Added AWR & Scoring modules

ParaUtils/AWR/__init__.py

@@ -0,0 +1,25 @@
+import pandas as pd
+import numpy as np
+from ParaUtils import parse_WPS_rankings
+from ParaUtils.Standards import LA2028_Events
+
+from pathlib import Path
+module_dir = Path(__file__).parent
+
+def set_AWR(DF):
+    CAN = DF[DF.NPC == 'CAN']
+    NR4 = DF[(DF.NPC_Rank > 3) & ~DF.index.isin(CAN.index)]
+    pool = DF[~(DF.index.isin(CAN.index) | DF.index.isin(NR4.index))]
+    pool = pool.assign(AWR=pool.Seconds.apply(lambda S: 1+len(pool[pool.Seconds < S])))
+    return (
+        pd.concat([
+            CAN.assign(AWR='CAN'),
+            NR4.assign(AWR='NR > 3'),
+            pool
+        ])
+        .sort_values('Seconds AWR'.split())
+    )
+
+Current_AWR = (
+    pd.read_excel(module_dir / '2025 Fall Performance AWR - 2025-10-07.xlsx')
+)

ParaUtils/AWR/year2025/Performance/__init__.py

@@ -0,0 +1,48 @@
+import pandas as pd
+import numpy as np
+from ParaUtils import parse_WPS_rankings
+from ParaUtils.Standards import LA2028_Events
+from ParaUtils.AWR import set_AWR
+
+from pathlib import Path
+module_dir = Path(__file__).parent
+
+ML = (
+    pd.read_excel(module_dir / '2025_10_07 World Para Swimming Online Classification Master List.xlsx',header=8)
+    .pipe(lambda df: df.rename(columns={c:c.replace(' ','_') for c in df.columns}))
+    .rename(columns={'ID':'SDMS_ID'})
+    .loc[:,'NPC Given_Name Family_Name SDMS_ID Gender S SB SM'.split()]
+    .assign(S=lambda df: df.S.apply(lambda S: int(''.join([c for c in '0'+str(S) if c.isdigit()]))))
+    .assign(SB=lambda df: df.SB.apply(lambda S: int(''.join([c for c in '0'+str(S) if c.isdigit()]))))
+    .assign(SM=lambda df: df.SM.apply(lambda S: int(''.join([c for c in '0'+str(S) if c.isdigit()]))))
+)
+
+AWR = parse_WPS_rankings(pd.read_excel(module_dir / '2025_10_07 World Para Swimming Online Rankings.xlsx',header=8))
+AWR = (
+    AWR
+    .pipe(lambda df: df.rename(columns={c:c.replace(' ','_') for c in df.columns}))
+    
+    #Update SportClass with MasterList Info
+    .merge(ML['SDMS_ID S SB SM'.split()],on='SDMS_ID',how='inner')
+    .assign(Category=lambda df: df.Stroke.apply(lambda S: {'Breaststroke':'SB','Medley':'SM'}.get(S,'S')))
+    .groupby('Category',group_keys=False)
+    .apply(lambda df: df.assign(SportClass=df.loc[:,df.Category.values[0]]))
+    
+    #Group by LA2028 Events
+    .merge(LA2028_Events,on='Gender SportClass Stroke Distance'.split(),how='inner')
+    
+    #Rank by NPC
+    .groupby('Gender EventClass Stroke Distance NPC'.split(),group_keys=False)
+    .apply(lambda df: df.assign(NPC_Rank=df.Seconds.apply(lambda S: 1+len(df[df.Seconds < S]))))
+    
+    #Set AWR, 3 per NPC excluding Canadians
+    .groupby('Gender EventClass Stroke Distance'.split(),group_keys=False)
+    .apply(set_AWR)
+    
+    #Set 2/3 threshold for DEV Cards
+    .groupby('Gender EventClass Stroke Distance'.split(),group_keys=False)
+    .apply(lambda df: df.assign(TopTwoThirds=int(np.floor(len(df)*2/3))))
+    
+    #Sort
+    .sort_values('Gender Stroke Distance EventClass Seconds AWR'.split())
+)

ParaUtils/AWR/year2025/Projected/__init__.py

@@ -0,0 +1,89 @@
+import pandas as pd
+import numpy as np
+from ParaUtils import parse_WPS_rankings
+from ParaUtils.Standards import WC2025_Events
+from ParaUtils.AWR import set_AWR
+
+from pathlib import Path
+module_dir = Path(__file__).parent
+
+fnames = ['Rankings 2023.xlsx','Rankings 2024.xlsx','Rankings 2025 2025-04-02.xlsx']
+raw = (
+    pd.concat([
+        pd.read_excel(module_dir / fname,header=8)
+        for fname in fnames
+    ])
+    .pipe(lambda df: parse_WPS_rankings(df))
+
+    #best results per athlete regardless of sportclass at performance
+    .sort_values('Seconds')
+    .groupby('SDMS_ID Stroke Distance'.split())
+    .head(1)
+    
+    #select columns
+    .pipe(lambda df: df['Gender SportClass Distance Stroke Result Seconds SDMS_ID NPC Given_Name Family_Name Date'.split()])
+    
+    #set helper column Cat
+    .assign(Cat=lambda df: df.Stroke.apply(lambda S: {'Breaststroke':'SB','Medley':'SM'}.get(S,'S')))
+)
+
+ML = (
+    pd.concat([
+        pd.read_excel(module_dir / 'Masterlist 2024.xlsx',header=8).assign(Year=2024),
+        pd.read_excel(module_dir / 'Masterlist 2025 2025-04-02.xlsx',header=8).assign(Year=2025),
+    ])
+    .reset_index(drop=True)
+    .pipe(lambda df: df.rename(columns={c:c.replace(' ','_') for c in df.columns}))
+    .rename(columns={'ID':'SDMS_ID','Status':'Status_S','Status.1':'Status_SB','Status.2':'Status_SM'})
+    .sort_values('Year')
+    .groupby('SDMS_ID')
+    .tail(1)
+    .pipe(lambda df: df['SDMS_ID Year S SB SM Status_S Status_SB Status_SM'.split()])
+    .assign(Helper=lambda df: df.Status_S.astype(str).str.upper().str.contains('N') | df.Status_SB.astype(str).str.upper().str.contains('N') | df.Status_SM.astype(str).str.upper().str.contains('N'))
+    .pipe(lambda df: df[~df.Helper])
+    .melt(id_vars='Helper SDMS_ID Year'.split())
+    .pipe(lambda df: df[~df.value.isin('NE CNC'.split())])
+    .dropna()
+    .assign(Cat=lambda df: df.variable.apply(lambda S: S.split('_')[-1]))
+    .assign(Type=lambda df: df.variable.replace('S','SportClass_S').replace('SB','SportClass_SB').replace('SM','SportClass_SM').apply(lambda S: S.split('_')[0]))
+    .pipe(lambda df: pd.pivot_table(df,index='SDMS_ID Year Cat'.split(),columns='Type',values='value',aggfunc=min))
+    .dropna()
+    .reset_index()
+    .assign(SportClass=lambda df: df.SportClass.apply(lambda S: int(''.join([c for c in str(S) if c.isdigit()]))))
+    .drop('Status',axis=1)
+    .pipe(lambda df: pd.concat([df,(
+        raw
+        .pipe(lambda df: df[df.Date.dt.year == 2023])
+        .assign(Year=2023)
+        .pipe(lambda df: df['SDMS_ID Year Cat SportClass'.split()])
+    )]))
+    .sort_values('Year')
+    .groupby('SDMS_ID Cat'.split())
+    .tail(1)
+)
+
+AWR = (
+    raw
+
+    #set sportclass to most recent ML or results from 2023
+    .merge(ML,on='SDMS_ID Cat'.split(),how='inner')
+    .drop('SportClass_x',axis=1)
+    .rename(columns={'SportClass_y':'SportClass'})
+    
+    #filter to 2025 WC events including swimups
+    .merge(WC2025_Events,on='Gender SportClass Stroke Distance'.split(),how='inner')
+    
+    #best performance per event per swimmer per eventclass
+    .sort_values('Seconds')
+    .groupby('SDMS_ID EventClass Stroke Distance'.split())
+    .head(1)
+    
+    #set National Rankings
+    .groupby('NPC Gender EventClass Stroke Distance'.split(),group_keys=False)
+    .apply(lambda df: df.assign(NPC_Rank=df.Seconds.apply(lambda S: 1+len(df[df.Seconds < S]))))
+    
+    #set AWR: 3 per country, no Canadians
+    .groupby('Gender EventClass Stroke Distance'.split(),group_keys=False)
+    .apply(set_AWR)
+    .sort_values('Gender Stroke Distance SportClass Seconds'.split())
+)

ParaUtils/Score/__init__.py

@@ -0,0 +1,39 @@
+import pandas as pd
+import numpy as np
+
+from pathlib import Path
+module_dir = Path(__file__).parent
+
+SNC_Seeds = (
+    #pd.read_excel(module_dir / 'SNC_Seeds.xlsx')
+    pd.read_excel(module_dir / '2025 Swimming Canada Para Points Calculator.xlsx')
+    .assign(SportClass=lambda df: df.SportClass.astype(str))
+)
+def SNC_Score(DF):
+    Score = lambda x,scale: 1000*(((1-np.exp(-0.4*(np.exp(scale*x)-1)))/0.95)**3)
+    prepped = (
+        DF
+        .merge(SNC_Seeds,on='Gender Course Stroke Distance SportClass'.split(),how='left')
+        .assign(V=lambda df: df.Distance/df.Seconds)
+    )
+    return (
+        prepped
+        .assign(Score=lambda df: df.apply(lambda S: Score(S.V,S.Scale),axis=1).fillna(0).astype(int))
+        .drop('Scale',axis=1)
+    )
+
+WPS_Seeds = (
+    pd.read_excel(module_dir / '2024 World Para Swimming Points Calculator.xlsx',sheet_name='Parameters')
+    .assign(Gender=lambda df: df.Gender.apply(lambda S: S[0]))
+    .pipe(lambda df: pd.concat([df,df.Event.str.extract(r"(?P<Distance>\d+) m (Individual )*(?P<Stroke>[A-z]+)")],axis=1))
+    .assign(SportClass=lambda df: df.Class.apply(lambda S: ''.join([c for c in str(S) if c.isdigit()])))
+    .astype({'Distance':int})
+    .assign(Course='LCM')
+    .pipe(lambda df: df['Gender Course SportClass Distance Stroke a b c'.split()])
+)
+def WPS_Score(DF):
+    return (
+        DF.merge(WPS_Seeds,on='Gender Course SportClass Distance Stroke'.split(),how='left')
+        .assign(WPS_Score=lambda df: (df.a*np.exp(-np.exp(df.b-(df.c/df.Seconds)))).fillna(0).astype(int))
+        .drop('a b c'.split(),axis=1)
+    )

ParaUtils/Standards/__init__.py

@@ -0,0 +1,40 @@
+import pandas as pd
+import numpy as np
+
+from pathlib import Path
+module_dir = Path(__file__).parent
+
+def add_possible_swimups(DF):
+    ec = DF.EventClass.values[0]
+    if ec in [2,3,4,5,6,7,8,9,10,12,13]:
+        sc = [ec,ec-1]
+    else:
+        sc = [ec]
+    return DF.assign(SportClass=[sc]*len(DF))
+
+def set_swimups(DF):
+    inclass = DF[DF.EventClass == DF.SportClass]
+    swimup = DF[~DF.index.isin(inclass) & ~DF.SportClass.isin(DF.EventClass)]
+    return pd.concat([inclass,swimup])
+
+
+WC2025_MQS_MET = (
+    pd.read_excel(module_dir / '2025 WPS WC MQS and METs.xlsx')
+)
+WC2025_Events = WC2025_MQS_MET.drop('MQS MET'.split(),axis=1)
+
+LA2028_Events = (
+    pd.read_excel(module_dir / 'Draft LA2028 Events.xlsx')
+    .ffill()
+    .groupby('EventClass',group_keys=False)
+    .apply(add_possible_swimups)
+    .explode('SportClass')
+    .reset_index(drop=True)
+    .groupby('Gender Distance Stroke'.split(),group_keys=False)
+    .apply(set_swimups)
+    .sort_values('Gender Stroke Distance EventClass SportClass'.split())
+    .reset_index(drop=True)
+    .astype({'Distance':int,'EventClass':int,'SportClass':int})
+)
+
+__all__ = 'WC2025_MQS_MET WC2025_Events LA2028_Events'.split()

ParaUtils/utils.py

@@ -1,6 +1,6 @@
 #Bits and bobs used for many different projects. Junk drawer module
-import pandas
-import numpy
+import pandas as pd
+import numpy as np
 
 
 #Useful functions for parsing race-like durations, and normalizing their string reps
@@ -9,7 +9,7 @@ def t2f(S):
         return None
     m,s = ('0:%s' % S).split(':')[-2:]
     try:
-        return numpy.round(60*int(m) + float(s),2)
+        return np.round(60*int(m) + float(s),2)
     except:
         return -1
 
@@ -24,7 +24,7 @@ def f2t(S):
     return f'{m:02}:{s:02}.{round(hs*100):02}'
 
 #Canada Summer Games eligible events
-CSG = pandas.DataFrame([
+CSG = pd.DataFrame([
     {'Stroke':'Butterfly','Distance':50,'SportClass':[1,2,3,4,5,6,7]},
     {'Stroke':'Butterfly','Distance':100,'SportClass':[8,9,10,11,12,13,14]},
     {'Stroke':'Backstroke','Distance':50,'SportClass':[1,2,3,4,5]},
@@ -61,7 +61,3 @@ def parse_WPS_rankings(DF):
         #Drop excess columns
         .pipe(lambda df: df['Gender SportClass Distance Stroke Result Seconds SDMS_ID NPC Given_Name Family_Name Date'.split()])
     )
-
-
-
-__version__ = "0.1.1"