stimmenfryslan/notebooks/Gabmap Pronunciation Tables...

158 lines
4.2 KiB
Plaintext

{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Geographical pronunciation tables\n",
"\n",
"Creates gabmap files with region centroids, percentages and pronunciations for wijken in Friesland."
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import sys\n",
"sys.path.append('..')\n",
"\n",
"import pandas\n",
"import MySQLdb\n",
"import json\n",
"import copy\n",
"\n",
"db = MySQLdb.connect(user='root', passwd='Nmmxhjgt1@', db='stimmen', charset='utf8')\n",
"\n",
"from shapely.geometry import shape, Point\n",
"\n",
"from gabmap import create_gabmap_dataframes"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"with open('../data/Friesland_wijken.geojson') as f:\n",
" regions = json.load(f)"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"# Answers to how participants state a word should be pronounced\n",
"\n",
"answers = pandas.read_sql('''\n",
"SELECT prediction_quiz_id, user_lat, user_lng, question_text, answer_text\n",
"FROM core_surveyresult as survey\n",
"INNER JOIN core_predictionquizresult as result ON survey.id = result.survey_result_id\n",
"INNER JOIN core_predictionquizresultquestionanswer as answer\n",
" ON result.id = answer.prediction_quiz_id\n",
"''', db)"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"zero_latlng_questions = {\n",
" q\n",
" for q, row in answers.groupby('question_text').agg('std').iterrows()\n",
" if row['user_lat'] == 0 and row['user_lng'] == 0\n",
"}\n",
"answers_filtered = answers[answers['question_text'].map(lambda x: x not in zero_latlng_questions)].copy()"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array(['gegaan', 'avond', 'heel', 'dag', 'bij (insect)', 'sprak (toe)',\n",
" 'oog', 'armen (lichaamsdeel)', 'kaas', 'deurtje', 'koken',\n",
" 'borst (lichaamsdeel)', 'vis', 'zaterdag', 'trein', 'geel', 'tand',\n",
" 'gezet', 'blad (aan een boom)'], dtype=object)"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"answers_filtered['question_text'].unique()"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
"answers_filtered['question_text'] = answers_filtered['question_text'].map(\n",
" lambda x: x.replace('\"', '').replace('*', ''))\n",
"\n",
"answers_filtered['answer_text'] = answers_filtered['answer_text'].map(\n",
" lambda x: x[x.find('('):x.find(')')][1:])"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [],
"source": [
"centroids, pronunciations, counts = create_gabmap_dataframes(\n",
" regions, answers_filtered,\n",
" latitude_column='user_lat', longitude_column='user_lng',\n",
" word_column='question_text', pronunciation_column='answer_text',\n",
" region_name_property='gemeente_en_wijk_naam'\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [],
"source": [
"pronunciations.to_csv('../data/Friesland_wijken_pronunciations.gabmap.tsv', sep='\\t')\n",
"counts.to_csv('../data/Friesland_wijken_pronunciation_percentages.gabmap.tsv', sep='\\t')\n",
"centroids.to_csv('../data/Friesland_wijken_centroids.gabmap.tsv', sep='\\t', columns=['longitude', 'latitude'])"
]
}
],
"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": "3.6.5"
}
},
"nbformat": 4,
"nbformat_minor": 2
}