Add Getting Data section with Ibis #104
Description
Hello, I work on Ibis and with the default backend (duckdb) we can query overture maps very easily.
Would you be open to a PR contribution to your docs, to add this to the "Getting Data Section"? I can work on multiple examples, but to start it would be something like this.
# install instructions
$ pip install 'ibis-framework[duckdb,geospatial]'import ibis
from ibis import _
# by default it gets duckdb backend
con = ibis.get_backend()
# example of how to get infrastructure data of `subtype="power"` for a `bbox` around Washington DC
# and selecting only a few columns
url = "s3://overturemaps-us-west-2/release/2024-07-22.0/theme=base/type=infrastructure/*"
t = con.read_parquet(url, table_name="infra-power-dc")
# so far no execution
expr = t.filter(_.bbox.xmin > -77.119795,
_.bbox.xmax < -76.909366,
_.bbox.ymin > 38.791631,
_.bbox.ymax < 38.995968,
_.subtype=="power"
).select(["names",
"geometry",
"sources",
"class"])
con.to_parquet(expr, "infra-power-dc-ibis.parquet")
t_power_dc = con.read_parquet("infra-power-dc-ibis.parquet")
# turn interactive mode to preview data
ibis.options.interactive = True
# inspect data where `class=="power_line", and select only few columns
t_infra.filter(t_infra["class"]=="power_line")["names", "geometry","class"]
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┓
┃ names ┃ geometry ┃ class ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━┩
│ struct<primary: string, common: map<string, string>, rules: array<struct<varian… │ geospatial:geometry │ string │
├──────────────────────────────────────────────────────────────────────────────────┼──────────────────────────────────────────────────────────────────────────────────┼────────────┤
│ NULL │ <LINESTRING (-77.113 38.805, -77.113 38.805, -77.112 38.806, -77.111 38.806,...> │ power_line │
│ NULL │ <LINESTRING (-77.11 38.818, -77.11 38.818, -77.111 38.818, -77.112 38.819, -...> │ power_line │
│ NULL │ <LINESTRING (-77.098 38.848, -77.097 38.848, -77.097 38.848, -77.097 38.848,...> │ power_line │
│ {'primary': '230kV transmission line', 'common': None, ... +1} │ <LINESTRING (-77.097 38.848, -77.096 38.848, -77.095 38.847, -77.094 38.847,...> │ power_line │
│ {'primary': '230kV transmission line', 'common': None, ... +1} │ <LINESTRING (-77.059 38.796, -77.061 38.796)> │ power_line │
│ NULL │ <LINESTRING (-77.06 38.799, -77.06 38.799, -77.061 38.797, -77.061 38.796)> │ power_line │
│ {'primary': '230kV transmission line', 'common': None, ... +1} │ <LINESTRING (-77.057 38.795, -77.059 38.796)> │ power_line │
│ {'primary': '230kV transmission line', 'common': None, ... +1} │ <LINESTRING (-77.055 38.797, -77.055 38.796, -77.055 38.796, -77.055 38.795,...> │ power_line │
│ {'primary': '230kV transmission line', 'common': None, ... +1} │ <LINESTRING (-77.055 38.797, -77.055 38.796, -77.055 38.795, -77.057 38.795)> │ power_line │
│ {'primary': '230kV transmission line', 'common': None, ... +1} │ <LINESTRING (-77.087 38.844, -77.086 38.844, -77.085 38.844, -77.084 38.844,...> │ power_line │
│ … │ … │ … │
└──────────────────────────────────────────────────────────────────────────────────┴──────────────────────────────────────────────────────────────────────────────────┴────────────┘