def process(h5file, ratio):
isomerlist = ["scyllo", "chiro", "water"]
plot_data = []
mean_contact_list = []
std_contact_list = []
#read in files for each system and aggregate
format="pp_nonpolar_vs_t.xvg"
for iso in isomerlist:
print "processing", iso
pattern = re.compile(r"%(iso)s.*%(ratio)s.*%(format)s" % vars())
if iso == "water":
pattern = re.compile(r"%(iso)s.*%(format)s" % vars())
datalist=[]
for table in h5file.listNodes(where='/pp_nonpolar'):
table_path = os.path.join('/pp_nonpolar', table.name)
if pattern.search(table.name):
data = myh5.getTableAsMatrix(h5file, table_path)
if data is not None:
data = data.astype('float')
datalist.append(data[0:config.LASTFRAME, 1])
else:
print "no data was read in"
print "datalist", datalist
data_matrix = numpy.transpose(numpy.vstack(datalist))
print "data_matrix", data_matrix, data_matrix.shape
avg, std = utils.summary_statistics(data_matrix, sum_across="columns")
avg_contacts = numpy.average(data_matrix[config.STARTFRAME:config.LASTFRAME], axis=0)
mean_contact = numpy.average(avg_contacts)
std_contact = numpy.std(avg_contacts)
print mean_contact
print std_contact
mean_contact_list.append(mean_contact)
std_contact_list.append(std_contact)
avg_smoothed = utils.smooth(avg/config.NMOLECULES, 500, time_present=False, timestep=2)
std_smoothed = utils.smooth(std/config.NMOLECULES, 500, time_present=True, timestep=2)
plot_data.append(avg_smoothed)
plot_data.append(std_smoothed)
timeseries_matrix = numpy.hstack(plot_data)
print "timeseries_matrix", timeseries_matrix, timeseries_matrix.shape
print "time", timeseries_matrix[:,0]
numpy.savetxt(ratio + "_pp_nonpolar_smoothed.txt.gz", timeseries_matrix, fmt='%0.3f')
utils.savetxt(ratio + "_avg_pp_nonpolar_contact.txt", "#scyllo chiro water", numpy.vstack([mean_contact_list, std_contact_list]), fmt='%0.3f')
return timeseries_matrix
def process(h5file, ratio, format="p2p_vs_t.dat"):
# given a h5file return a list of data to be plotted as line plots
# and a corresponding list of labels
header = "# time average_inter std_inter average_intra std_intra"
datalist = []
labellist = []
isomerlist = ["scyllo", "chiro", "water"]
mean_contact_list = []
std_contact_list = []
for iso in isomerlist:
print "processing", iso
pattern = re.compile(r"%(iso)s.*%(ratio)s.*%(format)s" % vars())
if iso == "water":
pattern = re.compile(r"%(iso)s.*%(format)s" % vars())
data_inter = []
data_intra = []
for table in h5file.listNodes(where='/polar'):
table_path = os.path.join('/polar', table.name)
if pattern.search(table.name):
print "processing", table.name
data = myh5.getTableAsMatrix(h5file, table_path, dtype=numpy.int32)
data = data.astype('float')
print "converted to float32", data
nrows, ncols = data.shape
assert nrows > ncols
print "Test data read in dimensions", data.shape, data.dtype
data_inter.append(data[0:config.LASTFRAME,1])
data_intra.append(data[0:config.LASTFRAME,2])
# compute summary statistics
print "summarizing statistics ... "
inter_matrix = utils.array_list_to_matrix(data_inter)
intra_matrix = utils.array_list_to_matrix(data_intra)
average_inter, std_inter = utils.summary_statistics(inter_matrix)
average_intra, std_intra = utils.summary_statistics(intra_matrix)
# compute the time average number of contacts and its std error
avg_contacts = numpy.average(inter_matrix, axis=0)
mean_contact = numpy.average(avg_contacts)
std_contact = numpy.std(avg_contacts)
mean_contact_list.append(mean_contact)
std_contact_list.append(std_contact)
print mean_contact, std_contact
time = data[0:config.LASTFRAME,0]
# print "Test: dimensions of average_inter", average_inter.shape
plotdata = utils.array_list_to_matrix([ time, average_inter, std_inter, average_intra, std_intra ])
print "plotdata", plotdata
print "Test: dimensions of plotdata for", iso, ratio, plotdata.shape
plotdata_smoothed = utils.smooth(plotdata, 500, time_present=True, timestep=2)
print plotdata_smoothed
datalist.append(plotdata_smoothed)
print "smoothed data", plotdata_smoothed, plotdata_smoothed.shape
ratiolabel = config.RATIO[ratio]
if iso == "water":
labellist.append("water" % vars())
else:
labellist.append("%(iso)s (%(ratiolabel)s)" % vars())
utils.savetxt('%(ratio)s_p2p_vs_t.txt' % vars(), header, plotdata, fmt='%0.2f')
utils.savetxt('%(ratio)s_p2p_vs_t_smoothed.txt' % vars(), header, plotdata_smoothed, fmt='%0.2f')
utils.savetxt('%(ratio)s_avg_contacts_w_err.txt' % vars(), "#scyllo chiro water", numpy.vstack([mean_contact_list, std_contact_list]), fmt='%0.2f')
return (datalist, labellist)
