def read_data_for_features_extraction(save=False):
"""
Extracts the features from all seismic files
If option 'save' is set, then save the pandas DataFrame as a .csv file
"""
from options import MultiOptions
opt = MultiOptions()
if save:
if os.path.exists(opt.opdict['feat_filepath']):
print "WARNING !! File %s already exists"%opt.opdict['feat_filepath']
print "Check if you really want to replace it..."
sys.exit()
list_features = opt.opdict['feat_list']
df = pd.DataFrame(columns=list_features)
hob_all = {}
# Classification
tsort = opt.read_classification()
tsort.index = tsort.Date
tsort = tsort.reindex(columns=['Date','Type'])
list_sta = opt.opdict['stations']
for ifile in range(tsort.shape[0]):
date = tsort.values[ifile,0]
type = tsort.values[ifile,1]
for sta in list_sta:
print "#####",sta
counter = 0
for comp in opt.opdict['channels']:
ind = (date,sta,comp)
dic = pd.DataFrame(columns=list_features,index=[ind])
dic['EventType'] = type
dic['Ponset'] = 0
list_files = glob.glob(os.path.join(opt.opdict['datadir'],sta,'*%s.D'%comp,'*%s.D*%s_%s*'%(comp,str(date)[:8],str(date)[8:])))
list_files.sort()
if len(list_files) > 0:
file = list_files[0]
print ifile, file
if opt.opdict['option'] == 'norm':
counter = counter + 1
dic = extract_norm_features(list_features,date,file,dic)
elif opt.opdict['option'] == 'hash':
permut_file = '%s/permut_%s'%(opt.opdict['libdir'],opt.opdict['feat_test'].split('.')[0])
dic = extract_hash_features(list_features,date,file,dic,permut_file,plot=True)
df = df.append(dic)
if counter == 3 and ('Rectilinearity' in list_features or 'Planarity' in list_features or 'Azimuth' in list_features or 'Incidence' in list_features):
from waveform_features import polarization_analysis
d_mean = (df.Dur[(date,sta,comp)] + df.Dur[(date,sta,'E')] + df.Dur[(date,sta,'Z')])/3.
po_mean = int((df.Ponset[(date,sta,comp)] + df.Ponset[(date,sta,'E')] + df.Ponset[(date,sta,'Z')])/3)
list_files = [file,file.replace("N.D","E.D"),file.replace("N.D","Z.D")]
rect, plan, az, iang = polarization_analysis(list_files,d_mean,po_mean,plot=False)
if 'Rectilinearity' in list_features:
df.Rectilinearity[(date,sta,'Z')], df.Rectilinearity[(date,sta,'N')], df.Rectilinearity[(date,sta,'E')] = rect, rect, rect
if 'Planarity' in list_features:
df.Planarity[(date,sta,'Z')], df.Planarity[(date,sta,'N')], df.Planarity[(date,sta,'E')] = plan, plan, plan
if list_features or 'Azimuth':
df.Azimuth[(date,sta,'Z')], df.Azimuth[(date,sta,'N')], df.Azimuth[(date,sta,'E')] = az, az, az
if 'Incidence' in list_features:
df.Incidence[(date,sta,'Z')], df.Incidence[(date,sta,'N')], df.Incidence[(date,sta,'E')] = iang, iang, iang
if save:
print "Features written in %s"%opt.opdict['feat_filepath']
df.to_csv(opt.opdict['feat_filepath'])
def read_data_for_features_extraction(save=False):
"""
Extracts the features from all seismic files
If option 'save' is set, then save the pandas DataFrame as a .csv file
"""
from options import MultiOptions
opt = MultiOptions()
if save:
if os.path.exists(opt.opdict['feat_filename']):
print "WARNING !! File %s already exists" % opt.opdict[
'feat_filename']
print "Check if you really want to replace it..."
sys.exit()
list_features = opt.opdict['feat_list']
df = pd.DataFrame(columns=list_features)
hob_all = {}
# Classification
tsort = opt.read_classification()
tsort.index = tsort.Date
tsort = tsort.reindex(columns=['Date', 'Type'])
list_sta = opt.opdict['stations']
for ifile in range(tsort.shape[0]):
date = tsort.values[ifile, 0]
type = tsort.values[ifile, 1]
for sta in list_sta:
print "#####", sta
counter = 0
for comp in opt.opdict['channels']:
ind = (date, sta, comp)
dic = pd.DataFrame(columns=list_features, index=[ind])
dic['EventType'] = type
dic['Ponset'] = 0
list_files = glob.glob(
os.path.join(
opt.opdict['datadir'], sta, '*%s.D' % comp,
'*%s.D*%s_%s*' % (comp, str(date)[:8], str(date)[8:])))
list_files.sort()
if len(list_files) > 0:
file = list_files[0]
print ifile, file
if opt.opdict['option'] == 'norm':
counter = counter + 1
dic = extract_norm_features(list_features, date, file,
dic)
elif opt.opdict['option'] == 'hash':
permut_file = '%s/permut_%s' % (
opt.opdict['libdir'],
opt.opdict['feat_test'].split('.')[0])
dic = extract_hash_features(list_features,
date,
file,
dic,
permut_file,
plot=True)
df = df.append(dic)
if counter == 3 and ('Rectilinearity' in list_features
or 'Planarity' in list_features
or 'Azimuth' in list_features
or 'Incidence' in list_features):
from waveform_features import polarization_analysis
d_mean = (df.Dur[(date, sta, comp)] + df.Dur[
(date, sta, 'E')] + df.Dur[(date, sta, 'Z')]) / 3.
po_mean = int((df.Ponset[(date, sta, comp)] + df.Ponset[
(date, sta, 'E')] + df.Ponset[(date, sta, 'Z')]) / 3)
list_files = [
file,
file.replace("N.D", "E.D"),
file.replace("N.D", "Z.D")
]
rect, plan, az, iang = polarization_analysis(list_files,
d_mean,
po_mean,
plot=False)
if 'Rectilinearity' in list_features:
df.Rectilinearity[(date, sta, 'Z')], df.Rectilinearity[(
date, sta,
'N')], df.Rectilinearity[(date, sta,
'E')] = rect, rect, rect
if 'Planarity' in list_features:
df.Planarity[(date, sta, 'Z')], df.Planarity[(
date, sta,
'N')], df.Planarity[(date, sta,
'E')] = plan, plan, plan
if list_features or 'Azimuth':
df.Azimuth[(date, sta, 'Z')], df.Azimuth[(
date, sta, 'N')], df.Azimuth[(date, sta,
'E')] = az, az, az
if 'Incidence' in list_features:
df.Incidence[(date, sta, 'Z')], df.Incidence[(
date, sta,
'N')], df.Incidence[(date, sta,
'E')] = iang, iang, iang
if save:
print "Features written in %s" % opt.opdict['feat_filename']
df.to_csv(opt.opdict['feat_filename'])
