loone-data-prep 0.1.5__tar.gz → 0.1.6__tar.gz

{loone_data_prep-0.1.5 → loone_data_prep-0.1.6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: loone_data_prep
-Version: 0.1.5
+Version: 0.1.6
 Summary: Prepare data to run the LOONE model.
 Author-email: Osama Tarabih <osamatarabih@usf.edu>
 Maintainer-email: Michael Souffront <msouffront@aquaveo.com>, James Dolinar <jdolinar@aquaveo.com>

{loone_data_prep-0.1.5 → loone_data_prep-0.1.6}/loone_data_prep/LOONE_DATA_PREP.py

@@ -418,7 +418,7 @@ def main(input_dir: str, output_dir: str) -> None:
     Stg_3A28 = pd.read_csv(f'{input_dir}/Stg_3A28.csv')
     Stg_3A28 = DF_Date_Range(Stg_3A28, St_Yr, St_M, St_D, En_Yr, En_M, En_D)
     WCA_Stg = pd.DataFrame(Stg_3A28['date'], columns=['date'])
-    WCA_Stg['3A-NW'] = Stg_3ANW['3A-NW_STG_ft NGVD29'].values
+    WCA_Stg['3A-NW'] = Stg_3ANW.iloc[:, -1].values
     WCA_Stg['2A-17'] = Stg_2A17.iloc[:, -1].values
     WCA_Stg['3A-3'] = Stg_3A3.iloc[:, -1].values
     WCA_Stg['3A-4'] = Stg_3A4.iloc[:, -1].values

{loone_data_prep-0.1.5 → loone_data_prep-0.1.6}/loone_data_prep/flow_data/forecast_bias_correction.py

@@ -1,4 +1,5 @@
 import sys
+import os
 import pandas as pd
 import geoglows
 
@@ -12,6 +13,7 @@ def get_bias_corrected_data(
     observed_data_path: str,
     station_ensembles: pd.DataFrame,
     station_stats: pd.DataFrame,
+    cache_path: str = None,
 ) -> dict:
     # Load the observed data from a CSV file
     observed_data = pd.read_csv(
@@ -34,7 +36,23 @@ def get_bias_corrected_data(
     prepared_od = prep_observed_data(observed_data)
 
     # Get the historical simulation data for the given reach ID
-    historical_data = geoglows.streamflow.historic_simulation(reach_id)
+    historical_data = None
+    
+    if cache_path is None:
+        historical_data = geoglows.streamflow.historic_simulation(reach_id)
+    else:
+        # Create the geoglows cache directory if it doesn't exist
+        geoglows_cache_path = os.path.join(cache_path, 'geoglows_cache')
+        if not os.path.exists(geoglows_cache_path):
+            os.makedirs(geoglows_cache_path)
+        
+        # Check if the historical simulation data is already cached
+        if os.path.exists(os.path.join(geoglows_cache_path, f'{reach_id}_historic_simulation.csv')):
+            historical_data = pd.read_csv(os.path.join(geoglows_cache_path, f'{reach_id}_historic_simulation.csv'), index_col=0)
+            historical_data.index = pd.to_datetime(historical_data.index)
+        else:
+            historical_data = geoglows.streamflow.historic_simulation(reach_id)
+            historical_data.to_csv(os.path.join(geoglows_cache_path, f'{reach_id}_historic_simulation.csv'))
 
     # Correct the forecast bias in the station ensembles
     station_ensembles = geoglows.bias.correct_forecast(

{loone_data_prep-0.1.5 → loone_data_prep-0.1.6}/loone_data_prep/flow_data/get_forecast_flows.py

@@ -366,6 +366,7 @@ def main(
     forecast_date: str = FORECAST_DATE,
     bias_corrected: bool = False,
     observed_data_dir: str | None = None,
+    cache_path: str | None = None,
 ):
     """Downloads the flow forecasts for the given station ids and writes them
         out as .csv files.
@@ -379,6 +380,8 @@ def main(
             Default is False.
         observed_data_dir (str): The path to the observed flow data directory
             (only needed if bias_corrected is True).
+        cache_path (str): The path to the cache directory for geoglows data. 
+            Should hold a directory named geoglows_cache that holds the cached files. Use None to not use a cache.
     """
     # Local Variables
     reach_ids = {}
@@ -428,6 +431,7 @@ def main(
                     observed_data_path,
                     station_ensembles,
                     station_stats,
+                    cache_path,
                 )
 
         ensembles_to_csv(

{loone_data_prep-0.1.5 → loone_data_prep-0.1.6}/loone_data_prep/utils.py

@@ -4,6 +4,7 @@ import datetime
 import math
 from glob import glob
 from calendar import monthrange
+import traceback
 import numpy as np
 import pandas as pd
 from retry import retry
@@ -635,8 +636,9 @@ def nutrient_prediction(
                 predicted_column.columns = [column_name]
 
                 prediction_columns.append(predicted_column)
-            except RuntimeWarning:
-                breakpoint()
+            except RuntimeWarning as e:
+                print(f"Unexpected RuntimeWarning: {str(e)}")
+                traceback.print_exc()
 
         # Concat individual ensemble columns together into one pandas DataFrame
         out_dataframe = pd.concat(objs=prediction_columns, axis="columns")

{loone_data_prep-0.1.5 → loone_data_prep-0.1.6}/loone_data_prep.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: loone_data_prep
-Version: 0.1.5
+Version: 0.1.6
 Summary: Prepare data to run the LOONE model.
 Author-email: Osama Tarabih <osamatarabih@usf.edu>
 Maintainer-email: Michael Souffront <msouffront@aquaveo.com>, James Dolinar <jdolinar@aquaveo.com>

{loone_data_prep-0.1.5 → loone_data_prep-0.1.6}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "loone_data_prep"
-version = "0.1.5"
+version = "0.1.6"
 description = "Prepare data to run the LOONE model."
 readme = "README.md"
 license = { file = "LICENSE" }