# This is Data prep used for testing purposes (no Django environment) # Uses the debug SQLite database for stroke data from rowingdata import rowingdata as rrdata from rowingdata import make_cumvalues from rowingdata import rower as rrower from rowingdata import main as rmain from time import strftime from pandas import DataFrame,Series import pandas as pd import numpy as np import itertools from sqlalchemy import create_engine import sqlalchemy as sa from rowsandall_app.settings import DATABASES from rowsandall_app.settings_dev import DATABASES as DEV_DATABASES from utils import lbstoN try: user = DATABASES['default']['USER'] except KeyError: user = '' try: password = DATABASES['default']['PASSWORD'] except KeyError: password = '' try: database_name = DATABASES['default']['NAME'] except KeyError: database_name = '' try: host = DATABASES['default']['HOST'] except KeyError: host = '' try: port = DATABASES['default']['PORT'] except KeyError: port = '' database_url = 'mysql://{user}:{password}@{host}:{port}/{database_name}'.format( user=user, password=password, database_name=database_name, host=host, port=port, ) database_name_dev = DEV_DATABASES['default']['NAME'] database_url_debug = 'sqlite:///'+database_name_dev # mapping the DB column names to the CSV file column names columndict = { 'time':'TimeStamp (sec)', 'hr':' HRCur (bpm)', 'pace':' Stroke500mPace (sec/500m)', 'spm':' Cadence (stokes/min)', 'power':' Power (watts)', 'averageforce':' AverageDriveForce (lbs)', 'drivelength':' DriveLength (meters)', 'peakforce':' PeakDriveForce (lbs)', 'distance':' Horizontal (meters)', 'catch':'catch', 'finish':'finish', 'peakforceangle':'peakforceangle', 'wash':'wash', 'slip':'wash', 'workoutstate':' WorkoutState', 'cumdist':'cum_dist', } from scipy.signal import savgol_filter import datetime def niceformat(values): out = [] for v in values: formattedv = strfdelta(v) out.append(formattedv) return out def strfdelta(tdelta): try: minutes,seconds = divmod(tdelta.seconds,60) tenths = int(tdelta.microseconds/1e5) except AttributeError: minutes,seconds = divmod(tdelta.view(np.int64),60e9) seconds,rest = divmod(seconds,1e9) tenths = int(rest/1e8) res = "{minutes:0>2}:{seconds:0>2}.{tenths:0>1}".format( minutes=minutes, seconds=seconds, tenths=tenths, ) return res def nicepaceformat(values): out = [] for v in values: formattedv = strfdelta(v) out.append(formattedv) return out def timedeltaconv(x): if not np.isnan(x): dt = datetime.timedelta(seconds=x) else: dt = datetime.timedelta(seconds=350.) return dt def rdata(file,rower=rrower()): try: res = rrdata(file,rower=rower) except IOError: try: res = rrdata(file+'.gz',rower=rower) except IOError: res = 0 return res def totaltime_sec_to_string(totaltime): hours = int(totaltime / 3600.) if hours > 23: message = 'Warning: The workout duration was longer than 23 hours. ' hours = 23 minutes = int((totaltime - 3600. * hours) / 60.) if minutes > 59: minutes = 59 if not message: message = 'Warning: there is something wrong with the workout duration' seconds = int(totaltime - 3600. * hours - 60. * minutes) if seconds > 59: seconds = 59 if not message: message = 'Warning: there is something wrong with the workout duration' tenths = int(10 * (totaltime - 3600. * hours - 60. * minutes - seconds)) if tenths > 9: tenths = 9 if not message: message = 'Warning: there is something wrong with the workout duration' duration = "%s:%s:%s.%s" % (hours, minutes, seconds, tenths) return duration # Creates C2 stroke data def create_c2_stroke_data_db( distance,duration,workouttype, workoutid,starttimeunix,csvfilename,debug=False): nr_strokes = int(distance/10.) totalseconds = duration.hour*3600. totalseconds += duration.minute*60. totalseconds += duration.second totalseconds += duration.microsecond/1.e6 spm = 60.*nr_strokes/totalseconds step = totalseconds/float(nr_strokes) elapsed = np.arange(nr_strokes)*totalseconds/(float(nr_strokes-1)) dstep = distance/float(nr_strokes) d = np.arange(nr_strokes)*distance/(float(nr_strokes-1)) unixtime = starttimeunix + elapsed pace = 500.*totalseconds/distance if workouttype in ['rower','slides','dynamic']: velo = distance/totalseconds power = 2.8*velo**3 else: power = 0 df = pd.DataFrame({ 'TimeStamp (sec)': unixtime, ' Horizontal (meters)': d, ' Cadence (stokes/min)': spm, ' Stroke500mPace (sec/500m)':pace, ' ElapsedTime (sec)':elapsed, ' Power (watts)':power, ' HRCur (bpm)':np.zeros(nr_strokes), ' longitude':np.zeros(nr_strokes), ' latitude':np.zeros(nr_strokes), ' DragFactor':np.zeros(nr_strokes), ' DriveLength (meters)':np.zeros(nr_strokes), ' StrokeDistance (meters)':np.zeros(nr_strokes), ' DriveTime (ms)':np.zeros(nr_strokes), ' StrokeRecoveryTime (ms)':np.zeros(nr_strokes), ' AverageDriveForce (lbs)':np.zeros(nr_strokes), ' PeakDriveForce (lbs)':np.zeros(nr_strokes), ' lapIdx':np.zeros(nr_strokes), 'cum_dist': d }) timestr = strftime("%Y%m%d-%H%M%S") df[' ElapsedTime (sec)'] = df['TimeStamp (sec)'] res = df.to_csv(csvfilename,index_label='index', compression='gzip') data = dataprep(df,id=workoutid,bands=False,debug=debug) return data # Saves C2 stroke data to CSV and database def add_c2_stroke_data_db(strokedata,workoutid,starttimeunix,csvfilename, debug=False): res = make_cumvalues(0.1*strokedata['t']) cum_time = res[0] lapidx = res[1] unixtime = cum_time+starttimeunix # unixtime[0] = starttimeunix seconds = 0.1*strokedata.ix[:,'t'] nr_rows = len(unixtime) try: latcoord = strokedata.ix[:,'lat'] loncoord = strokedata.ix[:,'lon'] except: latcoord = np.zeros(nr_rows) loncoord = np.zeros(nr_rows) try: strokelength = strokedata.ix[:,'strokelength'] except: strokelength = np.zeros(nr_rows) dist2 = 0.1*strokedata.ix[:,'d'] try: spm = strokedata.ix[:,'spm'] except KeyError: spm = 0*dist2 try: hr = strokedata.ix[:,'hr'] except KeyError: hr = 0*spm pace = strokedata.ix[:,'p']/10. pace = np.clip(pace,0,1e4) pace = pace.replace(0,300) velo = 500./pace power = 2.8*velo**3 # save csv # Create data frame with all necessary data to write to csv df = pd.DataFrame({'TimeStamp (sec)':unixtime, ' Horizontal (meters)': dist2, ' Cadence (stokes/min)':spm, ' HRCur (bpm)':hr, ' longitude':loncoord, ' latitude':latcoord, ' Stroke500mPace (sec/500m)':pace, ' Power (watts)':power, ' DragFactor':np.zeros(nr_rows), ' DriveLength (meters)':np.zeros(nr_rows), ' StrokeDistance (meters)':strokelength, ' DriveTime (ms)':np.zeros(nr_rows), ' StrokeRecoveryTime (ms)':np.zeros(nr_rows), ' AverageDriveForce (lbs)':np.zeros(nr_rows), ' PeakDriveForce (lbs)':np.zeros(nr_rows), ' lapIdx':lapidx, ' ElapsedTime (sec)':seconds, 'cum_dist': dist2 }) df.sort_values(by='TimeStamp (sec)',ascending=True) timestr = strftime("%Y%m%d-%H%M%S") # Create CSV file name and save data to CSV file res = df.to_csv(csvfilename,index_label='index', compression='gzip') data = dataprep(df,id=workoutid,bands=False,debug=debug) return data # Processes painsled CSV file to database def save_workout_database(f2,r,dosmooth=True,workouttype='rower', dosummary=True,title='Workout', notes='',totaldist=0,totaltime=0, summary='', makeprivate=False, oarlength=2.89,inboard=0.88): message = None powerperc = 100*np.array([r.pw_ut2, r.pw_ut1, r.pw_at, r.pw_tr,r.pw_an])/r.ftp # make workout and put in database rr = rrower(hrmax=r.max,hrut2=r.ut2, hrut1=r.ut1,hrat=r.at, hrtr=r.tr,hran=r.an,ftp=r.ftp, powerperc=powerperc,powerzones=r.powerzones) row = rdata(f2,rower=rr) checks = row.check_consistency() allchecks = 1 for key,value in checks.iteritems(): if not value: allchecks = 0 if not allchecks: #row.repair() pass if row == 0: return (0,'Error: CSV data file not found') if dosmooth: # auto smoothing pace = row.df[' Stroke500mPace (sec/500m)'].values velo = 500./pace f = row.df['TimeStamp (sec)'].diff().mean() if f !=0: windowsize = 2*(int(10./(f)))+1 else: windowsize = 1 if not 'originalvelo' in row.df: row.df['originalvelo'] = velo if windowsize > 3 and windowsize23: message = 'Warning: The workout duration was longer than 23 hours. ' hours = 23 minutes = int((totaltime - 3600.*hours)/60.) if minutes>59: minutes = 59 if not message: message = 'Warning: there is something wrong with the workout duration' seconds = int(totaltime - 3600.*hours - 60.*minutes) if seconds > 59: seconds = 59 if not message: message = 'Warning: there is something wrong with the workout duration' tenths = int(10*(totaltime - 3600.*hours - 60.*minutes - seconds)) if tenths > 9: tenths = 9 if not message: message = 'Warning: there is something wrong with the workout duration' duration = "%s:%s:%s.%s" % (hours,minutes,seconds,tenths) if dosummary: summary = row.summary() summary += '\n' summary += row.intervalstats() workoutdate = row.rowdatetime.strftime('%Y-%m-%d') workoutstarttime = row.rowdatetime.strftime('%H:%M:%S') workoutstartdatetime = thetimezone.localize(row.rowdatetime).astimezone(utc) if makeprivate: privacy = 'private' else: privacy = 'visible' # check for duplicate start times ws = Workout.objects.filter(startdatetime=workoutstartdatetime, user=r) if (len(ws) != 0): message = "Warning: This workout probably already exists in the database" privacy = 'private' w = Workout(user=r,name=title,date=workoutdate, workouttype=workouttype, duration=duration,distance=totaldist, weightcategory=r.weightcategory, starttime=workoutstarttime, csvfilename=f2,notes=notes,summary=summary, maxhr=maxhr,averagehr=averagehr, startdatetime=workoutstartdatetime, inboard=inboard,oarlength=oarlength, privacy=privacy) w.save() if privacy == 'visible': ts = Team.objects.filter(rower=r) for t in ts: w.team.add(t) # put stroke data in database res = dataprep(row.df,id=w.id,bands=True, barchart=True,otwpower=True,empower=True,inboard=inboard) return (w.id,message) def handle_nonpainsled(f2,fileformat,summary=''): oarlength = 2.89 inboard = 0.88 # handle RowPro: if (fileformat == 'rp'): row = RowProParser(f2) # handle TCX if (fileformat == 'tcx'): row = TCXParser(f2) # handle Mystery if (fileformat == 'mystery'): row = MysteryParser(f2) # handle RowPerfect if (fileformat == 'rowperfect3'): row = RowPerfectParser(f2) # handle ErgData if (fileformat == 'ergdata'): row = ErgDataParser(f2) # handle CoxMate if (fileformat == 'coxmate'): row = CoxMateParser(f2) # handle Mike if (fileformat == 'bcmike'): row = BoatCoachAdvancedParser(f2) # handle BoatCoach OTW if (fileformat == 'boatcoachotw'): row = BoatCoachOTWParser(f2) # handle BoatCoach if (fileformat == 'boatcoach'): row = BoatCoachParser(f2) # handle painsled desktop if (fileformat == 'painsleddesktop'): row = painsledDesktopParser(f2) # handle speed coach GPS if (fileformat == 'speedcoach'): row = speedcoachParser(f2) # handle speed coach GPS 2 if (fileformat == 'speedcoach2'): row = SpeedCoach2Parser(f2) try: oarlength,inboard = get_empower_rigging(f2) summary = row.allstats() except: pass # handle ErgStick if (fileformat == 'ergstick'): row = ErgStickParser(f2) # handle FIT if (fileformat == 'fit'): row = FITParser(f2) s = fitsummarydata(f2) s.setsummary() summary = s.summarytext f_to_be_deleted = f2 # should delete file f2 = f2[:-4]+'o.csv' row.write_csv(f2,gzip=True) #os.remove(f2) try: os.remove(f_to_be_deleted) except: os.remove(f_to_be_deleted+'.gz') return (f2,summary,oarlength,inboard) # Create new workout from file 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_file(r,f2, workouttype='rower', title='Workout', makeprivate=False, notes=''): message = None fileformat = get_file_type(f2) summary = '' oarlength = 2.89 inboard = 0.88 if len(fileformat)==3 and fileformat[0]=='zip': f_to_be_deleted = f2 with zipfile.ZipFile(f2) as z: for fname in z.namelist(): f3 = z.extract(fname,path='media/') id,message,f2 = new_workout_from_file(r,f3, workouttype=workouttype, makeprivate=makeprivate, title = title, notes='') os.remove(f_to_be_deleted) return id,message,f2 # Some people try to upload Concept2 logbook summaries if fileformat == 'c2log': os.remove(f2) message = "This C2 logbook summary does not contain stroke data. Please download the Export Stroke Data file from the workout details on the C2 logbook." return (0,message,f2) if fileformat == 'nostrokes': os.remove(f2) message = "It looks like this file doesn't contain stroke data." return (0,message,f2) # Some people try to upload RowPro summary logs if fileformat == 'rowprolog': os.remove(f2) message = "This RowPro logbook summary does not contain stroke data. Please use the Stroke Data CSV file for the individual workout in your log." return (0,message,f2) # Sometimes people try an unsupported file type. # Send an email to info@rowsandall.com with the file attached # for me to check if it is a bug, or a new file type # worth supporting if fileformat == 'unknown': message = "We couldn't recognize the file type" if settings.DEBUG: res = handle_sendemail_unrecognized.delay(f2, r.user.email) else: res = queuehigh.enqueue(handle_sendemail_unrecognized, f2,r.user.email) return (0,message,f2) # handle non-Painsled by converting it to painsled compatible CSV if (fileformat != 'csv'): try: f2,summary,oarlength,inboard = handle_nonpainsled(f2, fileformat, summary=summary) except: errorstring = str(sys.exc_info()[0]) message = 'Something went wrong: '+errorstring return (0,message,'') dosummary = (fileformat != 'fit') id,message = save_workout_database(f2,r, workouttype=workouttype, makeprivate=makeprivate, dosummary=dosummary, summary=summary, inboard=inboard,oarlength=oarlength, title=title) return (id,message,f2) def delete_strokedata(id,debug=False): if debug: engine = create_engine(database_url_debug, echo=False) else: engine = create_engine(database_url, echo=False) query = sa.text('DELETE FROM strokedata WHERE workoutid={id};'.format( id=id, )) with engine.connect() as conn, conn.begin(): try: result = conn.execute(query) except: print "Database Locked" conn.close() engine.dispose() def update_strokedata(id,df,debug=False): delete_strokedata(id,debug=debug) if debug: print "updating ",id rowdata = dataprep(df,id=id,bands=True,barchart=True,otwpower=True, debug=debug) return rowdata def testdata(time,distance,pace,spm): t1 = np.issubdtype(time,np.number) t2 = np.issubdtype(distance,np.number) t3 = np.issubdtype(pace,np.number) t4 = np.issubdtype(spm,np.number) return t1 and t2 and t3 and t4 def getsmallrowdata_db(columns,ids=[],debug=False): data = read_cols_df_sql(ids,columns,debug=debug) return data def fitnessmetric_to_sql(m,table='powertimefitnessmetric',debug=False, doclean=False): # test if nan among values if np.nan in m.values(): for key in m.keys(): if np.isnan([m[key]]): m[key] = -1 if debug: engine = create_engine(database_url_debug, echo=False) else: engine = create_engine(database_url, echo=False) columns = ', '.join(m.keys()) if debug: placeholders = ", ".join(["?"] * len(m)) else: placeholders = ", ".join(["%s"] * len(m)) query = "INSERT into %s ( %s ) Values (%s)" % (table, columns, placeholders) query2 = "DELETE FROM %s WHERE PowerFourMin < 0 and PowerOneHour < 0 and PowerTwoK < 0 and user_id = %s " % (table,m['user_id']) values = tuple(m[key] for key in m.keys()) with engine.connect() as conn, conn.begin(): result = conn.execute(query,values) if doclean: result2 = conn.execute(query2) conn.close() engine.dispose() return 1 def read_cols_df_sql(ids,columns,debug=False): columns = list(columns)+['distance','spm'] columns = [x for x in columns if x != 'None'] columns = list(set(columns)) cls = '' ids = [int(id) for id in ids] if debug: engine = create_engine(database_url_debug, echo=False) else: engine = create_engine(database_url, echo=False) for column in columns: cls += column+', ' cls = cls[:-2] if len(ids) == 0: query = sa.text('SELECT {columns} FROM strokedata WHERE workoutid=0'.format( columns = cls, )) elif len(ids) == 1: query = sa.text('SELECT {columns} FROM strokedata WHERE workoutid={id}'.format( id = ids[0], columns = cls, )) else: query = sa.text('SELECT {columns} FROM strokedata WHERE workoutid IN {ids}'.format( columns = cls, ids = tuple(ids), )) df = pd.read_sql_query(query,engine) engine.dispose() return df def read_df_sql(id,debug=False): if debug: engine = create_engine(database_url_debug, echo=False) print "read_df",id print database_url_debug else: engine = create_engine(database_url, echo=False) df = pd.read_sql_query(sa.text( 'SELECT * FROM strokedata WHERE workoutid={id}'.format( id=id )), engine) engine.dispose() return df def getcpdata_sql(rower_id,table='cpdata',debug=False): if debug: engine = create_engine(database_url_debug, echo=False) else: engine = create_engine(database_url, echo=False) query = sa.text('SELECT * from {table} WHERE user={rower_id};'.format( rower_id=rower_id, table=table, )) connection = engine.raw_connection() df = pd.read_sql_query(query, engine) return df def deletecpdata_sql(rower_id,table='cpdata',debug=False): if debug: engine = create_engine(database_url_debug, echo=False) else: engine = create_engine(database_url, echo=False) query = sa.text('DELETE from {table} WHERE user={rower_id};'.format( rower_id=rower_id, table=table, )) with engine.connect() as conn, conn.begin(): try: result = conn.execute(query) except: print "Database locked" conn.close() engine.dispose() def delete_agegroup_db(age,sex,weightcategory,debug=False): if debug: engine = create_engine(database_url_debug, echo=False) else: engine = create_engine(database_url, echo=False) query = sa.text('DELETE from {table} WHERE age={age} and weightcategory = {weightcategory} and sex={sex};'.format( sex=sex, age=age, weightcategory=weightcategory, table='calcagegrouprecords' )) with engine.connect() as conn, conn.begin(): try: result = conn.execute(query) except: print "Database locked" conn.close() engine.dispose() def update_agegroup_db(age,sex,weightcategory,wcdurations,wcpower, debug=False): delete_agegroup_db(age,sex,weightcategory,debug=debug) df = pd.DataFrame( { 'duration':wcdurations, 'power':wcpower, } ) df['sex'] = sex df['age'] = age df['weightcategory'] = weightcategory if debug: engine = create_engine(database_url_debug, echo=False) else: engine = create_engine(database_url, echo=False) table = 'calcagegrouprecords' with engine.connect() as conn, conn.begin(): df.to_sql(table, engine, if_exists='append', index=False) conn.close() engine.dispose() def updatecpdata_sql(rower_id,delta,cp,table='cpdata',distance=pd.Series([]),debug=False): deletecpdata_sql(rower_id,table=table,debug=debug) df = pd.DataFrame( { 'delta':delta, 'cp':cp, 'user':rower_id } ) if not distance.empty: df['distance'] = distance if debug: engine = create_engine(database_url_debug, echo=False) else: engine = create_engine(database_url, echo=False) with engine.connect() as conn, conn.begin(): df.to_sql(table, engine, if_exists='append', index=False) conn.close() engine.dispose() def smalldataprep(therows,xparam,yparam1,yparam2): df = pd.DataFrame() if yparam2 == 'None': yparam2 = 'power' df[xparam] = [] df[yparam1] = [] df[yparam2] = [] df['distance'] = [] df['spm'] = [] for workout in therows: f1 = workout.csvfilename try: rowdata = dataprep(rrdata(f1).df) rowdata = pd.DataFrame({xparam: rowdata[xparam], yparam1: rowdata[yparam1], yparam2: rowdata[yparam2], 'distance': rowdata['distance'], 'spm': rowdata['spm'], } ) df = pd.concat([df,rowdata],ignore_index=True) except IOError: try: rowdata = dataprep(rrdata(f1+'.gz').df) rowdata = pd.DataFrame({xparam: rowdata[xparam], yparam1: rowdata[yparam1], yparam2: rowdata[yparam2], 'distance': rowdata['distance'], 'spm': rowdata['spm'], } ) df = pd.concat([df,rowdata],ignore_index=True) except IOError: pass return df def dataprep(rowdatadf,id=0,bands=True,barchart=True,otwpower=True, empower=True,debug=False,inboard=0.88,forceunit='lbs'): if rowdatadf.empty: if debug: print "empty" return 0 if debug: print "dataprep",id rowdatadf.set_index([range(len(rowdatadf))],inplace=True) t = rowdatadf.ix[:,'TimeStamp (sec)'] t = pd.Series(t-rowdatadf.ix[0,'TimeStamp (sec)']) row_index = rowdatadf.ix[:,' Stroke500mPace (sec/500m)'] > 3000 rowdatadf.loc[row_index,' Stroke500mPace (sec/500m)'] = 3000. p = rowdatadf.ix[:,' Stroke500mPace (sec/500m)'] hr = rowdatadf.ix[:,' HRCur (bpm)'] spm = rowdatadf.ix[:,' Cadence (stokes/min)'] cumdist = rowdatadf.ix[:,'cum_dist'] power = rowdatadf.ix[:,' Power (watts)'] averageforce = rowdatadf.ix[:,' AverageDriveForce (lbs)'] drivelength = rowdatadf.ix[:,' DriveLength (meters)'] try: workoutstate = rowdatadf.ix[:,' WorkoutState'] except KeyError: workoutstate = 0*hr peakforce = rowdatadf.ix[:,' PeakDriveForce (lbs)'] forceratio = averageforce/peakforce forceratio = forceratio.fillna(value=0) try: drivetime = rowdatadf.ix[:,' DriveTime (ms)'] recoverytime = rowdatadf.ix[:,' StrokeRecoveryTime (ms)'] rhythm = 100.*drivetime/(recoverytime+drivetime) rhythm = rhythm.fillna(value=0) except: rhythm = 0.0*forceratio f = rowdatadf['TimeStamp (sec)'].diff().mean() if f != 0: windowsize = 2*(int(10./(f)))+1 else: windowsize = 1 if windowsize <= 3: windowsize = 5 if windowsize > 3 and windowsize0: drivelength = arclength elif drivelength.mean() == 0: drivelength = driveenergy/(averageforce*4.44822) try: slip = rowdatadf.ix[:,'slip'] except KeyError: slip = 0*t try: totalangle = finish-catch effectiveangle = finish-wash-catch-slip except ValueError: totalangle = 0*t effectiveangle = 0*t if windowsize > 3 and windowsize