Test
\n", " \n", " \n", " \n", " ''',\n", " options=[\n", " '',\n", " '',\n", " ''])\n", "\n", " # Then\n", " assertEqualHTML(\n", " htmlActual,\n", " '''\n", " \n", " \n", "Test
\n", " \n", " \n", " \n", " ''')\n", "\n", "# adapted from https://stackoverflow.com/questions/8006909/pretty-print-assertequal-for-html-strings\n", "\n", "\n", "def assertEqualHTML(string1, string2, file1='', file2=''):\n", " u'''\n", " Compare two unicode strings containing HTML.\n", " A human friendly diff goes to logging.error() if they\n", " are not equal, and an exception gets raised.\n", " '''\n", " from bs4 import BeautifulSoup as bs\n", " import difflib\n", "\n", " def short(mystr):\n", " max = 20\n", " if len(mystr) > max:\n", " return mystr[:max]\n", " return mystr\n", " p = []\n", " for mystr, file in [(string1, file1), (string2, file2)]:\n", " if not isinstance(mystr, str):\n", " raise Exception(u'string ist not unicode: %r %s' %\n", " (short(mystr), file))\n", " soup = bs(mystr)\n", " pretty = soup.prettify()\n", " p.append(pretty)\n", " if p[0] != p[1]:\n", " for line in difflib.unified_diff(p[0].splitlines(), p[1].splitlines(), fromfile=file1, tofile=file2):\n", " display(line)\n", " display(p[0], ' != ', p[1])\n", " raise Exception('Not equal %s %s' % (file1, file2))\n" ] }, { "cell_type": "code", "execution_count": null, "id": "403f8b7b", "metadata": {}, "outputs": [], "source": [ "from bs4 import BeautifulSoup\n", "\n", "\n", "def saveKreisOptions(kreisOptions):\n", " HtmlTransformerUtil().applySoupTransformerToFile(\n", " file = \"../../docs/intensivstationen.html\",\n", " soupTransformer =\n", " lambda soup:\n", " BeautifulSoup(\n", " KreisOptionsSetter().setKreisOptions(html = str(soup), options = kreisOptions),\n", " 'lxml'))\n" ] }, { "cell_type": "code", "execution_count": null, "id": "5dd8d864", "metadata": {}, "outputs": [], "source": [ "saveKreisOptions(kreisOptions)" ] }, { "cell_type": "code", "execution_count": null, "id": "43c2f826", "metadata": {}, "outputs": [], "source": [ "import os\n", "\n", "\n", "class IOUtils:\n", "\n", " def saveDictAsJson(dict, file):\n", " IOUtils.ensurePath(file)\n", " with open(file, 'w') as outfile:\n", " json.dump(dict, outfile)\n", "\n", " @staticmethod\n", " def ensurePath(file):\n", " directory = os.path.dirname(file)\n", " if not os.path.exists(directory):\n", " os.makedirs(directory)\n" ] }, { "cell_type": "code", "execution_count": null, "id": "997a4bdb", "metadata": {}, "outputs": [], "source": [ "def getIntensiveCareBeds(timeSeries, kreis = None):\n", " if kreis is not None:\n", " return timeSeries[timeSeries['Kreis'] == kreis][['date', 'betten_belegt', 'betten_frei', 'Einwohnerzahl']]\n", " else:\n", " return timeSeries.groupby('date').agg(**{\n", " 'betten_belegt': pd.NamedAgg(column = 'betten_belegt', aggfunc = 'sum'),\n", " 'betten_frei': pd.NamedAgg(column = 'betten_frei', aggfunc = 'sum'),\n", " 'Einwohnerzahl': pd.NamedAgg(column = 'Einwohnerzahl', aggfunc = 'sum')\n", " }).reset_index()" ] }, { "cell_type": "code", "execution_count": null, "id": "a97f5b2b", "metadata": {}, "outputs": [], "source": [ "import json\n", "\n", "\n", "def getAndPersistIntensiveCareBeds(timeSeries, kreis = None):\n", " intensiveCareBeds = getIntensiveCareBeds(timeSeries, kreis)\n", " display(kreis)\n", " _saveAsJson(intensiveCareBeds, _getFilename(kreis))\n", " return intensiveCareBeds\n", "\n", "\n", "def _saveAsJson(intensiveCareBeds, file):\n", " IOUtils.saveDictAsJson(\n", " {\n", " 'population': int(intensiveCareBeds.iloc[0]['Einwohnerzahl']),\n", " 'data': _intensiveCareBeds2Dict(intensiveCareBeds),\n", " },\n", " file)\n", "\n", "\n", "def _intensiveCareBeds2Dict(intensiveCareBeds):\n", " df = intensiveCareBeds[['date', 'betten_belegt', 'betten_frei']].copy()\n", " df['date'] = df['date'].dt.strftime('%Y-%m-%d')\n", " return df.to_dict(orient = \"records\")\n", "\n", "\n", "def _getFilename(kreis):\n", " return '../../docs/data/intensivstationen/intensivstationen-{suffix}.json'.format(suffix = _getSuffix(kreis))\n", "\n", "\n", "def _getSuffix(kreis):\n", " return kreis if kreis is not None else 'de'\n" ] }, { "cell_type": "code", "execution_count": null, "id": "349edd73", "metadata": {}, "outputs": [], "source": [ "getAndPersistIntensiveCareBeds(timeSeries)" ] }, { "cell_type": "code", "execution_count": null, "id": "1b97137f", "metadata": {}, "outputs": [], "source": [ "for kreis in kreisValues:\n", " getAndPersistIntensiveCareBeds(timeSeries, kreis)" ] }, { "cell_type": "code", "execution_count": null, "id": "d9d4acab", "metadata": {}, "outputs": [], "source": [ "class MedianOfFreeBedsByKreisTableFactory:\n", " \n", " def __init__(self, dataFrame):\n", " self.dataFrame = dataFrame\n", "\n", " def createMedianOfFreeBedsByKreisTable(self):\n", " self.dataFrame['free_beds_divided_by_all_beds_in_percent'] = self.dataFrame['betten_frei'] / (self.dataFrame['betten_frei'] + self.dataFrame['betten_belegt']) * 100\n", " aggregated = self.dataFrame.groupby('Kreis').agg(\n", " median_free_beds_in_percent =\n", " pd.NamedAgg(\n", " column = 'free_beds_divided_by_all_beds_in_percent',\n", " aggfunc = 'median'))\n", " return aggregated.sort_values(by = 'median_free_beds_in_percent', ascending = False)" ] }, { "cell_type": "code", "execution_count": null, "id": "a739d4d1", "metadata": {}, "outputs": [], "source": [ "from pandas.testing import assert_frame_equal\n", "import statistics\n", "\n", "class MedianOfFreeBedsByKreisTableFactoryTest(unittest.TestCase):\n", "\n", " def test_createMedianOfFreeBedsByKreisTable(self):\n", " # Given\n", " dataFrame = TestHelper.createDataFrame(\n", " columns = ['date', 'betten_frei', 'betten_belegt', 'Kreis'],\n", " data = [ ['2020-04-24', 40, 38, 'Flensburg, Stadt'],\n", " ['2020-04-24', 42, 36, 'Flensburg, Stadt'],\n", " ['2020-04-24', 44, 34, 'Flensburg, Stadt'],\n", " ['2020-04-24', 9, 10, 'Bamberg']],\n", " index = [\n", " 0,\n", " 1,\n", " 2,\n", " 3])\n", " medianOfFreeBedsByKreisTableFactory = MedianOfFreeBedsByKreisTableFactory(dataFrame)\n", " \n", " # When\n", " medianOfFreeBedsByKreisTable = medianOfFreeBedsByKreisTableFactory.createMedianOfFreeBedsByKreisTable()\n", "\n", " # Then\n", " assert_frame_equal(\n", " medianOfFreeBedsByKreisTable,\n", " TestHelper.createDataFrame(\n", " columns = ['median_free_beds_in_percent'],\n", " data = [ [statistics.median([40/(40 + 38) * 100, 42/(42 + 36) * 100, 44/(44 + 34) * 100])],\n", " [9/(9 + 10) * 100]],\n", " index = pd.Index(\n", " name = 'Kreis',\n", " data = [\n", " 'Flensburg, Stadt',\n", " 'Bamberg'\n", " ])),\n", " check_dtype = False)" ] }, { "cell_type": "code", "execution_count": null, "id": "af22cdc5", "metadata": {}, "outputs": [], "source": [ "unittest.main(argv = [''], verbosity = 2, exit = False)" ] }, { "cell_type": "code", "execution_count": null, "id": "0218cdb4", "metadata": {}, "outputs": [], "source": [ "def publish():\n", " %cd /home/frankknoll/Dokumente/Corona/projects/HowBadIsMyBatch-pages\n", " ! git add -A\n", " ! git commit -m \"updating data\"\n", " ! git push" ] }, { "cell_type": "code", "execution_count": null, "id": "5f173c2b", "metadata": {}, "outputs": [], "source": [ "publish()" ] } ], "metadata": { "kernelspec": { "display_name": "Python 3 (ipykernel)", "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": "3.9.7" } }, "nbformat": 4, "nbformat_minor": 5 }