py-ewr 2.2.3__tar.gz → 2.2.5__tar.gz

{py_ewr-2.2.3 → py_ewr-2.2.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: py_ewr
-Version: 2.2.3
+Version: 2.2.5
 Summary: Environmental Water Requirement calculator
 Home-page: https://github.com/MDBAuth/EWR_tool
 Author: Martin Job
@@ -34,14 +34,14 @@ 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 2.2.3 README**
+### **EWR tool version 2.2.5 README**
 
-### **Notes on recent version update**
+### **Notes on recent version updates**
+- 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.
-- ten thousand year handling - This has been briefly taken offline for this version.
 - 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
 - New EWRs: New Qld EWRs - SF_FD and BF_FD used to look into the FD EWRs in closer detail.
 

{py_ewr-2.2.3 → py_ewr-2.2.5}/README.md

@@ -3,14 +3,14 @@
 [![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 2.2.3 README**
+### **EWR tool version 2.2.5 README**
 
-### **Notes on recent version update**
+### **Notes on recent version updates**
+- 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.
-- ten thousand year handling - This has been briefly taken offline for this version.
 - 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
 - New EWRs: New Qld EWRs - SF_FD and BF_FD used to look into the FD EWRs in closer detail.
 

{py_ewr-2.2.3 → py_ewr-2.2.5}/py_ewr/data_inputs.py

@@ -416,3 +416,27 @@ def get_scenario_gauges(gauge_results: dict) -> list:
         for gauge in scenario.keys():
             scenario_gauges.append(gauge)
     return list(set(scenario_gauges))
+
+
+def gauge_groups(parameter_sheet: pd.DataFrame) -> dict:
+    '''
+    Returns a dictionary of flow, level, and lake level gauges based on the parameter sheet and some hard coding of other EWRs
+
+    Args:
+        parameter_sheet (pd.DataFrame): input parameter sheet
+    
+    Returns:
+        dict: keys as flow, level, and lake level gauges, values as the list of gauges
+    '''
+    
+    # Hard coded gauges for the CLLMM EWRs
+    hard_code_levels = ['A4260527', 'A4260524', 'A4260633', 'A4261209', 'A4261165']
+    hard_code_lake_levels = ['A4261133', 'A4260574', 'A4260575']
+
+    flow_gauges = set(parameter_sheet[parameter_sheet['GaugeType'] == 'F']['Gauge']) + set(parameter_sheet['Multigauge'])
+    level_gauges = set(parameter_sheet[parameter_sheet['GaugeType'] == 'L']['Gauge']) + set(parameter_sheet['WeirpoolGauge']) + set(hard_code_levels)
+    lake_level_gauges = set(parameter_sheet[parameter_sheet['GaugeType'] == 'LL']['Gauge'])+set(hard_code_lake_levels)
+
+    return flow_gauges, level_gauges, lake_level_gauges
+
+# def gauges_to_measurand()

{py_ewr-2.2.3 → py_ewr-2.2.5}/py_ewr/evaluate_EWRs.py

@@ -446,9 +446,18 @@ def get_index_date(date_index:Any)-> datetime.date:
     if type(date_index) == pd._libs.tslibs.timestamps.Timestamp:
         return date_index.date()
     if type(date_index) == pd._libs.tslibs.period.Period:
-        return date_index.to_timestamp().date()
-    else:
+        date_index_str = date_index.strftime('%Y-%m-%d')
+        # For dates between the years 100 and 999 we need to add a 0 onto the date string so strptime doesnt break
+        if ((int(date_index_str.split('-')[0]) >= 100) and (int(date_index_str.split('-')[0]) < 1000)):
+            date_index_str = '0' + date_index_str
+        n = datetime.datetime.strptime(date_index_str, '%Y-%m-%d').date()
+        return n
+    if type(date_index) == str:
+        n = datetime.datetime.strptime(date_index, '%Y-%m-%d').date()
+        return n
+    if type(date_index) == datetime.date:
         return date_index
+    #     return date_index #TODO: should this break? i.e. we arent expecting other date formats
 
 #----------------------------------- EWR handling functions --------------------------------------#
 
@@ -1958,7 +1967,8 @@ def water_stability_check(EWR_info:Dict, iteration:int, flows:List, all_events:D
     if levels_are_stable:
         # record event opportunity for the next n days for the total period of (EggDaysSpell)+ larvae (LarvaeDaysSpell)
         # if the last day of the event is not over the last day of the event window
-        iteration_date = flow_date.to_timestamp().date()
+        iteration_date = get_index_date(flow_date)
+        # iteration_date = flow_date.date()#flow_date.to_timestamp().date()
         last_day_window = get_last_day_of_window(iteration_date, EWR_info['end_month'])
         event_size = EWR_info['eggs_days_spell'] + EWR_info['larvae_days_spell']
         if is_date_in_window(iteration_date, last_day_window, event_size):
@@ -1995,7 +2005,8 @@ def water_stability_level_check(EWR_info:Dict, iteration:int, all_events:Dict, w
     if levels_are_stable:
         # record event opportunity for the next n days for the total period of (EggDaysSpell)+ larvae (LarvaeDaysSpell)
         # if the last day of the event is not over the last day of the event window
-        iteration_date = flow_date.to_timestamp().date()
+        iteration_date = get_index_date(flow_date)
+        # iteration_date = flow_date.date()#flow_date.to_timestamp().date()
         last_day_window = get_last_day_of_window(iteration_date, EWR_info['end_month'])
         event_size = EWR_info['eggs_days_spell'] + EWR_info['larvae_days_spell']
         if is_date_in_window(iteration_date, last_day_window, event_size):
@@ -2604,7 +2615,7 @@ def lower_lakes_level_check(EWR_info: dict, levels: pd.Series, event: list, all_
 #------------------------------------ Calculation functions --------------------------------------#
 
 
-def create_water_stability_event(flow_date: pd.Period, flows:List, iteration: int, EWR_info:dict)->List:
+def create_water_stability_event(flow_date: pd.Timestamp, flows:List, iteration: int, EWR_info:dict)->List:#pd.Period
     """create overlapping event that meets an achievement for fish recruitment water stability
 
     Args:
@@ -2617,7 +2628,8 @@ def create_water_stability_event(flow_date: pd.Period, flows:List, iteration: in
     """
     event_size = EWR_info['eggs_days_spell'] + EWR_info['larvae_days_spell']
     event_flows = flows[iteration: iteration + event_size]
-    start_event_date = flow_date.to_timestamp().date()
+    start_event_date = get_index_date(flow_date)
+    # start_event_date = flow_date.date()#flow_date.to_timestamp().date()
     event_dates = [ start_event_date + timedelta(i) for i in range(event_size)]
     
     return [(d, flow)  for d, flow in zip(event_dates, event_flows)]
@@ -3800,6 +3812,7 @@ def nest_calc_percent_trigger(EWR_info:Dict, flows:List, water_years:List, dates
     Returns:
         tuple: final output with the calculation of volume all_events, durations
     """
+    #TODO can we clean up the flow_date and iteration_date parts
     event = []
     total_event = 0
     all_events = construct_event_dict(water_years)
@@ -3807,19 +3820,25 @@ def nest_calc_percent_trigger(EWR_info:Dict, flows:List, water_years:List, dates
     gap_track = 0
     for i, flow in enumerate(flows[:-1]):   
             flow_date = dates[i]
+            iteration_date = get_index_date(flow_date)
             flow_percent_change = calc_flow_percent_change(i, flows)
             trigger_day = date(dates[i].year,EWR_info["trigger_month"], EWR_info["trigger_day"])
             cut_date = calc_nest_cut_date(EWR_info, i, dates)
-            is_in_trigger_window = dates[i].to_timestamp().date() >= trigger_day \
-                                   and dates[i].to_timestamp().date() <= trigger_day + timedelta(days=14)
+            is_in_trigger_window = iteration_date >= trigger_day \
+                                   and iteration_date <= trigger_day + timedelta(days=14) #.to_timestamp() .to_timestamp()
+            # is_in_trigger_window = dates[i].date() >= trigger_day \
+            #                        and dates[i].date() <= trigger_day + timedelta(days=14) #.to_timestamp() .to_timestamp()
             iteration_no_event = 0
             
             ## if there IS an ongoing event check if we are on the trigger season window 
             # if yes then check the current flow
             if total_event > 0:
-                if (dates[i].to_timestamp().date() >= trigger_day) and (dates[i].to_timestamp().date() <= cut_date):
+                if (iteration_date >= trigger_day) and (iteration_date <= cut_date):
                     event, all_events, gap_track, total_event, iteration_no_event = nest_flow_check(EWR_info, i, flow, event, all_events, 
-                                                         gap_track, water_years, total_event, flow_date, flow_percent_change, iteration_no_event)
+                                                         gap_track, water_years, total_event, flow_date, flow_percent_change, iteration_no_event) #.to_timestamp() .to_timestamp()
+                # if (dates[i].date() >= trigger_day) and (dates[i].date() <= cut_date):
+                #     event, all_events, gap_track, total_event, iteration_no_event = nest_flow_check(EWR_info, i, flow, event, all_events, 
+                #                                          gap_track, water_years, total_event, flow_date, flow_percent_change, iteration_no_event) #.to_timestamp() .to_timestamp()
 
                 # this path will only be executed if an event extends beyond the cut date    
                 else:
@@ -3840,18 +3859,23 @@ def nest_calc_percent_trigger(EWR_info:Dict, flows:List, water_years:List, dates
     
     # Check final iteration in the flow timeseries, saving any ongoing events/event gaps to their spots in the dictionaries:
     # reset all variable to last flow
-    flow_date = dates[-1].to_timestamp().date()
+
+    # flow_date = dates[-1].date()#.to_timestamp()
+    flow_date = dates[-1]
+    iteration_date = get_index_date(dates[-1])
     flow_percent_change = calc_flow_percent_change(-1, flows)
     trigger_day = date(dates[-1].year,EWR_info["trigger_month"], EWR_info["trigger_day"])
     cut_date = calc_nest_cut_date(EWR_info, -1, dates)
-    is_in_trigger_window = dates[-1].to_timestamp().date() >= trigger_day - timedelta(days=7) \
-    and dates[-1].to_timestamp().date() <= trigger_day + timedelta(days=7)
+    is_in_trigger_window = iteration_date >= trigger_day - timedelta(days=7) \
+    and iteration_date <= trigger_day + timedelta(days=7) #.to_timestamp() .to_timestamp()
+    # is_in_trigger_window = dates[-1].date() >= trigger_day - timedelta(days=7) \
+    # and dates[-1].date() <= trigger_day + timedelta(days=7) #.to_timestamp() .to_timestamp()
     iteration_no_event = 0
 
     if total_event > 0:
 
-        if (flow_date >= trigger_day ) \
-            and (flow_date <= cut_date):
+        if (iteration_date >= trigger_day ) \
+            and (iteration_date <= cut_date): # Was flow_date instead of iteration date in both instances
             event, all_events,  gap_track, total_event, iteration_no_event = nest_flow_check(EWR_info, -1, flows[-1], event, all_events, 
                                                              gap_track, water_years, total_event, flow_date, flow_percent_change, iteration_no_event)
 

{py_ewr-2.2.3 → py_ewr-2.2.5}/py_ewr/observed_handling.py

@@ -35,7 +35,6 @@ def categorise_gauges(gauges: list, ewr_table_path:str = None) -> tuple:
         if gauge in gauges:
             level_gauges.append(gauge)
     lake_level_gauges_to_add = EWR_TABLE[EWR_TABLE['GaugeType']=='LL']['Gauge'].to_list()
-    # print(lake_level_gauges_to_add)
     for gauge in lake_level_gauges_to_add:
         if gauge in gauges:
             lake_level_gauges.append(gauge)
@@ -130,7 +129,7 @@ def observed_cleaner(input_df: pd.DataFrame, dates: dict) -> pd.DataFrame:
     start_date = datetime(dates['start_date'].year, dates['start_date'].month, dates['start_date'].day)
     end_date = datetime(dates['end_date'].year, dates['end_date'].month, dates['end_date'].day)
     
-    df_index = pd.date_range(start=start_date,end=end_date - timedelta(days=1)).to_period()
+    df_index = pd.date_range(start=start_date,end=end_date - timedelta(days=1))#.to_period()
     gauge_data_df = pd.DataFrame()
     gauge_data_df['Date'] = df_index
     gauge_data_df = gauge_data_df.set_index('Date')
@@ -139,7 +138,7 @@ def observed_cleaner(input_df: pd.DataFrame, dates: dict) -> pd.DataFrame:
     
     
     input_df['Date'] = pd.to_datetime(input_df['DATETIME'], format = '%Y-%m-%d')
-    input_df['Date'] = input_df['Date'].apply(lambda x: x.to_period(freq='D'))
+    # input_df['Date'] = input_df['Date'].apply(lambda x: x.to_period(freq='D'))
 
     # Check with states for more codes:
     bad_data_codes = data_inputs.get_bad_QA_codes()
@@ -178,12 +177,12 @@ class ObservedHandler:
         
         # Classify gauges:
         flow_gauges, level_gauges, lake_level_gauges = categorise_gauges(self.gauges, self.parameter_sheet)
-        print('flow gauges')
-        print(flow_gauges)
-        print('level gauges')
-        print(level_gauges)
-        print('lake level gauges')
-        print(lake_level_gauges)
+        # print('flow gauges')
+        # print(flow_gauges)
+        # print('level gauges')
+        # print(level_gauges)
+        # print('lake level gauges')
+        # print(lake_level_gauges)
         # Call state API for flow and level gauge data, then combine to single dataframe
         log.info(f'Including gauges: flow gauges: { ", ".join(flow_gauges)} level gauges: { ", ".join(level_gauges)} lake level gauges: { ", ".join(lake_level_gauges)}')