521
522
523
524
525
  {
   "cell_type": "markdown",
   "id": "therapeutic-allen",
   "metadata": {},
   "source": [
526
    "## **Analysis Part 2 - Users**"
Sarah Heidekorn's avatar
Sarah Heidekorn committed
527
528
529
530
   ]
  },
  {
   "cell_type": "code",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
531
   "execution_count": 6,
Sarah Heidekorn's avatar
Sarah Heidekorn committed
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
   "id": "middle-fisher",
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'https://api.ohsome.org/v1/users/count/groupBy/boundary'"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
Sarah Heidekorn's avatar
Sarah Heidekorn committed
548
      "image/png": "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\n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
549
      "text/plain": [
Sarah Heidekorn's avatar
Sarah Heidekorn committed
550
       "<Figure size 720x792 with 4 Axes>"
Sarah Heidekorn's avatar
Sarah Heidekorn committed
551
552
553
554
555
556
557
558
559
560
561
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "def groupBy():\n",
    "    resU = users(\"/count/groupBy/boundary\"\n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
562
    "         ,filter=filter_req          \n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
563
564
565
566
567
568
569
570
571
572
573
    "         ,bpolys=regions\n",
    "         ,time=t_mon)\n",
    "    display(resU.url)\n",
    "    green_u = resU.json()\n",
    "    #display(green_u)\n",
    "    df = pd.DataFrame()\n",
    "    for groupBy in green_u['groupByResult']:\n",
    "        series = pd.Series({row['fromTimestamp']:row['value'] for row in groupBy['result']})\n",
    "        df[groupBy['groupByObject']] = series\n",
    "    df.set_index(pd.to_datetime(df.index),inplace=True)\n",
    "    df.to_pickle(\"./df_users.pkl\")\n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
574
    "    df.plot(kind='line', subplots=True, sharex=False, sharey=True, figsize=(10,11), fontsize=9)\n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
575
576
577
    "groupBy()"
   ]
  },
578
579
  {
   "cell_type": "markdown",
580
   "id": "revolutionary-sigma",
581
582
   "metadata": {},
   "source": [
Sarah Heidekorn's avatar
Sarah Heidekorn committed
583
    "#### In the graphic above you can see the user numbers of the natural=wood as well as landuse=forest tag over the years"
584
585
   ]
  },
Sarah Heidekorn's avatar
Sarah Heidekorn committed
586
587
588
589
590
  {
   "cell_type": "markdown",
   "id": "confidential-purchase",
   "metadata": {},
   "source": [
591
    "#### Edmonton:\t  \n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
592
    "\n",
593
    "Let's start from the top again.\n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
594
    "There's almost no user activity from 2008 up until the end 2010. Notable user activity first starts around 2011 so at the same time as the main increase in density values. One can observe that for certain time periods the user count keeps falling back to low or no user activity at all. Thhhe peak is reached by the end of 2017 but even after, there are still some quite high values. Furthermore, the peak also marks the time of the last notable increase in density information.\n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
595
596
    "\n",
    "\n",
597
    "#### Halifax:\t  \n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
598
    "\n",
599
    "For the Halifax region there was nearly no user activity at all up until mid 2010 apart from a very short peak in the very beginning. The first peak in 2010 is in accord with the first strong density increase. However, after that the user numbers stay more or less on the same overall level until 2017 when they are peaking until about June of th same year which appears to be fitting the decreasing density values around this time period either. There's one last peak in 2020.\n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
600
601
    "\n",
    "\n",
602
    "#### Vancouver: \n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
603
    "\n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
604
    "For the Metro Vancouver region there are only very short timespans of complete user inactivity and an overall increasing trend is observable. The maximum user count is reached around Mid 2020 whilst the first density peak is at the same time as the first peak in user activity 2008. The increasing trend in user counts begins at around 2010, yet shortly after there is a fast decrease in density probably due to wrong or double values that were corrected. This might be related to the CanVec imports as one of the most important data sources.\n",
605
606
607
    "\n",
    "\n",
    "#### Ottawa:    \n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
608
    "\n",
609
    "In Ottawa there are three times of minor user activity until 2009 and subsequently an increasing trend until 2018 with times of lower user activity between 2014 and Mid 2015. The local mapping community also [mentions](https://wiki.openstreetmap.org/wiki/Ottawa#Status) that most of the info is from CanVac data."
Sarah Heidekorn's avatar
Sarah Heidekorn committed
610
611
612
613
   ]
  },
  {
   "cell_type": "code",
614
   "execution_count": 10,
Sarah Heidekorn's avatar
Sarah Heidekorn committed
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
   "id": "liable-victim",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>region</th>\n",
       "      <th>mean</th>\n",
       "      <th>median</th>\n",
       "      <th>min</th>\n",
       "      <th>max</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Vancouver</td>\n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
650
       "      <td>7</td>\n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
651
652
653
654
655
656
657
       "      <td>6.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>25.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Halifax</td>\n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
658
       "      <td>3</td>\n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
659
660
661
662
663
664
665
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>13.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Edmonton</td>\n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
666
       "      <td>2</td>\n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
667
668
669
670
671
672
673
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>7.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Ottawa</td>\n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
674
       "      <td>3</td>\n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
675
676
677
678
679
680
681
682
683
       "      <td>3.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>13.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
Sarah Heidekorn's avatar
Sarah Heidekorn committed
684
685
686
687
688
       "      region  mean  median  min   max\n",
       "0  Vancouver     7     6.0  0.0  25.0\n",
       "1    Halifax     3     2.0  0.0  13.0\n",
       "2   Edmonton     2     1.0  0.0   7.0\n",
       "3     Ottawa     3     3.0  0.0  13.0"
Sarah Heidekorn's avatar
Sarah Heidekorn committed
689
690
691
692
693
694
695
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
Sarah Heidekorn's avatar
Sarah Heidekorn committed
696
      "image/png": "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\n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
697
      "text/plain": [
Sarah Heidekorn's avatar
Sarah Heidekorn committed
698
       "<Figure size 576x432 with 1 Axes>"
Sarah Heidekorn's avatar
Sarah Heidekorn committed
699
700
701
702
703
704
705
706
707
708
709
710
711
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "#read output dataset:\n",
    "df_users = pd.read_pickle(\"./df_users.pkl\")\n",
    "\n",
    "val_u = {'region':['Vancouver', 'Halifax', 'Edmonton', 'Ottawa'], \n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
712
    "'mean': [7, 3, 2, 3], \n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
713
714
715
    "'median': [6.0, 2.0, 1.0, 3.0], 'min':[0.0, 0.0, 0.0, 0.0], 'max':[25.0, 13.0, 7.0, 13.0]}\n",
    "val_users = pd.DataFrame(val_u)\n",
    "\n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
716
    "df_users.plot(kind='box', figsize=(8,6), fontsize=9)\n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
717
    "display (val_users)\n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
718
    "\n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
719
720
    "\n",
    "\n",
721
    "#The table was again created by searching for the mean, median, minimum and maximum values of each region."
Sarah Heidekorn's avatar
Sarah Heidekorn committed
722
723
   ]
  },
724
725
  {
   "cell_type": "markdown",
726
   "id": "bibliographic-vatican",
727
728
   "metadata": {},
   "source": [
Sarah Heidekorn's avatar
Sarah Heidekorn committed
729
730
    "When looking at the minimum value of the user data output, all the regions have the value 0, so during the observed time intervals, there were periods where no user performed any modification on features fitting to the analyzed filter. \n",
    "Again, Edmonton had the lowest values (mean, median & maximum), which might be yet another reason for the overall lower values in density of tree related polygon-tags.\n",
731
    "\n",
732
733
734
735
736
737
    "Halifax and Ottawa both have the same maximum value yet Ottawa is higher in mean as well as median. And the highest overall user-values are to be found for Vancouver.\n",
    "\n",
    "**User activity Ranking:** \n",
    "1. Vancouver\n",
    "2. Ottawa\n",
    "3. Halifax\n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
738
    "4. Edmonton"
739
740
741
742
   ]
  },
  {
   "cell_type": "markdown",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
743
   "id": "blind-trademark",
744
745
746
   "metadata": {},
   "source": [
    "### Final Ranking:\n",
747
    "\n",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
748
749
750
751
752
    "Since both Vancouver & Ottawa made it to the top in one of the rankings it appears to be useful to announce 2 winners this time: Vancouver in terms of user counts and Ottawa in terms of overall density development.\n",
    "This leaves us with following ranking:\n",
    "\n",
    "1. Vancouver & Ottawa\n",
    "2. Halifax\n",
753
754
755
756
    "3. Edmonton\n",
    "\n",
    "\n",
    "Thanks for reading this months blogpost & additional notebook. Stay tuned for more notebooks and blogposts in the future!"
757
758
   ]
  },
Sarah Heidekorn's avatar
Sarah Heidekorn committed
759
760
761
  {
   "cell_type": "code",
   "execution_count": null,
Sarah Heidekorn's avatar
Sarah Heidekorn committed
762
   "id": "passive-trader",
Sarah Heidekorn's avatar
Sarah Heidekorn committed
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.7.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}