non working version

rowers/dataprep.py

@@ -12,7 +12,8 @@ from rowingdata import get_file_type,get_empower_rigging
 
 from pandas import DataFrame,Series
 from pytz import timezone as tz,utc
-
+from django.utils import timezone
+from time import strftime,strptime,mktime,time,daylight
 from django.utils.timezone import get_current_timezone
 thetimezone = get_current_timezone()
 from rowingdata import (
@@ -80,7 +81,8 @@ columndict = {
     'finish':'finish',
     'peakforceangle':'peakforceangle',
     'wash':'wash',
-    'slip':'wash',    
+    'slip':'wash',
+    'workoutstate':' WorkoutState',
     }
     
 from scipy.signal import savgol_filter
@@ -621,6 +623,62 @@ def new_workout_from_file(r,f2,
 
     return (id,message,f2)
 
+# Create new workout from data frame and store it in the database
+# This routine should be used everywhere in views.py and mailprocessing.py
+# Currently there is code duplication
+def new_workout_from_df(r,df,
+                        title='New Workout',
+                        parent=None):
+
+    message = None
+
+    summary = ''
+    if parent:
+        oarlength = parent.oarlength
+        inboard = parent.inboard
+        workouttype = parent.workouttype
+        notes=parent.notes
+        summary=parent.summary
+        makeprivate=parent.privacy
+        startdatetime=parent.startdatetime
+    else:        
+        oarlength = 2.89
+        inboard = 0.88
+        workouttype = 'rower'
+        notes=''
+        summary=''
+        makeprivate=False
+        startdatetime = timezone.now()
+
+    timestr = strftime("%Y%m%d-%H%M%S")
+
+    csvfilename ='media/Fusion_'+timestr+'.csv'
+
+    df.rename(columns = columndict,inplace=True)
+    starttimeunix = mktime(startdatetime.utctimetuple())
+    df[' ElapsedTime (sec)'] = df['TimeStamp (sec)']
+    df['TimeStamp (sec)'] = df['TimeStamp (sec)']+starttimeunix
+
+    row = rrdata(df=df)
+    row.write_csv(csvfilename,gzip=True)
+    
+    #res =  df.to_csv(csvfilename+'.gz',index_label='index',
+    #                 compression='gzip')
+
+    id,message = save_workout_database(csvfilename,r,
+                                       workouttype=workouttype,
+                                       title=title,
+                                       notes=notes,
+                                       oarlength=oarlength,
+                                       inboard=inboard,
+                                       makeprivate=makeprivate,
+                                       dosmooth=False)
+        
+
+    return (id,message)
+
+
+
 # Compare the data from the CSV file and the database
 # Currently only calculates number of strokes. To be expanded with
 # more elaborate testing if needed
@@ -696,10 +754,10 @@ def repair_data(verbose=False):
 # A wrapper around the rowingdata class, with some error catching
 def rdata(file,rower=rrower()):
     try:
-	res = rrdata(file,rower=rower)
+	res = rrdata(csvfile=file,rower=rower)
     except IOError,IndexError:
         try:
-            res = rrdata(file+'.gz',rower=rower)
+            res = rrdata(csvfile=file+'.gz',rower=rower)
         except IOError,IndexError:
 	    res = 0
 
@@ -900,11 +958,21 @@ def smalldataprep(therows,xparam,yparam1,yparam2):
 
 # data fusion
 def datafusion(id1,id2,columns,offset):
-    df1 = getrowdata_db(id=id1)
+    df1,w1 = getrowdata_db(id=id1)
+    df1 = df1.drop(['cumdist',
+                    'hr_ut2',
+		    'hr_ut1',
+		    'hr_at',
+		    'hr_tr',
+		    'hr_an',
+		    'hr_max',],
+                   1,errors='ignore')
     columns = ['time']+columns
-    df2 = getsmallrowdata_db(columns,ids=[id2])
+    df2 = getsmallrowdata_db(columns,ids=[id2],doclean=False)
 
-    keep1 = set(df1.columns)
+    print df1['pace'].mean()/1000.,'mies'
+    
+    keep1 = {c:c for c in set(df1.columns)}
     for c in columns:
         keep1.pop(c)
     
@@ -913,10 +981,14 @@ def datafusion(id1,id2,columns,offset):
             df1 = df1.drop(c,1,errors='ignore')
 
     df = pd.concat([df1,df2],ignore_index=True)
-    df = df.sort_value(['time'])
-    df.interpolate(method='linear',axis=0,limit_direction='both')
+    df = df.sort_values(['time'])
+    df = df.interpolate(method='linear',axis=0,limit_direction='both')
     df.fillna(method='bfill',inplace=True)
-
+    
+    df['time'] = df['time']/1000.
+    df['pace'] = df['pace']/1000.
+    print df['pace'].mean(),'noot'
+    
     return df
 
 # This is the main routine.
@@ -933,6 +1005,7 @@ def dataprep(rowdatadf,id=0,bands=True,barchart=True,otwpower=True,
     rowdatadf.loc[row_index,' Stroke500mPace (sec/500m)'] = 3000.
 
     p = rowdatadf.ix[:,' Stroke500mPace (sec/500m)']
+    print p.mean(),'aap'
     hr = rowdatadf.ix[:,' HRCur (bpm)']
     spm = rowdatadf.ix[:,' Cadence (stokes/min)']
     cumdist = rowdatadf.ix[:,'cum_dist']