def test_4():
m = random.choice(range(1,10))
e = random.choice(range(4))
n = m*10**e
n |= 1 # ensure odd
l = list(range(n))
random.shuffle(l)
# median is in this case also the max deviation.
median = (n-1)/2
assert math.ceil(median/2.0) == mad.mad(l)
def test():
result = {}
func = {
'sim_euc': similarity.sim_euc,
'sim_man': similarity.sim_man,
'sim_Lmax': similarity.sim_Lmax
}
for fun in func: #For all three Metrics
for k in [10, 50,
100]: #check for three different k values(Handpicked)
result.setdefault(fun, {})
for i in [1, 2, 3, 4, 5]: # 5 fold cross validation
madScore = 0
madlist = []
print("Running", i, "Validation for function", fun,
"k value is", k)
#print("In script")
#print('./Datastore/rec_'+str(fun)+ '_'+str(k) + '_'+ str(i)+'.json')
recEngineAlgo.getRecommendation(
i,
load.readPrefs('./Datastore/prefsTrain' + str(i) +
'.json'),
load.readPrefs('./Datastore/movies.json'), k, func[fun])
madScore = mad.mad(
load.readPrefs('./Datastore/rec_' + str(fun) + '_' +
str(k) + '_' + str(i) + '.json'),
load.readPrefs('./Datastore/prefsTest' + str(i) + '.json'))
print("Madscore for", i, "validation for function", fun,
"with k value", k, "is", madScore)
madlist.append(madScore)
for item in madlist: #Taking average Mad
madScore = madScore + item
print("Final MadScore for func:", str(fun), "and k:", k, "is:",
round(madScore / 5, 2))
result[fun][k] = round(madScore / 5, 2)
print(result)
with open('./Datastore/result.json',
'w') as fp: #storing the result in dictionary
json.dump(result, fp)
def _nee2gpp_reichstein(df, ff, isday, undef=-9999, nogppnight=False):
"""
Calculate photosynthesis (GPP) and ecosystem respiration (RECO) from original
Eddy flux data, using several fits of Reco vs. temperature of nighttime data
over the season, as in Reichstein et al. (2005), in order to calculate Reco
and then GPP = Reco - NEE.
Parameters
----------
df : pandas.Dataframe
time series of CO2 fluxes and air temperature.
pandas.Dataframe with the columns
'FC' or 'NEE' (or starting with 'FC\_' or 'NEE\_') for observed CO2 flux [umol(CO2) m-2 s-1]
'TA' (or starting with 'TA\_') for air temperature [K]
The index is taken as date variable.
ff : pandas.Dataframe
flag Dataframe or array has the same shape as `df`. Non-zero values in
`ff` will be treated as missing values in `df`.
`ff` must follow the same rules as `df`.
isday : array_like of bool
True when it is day, False when night. Must have the same length as `df.shape[0].`
undef : float, optional
values having `undef` value are treated as missing values in `df` (default: -9999)
nogppnight : float, optional
GPP will be set to zero at night. RECO will then equal NEE at night (default: False)
Returns
-------
pandas.Dataframe
pandas.Dataframe with two columns 'GPP' and 'RECO' with estimated
photosynthesis and ecosystem respiration.
Literature
----------
Reichstein et al. (2005)
On the separation of net ecosystem exchange into assimilation and ecosystem
respiration: review and improved algorithm,
Global Change Biology 11, 1424-1439
Examples
--------
>>> from fread import fread
>>> from date2dec import date2dec
>>> from dec2date import dec2date
>>> ifile = 'test_nee2gpp.csv'
>>> undef = -9999.
>>> dat = fread(ifile, skip=2, transpose=True)
>>> ndat = dat.shape[1]
>>> head = fread(ifile, skip=2, header=True)
>>> head1 = head[0]
>>> # date
>>> jdate = date2dec(dy=dat[0,:], mo=dat[1,:], yr=dat[2,:], hr=dat[3,:], mi=dat[4,:])
>>> adate = dec2date(jdate, eng=True)
>>> # colhead
>>> idx = []
>>> for i in head1:
... if i in ['NEE', 'rg', 'Tair', 'VPD']: idx.append(head1.index(i))
>>> colhead = ['FC', 'SW_IN', 'TA', 'VPD']
>>> # data
>>> dfin = dat[idx,:]
>>> dfin[2,:] = np.where(dfin[2,:] == undef, undef, dfin[2,:]+273.15)
>>> dfin[3,:] = np.where(dfin[3,:] == undef, undef, dfin[3,:]*100.)
>>> # flag
>>> flag = np.where(dfin == undef, 2, 0)
>>> # partition
>>> GPP, Reco = nee2gpp(dfin, flag=flag, date=adate, colhead=colhead, undef=undef, method='local')
>>> print(GPP[1120:1128])
[-9.99900000e+03 -9.99900000e+03 -9.99900000e+03 4.40606871e+00
8.31942152e+00 1.06242542e+01 8.49245664e+00 1.12381973e+01]
>>> print(Reco[1120:1128])
[1.68311981 1.81012431 1.9874173 2.17108871 2.38759152 2.64372415
2.90076664 3.18592735]
>>> GPP, Reco = nee2gpp(dfin, flag=flag, date=adate, colhead=colhead, undef=undef, method='local')
>>> print(GPP[1120:1128])
[-9.99900000e+03 -9.99900000e+03 -9.99900000e+03 4.40606871e+00
8.31942152e+00 1.06242542e+01 8.49245664e+00 1.12381973e+01]
>>> GPP, Reco = nee2gpp(dfin, flag=flag, date=adate, colhead=colhead, undef=undef, method='Reichstein')
>>> print(GPP[1120:1128])
[-9.99900000e+03 -9.99900000e+03 -9.99900000e+03 4.40606871e+00
8.31942152e+00 1.06242542e+01 8.49245664e+00 1.12381973e+01]
>>> GPP, Reco = nee2gpp(dfin, flag=flag, date=adate, colhead=colhead, undef=undef, method='reichstein')
>>> print(GPP[1120:1128])
[-9.99900000e+03 -9.99900000e+03 -9.99900000e+03 4.40606871e+00
8.31942152e+00 1.06242542e+01 8.49245664e+00 1.12381973e+01]
History
-------
Written Matthias Cuntz, Mar 2012
Modified Arndt Piayda, Mar 2012 - undef=np.nan
Matthias Cuntz, Nov 2012 - individual routine
Matthias Cuntz, Feb 2013 - ported to Python 3
"""
# Variables
fc_id = ''
for cc in df.columns:
if cc.startswith('FC_') or (cc == 'FC') or cc.startswith('NEE_') or (
cc == 'NEE'):
fc_id = cc
break
ta_id = ''
for cc in df.columns:
if cc.startswith('TA_') or (cc == 'TA'):
ta_id = cc
break
assert fc_id, 'Carbon net flux with name FC or NEE or starting with FC_ or NEE_ must be in input.'
assert ta_id, 'Air temperature with name TA or starting with TA_ must be in input.'
nee = np.ma.array(df[fc_id], mask=(ff[fc_id] > 0))
t = np.ma.array(df[ta_id], mask=(ff[ta_id] > 0))
misday = np.ma.array(isday,
mask=((~np.isfinite(isday)) | (isday == undef)))
dates = df.index.to_julian_date()
# Partition - Local relationship = Reichstein et al. (2005)
ndata = nee.size
GPP = np.ones(ndata) * undef
Reco = np.ones(ndata) * undef
dfout = pd.DataFrame({'GPP': GPP, 'RECO': Reco}, index=df.index)
# Select valid nighttime
mask = misday | nee.mask | t.mask | misday.mask
ii = np.where(~mask)[0]
if (ii.size == 0):
# raise ValueError('Error _nee2gpp_reichstein: no valid nighttime data.')
print('Warning _nee2gpp_reichstein: no valid nighttime data.')
return dfout
jul = dates[ii]
tt = np.ma.compressed(t[ii])
net = np.ma.compressed(nee[ii])
# 1. each 5 days, in 15 day period, fit if range of T > 5
locp = [] # local param
locs = [] # local err
dmin = np.floor(np.amin(jul)).astype(
np.int) # be aware that julian days starts at noon, i.e. 1.0 is 12h
dmax = np.ceil(np.amax(jul)).astype(
np.int
) # so the search will be from noon to noon and thus includes all nights
for i in range(dmin, dmax, 5):
iii = np.where((jul >= i) & (jul < (i + 14)))[0]
niii = iii.size
if niii > 6:
tt1 = tt[iii]
net1 = net[iii]
mm = ~mad(net1, z=4.5) # make fit more robust by removing outliers
if (np.ptp(tt[iii]) >= 5.) & (np.sum(mm) > 6):
p, temp1, temp2 = opt.fmin_tnc(cost_lloyd_fix, [2., 200.],
bounds=[[0., None], [0., None]],
args=(tt1[mm], net1[mm]),
approx_grad=True,
disp=False)
try:
p1, c = opt.curve_fit(lloyd_fix,
tt1[mm],
net1[mm],
p0=p,
maxfev=10000) # params, covariance
if np.all(np.isfinite(
c)): # possible return of curvefit: c=inf
s = np.sqrt(np.diag(c))
else:
s = 10. * np.abs(p)
except:
s = 10. * np.abs(p)
locp += [p]
locs += [s]
# if ((s[1]/p[1])<0.5) & (p[1] > 0.): pdb.set_trace()
if len(locp) == 0:
# raise ValueError('Error _nee2gpp_reichstein: No local relationship found.')
print('Warning _nee2gpp_reichstein: No local relationship found.')
return dfout
locp = np.squeeze(np.array(locp).astype(np.float))
locs = np.squeeze(np.array(locs).astype(np.float))
# 2. E0 = avg of best 3
# Reichstein et al. (2005), p. 1430, 1st paragraph.
with warnings.catch_warnings():
warnings.simplefilter("ignore")
iii = np.where((locp[:, 1] > 0.) & (locp[:, 1] < 450.)
& (np.abs(locs[:, 1] / locp[:, 1]) < 0.5))[0]
niii = iii.size
if niii == 0:
# raise ValueError('Error _nee2gpp_reichstein: No good local relationship found.')
# loosen the criteria: take the best three estimates anyway
iii = np.where((locp[:, 1] > 0.))[0]
niii = iii.size
if niii < 1:
# raise ValueError('Error _nee2gpp_reichstein: No E0>0 found.')
print('Warning _nee2gpp_reichstein: No E0>0 found.')
return dfout
lp = locp[iii, :]
ls = locs[iii, :]
iis = np.argsort(ls[:, 1])
bestp = np.mean(lp[iis[0:np.minimum(3, niii)], :], axis=0)
bests = np.mean(ls[iis[0:np.minimum(3, niii)], :], axis=0)
elif niii == 1:
bestp = np.squeeze(locp[iii, :])
bests = np.squeeze(locs[iii, :])
elif niii == 2:
bestp = np.mean(locp[iii, :], axis=0)
bests = np.mean(locs[iii, :], axis=0)
# ls = locs[iii,:]
# iis = np.argsort(ls[:,1])
else:
lp = locp[iii, :]
ls = locs[iii, :]
iis = np.argsort(ls[:, 1])
bestp = np.mean(lp[iis[0:3], :], axis=0)
bests = np.mean(ls[iis[0:3], :], axis=0)
# 3. Refit Rref with fixed E0, each 4 days
refp = [] # Rref param
refii = [] # mean index of data points
E0 = bestp[1]
et = lloyd_fix(tt, 1., E0)
for i in range(dmin, dmax, 4):
iii = np.where((jul >= i) & (jul < (i + 4)))[0]
niii = iii.size
if niii > 3:
# Calc directly minisation of (nee-p*et)**2
p, temp1, temp2 = opt.fmin_tnc(cost_abs, [2.],
bounds=[[0., None]],
args=(lloyd_only_rref_p, et[iii],
net[iii]),
approx_grad=True,
disp=False)
refp += [p]
refii += [np.int((iii[0] + iii[-1]) // 2)]
if len(refp) == 0:
# raise ValueError('Error _nee2gpp_reichstein: No ref relationship found.')
print('Warning _nee2gpp_reichstein: No ref relationship found.')
return dfout
refp = np.squeeze(np.array(refp))
refii = np.squeeze(np.array(refii))
# 4. Interpol Rref
Rref = np.interp(dates, jul[refii], refp)
# 5. Calc Reco
Reco = np.ones(ndata) * undef
ii = np.where(~t.mask)[0]
Reco[ii] = lloyd_fix(t[ii], Rref[ii], E0)
# 6. Calc GPP
GPP = np.ones(ndata) * undef
ii = np.where(~(t.mask | nee.mask))[0]
GPP[ii] = Reco[ii] - nee[ii]
# 7. Set GPP=0 at night, if wanted
if nogppnight:
mask = misday | nee.mask | t.mask | misday.mask # night
ii = np.where(~mask)[0]
Reco[ii] = nee[ii]
GPP[ii] = 0.
# and prohibit negative gpp at any time
mask = nee.mask | t.mask | (GPP > 0.)
ii = np.where(~mask)[0]
Reco[ii] -= GPP[ii]
GPP[ii] = 0.
dfout = pd.DataFrame({'GPP': GPP, 'RECO': Reco}, index=df.index)
return dfout
def test_3():
assert 1 == mad.mad([1,2,3])
def madspikes(dfin,
flag=None,
isday=None,
colhead=None,
undef=-9999,
nscan=15 * 48,
nfill=1 * 48,
z=7,
deriv=2,
swthr=10.,
plot=False):
"""
Spike detection for using a moving median absolute difference filter.
Used with Eddy vovariance data in Papale et al. (Biogeosciences, 2006).
Parameters
----------
dfin : pandas.Dataframe or numpy.array
time series of data where spike detection with MAD should be applied.
`dfin` can be a pandas.Dataframe.
`dfin` can also me a numpy array. In this case `colhead` must be given.
MAD will be applied along axis=0, i.e. on each column of axis=1.
flag : pandas.Dataframe or numpy.array, optional
flag Dataframe or array has the same shape as dfin. Non-zero values in
`flag` will be treated as missing values in `dfin`.
If `flag` is numpy array, `df.columns.values` will be used as column heads.
isday : array_like of bool, optional
True when it is day, False when night. Must have the same length as dfin.shape[0].
If `isday` is not given, `dfin` must have a column with head 'SW_IN' or
starting with 'SW_IN'. `isday` will then be `dfin['SW_IN'] > swthr`.
colhed : array_like of str, optional
column names if `dfin` is numpy array.
undef : float, optional
values having `undef` value are treated as missing values in `dfin` (default: -9999)
np.nan is not allowed (working).
nscan : int, optional
size of moving window to calculate mad in time steps (default: 15*48)
nfill : int, optional
step size of moving window to calculate mad in time steps (default: 1*48)
mad will be calculated in `nscan` time window. Resulting mask will be applied
only in `nfill` window in the middle of the `nscan` window. Then `nscan` window
will be moved by `nfill` time steps.
z : float, optional
Input is allowed to deviate maximum `z` standard deviations from the median (default: 7)
deriv : int, optional
0: Act on raw input.
1: Use first derivatives.
2: Use 2nd derivatives (default).
swthr : float, optional
Threshold to determine daytime from incoming shortwave radiation if `isday` not given (default: 10).
plot : bool, optional
True: data and spikes are plotted into madspikes.pdf (default: False).
Returns
-------
pandas.Dataframe or numpy array
flags, 0 everywhere except detected spikes set to 2.
History
-------
Written, Matthias Cuntz & Tino Rau, 2008
Maintained, Arndt Piayda, Aug 2014
Modified, Matthias Cuntz, Apr 2020 - input can be pandas Dataframe or numpy array(s)
- removed iteration
Matthias Cuntz, May 2020 - numpy docstring format
"""
# numpy or panda
if isinstance(dfin, (np.ndarray, np.ma.MaskedArray)):
isnumpy = True
istrans = False
assert colhead is not None, 'colhead must be given if input is numpy.ndarray.'
if dfin.shape[0] == len(colhead):
istrans = True
df = pd.DataFrame(dfin.T, columns=colhead)
elif dfin.shape[1] == len(colhead):
df = pd.DataFrame(dfin, columns=colhead)
else:
raise ValueError(
'Length of colhead must be number of columns in input array. len(colhead)='
+ str(len(colhead)) + ' shape(input)=(' + str(dfin.shape[0]) +
',' + str(dfin.shape[1]) + ').')
else:
isnumpy = False
istrans = False
assert isinstance(
dfin, pd.core.frame.DataFrame
), 'Input must be either numpy.ndarray or pandas.DataFrame.'
df = dfin.copy(deep=True)
# Incoming flags
if flag is not None:
if isinstance(flag, (np.ndarray, np.ma.MaskedArray)):
fisnumpy = True
fistrans = False
if flag.shape[0] == len(df):
ff = pd.DataFrame(flag, columns=df.columns.values)
elif flag.shape[1] == len(df):
fistrans = True
ff = pd.DataFrame(flag.T, columns=df.columns.values)
else:
raise ValueError(
'flag must have same shape as data array. data: ({:d},{:d}); flag: ({:d},{:d})'
.format(dfin.shape[0], dfin.shape[1], flag.shape[0],
flag.shape[1]))
ff = ff.set_index(df.index)
else:
fisnumpy = False
fistrans = False
assert isinstance(
flag, pd.core.frame.DataFrame
), 'Flag must be either numpy.ndarray or pandas.DataFrame.'
ff = flag.copy(deep=True)
else:
fisnumpy = isnumpy
fistrans = istrans
# flags: 0: good; 1: input flagged; 2: output flagged
ff = df.copy(deep=True).astype(int)
ff[:] = 0
ff[df == undef] = 1
ff[df.isna()] = 1
# day or night
if isday is None:
sw_id = ''
for cc in df.columns:
if cc.startswith('SW_IN'):
sw_id = cc
break
assert sw_id, 'Global radiation with name SW or starting with SW_ must be in input if isday not given.'
isday = df[
sw_id] > swthr # Papale et al. (Biogeosciences, 2006): 20; REddyProc: 10
if isinstance(isday, (pd.core.series.Series, pd.core.frame.DataFrame)):
isday = isday.to_numpy()
isday[isday == undef] = np.nan
ff[np.isnan(isday)] = 1
# parameters
nrow, ncol = df.shape
half_scan_win = nscan // 2
half_fill_win = nfill // 2
# calculate dusk and dawn times and separate in day and night
isdawn = np.zeros(nrow, dtype=np.bool)
isdusk = np.zeros(nrow, dtype=np.bool)
dis = isday.astype(int) - np.roll(isday, -1).astype(int) # .astype(bool)
isdawn[:-1] = np.where(dis[:-1] == -1, True, False)
isdusk[:-1] = np.where(dis[:-1] == 1, True, False)
isddday = isdawn
tmp = np.roll(isdusk, 1)
isddday[1:] += tmp[1:] # start and end of day
isddnight = isdusk
tmp = np.roll(isdawn, 1)
isddnight[1:] += tmp[1:] # start and end of night
# iterate over each column of data
if plot:
import matplotlib.pyplot as plt
import matplotlib.backends.backend_pdf as pdf
pd.plotting.register_matplotlib_converters()
pp = pdf.PdfPages('madspikes.pdf')
cols = list(df.columns)
for hcol in df.columns:
if hcol.startswith == 'SW_IN': continue
data = df[hcol]
dflag = ff[hcol]
# get day and night data
data_day = data.copy(deep=True)
data_day[~(isday | isddday) | (dflag != 0) | (data == undef)] = np.nan
data_night = data.copy(deep=True)
data_night[~(~isday | isddnight) | (dflag != 0) |
(data == undef)] = np.nan
# iterate over fill window
for j in range(half_fill_win, nrow - 1, 2 * half_fill_win):
j1 = max(j - half_scan_win - 1, 0)
j2 = min(j + half_scan_win + 1, nrow)
fill_start = max(j - half_fill_win, 1)
fill_end = min(j + half_fill_win, nrow - 1)
dd = data_day[j1:j2].to_numpy()
day_flag = mad(np.ma.masked_array(data=dd, mask=np.isnan(dd)),
z=z,
deriv=deriv)
ff.iloc[fill_start:fill_end, cols.index(hcol)] += np.where(
day_flag[fill_start - j1 - 1:fill_end - j1 - 1], 2, 0)
nn = data_night[j1:j2]
night_flag = mad(np.ma.masked_array(data=nn, mask=np.isnan(nn)),
z=z,
deriv=deriv)
ff.iloc[fill_start:fill_end, cols.index(hcol)] += np.where(
night_flag[fill_start - j1 - 1:fill_end - j1 - 1], 2, 0)
if plot:
fig = plt.figure(1)
sub = fig.add_subplot(111)
valid = ff[hcol] == 0
l1 = sub.plot(data[valid], 'ob')
l3 = sub.plot(data[ff[hcol] == 2], 'or')
plt.title(hcol)
pp.savefig(fig)
plt.close(fig)
# Finish
if plot:
pp.close()
if fisnumpy:
if fistrans:
return ff.to_numpy().T
else:
return ff.to_numpy()
else:
return ff