geowatch.cli.stac_search module¶

Performs the stac search to create the .input file needed for geowatch.cli.queue_cli.prepare_ta2_dataset.

SeeAlso:: ../demo/demo_region.py ../stac/stac_search_builder.py

CommandLine

# Create a demo region file
xdoctest geowatch.demo.demo_region demo_khq_region_fpath

DATASET_SUFFIX=DemoKHQ-2022-06-10-V2
DEMO_DPATH=$HOME/.cache/geowatch/demo/datasets

REGION_FPATH="$HOME/.cache/geowatch/demo/annotations/KHQ_R001.geojson"
SITE_GLOBSTR="$HOME/.cache/geowatch/demo/annotations/KHQ_R001_sites/*.geojson"

START_DATE=$(jq -r '.features[] | select(.properties.type=="region") | .properties.start_date' "$REGION_FPATH")
END_DATE=$(jq -r '.features[] | select(.properties.type=="region") | .properties.end_date' "$REGION_FPATH")
REGION_ID=$(jq -r '.features[] | select(.properties.type=="region") | .properties.region_id' "$REGION_FPATH")
SEARCH_FPATH=$DEMO_DPATH/stac_search.json
RESULT_FPATH=$DEMO_DPATH/all_sensors_kit/${REGION_ID}.input

mkdir -p "$DEMO_DPATH"

# Create the search json wrt the sensors and processing level we want
python -m geowatch.stac.stac_search_builder \
    --start_date="$START_DATE" \
    --end_date="$END_DATE" \
    --cloud_cover=40 \
    --sensors=sentinel-2-l2a \
    --out_fpath "$SEARCH_FPATH"
cat "$SEARCH_FPATH"

# Delete this to prevent duplicates
rm -f "$RESULT_FPATH"
# Create the .input file
python -m geowatch.cli.stac_search \
    -rf "$REGION_FPATH" \
    -sj "$SEARCH_FPATH" \
    -m area \
    --verbose 2 \
    -o "${RESULT_FPATH}"

# Construct the TA2-ready dataset
python -m geowatch.cli.queue_cli.prepare_ta2_dataset \
    --dataset_suffix=$DATASET_SUFFIX \
    --s3_fpath "${RESULT_FPATH}" \
    --collated False \
    --dvc_dpath="$DEMO_DPATH" \
    --aws_profile=iarpa \
    --region_globstr="$REGION_FPATH" \
    --site_globstr="$SITE_GLOBSTR" \
    --fields_workers=8 \
    --convert_workers=8 \
    --align_workers=26 \
    --cache=0 \
    --ignore_duplicates=0 \
    --visualize=True \
    --backend=serial --run=0

CommandLine

# Alternate invocation
# Create a demo region file
xdoctest geowatch.demo.demo_region demo_khq_region_fpath

DATASET_SUFFIX=DemoKHQ-2022-06-10-V3
DEMO_DPATH=$HOME/.cache/geowatch/demo/datasets
REGION_FPATH="$HOME/.cache/geowatch/demo/annotations/KHQ_R001.geojson"
REGION_ID=$(jq -r '.features[] | select(.properties.type=="region") | .properties.region_id' "$REGION_FPATH")
RESULT_FPATH=$DEMO_DPATH/all_sensors_kit/${REGION_ID}.input

mkdir -p "$DEMO_DPATH"

# Define SMART_STAC_API_KEY
source "$HOME"/code/watch/secrets/secrets

# Delete this to prevent duplicates
rm -f "$RESULT_FPATH"
# Create the .input file
python -m geowatch.cli.stac_search \
    --region_file "$REGION_FPATH" \
    --api_key=env:SMART_STAC_API_KEY \
    --search_json "auto" \
    --cloud_cover 10 \
    --sensors=TA1-L8-ACC \
    --mode area \
    --verbose 2 \
    --outfile "${RESULT_FPATH}"

CommandLine

# Alternate invocation
# Create a demo region file

DVC_DPATH=$(geowatch_dvc --tags="phase2_data" --hardware=auto)
REGION_FPATH=$DVC_DPATH/annotations/region_models/BR_R005.geojson

# Define SMART_STAC_API_KEY
source "$HOME"/code/watch/secrets/secrets

# Delete this to prevent duplicates
rm -f "$RESULT_FPATH"
# Create the .input file
python -m geowatch.cli.stac_search \
    --region_file "$REGION_FPATH" \
    --api_key=env:SMART_STAC_API_KEY \
    --search_json "auto" \
    --cloud_cover 100 \
    --sensors=TA1-S2-L8-WV-PD-ACC \
    --mode area \
    --verbose 2 \
    --outfile "./result.input"

###
### - Debug case

DVC_DPATH=$(geowatch_dvc --tags="phase2_data" --hardware=auto)

# Load SMART_STAC_API_KEY
source "$HOME"/code/watch/secrets/secrets

python -m geowatch.cli.stac_search \
    --region_file "$DVC_DPATH/annotations/region_models/US_R007.geojson" \
    --search_json "auto" \
    --cloud_cover "0" \
    --sensors "TA1-S2-L8-WV-PD-ACC-1" \
    --api_key "env:SMART_STAC_API_KEY" \
    --max_products_per_region "None" \
    --append_mode=False \
    --mode area \
    --verbose 100000 \
    --outfile "./test_result.input"

class geowatch.cli.stac_search.StacSearchConfig(*args, **kwargs)[source]¶

Bases: DataConfig

Execute a STAC query

Valid options: []

Parameters:

*args – positional arguments for this data config
**kwargs – keyword arguments for this data config

default = {'allow_failure': <Value(False)>, 'api_key': <Value('env:SMART_STAC_API_KEY')>, 'append_mode': <Value(True)>, 'cloud_cover': <Value(10)>, 'max_products_per_region': <Value(None)>, 'mode': <Value('id')>, 'outfile': <Value(None)>, 'query_workers': <Value(0)>, 'region_file': <Value(None)>, 'region_globstr': <Value(None)>, 's3_dest': <Value(None)>, 'search_json': <Value(None)>, 'sensors': <Value('L2')>, 'site_file': <Value(None)>, 'verbose': <Value(2)>}¶

geowatch.cli.stac_search.main(cmdline=True, **kwargs)[source]¶

Execute the stac search and write the input file

Example

>>> # xdoctest: +REQUIRES(env:SLOW_DOCTEST)
>>> # xdoctest: +REQUIRES(--network)
>>> from geowatch.cli.stac_search import *  # NOQA
>>> from geowatch.demo import demo_region
>>> from geowatch.stac import stac_search_builder
>>> from kwgis.utils import util_gis
>>> import ubelt as ub
>>> dpath = ub.Path.appdir('geowatch/tests/test-stac-search').ensuredir()
>>> search_fpath = dpath / 'stac_search.json'
>>> region_fpath = demo_region.demo_khq_region_fpath()
>>> region = util_gis.load_geojson(region_fpath)
>>> result_fpath = dpath / 'demo.input'
>>> start_date = region['start_date'].iloc[0]
>>> end_date = region['end_date'].iloc[0]
>>> stac_search_builder.main(
>>>     cmdline=0,
>>>     start_date=start_date,
>>>     end_date=end_date,
>>>     cloud_cover=10,
>>>     out_fpath=search_fpath,
>>> )
>>> kwargs = {
>>>     'region_file': str(region_fpath),
>>>     'search_json': str(search_fpath),
>>>     'mode': 'area',
>>>     'verbose': 2,
>>>     'outfile': str(result_fpath),
>>> }
>>> result_fpath.delete()
>>> cmdline = 0
>>> main(cmdline=cmdline, **kwargs)
>>> # results are in the
>>> from geowatch.cli.baseline_framework_ingress import read_input_stac_items
>>> items = read_input_stac_items(result_fpath)
>>> len(items)
>>> for item in items:
>>>     print(item['properties']['eo:cloud_cover'])
>>>     print(item['properties']['datetime'])

class geowatch.cli.stac_search.StacSearcher(logger=None)[source]¶

Bases: object

Example

>>> # xdoctest: +REQUIRES(env:GEOWATCH_ENABLE_NETWORK_TESTS)
>>> # xdoctest: +REQUIRES(env:SLOW_DOCTEST)
>>> from geowatch.cli.stac_search import *  # NOQA
>>> import tempfile
>>> provider = "https://earth-search.aws.element84.com/v0"
>>> geom = {'type': 'Polygon',
>>>         'coordinates': [[[54.960669, 24.782276],
>>>                          [54.960669, 25.03516],
>>>                          [55.268326, 25.03516],
>>>                          [55.268326, 24.782276],
>>>                          [54.960669, 24.782276]]]}
>>> collections = ["sentinel-2-l2a"]
>>> start = '2020-03-14'
>>> end = '2020-05-04'
>>> query = {}
>>> headers = {}
>>> self = StacSearcher()
>>> features = self.by_geometry(provider, geom, collections, start_date, end_date,
>>>                  query, headers)
>>> print('features = {}'.format(ub.urepr(features, nl=1)))

by_geometry(provider, geom, collections, start, end, query, headers, max_products_per_region=None, verbose=1)[source]¶

by_id(provider, collections, stac_id, outfile, query, headers)[source]¶

geowatch.cli.stac_search.area_query(region_fpath, search_json, searcher, temp_dir, config, logger, verbose=1)[source]¶