cboettig

import ibis
from ibis import _
con = ibis.duckdb.connect()

# example query, could be anything
subset = (gbif
  .filter(_["class"] == "Aves")
  .rename(hex = "h8")
  .group_by(_.hex)
  .agg(n = _.count())

cboettig

To solve

ImportError: cannot import name 'types' from 'geoarrow' (unknown location), 

install geoarrow-types.

ibis may also need geoarrow-cto work with geoparquet now.

cboettig

import os
from langchain_openai import ChatOpenAI
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.runnables import ConfigurableField
from langchain_core.tools import tool
from langchain.agents import create_tool_calling_agent, AgentExecutor
@tool
def multiply(x: float, y: float) -> float:
    """Multiply 'x' times 'y'."""
    return x * y

cboettig

import ibis
con = ibis.duckdb.connect()

con.raw_sql(f'''
CREATE OR REPLACE SECRET secret (
    TYPE S3,
    ENDPOINT 'sdsc.osn.xsede.org',
    URL_STYLE 'path'

);

cboettig

import ibis
from ibis import _
con = ibis.duckdb.connect(extensions=["spatial"])


## Read a geospatial file other than parquet (via GDAL)
rivers_geojson = "https://data.source.coop/cboettig/us-rivers/nhd_flowline_national.geojson"
rivers = con.read_geo(rivers_geojson)

## Read geoparquet

cboettig

conn.sql('''
SELECT *
FROM information_schema.columns 
WHERE table_name = 'families';
'''
)

cboettig

# Be sure to put a copy of the license file in "$HOME/gurobi.lic" for this to work!!

# Download the release
wget https://packages.gurobi.com/11.0/gurobi11.0.1_linux64.tar.gz # or path to most recent linux_64 download from https://www.gurobi.com/downloads/gurobi-software/

# extract:
tar -xvf gurobi*_linux64.tar.gz

# Set environmental variables

cboettig

import xarray as xr
import rasterio
import rioxarray
import earthaccess
import os
from timebudget import timebudget
from pathlib import Path

# assumes we have a ~/.netrc created
cookies = os.path.expanduser("~/.urs_cookies")

cboettig

## Using Forecasts data, ~ 300+ GB in many very small partitions!

uri <- "s3://anonymous@bio230014-bucket01/neon4cast-forecasts/parquet/aquatics?endpoint_override=sdsc.osn.xsede.org"
bench::bench_time(df <- duckdbfs::open_dataset(uri))
# process    real 
#   1.23m   4.91m

bench::bench_time( df <- arrow::open_dataset(uri))
# process    real 
#  4.21m  32.46m 

cboettig

## examples
# requires GDAL >= 3.6
edl_set_token()
library(stars)
url <- "https://data.lpdaac.earthdatacloud.nasa.gov/lp-prod-protected/HLSL30.020/HLS.L30.T56JKT.2023246T235950.v2.0/HLS.L30.T56JKT.2023246T235950.v2.0.SAA.tif"
x <- read_stars(paste0("/vsicurl/",url))
plot(x)