py-ewr 2.2.5__py3-none-any.whl → 2.2.7__py3-none-any.whl

py_ewr/scenario_handling.py

@@ -1,7 +1,7 @@
 from typing import Dict, List
 import csv
 import os
-import urllib
+import urllib.request
 import re
 from datetime import datetime, date
 import logging
@@ -436,13 +436,63 @@ def extract_gauge_from_string(input_string: str) -> str:
     gauge = input_string.split('_')[0]
     return gauge
 
-# def match_MDBA_nodes_dev(input_df: pd.DataFrame, model_metadata: pd.DataFrame, ewr_table_path: str) -> tuple:
-#     '''
-#     Iterate over the gauges in the parameter sheet, 
-#     find all the occurences of that gauge in the ARWC column in the model metadata file,
-#     for each match, search for the matching siteID in the model file,
-#     append the column to the flow dataframe.
+def match_MDBA_nodes(input_df: pd.DataFrame, model_metadata: pd.DataFrame, ewr_table_path: str) -> tuple:
+    '''
+    Iterate over the gauges in the parameter sheet, 
+    find all the occurences of that gauge in the ARWC column in the model metadata file,
+    for each match, search for the matching siteID in the model file,
+    append the column to the flow dataframe.
+
+    Args:
+        input_df (pd.DataFrame): flow/water level dataframe
+        model_metadata (pd.DataFrame): dataframe linking model nodes to gauges
+
+    Returns:
+        tuple[pd.DataFrame, pd.DataFrame]: flow dataframe, water level dataframe
+
+    '''
+    
+    df_flow = pd.DataFrame(index = input_df.index)
+    df_level = pd.DataFrame(index = input_df.index)
+
+    unique_gauges = data_inputs.get_gauges('all gauges')
+    flow_gauges = data_inputs.get_gauges('flow gauges', ewr_table_path=ewr_table_path)
+    level_gauges = data_inputs.get_gauges('level gauges', ewr_table_path=ewr_table_path)
+    
+    report = pd.DataFrame(index = list(set(list(flow_gauges) + list(level_gauges))), columns = ['flow', 'level'])
+    report['flow'] = 'N'
+    report['level'] = 'N'
+    measurands = ['1', '35']
+    #Iterate over all gauges that have EWRs attached
+    for gauge in unique_gauges:
+        # Subset of the SiteID file with the gauges
+        subset_df = model_metadata[model_metadata['AWRC'] == gauge]
+        # Iterate over the unique measurands of interest (currently flow=1 and level/lake level=35)
+        for measure in measurands:
+            # Iterate over the occurences of the gauge and check if the matching SiteID file is in the model file with the correct measurand
+            for index, siteID in subset_df.iterrows(): 
+                site_mm = siteID['SITEID']
+                model_file_subset = input_df.filter(regex=rf"^{site_mm}-{measure}(?=-)", axis = 1)
+                # Just use the first column if there are multiple of the same siteID-measurand occurences
+                if not model_file_subset.empty:
+                    if (measure == '1') and (gauge in flow_gauges):
+                        df_flow[gauge] = model_file_subset.iloc[:,0]
+                        report.at[gauge, 'flow'] = 'Y'
+                    if (measure == '35') and (gauge in level_gauges):
+                        df_level[gauge] = model_file_subset.iloc[:,0]
+                        report.at[gauge, 'level'] = 'Y'
+
+    if df_flow.empty and df_level.empty:
+        raise ValueError('No relevant gauges and or measurands found in dataset, the EWR tool cannot evaluate this model output file') 
+ 
+    # report.to_csv('report_v1.csv')  
+    return df_flow, df_level
+
 
+# def match_MDBA_nodes_old(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
+    
 #     Args:
 #         input_df (pd.DataFrame): flow/water level dataframe
 #         model_metadata (pd.DataFrame): dataframe linking model nodes to gauges
@@ -451,67 +501,38 @@ def extract_gauge_from_string(input_string: str) -> str:
 #         tuple[pd.DataFrame, pd.DataFrame]: flow dataframe, water level dataframe
 
 #     '''
+
+#     flow_gauges = data_inputs.get_gauges('flow gauges', ewr_table_path=ewr_table_path)
+#     level_gauges = data_inputs.get_gauges('level gauges', ewr_table_path=ewr_table_path)
+#     measurands = ['1', '35']
 #     df_flow = pd.DataFrame(index = input_df.index)
 #     df_level = pd.DataFrame(index = input_df.index)
-
-#     unique_gauges = #Get unique gauges from the parameter sheet
-#     #TODO: include logic to have the measurand included
-#     for i in unique_gauges:
-#         # Subset of the SiteID file with the gauges
-#         subset_df = model_metadata[model_metadata['AWRC'] == i]
-#         # Iterate over the occurences of the gauge and check if the matching SiteID file is in the model file
-#         for j in subset_df.iterrows:
-#             site_mm = j['SITEID']
-#             if site_mm in input_df.columns:
-#                 df_flow[i] = input_df[site_mm+INPUT_MEASURAND+ANY_QUALITY_CODE]
-#                 or
-#                 df_level[i] = input_df[site_mm+INPUT_MEASURAND+ANY_QUALITY_CODE]
+#     for col in input_df.columns:
+#         col_clean = col.replace(' ', '')
+#         site = col_clean.split('-')[0]
+#         measure = col_clean.split('-')[1]
+#         if ((measure in measurands) and (model_metadata['SITEID'] == site).any()):
+#             subset = model_metadata.query("SITEID==@site")
+#             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 and df_level.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
-
-
-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
     
-    Args:
-        input_df (pd.DataFrame): flow/water level dataframe
-        model_metadata (pd.DataFrame): dataframe linking model nodes to gauges
-
-    Returns:
-        tuple[pd.DataFrame, pd.DataFrame]: flow dataframe, water level dataframe
-
-    '''
+#     df_flow.to_csv('existing_flow_mapped.csv')
+#     df_level.to_csv('existing_level_mapped.csv')
 
-    flow_gauges = data_inputs.get_gauges('flow gauges', ewr_table_path=ewr_table_path)
-    level_gauges = data_inputs.get_gauges('level gauges', ewr_table_path=ewr_table_path)
-    measurands = ['1', '35']
-    df_flow = pd.DataFrame(index = input_df.index)
-    df_level = pd.DataFrame(index = input_df.index)
-    for col in input_df.columns:
-        col_clean = col.replace(' ', '')
-        site = col_clean.split('-')[0]
-        measure = col_clean.split('-')[1]
-        if ((measure in measurands) and (model_metadata['SITEID'] == site).any()):
-            subset = model_metadata.query("SITEID==@site")
-            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
+#     return df_flow, df_level
 
 def match_NSW_nodes(input_df: pd.DataFrame, model_metadata: pd.DataFrame) -> tuple:
     '''Checks if the source file columns have EWRs available, returns a flow and level dataframe with only 

{py_ewr-2.2.5.dist-info → py_ewr-2.2.7.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: py_ewr
-Version: 2.2.5
+Version: 2.2.7
 Summary: Environmental Water Requirement calculator
 Home-page: https://github.com/MDBAuth/EWR_tool
 Author: Martin Job
@@ -12,21 +12,21 @@ Classifier: Operating System :: OS Independent
 Classifier: Development Status :: 4 - Beta
 Classifier: Programming Language :: Python
 Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.8
 Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
 Classifier: Framework :: Pytest
 Description-Content-Type: text/markdown
 License-File: LICENSE
-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: pandas >2
+Requires-Dist: requests >2
 Requires-Dist: mdba-gauge-getter ==0.5.1
-Requires-Dist: cachetools ==5.2.0
-Requires-Dist: xarray ==2023.01.0
-Requires-Dist: netCDF4 ==1.6.4
+Requires-Dist: cachetools >5
+Requires-Dist: xarray
+Requires-Dist: h5py
+Requires-Dist: netCDF4
 Requires-Dist: numpy <2
 
 [![CI](https://github.com/MDBAuth/EWR_tool/actions/workflows/test-release.yml/badge.svg)]()
@@ -34,12 +34,16 @@ 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 2.2.5 README**
+### **EWR tool version 2.2.7 README**
 
 ### **Notes on recent version updates**
+- Including draft objective mapping files in the package (see below sub heading **Objective mapping** for more information). Objective mapping has been therefore pulled out of the parameter sheet
+- Including an example parallel processing script for running the EWR tool
+- Adding handling for cases where there are single MDBA bigmod site IDs mapping to multiple different gauges
+- Fix SDL resource unit mapping in the parameter sheet
+- Adding lat and lon to the parameter sheet
 - ten thousand year handling - this has been brought back online.
 - 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.
 - bug fixes: spells of length equal to the minimum required spell length were getting filtered out of the successful events table and successful interevents table, fixed misclassification of some gauges to flow, level, and lake level categories
@@ -47,7 +51,7 @@ Requires-Dist: numpy <2
 
 ### **Installation**
 
-Note - requires Python 3.8 or newer
+Note - requires Python 3.9 to 3.13 (inclusive)
 
 Step 1. 
 Upgrade pip
@@ -109,7 +113,30 @@ all_successful_interEvents = ewr_oh.get_all_successful_interEvents()
 ### Option 2: Running model scenarios through the EWR tool
 
 1. Tell the tool where the model files are (can either be local or in a remote location)
-2. Tell the tool what format the model files are in (Current model format options: 'Bigmod - MDBA', 'Source - NSW (res.csv)', 'Standard time-series' - see manual for formatting requirements)
+2. Tell the tool what format the model files are in. The current model format options are: 
+    - 'Bigmod - MDBA'
+        Bigmod formatted outputs
+    - 'Source - NSW (res.csv)'
+        Source res.csv formatted outputs
+    - 'Standard time-series'
+        The first column header should be *Date* with the date values in the YYYY-MM-DD format.
+        The next columns should have the *gauge* followed by *_* followed by either *flow* or *level*
+        E.g.
+        | Date | 409025_flow | 409025_level | 414203_flow |
+        | --- | --- | --- | --- |
+        | 1895-07-01 | 8505 | 5.25 | 8500 |
+        | 1895-07-02 | 8510 | 5.26 | 8505 |
+
+    - 'ten thousand year'
+        This has the same formatting requirements as the 'Standard time-series'. This can handle ten thousand years worth of hydrology data.
+        The first column header should be *Date* with the date values in the YYYY-MM-DD format.
+        The next columns should have the *gauge* followed by *_* followed by either *flow* or *level*
+        E.g.
+        | Date | 409025_flow | 409025_level | 414203_flow |
+        | --- | --- | --- | --- |
+        | 105-07-01 | 8505 | 5.25 | 8500 |
+        | 105-07-02 | 8510 | 5.26 | 8505 |
+
 
 ```python
 #USER INPUT REQUIRED>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>
@@ -199,11 +226,11 @@ For issues relating to the script, a tutorial, or feedback please contact Lara P
 
 
 **Disclaimer**
-Every effort has been taken to ensure the EWR database represents the original EWRs from state long term water plans as best as possible, and that the code within this tool has been developed to interpret and analyse these EWRs in an accurate way. However, there may still be unresolved bugs in the EWR parameter sheet and/or EWR tool. Please report any bugs to the issues tab under the GitHub project so we can investigate further. 
+Every effort has been taken to ensure the EWR database represents the original EWRs from state Long Term Water Plans (LTWPs) and Environmental Water Management Plans (EWMPs) as best as possible, and that the code within this tool has been developed to interpret and analyse these EWRs in an accurate way. However, there may still be unresolved bugs in the EWR parameter sheet and/or EWR tool. Please report any bugs to the issues tab under the GitHub project so we can investigate further. 
 
 
 **Notes on development of the dataset of EWRs**
-The MDBA has worked with Basin state representatives to ensure scientific integrity of EWRs has been maintained when translating from raw EWRs in the Basin state Long Term Water Plans (LTWPs) to the machine readable format found in the parameter sheet within this tool. 
+The MDBA has worked with Basin state representatives to ensure scientific integrity of EWRs has been maintained when translating from raw EWRs in the Basin state LTWPs and EWMPs to the machine readable format found in the parameter sheet within this tool. 
 
 **Compatibility**
 
@@ -226,11 +253,8 @@ NSW:
 
 Consult the user manual for instructions on how to run the tool. Please email the above email addresses for a copy of the user manual.
 
-To disable progress bars, as for example when running remote scripted runs, use 
-
-``` python
-import os
-os.environ["TQDM_DISABLE"] = "1"
-```
-*before* importing py-ewr in your script.
-
+**Objective mapping**
+Objective mapping csv files are now included in the EWR tool package. Currently this objective mapping is in an early draft format. The objective mapping will be finalised after consultation with relevant state representatives. The files are intended to be used together to link EWRs to the detailed objectives, theme level targets and specific goals. The three sheets are located in the py_ewr/parameter_metadata folder:
+- ewr2obj.csv: For each planning unit, gauge, ewr combination there are either one or many env_obj codes. These env_obj codes come under one of five different theme level targets (Native Fish, Native vegetation, Waterbirds, Other species or Ecosystem functions)
+- obj2target.csv: env_obj's are unique to their planning unit in the LTWP (noting there are often a lot of similarities between env_obj's in the same states). The plain english wording of the env objectives is also contained in this csv. The LTWP, planning unit and env_obj rows are repeated for each specific goal related to that LTWP, planning unit and env_obj. 
+- obj2yrtarget.csv: The environmental objectives are related to 5, 10 and 20 year targets

{py_ewr-2.2.5.dist-info → py_ewr-2.2.7.dist-info}/RECORD

@@ -1,20 +1,20 @@
 py_ewr/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-py_ewr/data_inputs.py,sha256=PtpFyikT_IoMj_Ont6UykSdyiZXapny_Yk1J9VxParQ,19494
-py_ewr/evaluate_EWRs.py,sha256=UlnNp4dR0sT5Y-Mp67kW7kYq9yEzpCg6SbCbBBb26ok,230950
+py_ewr/data_inputs.py,sha256=OLIxqq15yoEqLSRmBJP37erldUGRRvSNn2XwO8LKZA8,20080
+py_ewr/evaluate_EWRs.py,sha256=ahdcc6N37wc-e6-S6JSx6VFm9eNkef0JBPXz16-SAaU,231267
 py_ewr/io.py,sha256=Is0xPAzLx6-ylpTFyYJxMimkNVxxoTxUcknTk6bQbgs,840
 py_ewr/observed_handling.py,sha256=aVQYI8Qs-v5DZOA_r8bYluE3ilgM7Vjygs29jA6kpaA,17848
-py_ewr/scenario_handling.py,sha256=2U6hSDfclEmfmgP6baO_CQImnat3gH34W_PC0H3MO58,34328
+py_ewr/scenario_handling.py,sha256=95HdNNPkY-w77hxnHRJxfzmn9fBu6OqHM5iyoQPwOXE,35498
 py_ewr/summarise_results.py,sha256=CEHsx6hC5UidgYy-dCJW_buiktGKkTH9D_Yl5QpSzh8,31499
-py_ewr/model_metadata/SiteID_MDBA.csv,sha256=DcwFmBBoLmv1lGik40IwTMSjSBPaDsTt8Nluh2s7wjM,183665
+py_ewr/model_metadata/SiteID_MDBA.csv,sha256=GHDuO7pnk4JrlCOG5aBw77bD0HxvEU_-NQ0kT9CKDrU,167724
 py_ewr/model_metadata/SiteID_NSW.csv,sha256=UVBxN43Z5KWCvWhQ5Rh6TNEn35q4_sjPxKyHg8wPFws,6805
 py_ewr/model_metadata/iqqm_stations.csv,sha256=vl4CPtPslG5VplSzf_yLZulTrmab-mEBHOfzFtS1kf4,110
 py_ewr/parameter_metadata/ewr2obj.csv,sha256=TyUDM_lzTu2v50j-kx-cvcX4QpwC0Vbc5pGFMG6rtMQ,4583480
 py_ewr/parameter_metadata/ewr_calc_config.json,sha256=l1AgIRlf7UUmk3BNQ4r3kutU48pYHHVKmLELjoB-8rQ,17664
 py_ewr/parameter_metadata/obj2target.csv,sha256=DIcwrOyvNPhBdvplWb8GU-2Hu33NwYhrXenAbnRD-dM,1773425
 py_ewr/parameter_metadata/obj2yrtarget.csv,sha256=x-lvGTHMsXutSKfgN6_B0ujQueiu953lEk-_k8ybTNw,56681
-py_ewr/parameter_metadata/parameter_sheet.csv,sha256=IiYAvf0hG9fchuwqtfDZhI8WSPB5jgaaaJ0MLwfPYAw,899556
-py_ewr-2.2.5.dist-info/LICENSE,sha256=ogEPNDSH0_dhiv_lT3ifVIdgIzHAqNA_SemnxUfPBJk,7048
-py_ewr-2.2.5.dist-info/METADATA,sha256=aZBST6CZikIrr_ce3PTDYRrpw8I90TQDWRRy2mAisGM,10156
-py_ewr-2.2.5.dist-info/WHEEL,sha256=GV9aMThwP_4oNCtvEC2ec3qUYutgWeAzklro_0m4WJQ,91
-py_ewr-2.2.5.dist-info/top_level.txt,sha256=n3725d-64Cjyb-YMUMV64UAuIflzUh2_UZSxiIbrur4,7
-py_ewr-2.2.5.dist-info/RECORD,,
+py_ewr/parameter_metadata/parameter_sheet.csv,sha256=Pm741CUDywFJ_Jd8LN41YcimKvne-ey-gJskI13wTIk,772287
+py_ewr-2.2.7.dist-info/LICENSE,sha256=ogEPNDSH0_dhiv_lT3ifVIdgIzHAqNA_SemnxUfPBJk,7048
+py_ewr-2.2.7.dist-info/METADATA,sha256=yNiDURx97CzSTLq5BIHTYYv-Z4-j-RwdDSX_IJe9460,12521
+py_ewr-2.2.7.dist-info/WHEEL,sha256=P9jw-gEje8ByB7_hXoICnHtVCrEwMQh-630tKvQWehc,91
+py_ewr-2.2.7.dist-info/top_level.txt,sha256=n3725d-64Cjyb-YMUMV64UAuIflzUh2_UZSxiIbrur4,7
+py_ewr-2.2.7.dist-info/RECORD,,

{py_ewr-2.2.5.dist-info → py_ewr-2.2.7.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (75.1.0)
+Generator: setuptools (75.3.0)
 Root-Is-Purelib: true
 Tag: py3-none-any