GeofabrikReader.read_shp_zip

GeofabrikReader.read_shp_zip(subregion_name, layer_names=None, feature_names=None, data_dir=None, update=False, download=True, pickle_it=False, ret_pickle_path=False, rm_extracts=False, rm_shp_zip=False, verbose=False, **kwargs)

Read a .shp.zip data file of a geographic (sub)region.

Parameters:

• subregion_name (str) – name of a geographic (sub)region (case-insensitive) that is available on Geofabrik free download server

• layer_names (str | list | None) – name of a .shp layer, e.g. ‘railways’, or names of multiple layers; if None (default), all available layers

• feature_names (str | list | None) – name of a feature, e.g. ‘rail’, or names of multiple features; if None (default), all available features

• data_dir (str | None) – directory where the .shp.zip data file is located/saved; if None, the default directory

• update (bool) – whether to check to update pickle backup (if available), defaults to False

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

• pickle_it (bool) – whether to save the .shp data as a pickle file, defaults to False

• ret_pickle_path (bool) – (when pickle_it=True) whether to return a path to the saved pickle file

• rm_extracts (bool) – whether to delete extracted files from the .shp.zip file, defaults to False

• rm_shp_zip (bool) – whether to delete the downloaded .shp.zip file, defaults to False

• verbose (bool | int) – whether to print relevant information in console as the function runs, defaults to False

Returns:

dictionary of the shapefile data, with keys and values being layer names and tabular data (in the format of geopandas.GeoDataFrame), respectively

Return type:

dict | collections.OrderedDict | None

Examples:

>>> from pydriosm.reader import GeofabrikReader
>>> from pyhelpers.dirs import delete_dir

>>> gfr = GeofabrikReader()

>>> subrgn_name = 'London'
>>> dat_dir = "tests\osm_data"

>>> london_shp_data = gfr.read_shp_zip(
...     subregion_name=subrgn_name, data_dir=dat_dir, download=False, verbose=True)
The .shp.zip file for "Greater London" is not found.

>>> # Set `download=True`
>>> london_shp_data = gfr.read_shp_zip(
...     subregion_name=subrgn_name, data_dir=dat_dir, download=True, verbose=True)
Downloading "greater-london-latest-free.shp.zip"
    to "tests\osm_data\greater-london\" ... Done.
Extracting "tests\osm_data\greater-london\greater-london-latest-free.shp.zip"
    to "tests\osm_data\greater-london\greater-london-latest-free-shp\" ... Done.
Reading the shapefile(s) at
    "tests\osm_data\greater-london\greater-london-latest-free-shp\" ... Done.
>>> type(london_shp_data)
collections.OrderedDict
>>> list(london_shp_data.keys())
['buildings',
 'landuse',
 'natural',
 'places',
 'pofw',
 'pois',
 'railways',
 'roads',
 'traffic',
 'transport',
 'water',
 'waterways']

>>> # Data of the 'railways' layer
>>> london_shp_railways = london_shp_data['railways']
>>> london_shp_railways.head()
   osm_id  code  ...                                        coordinates shape_type
0   30804  6101  ...  [(0.0048644, 51.6279262), (0.0061979, 51.62926...          3
1  101298  6103  ...  [(-0.2249906, 51.493682), (-0.2251678, 51.4945...          3
2  101486  6103  ...  [(-0.2055497, 51.5195429), (-0.2051377, 51.519...          3
3  101511  6101  ...  [(-0.2119027, 51.5241906), (-0.2108059, 51.523...          3
4  282898  6103  ...  [(-0.1862586, 51.6159083), (-0.1868721, 51.613...          3
[5 rows x 9 columns]

>>> # Read data of the 'transport' layer only from the original .shp.zip file
>>> # (and delete any extracts)
>>> subrgn_layer = 'transport'

>>> # Set `rm_extracts=True` to remove the extracts
>>> london_shp_transport = gfr.read_shp_zip(
...     subregion_name=subrgn_name, layer_names=subrgn_layer, data_dir=dat_dir,
...     rm_extracts=True, verbose=True)
Reading the shapefile(s) at
    "tests\osm_data\greater-london\greater-london-latest-free-shp\" ... Done.
Deleting the extracts "tests\osm_data\greater-london\greater-london-latest-free-sh...
>>> type(london_shp_transport)
collections.OrderedDict
>>> list(london_shp_transport.keys())
['transport']
>>> london_shp_transport_ = london_shp_transport['transport']
>>> london_shp_transport_.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]

>>> # Read data of only the 'bus_stop' feature (in the 'transport' layer)
>>> # from the original .shp.zip file (and delete any extracts)
>>> feat_name = 'bus_stop'
>>> london_bus_stop = gfr.read_shp_zip(
...     subregion_name=subrgn_name, layer_names=subrgn_layer, feature_names=feat_name,
...     data_dir=dat_dir, rm_extracts=True, verbose=True)
Extracting the following layer(s):
    'transport'
    from "tests\osm_data\greater-london\greater-london-latest-free.shp.zip"
      to "tests\osm_data\greater-london\greater-london-latest-free-shp\" ... Done.
Reading the shapefile(s) at
    "tests\osm_data\greater-london\greater-london-latest-free-shp\" ... Done.
Deleting the extracts "tests\osm_data\greater-london\greater-london-latest-free-sh...
>>> type(london_bus_stop)
collections.OrderedDict
>>> list(london_bus_stop.keys())
['transport']

>>> fclass = london_bus_stop['transport'].fclass.unique()
>>> fclass
array(['bus_stop'], dtype=object)

>>> # Read multiple features of multiple layers
>>> # (and delete both the original .shp.zip file and extracts)
>>> subrgn_layers = ['traffic', 'roads']
>>> feat_names = ['parking', 'trunk']
>>> london_shp_tra_roa_par_tru = gfr.read_shp_zip(
...     subregion_name=subrgn_name, layer_names=subrgn_layers, feature_names=feat_names,
...     data_dir=dat_dir, rm_extracts=True, rm_shp_zip=True, verbose=True)
Extracting the following layer(s):
    'traffic'
    'roads'
    from "tests\osm_data\greater-london\greater-london-latest-free.shp.zip"
      to "tests\osm_data\greater-london\greater-london-latest-free-shp\" ... Done.
Reading the shapefile(s) at
    "tests\osm_data\greater-london\greater-london-latest-free-shp\" ... Done.
Deleting the extracts "tests\osm_data\greater-london\greater-london-latest-free-sh...
Deleting "tests\osm_data\greater-london\greater-london-latest-free.shp.zip" ... Done.
>>> type(london_shp_tra_roa_par_tru)
collections.OrderedDict
>>> list(london_shp_tra_roa_par_tru.keys())
['traffic', 'roads']

>>> # Data of the 'traffic' layer
>>> london_shp_tra_roa_par_tru['traffic'].head()
    osm_id  code  ...                                        coordinates shape_type
0  2956081  5260  ...  [(-0.0218269, 51.4369515), (-0.020097, 51.4372...          5
1  2956183  5260  ...  [(-0.0224697, 51.4452646), (-0.0223272, 51.445...          5
2  2956184  5260  ...  [(-0.0186703, 51.444221), (-0.0185442, 51.4447...          5
3  2956185  5260  ...  [(-0.0189846, 51.4481958), (-0.0189417, 51.448...          5
4  2956473  5260  ...  [(-0.0059602, 51.4579088), (-0.0058695, 51.457...          5
[5 rows x 6 columns]

>>> # Data of the 'roads' layer
>>> london_shp_tra_roa_par_tru['roads'].head()
   osm_id  code  ...                                        coordinates shape_type
7    1200  5112  ...  [(-0.2916285, 51.5160418), (-0.2915517, 51.516...          3
8    1201  5112  ...  [(-0.2925582, 51.5300857), (-0.2925916, 51.529...          3
9    1202  5112  ...  [(-0.2230893, 51.5735075), (-0.2228416, 51.573...          3
10   1203  5112  ...  [(-0.139105, 51.6101568), (-0.1395372, 51.6100...          3
11   1208  5112  ...  [(-0.1176027, 51.6124616), (-0.1169584, 51.612...          3
[5 rows x 12 columns]

>>> # Delete the example data and the test data directory
>>> delete_dir(dat_dir, verbose=True)
To delete the directory "tests\osm_data\" (Not empty)
? [No]|Yes: yes
Deleting "tests\osm_data\" ... Done.