GeofabrikReader.merge_subregion_layer_shp

GeofabrikReader.merge_subregion_layer_shp(subregion_names, layer_name, data_dir=None, method='pyshp', update=False, download_confirmation_required=True, rm_zip_extracts=True, merged_shp_dir=None, rm_shp_temp=True, verbose=False, ret_merged_shp_path=False)

Merge shapefiles for a specific layer of two or multiple geographic regions.

Parameters

  • subregion_names (list) – names of geographic region (case-insensitive) that is available on Geofabrik free download server

  • layer_name (str) – name of a layer (e.g. ‘railways’)

  • method (str) – the method used to merge/save shapefiles; options include: 'pyshp' (default) and 'geopandas' (or 'gpd') if method='geopandas', this function relies on geopandas.GeoDataFrame.to_file(); otherwise, it by default uses shapefile.Writer()

  • update (bool) – whether to update the source .shp.zip files, defaults to False

  • download_confirmation_required (bool) – whether to ask for confirmation before starting to download a file, defaults to True

  • data_dir (str or None) – directory where the .shp.zip data files are located/saved; if None (default), the default directory

  • rm_zip_extracts (bool) – whether to delete the extracted files, defaults to False

  • rm_shp_temp (bool) – whether to delete temporary layer files, defaults to False

  • merged_shp_dir (str or None) – if None (default), use the layer name as the name of the folder where the merged .shp files will be saved

  • verbose (bool or int) – whether to print relevant information in console, defaults to False

  • ret_merged_shp_path (bool) – whether to return the path to the merged .shp file, defaults to False

Returns

the path to the merged file when ret_merged_shp_path=True

Return type

list or str

Examples:

>>> import os
>>> from pyhelpers.dir import cd, delete_dir
>>> from pydriosm.reader import GeofabrikReader, read_shp_file

>>> geofabrik_reader = GeofabrikReader()

>>> # -- Example 1 ---------------------------------------------------------------

>>> # To merge 'railways' of Greater Manchester and West Yorkshire
>>> sr_names = ['Manchester', 'West Yorkshire']
>>> lyr_name = 'railways'
>>> dat_dir = "tests"

>>> path_to_merged_shp_file = geofabrik_reader.merge_subregion_layer_shp(
...     sr_names, lyr_name, dat_dir, verbose=True, ret_merged_shp_path=True)
Downloading "greater-manchester-latest-free.shp.zip" to "tests\" ... Done.
Downloading "west-yorkshire-latest-free.shp.zip" to "tests\" ... Done.
Extracting the following layer(s):
    'railways'
from "tests\greater-manchester-latest-free.shp.zip" ...
to "tests\greater-manchester-latest-free-shp\"
Done.
Extracting the following layer(s):
    'railways'
from "tests\west-yorkshire-latest-free.shp.zip" ...
to "tests\west-yorkshire-latest-free-shp\"
Done.
Merging the following shapefiles:
    "greater-manchester_gis_osm_railways_free_1.shp"
    "west-yorkshire_gis_osm_railways_free_1.shp"
In progress ... Done.
Find the merged shapefile at "tests\greater-manchester_west-yorkshire_railways\".

>>> print(os.path.relpath(path_to_merged_shp_file))
tests\...\greater-manchester_west-yorkshire_railways.shp

>>> # Read the merged data
>>> manchester_yorkshire_railways_shp = read_shp_file(path_to_merged_shp_file)

>>> manchester_yorkshire_railways_shp.head()
    osm_id  code  ...                                        coordinates shape_type
0   928999  6101  ...  [(-2.2844594, 53.4802681), (-2.2851997, 53.480...          3
1   929904  6101  ...  [(-2.2919566, 53.4619298), (-2.2924877, 53.461...          3
2   929905  6102  ...  [(-2.2794048, 53.4605819), (-2.2799773, 53.460...          3
3  3663332  6102  ...  [(-2.2382517, 53.4818141), (-2.2381708, 53.481...          3
4  3996086  6101  ...  [(-2.6003908, 53.4602313), (-2.6009371, 53.459...          3
[5 rows x 9 columns]

>>> # Delete the merged files
>>> delete_dir(os.path.dirname(path_to_merged_shp_file), verbose=True)
The directory "tests\greater-manchester_west-yorkshire_railways" is not empty.
Confirmed to delete it? [No]|Yes: yes
Deleting "tests\greater-manchester_west-yorkshire_railways" ... Done.

>>> # Delete the downloaded .shp.zip data files
>>> os.remove(cd(dat_dir, "greater-manchester-latest-free.shp.zip"))
>>> os.remove(cd(dat_dir, "west-yorkshire-latest-free.shp.zip"))

>>> # -- Example 2 ---------------------------------------------------------------

>>> # To merge 'transport' of Greater London, Kent and Surrey

>>> sr_names = ['London', 'Kent', 'Surrey']
>>> lyr_name = 'transport'

>>> path_to_merged_shp_file = geofabrik_reader.merge_subregion_layer_shp(
...     sr_names, lyr_name, dat_dir, verbose=True, ret_merged_shp_path=True)
To download .shp.zip data of the following geographic region(s):
    Greater London
    Kent
    Surrey
? [No]|Yes: yes
Downloading "greater-london-latest-free.shp.zip" to "tests\" ... Done.
Downloading "kent-latest-free.shp.zip" to "tests\" ... Done.
Downloading "surrey-latest-free.shp.zip" to "tests\" ... Done.
Extracting the following layer(s):
    'transport'
from "tests\greater-london-latest-free.shp.zip" ...
to "tests\greater-london-latest-free-shp\"
Done.
Extracting the following layer(s):
    'transport'
from "tests\kent-latest-free.shp.zip" ...
to "tests\kent-latest-free-shp\"
Done.
Extracting the following layer(s):
    'transport'
from "tests\surrey-latest-free.shp.zip" ...
to "tests\surrey-latest-free-shp\"
Done.
Merging the following shapefiles:
    "greater-london_gis_osm_transport_a_free_1.shp"
    "greater-london_gis_osm_transport_free_1.shp"
    "kent_gis_osm_transport_a_free_1.shp"
    "kent_gis_osm_transport_free_1.shp"
    "surrey_gis_osm_transport_a_free_1.shp"
    "surrey_gis_osm_transport_free_1.shp"
In progress ... Done.
Find the merged .shp file(s) at "tests\greater-london_kent_surrey_transport\".

>>> print(os.path.relpath(path_to_merged_shp_file))
tests\...\greater-london_kent_surrey_transport.shp

>>> # Read the merged shapefile
>>> merged_transport_shp = read_shp_file(path_to_merged_shp_file)

>>> merged_transport_shp.head()
     osm_id  ...  shape_type
0   5077928  ...           5
1   8610280  ...           5
2  15705264  ...           5
3  23077379  ...           5
4  24016945  ...           5
[5 rows x 6 columns]

>>> # Delete the merged files
>>> delete_dir(os.path.dirname(path_to_merged_shp_file), verbose=True)
The directory "tests\greater-london_kent_surrey_transport\" is not empty.
Confirmed to delete it? [No]|Yes: >? yes
Deleting "tests\greater-london_kent_surrey_transport\" ... Done.

>>> # Delete the downloaded .shp.zip data files
>>> os.remove(cd(dat_dir, "greater-london-latest-free.shp.zip"))
>>> os.remove(cd(dat_dir, "kent-latest-free.shp.zip"))
>>> os.remove(cd(dat_dir, "surrey-latest-free.shp.zip"))