import os
from lib.geolib_helper import get_shp_filepath, load_normalize_gov_shp_data
CURRENT_DIR = os.path.dirname(os.path.abspath(__file__))
BASE_DIR = os.path.dirname(CURRENT_DIR)
if __name__ == '__main__':
data_dir = os.path.join(BASE_DIR, 'data')
area_dimension_table_filepath = os.path.join(data_dir,
'area_dimension_table.csv')
village_shp_filepath = get_shp_filepath(
os.path.join(data_dir, 'taiwan_twd97_map_data_village'))
data_mart_dirpath = os.path.join(data_dir, 'aggregated-data_mart')
output_village_filepath = os.path.join(
data_mart_dirpath, 'simplified_taipei_village.geojson')
output_township_filepath = os.path.join(
data_mart_dirpath, 'simplified_taipei_township.geojson')
village_gpd = load_normalize_gov_shp_data(village_shp_filepath)
taipei_village_gpd = village_gpd[village_gpd['county_chinese_name'] ==
'臺北市']
taipei_village_gpd.set_index('village_code', drop=False, inplace=True)
taipei_township_gpd = taipei_village_gpd[['township_code', 'geometry'
]].dissolve(by='township_code')
# select tolerance of 0.05km, 1 point is about 111 km
tolerance = 0.05 / 111
import os
import pandas as pd
pd.set_option("mode.chained_assignment", None)
from lib.geolib_helper import get_shp_filepath, load_normalize_gov_shp_data
CURRENT_DIR = os.path.dirname(os.path.abspath(__file__))
BASE_DIR = os.path.dirname(CURRENT_DIR)
if __name__ == '__main__':
data_dir = os.path.join(BASE_DIR, 'data')
village_shp_filepath = get_shp_filepath(os.path.join(BASE_DIR, 'data', 'taiwan_twd97_map_data_village'))
filename = 'taipei_village_centroid_distance_km_matrix.csv'
output_filepath_list = [
os.path.join(CURRENT_DIR, 'data', filename),
os.path.join(data_dir, 'normalized-data_warehouse', filename)
]
output_filepath = os.path.join(CURRENT_DIR, 'data', 'taipei_village_centroid_distance_km_matrix.csv')
villages_shp_gdp = load_normalize_gov_shp_data(village_shp_filepath)
taipei_area_only = villages_shp_gdp[villages_shp_gdp['county_chinese_name'] == '臺北市']
taipei_area_only.set_index('village_code', inplace=True)
taipei_area_only['centroid'] = taipei_area_only.centroid
distance_km_matrix_dict = {}
for index, row in taipei_area_only.iterrows():
county_data_dirpah = os.path.join(data_dir, 'taiwan_twd97_map_data_county')
town_data_dirpath = os.path.join(data_dir,
'taiwan_twd97_map_data_township')
village_data_dirpath = os.path.join(data_dir,
'taiwan_twd97_map_data_village')
filename = 'area_dimension_table.csv'
output_filepath_list = [
os.path.join(CURRENT_DIR, 'data', filename),
os.path.join(
data_dir, 'normalized-data_warehouse', filename
), # to make things easier to lookup for non-technical user
]
county_shp = gpd.read_file(get_shp_filepath(county_data_dirpah))
town_shp = gpd.read_file(get_shp_filepath(town_data_dirpath))
village_shp = gpd.read_file(get_shp_filepath(village_data_dirpath))
# delete geometry data, make into simple df column with dimension data
county_df = county_shp.drop('geometry', axis=1)
town_df = town_shp.drop('geometry', axis=1)
village_df = village_shp.drop('geometry', axis=1)
# fix encoding on some bad chinese character encoding
change_on_multiple_columns(town_df, lambda x: 'name' in x.casefold(),
try_fix_encoding)
change_on_multiple_columns(county_df, lambda x: 'name' in x.casefold(),
try_fix_encoding)
change_on_multiple_columns(village_df, lambda x: 'name' in x.casefold(),
try_fix_encoding)