def featurize_data(pbmap, pbnames, lcdata, metadata, nobjects, featurefile):
"""
***Feature extractor for PLaSTiCC***
Extracts features from data by some Cesium library functions.
Builds a timeseries dictionary and for each time series extracts
features. Features described in file: feature_sets.
Created on Mon Apr 29 19:30:52 2019
@author: luisarribas
"""
print("")
print("EXTRACTING FEATURES")
print("===================")
print("")
print("Building Timeseries....wait")
print("===========================")
#**********************BUILD TIME SERIES**********************************
tsdict = OrderedDict()
for i in range(nobjects):
row = metadata[i]
thisid = row['object_id']
target = row['target']
meta = {'zBand':row['zBand'],\
'z':row['hostgal_photoz'],\
'zerr':row['hostgal_photoz_err'],\
'mag':row['magnitude'],\
'u-b':row['u-b'],\
'b-v':row['b-v']
}
ind = (lcdata['object_id'] == thisid)
thislc = lcdata[ind]
pbind = [(thislc['passband'] == pb) for pb in pbmap]
t = [thislc['mjd'][mask].data for mask in pbind]
m = [thislc['flux'][mask].data for mask in pbind]
e = [thislc['flux_err'][mask].data for mask in pbind]
tsdict[thisid] = TimeSeries(t=t, m=m, e=e,\
label=target, name=thisid, meta_features=meta,\
channel_names=pbnames )
print("")
print("OK!")
print(" ")
#***********************FEATURE EXTRACTION WITH CESIUM********************
warnings.simplefilter('ignore')
if os.path.exists(featurefile):
print("")
print("Loading features from file....wait")
print("==================================")
featuretable, _ = featurize.load_featureset(featurefile)
print("")
print("OK!")
print(" ")
else:
features_list = []
print("")
print("Computing features....wait")
print("==========================")
with schwimmbad.MultiPool() as pool:
results = pool.imap(worker, list(tsdict.values()))
for res in results:
features_list.append(res)
featuretable = featurize.assemble_featureset(features_list=features_list,\
time_series=tsdict.values())
featurize.impute_featureset(fset=featuretable,
strategy='constant',
value=0,
max_value=18446744073709551000,
inplace=True)
featurize.save_featureset(fset=featuretable, path=featurefile)
print("")
print("OK!")
print(" ")
#*******Build Pandas dataframe output*************************************
old_names = featuretable.columns.values
new_names = ['{}_{}'.format(x, pbmap.get(y, 'meta')) for x, y in old_names]
cols = [featuretable[col] for col in old_names]
allfeats = Table(cols, names=new_names, masked=False)
allfeats['target'] = metadata['target']
allfeats = allfeats.to_pandas()
allfeats = np.nan_to_num(allfeats)
new_names.append('target')
allfeats = Table(allfeats, names=new_names, masked=False)
allfeats = allfeats.to_pandas()
print("")
print("Extracted features = ", len(allfeats.columns))
print("==========================")
print("")
print("Nan Values detected = ", sum(len(allfeats) - allfeats.count()))
print("==========================")
return allfeats
