Created
November 28, 2017 15:11
-
-
Save johanvdw/5f02dcb907578d248aa2613d98caef44 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
{ | |
"cells": [ | |
{ | |
"cell_type": "code", | |
"execution_count": 1, | |
"metadata": { | |
"collapsed": false | |
}, | |
"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>grondwaterlocatie</th>\n", | |
" <th>filternummer</th>\n", | |
" <th>meetnet</th>\n", | |
" <th>aquifer</th>\n", | |
" <th>regime</th>\n", | |
" <th>diepte_onderkant_filter</th>\n", | |
" <th>lengte_filter</th>\n", | |
" </tr>\n", | |
" </thead>\n", | |
" <tbody>\n", | |
" <tr>\n", | |
" <th>0</th>\n", | |
" <td>1-0709</td>\n", | |
" <td>1</td>\n", | |
" <td>1</td>\n", | |
" <td>0254</td>\n", | |
" <td>freatisch</td>\n", | |
" <td>8.00</td>\n", | |
" <td>2.0</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>1</th>\n", | |
" <td>1-0709</td>\n", | |
" <td>2</td>\n", | |
" <td>1</td>\n", | |
" <td>0400</td>\n", | |
" <td>niet-freatisch</td>\n", | |
" <td>52.00</td>\n", | |
" <td>2.0</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>2</th>\n", | |
" <td>1-0709</td>\n", | |
" <td>3</td>\n", | |
" <td>1</td>\n", | |
" <td>0502</td>\n", | |
" <td>niet-freatisch</td>\n", | |
" <td>71.00</td>\n", | |
" <td>2.0</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>3</th>\n", | |
" <td>1-0709</td>\n", | |
" <td>4</td>\n", | |
" <td>1</td>\n", | |
" <td>0504</td>\n", | |
" <td>niet-freatisch</td>\n", | |
" <td>87.00</td>\n", | |
" <td>2.0</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>4</th>\n", | |
" <td>1-0709</td>\n", | |
" <td>5</td>\n", | |
" <td>1</td>\n", | |
" <td>0612</td>\n", | |
" <td>niet-freatisch</td>\n", | |
" <td>108.00</td>\n", | |
" <td>2.0</td>\n", | |
" </tr>\n", | |
" </tbody>\n", | |
"</table>\n", | |
"</div>" | |
], | |
"text/plain": [ | |
" grondwaterlocatie filternummer meetnet aquifer regime \\\n", | |
"0 1-0709 1 1 0254 freatisch \n", | |
"1 1-0709 2 1 0400 niet-freatisch \n", | |
"2 1-0709 3 1 0502 niet-freatisch \n", | |
"3 1-0709 4 1 0504 niet-freatisch \n", | |
"4 1-0709 5 1 0612 niet-freatisch \n", | |
"\n", | |
" diepte_onderkant_filter lengte_filter \n", | |
"0 8.00 2.0 \n", | |
"1 52.00 2.0 \n", | |
"2 71.00 2.0 \n", | |
"3 87.00 2.0 \n", | |
"4 108.00 2.0 " | |
] | |
}, | |
"execution_count": 1, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"import xml.etree.ElementTree as ET\n", | |
"import pandas as pd\n", | |
"ET.register_namespace('kern', 'http://kern.schemas.dov.vlaanderen.be')\n", | |
"tree = ET.parse(\"../tests/data/1-0709.xml\")\n", | |
"\n", | |
"filters = tree.findall(\"./filter\")\n", | |
"\n", | |
"\n", | |
"def get_filterlengte (opbouw): \n", | |
" tot = opbouw.find(\"./onderdeel[filterelement='filter']/tot\").text\n", | |
" van = opbouw.find(\"./onderdeel[filterelement='filter']/van\").text\n", | |
" return float(tot) - float(van)\n", | |
"\n", | |
"tl = [(f.find(\"grondwaterlocatie\").text,\n", | |
" f.find(\"identificatie\").text,\n", | |
" f.find(\"meetnet\").text,\n", | |
" f.find(\"ligging/aquifer\").text,\n", | |
" f.find(\"ligging/regime\").text,\n", | |
" f.find(\"opbouw\").find(\"./onderdeel[filterelement='filter']/tot\").text,\n", | |
" get_filterlengte(f.find(\"opbouw\"))\n", | |
" ) for f in filters]\n", | |
"\n", | |
"columns = [\"grondwaterlocatie\", \"filternummer\", \"meetnet\", \n", | |
" \"aquifer\", \"regime\", \"diepte_onderkant_filter\", \"lengte_filter\"]\n", | |
"filters_df = pd.DataFrame(tl, columns = columns)\n", | |
"\n", | |
"filters_df" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 2, | |
"metadata": { | |
"collapsed": false | |
}, | |
"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>grondwaterlocatie</th>\n", | |
" <th>x</th>\n", | |
" <th>y</th>\n", | |
" </tr>\n", | |
" </thead>\n", | |
" <tbody>\n", | |
" <tr>\n", | |
" <th>0</th>\n", | |
" <td>1-0709</td>\n", | |
" <td>152249.0</td>\n", | |
" <td>200614.0</td>\n", | |
" </tr>\n", | |
" </tbody>\n", | |
"</table>\n", | |
"</div>" | |
], | |
"text/plain": [ | |
" grondwaterlocatie x y\n", | |
"0 1-0709 152249.0 200614.0" | |
] | |
}, | |
"execution_count": 2, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"gwl = tree.findall(\"./grondwaterlocatie\")\n", | |
"tg = [(g.find(\"identificatie\").text,\n", | |
" g.find(\"puntligging/xy/x\").text,\n", | |
" g.find(\"puntligging/xy/y\").text\n", | |
" ) for g in gwl]\n", | |
"\n", | |
"columns = [\"grondwaterlocatie\",\"x\",\"y\"]\n", | |
"gwl_df = pd.DataFrame(tg, columns = columns)\n", | |
"gwl_df" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 3, | |
"metadata": { | |
"collapsed": false | |
}, | |
"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>grondwaterlocatie</th>\n", | |
" <th>x</th>\n", | |
" <th>y</th>\n", | |
" <th>filternummer</th>\n", | |
" <th>meetnet</th>\n", | |
" <th>aquifer</th>\n", | |
" <th>regime</th>\n", | |
" <th>diepte_onderkant_filter</th>\n", | |
" <th>lengte_filter</th>\n", | |
" </tr>\n", | |
" </thead>\n", | |
" <tbody>\n", | |
" <tr>\n", | |
" <th>0</th>\n", | |
" <td>1-0709</td>\n", | |
" <td>152249.0</td>\n", | |
" <td>200614.0</td>\n", | |
" <td>1</td>\n", | |
" <td>1</td>\n", | |
" <td>0254</td>\n", | |
" <td>freatisch</td>\n", | |
" <td>8.00</td>\n", | |
" <td>2.0</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>1</th>\n", | |
" <td>1-0709</td>\n", | |
" <td>152249.0</td>\n", | |
" <td>200614.0</td>\n", | |
" <td>2</td>\n", | |
" <td>1</td>\n", | |
" <td>0400</td>\n", | |
" <td>niet-freatisch</td>\n", | |
" <td>52.00</td>\n", | |
" <td>2.0</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>2</th>\n", | |
" <td>1-0709</td>\n", | |
" <td>152249.0</td>\n", | |
" <td>200614.0</td>\n", | |
" <td>3</td>\n", | |
" <td>1</td>\n", | |
" <td>0502</td>\n", | |
" <td>niet-freatisch</td>\n", | |
" <td>71.00</td>\n", | |
" <td>2.0</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>3</th>\n", | |
" <td>1-0709</td>\n", | |
" <td>152249.0</td>\n", | |
" <td>200614.0</td>\n", | |
" <td>4</td>\n", | |
" <td>1</td>\n", | |
" <td>0504</td>\n", | |
" <td>niet-freatisch</td>\n", | |
" <td>87.00</td>\n", | |
" <td>2.0</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>4</th>\n", | |
" <td>1-0709</td>\n", | |
" <td>152249.0</td>\n", | |
" <td>200614.0</td>\n", | |
" <td>5</td>\n", | |
" <td>1</td>\n", | |
" <td>0612</td>\n", | |
" <td>niet-freatisch</td>\n", | |
" <td>108.00</td>\n", | |
" <td>2.0</td>\n", | |
" </tr>\n", | |
" </tbody>\n", | |
"</table>\n", | |
"</div>" | |
], | |
"text/plain": [ | |
" grondwaterlocatie x y filternummer meetnet aquifer \\\n", | |
"0 1-0709 152249.0 200614.0 1 1 0254 \n", | |
"1 1-0709 152249.0 200614.0 2 1 0400 \n", | |
"2 1-0709 152249.0 200614.0 3 1 0502 \n", | |
"3 1-0709 152249.0 200614.0 4 1 0504 \n", | |
"4 1-0709 152249.0 200614.0 5 1 0612 \n", | |
"\n", | |
" regime diepte_onderkant_filter lengte_filter \n", | |
"0 freatisch 8.00 2.0 \n", | |
"1 niet-freatisch 52.00 2.0 \n", | |
"2 niet-freatisch 71.00 2.0 \n", | |
"3 niet-freatisch 87.00 2.0 \n", | |
"4 niet-freatisch 108.00 2.0 " | |
] | |
}, | |
"execution_count": 3, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"gwl_df.merge(filters_df, on=\"grondwaterlocatie\")" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [], | |
"source": [ | |
"\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": "3.5.3" | |
} | |
}, | |
"nbformat": 4, | |
"nbformat_minor": 2 | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment