py-ewr 2.2.1__tar.gz → 2.2.3__tar.gz

{py_ewr-2.2.1 → py_ewr-2.2.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: py_ewr
-Version: 2.2.1
+Version: 2.2.3
 Summary: Environmental Water Requirement calculator
 Home-page: https://github.com/MDBAuth/EWR_tool
 Author: Martin Job
@@ -23,7 +23,6 @@ Requires-Dist: ipython==8.8.0
 Requires-Dist: ipywidgets==7.7.0
 Requires-Dist: pandas==2.0.3
 Requires-Dist: requests==2.25.1
-Requires-Dist: tqdm>=4.66.1
 Requires-Dist: mdba-gauge-getter==0.5.1
 Requires-Dist: cachetools==5.2.0
 Requires-Dist: xarray==2023.01.0
@@ -35,9 +34,11 @@ Requires-Dist: numpy<2
 [![PyPI](https://img.shields.io/pypi/v/py-ewr)](https://pypi.org/project/py-ewr/)
 [![DOI](https://zenodo.org/badge/342122359.svg)](https://zenodo.org/badge/latestdoi/342122359)
 
-### **EWR tool version 2.2.1 README**
+### **EWR tool version 2.2.3 README**
 
 ### **Notes on recent version update**
+- Remove TQDM loading bars
+- Handle duplicate sites in MDBA siteID file - where a duplicate exists, the first match is used and the rest are skipped over
 - Adding new model format handling - 'IQQM - netcdf'
 - Standard time-series handling added - each column needs a gauge, followed by and underscore, followed by either flow or level (e.g. 409025_flow). This handling also has missing date filling - so any missing dates will be filled with NaN values in all columns.
 - ten thousand year handling - This has been briefly taken offline for this version.

{py_ewr-2.2.1 → py_ewr-2.2.3}/README.md

@@ -3,9 +3,11 @@
 [![PyPI](https://img.shields.io/pypi/v/py-ewr)](https://pypi.org/project/py-ewr/)
 [![DOI](https://zenodo.org/badge/342122359.svg)](https://zenodo.org/badge/latestdoi/342122359)
 
-### **EWR tool version 2.2.1 README**
+### **EWR tool version 2.2.3 README**
 
 ### **Notes on recent version update**
+- Remove TQDM loading bars
+- Handle duplicate sites in MDBA siteID file - where a duplicate exists, the first match is used and the rest are skipped over
 - Adding new model format handling - 'IQQM - netcdf'
 - Standard time-series handling added - each column needs a gauge, followed by and underscore, followed by either flow or level (e.g. 409025_flow). This handling also has missing date filling - so any missing dates will be filled with NaN values in all columns.
 - ten thousand year handling - This has been briefly taken offline for this version.

{py_ewr-2.2.1 → py_ewr-2.2.3}/py_ewr/evaluate_EWRs.py

@@ -10,7 +10,6 @@ import logging
 
 import pandas as pd
 import numpy as np
-from tqdm import tqdm
 
 from . import data_inputs
 
@@ -5086,9 +5085,7 @@ def calc_sorter(df_F:pd.DataFrame, df_L:pd.DataFrame, gauge:str, EWR_table:pd.Da
         EWR_codes = PU_table['Code']
         PU_df = pd.DataFrame()
         PU_events = {}
-        for i, EWR in enumerate(tqdm(EWR_codes, position = 0, leave = False,
-                                     bar_format='{l_bar}{bar:10}{r_bar}{bar:-10b}',
-                                     desc= str('Evaluating ewrs for '+ gauge))):
+        for i, EWR in enumerate(EWR_codes):
             events = {}
 
             MULTIGAUGE = is_multigauge(EWR_table, gauge, EWR, PU)

{py_ewr-2.2.1 → py_ewr-2.2.3}/py_ewr/observed_handling.py

@@ -3,7 +3,6 @@ from typing import Dict, List
 import logging
 
 import pandas as pd
-from tqdm import tqdm
 import numpy as np
 
 from . import data_inputs, evaluate_EWRs, summarise_results, scenario_handling

{py_ewr-2.2.1 → py_ewr-2.2.3}/py_ewr/scenario_handling.py

@@ -7,7 +7,6 @@ from datetime import datetime, date
 import logging
 
 import pandas as pd
-from tqdm import tqdm
 import xarray as xr
 import netCDF4
  
@@ -437,6 +436,8 @@ def extract_gauge_from_string(input_string: str) -> str:
     gauge = input_string.split('_')[0]
     return gauge
 
+
+
 def match_MDBA_nodes(input_df: pd.DataFrame, model_metadata: pd.DataFrame, ewr_table_path: str) -> tuple:
     '''Checks if the source file columns have EWRs available, returns a flow and level dataframe with only 
     the columns with EWRs available. Renames columns to gauges
@@ -461,11 +462,19 @@ def match_MDBA_nodes(input_df: pd.DataFrame, model_metadata: pd.DataFrame, ewr_t
         measure = col_clean.split('-')[1]
         if ((measure in measurands) and (model_metadata['SITEID'] == site).any()):
             subset = model_metadata.query("SITEID==@site")
-            gauge = subset["AWRC"].iloc[0]
-            if gauge in flow_gauges and measure == '1':
-                df_flow[gauge] = input_df[col]
-            if gauge in level_gauges and measure == '35':
-                df_level[gauge] = input_df[col]
+            for iset in range(len(subset)):
+                gauge = subset["AWRC"].iloc[iset]
+                if gauge in flow_gauges and measure == '1':
+                    df_flow[gauge] = input_df[col]
+                if gauge in level_gauges and measure == '35':
+                    aa=input_df[[col]]
+                    if (len(aa.columns)>1):
+                        print('More than one site has been identified, the first site is used')
+                        print('Site info: ', col)
+                        df_level[gauge] = aa.iloc[:,0]
+                    else:
+                        df_level[gauge] = input_df[col]
+
     if df_flow.empty:
         raise ValueError('No relevant gauges and or measurands found in dataset, the EWR tool cannot evaluate this model output file')      
     return df_flow, df_level
@@ -538,9 +547,7 @@ class ScenarioHandler:
         # Analyse all scenarios for EWRs
         detailed_results = {}
         detailed_events = {}
-        for scenario in tqdm(scenarios, position = 0, leave = True, 
-                            bar_format='{l_bar}{bar:10}{r_bar}{bar:-10b}',
-                            desc= 'Evaluating scenarios'):
+        for scenario in scenarios:
             if self.model_format == 'Bigmod - MDBA':
                 
                 data, header = unpack_model_file(scenarios[scenario], 'Dy', 'Field')

{py_ewr-2.2.1 → py_ewr-2.2.3}/py_ewr.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: py_ewr
-Version: 2.2.1
+Version: 2.2.3
 Summary: Environmental Water Requirement calculator
 Home-page: https://github.com/MDBAuth/EWR_tool
 Author: Martin Job
@@ -23,7 +23,6 @@ Requires-Dist: ipython==8.8.0
 Requires-Dist: ipywidgets==7.7.0
 Requires-Dist: pandas==2.0.3
 Requires-Dist: requests==2.25.1
-Requires-Dist: tqdm>=4.66.1
 Requires-Dist: mdba-gauge-getter==0.5.1
 Requires-Dist: cachetools==5.2.0
 Requires-Dist: xarray==2023.01.0
@@ -35,9 +34,11 @@ Requires-Dist: numpy<2
 [![PyPI](https://img.shields.io/pypi/v/py-ewr)](https://pypi.org/project/py-ewr/)
 [![DOI](https://zenodo.org/badge/342122359.svg)](https://zenodo.org/badge/latestdoi/342122359)
 
-### **EWR tool version 2.2.1 README**
+### **EWR tool version 2.2.3 README**
 
 ### **Notes on recent version update**
+- Remove TQDM loading bars
+- Handle duplicate sites in MDBA siteID file - where a duplicate exists, the first match is used and the rest are skipped over
 - Adding new model format handling - 'IQQM - netcdf'
 - Standard time-series handling added - each column needs a gauge, followed by and underscore, followed by either flow or level (e.g. 409025_flow). This handling also has missing date filling - so any missing dates will be filled with NaN values in all columns.
 - ten thousand year handling - This has been briefly taken offline for this version.

{py_ewr-2.2.1 → py_ewr-2.2.3}/py_ewr.egg-info/requires.txt

@@ -2,7 +2,6 @@ ipython==8.8.0
 ipywidgets==7.7.0
 pandas==2.0.3
 requests==2.25.1
-tqdm>=4.66.1
 mdba-gauge-getter==0.5.1
 cachetools==5.2.0
 xarray==2023.01.0

{py_ewr-2.2.1 → py_ewr-2.2.3}/setup.py

@@ -6,7 +6,7 @@ with open("README.md", "r", encoding="utf-8") as fh:
 
 setup(
     name="py_ewr",
-    version="2.2.1",
+    version="2.2.3",
     author="Martin Job",
     author_email="Martin.Job@mdba.gov.au",
     description="Environmental Water Requirement calculator",
@@ -35,7 +35,6 @@ setup(
         "ipywidgets==7.7.0",
         "pandas==2.0.3",
         "requests==2.25.1",
-        "tqdm>=4.66.1",
         "mdba-gauge-getter==0.5.1",
         "cachetools==5.2.0",
         "xarray==2023.01.0",

{py_ewr-2.2.1 → py_ewr-2.2.3}/tests/test_scenario_handling.py

@@ -12,7 +12,9 @@ from py_ewr import scenario_handling, data_inputs
 def test_match_MDBA_nodes():
     '''
     1. Ensure dataframe with flows and levels is split into two dataframes (one flow and one level dataframe)
+    2. Ensure first column is used when duplicate columns are loaded
     '''
+    # TEST 1 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>
     # Set up input data and pass to test function:
     model_metadata = data_inputs.get_MDBA_codes()
     data_df = {'Date': pd.date_range(start= datetime.strptime('2012-07-01', '%Y-%m-%d'), end = datetime.strptime('2016-06-30', '%Y-%m-%d')),
@@ -39,6 +41,36 @@ def test_match_MDBA_nodes():
     assert_frame_equal(df_F, expected_df_F)
     assert_frame_equal(df_L, expected_df_L)
 
+    # TEST 2 #>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>
+        # Set up input data and pass to test function:
+    model_metadata = data_inputs.get_MDBA_codes()
+    data_df = {'Date': pd.date_range(start= datetime.strptime('2012-07-01', '%Y-%m-%d'), end = datetime.strptime('2016-06-30', '%Y-%m-%d')),
+                'EUSTDS-1-8': [0]*1+[250]*350+[0]*9+[0]*5 + [0]*360+[0]*5 + [0]*2+[250]*345+[0]*1+[250]*17 + [0]*5+[250]*351+[250]*10, # Use
+                'EUSTDS-35-8': [0]*1+[250]*350+[0]*9+[0]*5 + [0]*360+[0]*5 + [0]*2+[250]*345+[0]*1+[250]*17 + [0]*5+[250]*351+[250]*10, # Skip
+                'EUSTUS-35-8': [0]*1+[250]*350+[0]*9+[0]*5 + [0]*360+[0]*5 + [0]*2+[250]*345+[0]*1+[250]*17 + [0]*5+[250]*351+[250]*10, # Skip
+                'EUSTUS-35-8': [0]*1+[250]*350+[0]*9+[0]*5 + [0]*360+[0]*5 + [0]*2+[250]*345+[0]*1+[250]*17 + [0]*5+[250]*351+[250]*10, # Use
+                'EUSTUS-1-8': [1]*1+[250]*350+[0]*9+[0]*5 + [0]*360+[0]*5 + [0]*2+[250]*345+[0]*1+[250]*17 + [0]*5+[250]*351+[250]*10, # Skip
+                }
+    df = pd.DataFrame(data = data_df)
+    df = df.set_index('Date')
+    
+    df_F, df_L = scenario_handling.match_MDBA_nodes(df, model_metadata, 'py_ewr/parameter_metadata/parameter_sheet.csv')
+
+    # Set up expected outputs and test:
+    data_expected_df_L = {'Date': pd.date_range(start= datetime.strptime('2012-07-01', '%Y-%m-%d'), end = datetime.strptime('2016-06-30', '%Y-%m-%d')),
+                            '414209': [0]*1+[250]*350+[0]*9+[0]*5 + [0]*360+[0]*5 + [0]*2+[250]*345+[0]*1+[250]*17 + [0]*5+[250]*351+[250]*10
+                            }
+    expected_df_L = pd.DataFrame(data_expected_df_L)
+    expected_df_L = expected_df_L.set_index('Date') 
+    data_expected_df_F = {'Date': pd.date_range(start= datetime.strptime('2012-07-01', '%Y-%m-%d'), end = datetime.strptime('2016-06-30', '%Y-%m-%d')),
+                            '414203': [0]*1+[250]*350+[0]*9+[0]*5 + [0]*360+[0]*5 + [0]*2+[250]*345+[0]*1+[250]*17 + [0]*5+[250]*351+[250]*10
+                            }
+    expected_df_F = pd.DataFrame(data_expected_df_F)
+    expected_df_F = expected_df_F.set_index('Date')
+    
+    assert_frame_equal(df_F, expected_df_F)
+    assert_frame_equal(df_L, expected_df_L)
+
 def test_match_NSW_nodes():
     '''
     1. Check NSW model nodes are mapped correctly to their gauges