# 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 rower as rrower
from rowingdata import main as rmain

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 utils import lbstoN

user = DATABASES['default']['USER']
password = DATABASES['default']['PASSWORD']
database_name = DATABASES['default']['NAME']
host = DATABASES['default']['HOST']
port = DATABASES['default']['PORT']

database_url = 'mysql://{user}:{password}@{host}:{port}/{database_name}'.format(
    user=user,
    password=password,
    database_name=database_name,
    host=host,
    port=port,
    )


database_url_debug = 'sqlite:///'+database_name


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

# 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)
    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 windowsize<len(velo):
	    velo2 = savgol_filter(velo,windowsize,3)
        else:
	    velo2 = velo

        velo3 = pd.Series(velo2)
        velo3 = velo3.replace([-np.inf,np.inf],np.nan)
        velo3 = velo3.fillna(method='ffill')
                
        pace2 = 500./abs(velo3)
        
        row.df[' Stroke500mPace (sec/500m)'] = pace2

        row.df = row.df.fillna(0)

        row.write_csv(f2,gzip=True)
        try:
            os.remove(f2)
        except:
            pass
                
    # recalculate power data
    if workouttype == 'rower' or workouttype == 'dynamic' or workouttype == 'slides':
	try:
	    row.erg_recalculatepower()
            row.write_csv(f2,gzip=True)
	except:
	    pass
            
    averagehr = row.df[' HRCur (bpm)'].mean()
    maxhr = row.df[' HRCur (bpm)'].max()
    
    if totaldist == 0:
        totaldist = row.df['cum_dist'].max()
    if totaltime == 0:
        totaltime = row.df['TimeStamp (sec)'].max()-row.df['TimeStamp (sec)'].min()
        totaltime = totaltime+row.df.ix[0,' ElapsedTime (sec)']



    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)

    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"

        
    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 TCX no HR
    if (fileformat == 'tcxnohr'):
	row = TCXParserNoHR(f2)
		    
    # handle RowPerfect
    if (fileformat == 'rowperfect3'):
        row = RowPerfectParser(f2)
            
    # handle ErgData
    if (fileformat == 'ergdata'):
	row = ErgDataParser(f2)

    # handle Mike
    if (fileformat == 'bcmike'):
        row = BoatCoachAdvancedParser(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=True):
    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=True):
    delete_strokedata(id)
    rowdata = dataprep(df,id=id,bands=True,barchart=True,otwpower=True,
                       debug=debug)
    
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=[]):
    prepmultipledata(ids)
    data = read_cols_df_sql(ids,columns)

    return data
        

def prepmultipledata(ids,verbose=False,debug=True):
    query = sa.text('SELECT DISTINCT workoutid FROM strokedata')
    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():
        res = conn.execute(query)
        res = list(itertools.chain.from_iterable(res.fetchall()))
    conn.close()
    engine.dispose()
    
    res = list(set(ids)-set(res))
    for id in res:
        rowdata,row = getrowdata(id=id)
        if verbose:
            print id
        if rowdata:
            data = dataprep(rowdata.df,id=id,bands=True,barchart=True,otwpower=True)    
    return res

def read_cols_df_sql(ids,columns,debug=True):
    columns = list(columns)+['distance','spm']
    columns = [x for x in columns if x != 'None']
    columns = list(set(columns))
    cls = ''
    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=True):
    if debug:
        engine = create_engine(database_url_debug, echo=False)
    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 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=True):
    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)
    
    f = rowdatadf['TimeStamp (sec)'].diff().mean()
    windowsize = 2*(int(10./(f)))+1
    if windowsize <= 3:
	windowsize = 5

    if windowsize > 3:
	spm = savgol_filter(spm,windowsize,3)
	hr = savgol_filter(hr,windowsize,3)
	drivelength = savgol_filter(drivelength,windowsize,3)
        forceratio = savgol_filter(forceratio,windowsize,3)

    try:
        t2 = t.fillna(method='ffill').apply(lambda x: timedeltaconv(x))
    except TypeError:
        t2 = 0*t

    
    p2 = p.fillna(method='ffill').apply(lambda x: timedeltaconv(x))


    drivespeed = drivelength/rowdatadf[' DriveTime (ms)']*1.0e3
    drivespeed = drivespeed.fillna(value=0)
    driveenergy = drivelength*averageforce*lbstoN
    distance = rowdatadf.ix[:,'cum_dist']




    data = DataFrame(
	dict(
	    time = t*1e3,
	    hr = hr,
	    pace = p*1e3,
	    spm = spm,
	    cumdist = cumdist,
	    ftime = niceformat(t2),
	    fpace = nicepaceformat(p2),
	    driveenergy=driveenergy,
	    power=power,
            workoutstate=workoutstate,
	    averageforce=averageforce,
	    drivelength=drivelength,
	    peakforce=peakforce,
            forceratio=forceratio,
	    distance=distance,
	    drivespeed=drivespeed,
	    )
	)

    if bands:
	# HR bands
	data['hr_ut2'] = rowdatadf.ix[:,'hr_ut2']
	data['hr_ut1'] = rowdatadf.ix[:,'hr_ut1']
	data['hr_at'] = rowdatadf.ix[:,'hr_at']
	data['hr_tr'] = rowdatadf.ix[:,'hr_tr']
	data['hr_an'] = rowdatadf.ix[:,'hr_an']
	data['hr_max'] = rowdatadf.ix[:,'hr_max']
	data['hr_bottom'] = 0.0*data['hr']

    if barchart:
	# time increments for bar chart
	time_increments = rowdatadf.ix[:,' ElapsedTime (sec)'].diff()
	time_increments[0] = time_increments[1]
	time_increments = 0.5*time_increments+0.5*np.abs(time_increments)
	x_right =  (t2+time_increments.apply(lambda x:timedeltaconv(x)))

	data['x_right'] = x_right

    if empower:
        try:
            wash = rowdatadf.ix[:,'wash']
            catch = rowdatadf.ix[:,'catch']
            finish = rowdatadf.ix[:,'finish']
            peakforceangle = rowdatadf.ix[:,'peakforceangle']
            driveenergy = rowdatadf.ix[:,'driveenergy']
            drivelength = driveenergy/(averageforce*4.44822)
            slip = rowdatadf.ix[:,'slip']
            if windowsize > 3:
                wash = savgol_filter(wash,windowsize,3)
                slip = savgol_filter(slip,windowsize,3)
                catch = savgol_filter(catch,windowsize,3)
                finish = savgol_filter(finish,windowsize,3)
                peakforceangle = savgol_filter(peakforceangle,windowsize,3)
                driveenergy = savgol_filter(driveenergy,windowsize,3)
                drivelength = savgol_filter(drivelength,windowsize,3)
            data['wash'] = wash
            data['catch'] = catch
            data['slip'] = slip
            data['finish'] = finish
            data['peakforceangle'] = peakforceangle
            data['driveenergy'] = driveenergy
            data['drivelength'] = drivelength
            data['peakforce'] = peakforce
            data['averageforce'] = averageforce
        except KeyError:
            pass
        
    if otwpower:
	try:
	    nowindpace = rowdatadf.ix[:,'nowindpace']
	except KeyError:
	    nowindpace = p
	try:
	    equivergpower = rowdatadf.ix[:,'equivergpower']
	except KeyError:
	    equivergpower = 0*p+50.
	
	nowindpace2 = nowindpace.apply(lambda x: timedeltaconv(x))
	ergvelo = (equivergpower/2.8)**(1./3.)

	ergpace = 500./ergvelo
	ergpace[ergpace == np.inf] = 240.
	ergpace2 = ergpace.apply(lambda x: timedeltaconv(x))

	data['ergpace'] = ergpace*1e3
	data['nowindpace'] = nowindpace*1e3
	data['equivergpower'] = equivergpower
	data['fergpace'] = nicepaceformat(ergpace2)
	data['fnowindpace'] = nicepaceformat(nowindpace2)

    data = data.replace([-np.inf,np.inf],np.nan)
    data = data.fillna(method='ffill')

    # write data if id given
    if id != 0:
        data['workoutid'] = id
        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():
            data.to_sql('strokedata',engine,if_exists='append',index=False)
        conn.close()
        engine.dispose()    
    return data