Offline CP calculations for OTW

A new table in the database with precalculated CP values. The data
are updated through RQ/Celery asynchronous functions

rowers/dataprep.py

@@ -17,6 +17,7 @@ from django.utils import timezone
 from time import strftime, strptime, mktime, time, daylight
 import arrow
 from django.utils.timezone import get_current_timezone
+
 thetimezone = get_current_timezone()
 from rowingdata import (
     TCXParser, RowProParser, ErgDataParser,
@@ -40,7 +41,7 @@ import itertools
 import math
 from tasks import (
     handle_sendemail_unrecognized, handle_sendemail_breakthrough,
-    handle_sendemail_hard
+    handle_sendemail_hard, handle_updatecp
 )
 
 from django.conf import settings
@@ -425,6 +426,112 @@ def paceformatsecs(values):
 
     return out
 
+def getcpdata_sql(rower_id):
+    engine = create_engine(database_url, echo=False)
+    query = sa.text('SELECT delta,cp from cpdata WHERE user={rower_id};'.format(
+        rower_id=rower_id
+        ))
+    connection = engine.raw_connection()
+    df = pd.read_sql_query(query, engine)
+
+    return df
+
+def deletecpdata_sql(rower_id):
+    engine = create_engine(database_url, echo=False)
+    query = sa.text('DELETE from cpdata WHERE user={rower_id};'.format(
+        rower_id=rower_id
+        ))
+    with engine.connect() as conn, conn.begin():
+        try:
+            result = conn.execute(query)
+        except:
+            print "Database locked"
+    conn.close()
+    engine.dispose()
+
+    
+    
+def updatecpdata_sql(rower_id,delta,cp):
+    deletecpdata_sql(rower_id)
+    df = pd.DataFrame(
+        {
+            'delta':delta,
+            'cp':cp,
+            'user':rower_id
+        }
+    )
+
+    engine = create_engine(database_url, echo=False)
+    with engine.connect() as conn, conn.begin():
+        df.to_sql('cpdata', engine, if_exists='append', index=False)
+    conn.close()
+    engine.dispose()
+
+
+def runcpupdate(rower):
+    startdate = timezone.now()-datetime.timedelta(days=365)
+    enddate = timezone.now()+datetime.timedelta(days=5)
+    theworkouts = Workout.objects.filter(user=rower,rankingpiece=True,
+				          workouttype='water',
+				          startdatetime__gte=startdate,
+					  startdatetime__lte=enddate)
+
+    theids = [w.id for w in theworkouts]
+
+
+    if settings.DEBUG:
+        res = handle_updatecp.delay(rower.id,theids,debug=True)
+    else:
+        res = queue.enqueue(handle_updatecp,rower.id,theids)
+
+    
+def fetchcp(rower,theworkouts):
+    # get all power data from database (plus workoutid)
+    theids = [int(w.id) for w in theworkouts]
+    columns = ['power','workoutid','time']
+    df = getsmallrowdata_db(columns,ids=theids)
+
+    dfgrouped = df.groupby(['workoutid'])
+    avgpower2 = dict(dfgrouped.mean()['power'].astype(int))
+
+    cpdf = getcpdata_sql(rower.id)
+
+    if not cpdf.empty:
+        return cpdf['delta'],cpdf['cp'],avgpower2
+    else:
+        if settings.DEBUG:
+            res = handle_updatecp.delay(rower.id,theids,debug=True)
+        else:
+            res = queue.enqueue(handle_updatecp,rower.id,theids)
+        return [],[],avgpower2
+
+    #  below is redundant
+    thesecs = []
+
+    for w in theworkouts:
+        timesecs = 3600*w.duration.hour
+	timesecs += 60*w.duration.minute
+	timesecs += w.duration.second
+	timesecs += 1.e-5*w.duration.microsecond
+	
+	thesecs.append(timesecs)
+
+    if len(thesecs) != 0:
+        maxt = 1.05*pd.Series(thesecs).max()
+    else:
+        maxt = 1000.
+
+        
+    logarr = datautils.getlogarr(maxt)
+
+        
+    delta,cpvalue,avgpower = datautils.getcp(dfgrouped,logarr)
+
+    updatecpdata_sql(rower.id,delta,cpvalue)
+
+    return delta,cpvalue,avgpower2
+
+
 # Processes painsled CSV file to database