def create_index(
vdf: vDataFrame,
gid: str,
g: str,
index: str,
overwrite: bool = False,
max_mem_mb: int = 256,
skip_nonindexable_polygons: bool = False,
):
"""
---------------------------------------------------------------------------
Creates a spatial index on a set of polygons to speed up spatial
intersection with a set of points.
Parameters
----------
vdf: vDataFrame
vDataFrame to use to compute the spatial join.
gid: str
Name of an integer column that uniquely identifies the polygon.
The gid cannot be NULL.
g: str
Name of a geometry or geography (WGS84) column or expression that
contains polygons and multipolygons. Only polygon and multipolygon
can be indexed. Other shape types are excluded from the index.
index: str
Name of the index.
overwrite: bool, optional
BOOLEAN value that specifies whether to overwrite the index, if an
index exists.
max_mem_mb: int, optional
A positive integer that assigns a limit to the amount of memory in
megabytes that create_index can allocate during index construction.
skip_nonindexable_polygons: bool, optional
In rare cases, intricate polygons (for instance, with too high
resolution or anomalous spikes) cannot be indexed. These polygons
are considered non-indexable.
When set to False, non-indexable polygons cause the index creation
to fail. When set to True, index creation can succeed by excluding
non-indexable polygons from the index.
Returns
-------
tablesample
An object containing the result. For more information, see
utilities.tablesample.
"""
check_types([
("vdf", vdf, [vDataFrame]),
("gid", gid, [str]),
("index", index, [str]),
("g", g, [str]),
("overwrite", overwrite, [bool]),
("max_mem_mb", max_mem_mb, [int]),
("skip_nonindexable_polygons", skip_nonindexable_polygons, [bool]),
])
vdf.are_namecols_in([gid, g])
gid, g = vdf.format_colnames([gid, g])
query = """SELECT
STV_Create_Index({0}, {1}
USING PARAMETERS
index='{2}',
overwrite={3} ,
max_mem_mb={4},
skip_nonindexable_polygons={5})
OVER()
FROM {6}""".format(
gid,
g,
index,
overwrite,
max_mem_mb,
skip_nonindexable_polygons,
vdf.__genSQL__(),
)
return to_tablesample(query)
def intersect(vdf: vDataFrame,
index: str,
gid: str,
g: str = "",
x: str = "",
y: str = ""):
"""
---------------------------------------------------------------------------
Spatially intersects a point or points with a set of polygons.
Parameters
----------
vdf: vDataFrame
vDataFrame to use to compute the spatial join.
index: str
Name of the index.
gid: str
An integer column or integer that uniquely identifies the spatial
object(s) of g or x and y.
g: str, optional
A geometry or geography (WGS84) column that contains points.
The g column can contain only point geometries or geographies.
x: str, optional
x-coordinate or longitude.
y: str, optional
y-coordinate or latitude.
Returns
-------
vDataFrame
object containing the result of the intersection.
"""
check_types([
("vdf", vdf, [vDataFrame]),
("gid", gid, [str]),
("g", g, [str]),
("x", x, [str]),
("y", y, [str]),
("index", index, [str]),
])
vdf.are_namecols_in([gid])
table = vdf.__genSQL__()
if g:
vdf.are_namecols_in(g)
g = vdf.format_colnames(g)
query = (f"(SELECT STV_Intersect({gid}, {g} USING PARAMETERS"
f" index='{index}') OVER (PARTITION BEST) AS "
f"(point_id, polygon_gid) FROM {table}) x")
elif x and y:
vdf.are_namecols_in([x, y])
x, y = vdf.format_colnames([x, y])
query = (f"(SELECT STV_Intersect({gid}, {x}, {y} USING PARAMETERS"
f" index='{index}') OVER (PARTITION BEST) AS "
f"(point_id, polygon_gid) FROM {table}) x")
else:
raise ParameterError("Either 'x' and 'y' or 'g' must not be empty.")
return vDataFrameSQL(query)