loose the limit of only processing the NADIR scenes

CHANGELOG.md

@@ -4,6 +4,10 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [0.4.0]
+
+### Fixed
+- Off-naider scenes will now be processed and will only be paired with other off-nadir scenes.
 
 ## [0.3.0]
 

landsat/src/main.py

@@ -62,10 +62,6 @@ def _qualifies_for_processing(
         log.log(log_level, f'{item.id} disqualifies for processing because it has too much cloud cover')
         return False
 
-    if item.properties['view:off_nadir'] != 0:
-        log.log(log_level, f'{item.id} disqualifies for processing because it is off-nadir')
-        return False
-
     log.log(log_level, f'{item.id} qualifies for processing')
     return True
 
@@ -99,11 +95,16 @@ def get_landsat_pairs_for_reference_scene(
         query=[
             f'landsat:wrs_path={reference.properties["landsat:wrs_path"]}',
             f'landsat:wrs_row={reference.properties["landsat:wrs_row"]}',
+            f'view:off_nadir={reference.properties["view:off_nadir"]}',
         ],
         datetime=[reference.datetime - max_pair_separation, reference.datetime - timedelta(seconds=1)],
     )
+
     items = [item for page in results.pages() for item in page if _qualifies_for_processing(item, max_cloud_cover)]
 
+    if len(items) == 0:
+        return gpd.GeoDataFrame()
+
     features = []
     for item in items:
         feature = item.to_dict()
@@ -137,8 +138,11 @@ def deduplicate_hyp3_pairs(pairs: gpd.GeoDataFrame) -> gpd.GeoDataFrame:
         user_id=EARTHDATA_USERNAME,
     )
 
-    df = pd.DataFrame([job.job_parameters['granules'] for job in jobs], columns=['reference', 'secondary'])
-
+    df = pd.DataFrame(
+        [[*job.job_parameters['granules'], *[job.job_id, job.status_code]] for job in jobs],
+        columns=['reference', 'secondary', 'job_id', 'status_code'],
+    )
+    df = df[df.status_code == 'SUCCEEDED']
     df = df.set_index(['reference', 'secondary'])
     pairs = pairs.set_index(['reference', 'secondary'])
 
@@ -192,6 +196,7 @@ def process_scene(
         return sdk.Batch()
 
     pairs = get_landsat_pairs_for_reference_scene(reference, max_pair_separation, max_cloud_cover)
+
     log.info(f'Found {len(pairs)} pairs for {scene}')
     with pd.option_context('display.max_rows', None, 'display.max_columns', None, 'display.width', None):
         log.debug(pairs.loc[:, ['reference', 'secondary']])