def compute_stack_stat(statfile, params):
#compute the number of cells
stat = pd.DataFrame.from_csv(statfile, sep='\t')
cellnum = pd.DataFrame()
for img in stat.Image_name.unique():
curstat = stat[stat.Image_name == img]
cellnum = cellnum.append(pd.Series({
'Number_of_glomeruli':
len(curstat),
'Image_name':
curstat.Image_name.iloc[0],
'Kidney_volume':
curstat.Kidney_volume.iloc[0],
'Mean_size':
curstat.Diameter.mean(),
'Stdev_of_size':
curstat.Diameter.std()
}),
ignore_index=True)
cellnum = filelib.extract_groups(cellnum)
cellnum.to_csv(params.inputfolder + '../statistics/stack_statistics.csv',
sep='\t')
def compute_size_distribution(statfile, params):
stat = pd.DataFrame.from_csv(statfile, sep='\t')
absvalues = True
#compute distribution of diameters
dmin = int(round(2 * float(params.minrad)))
dmax = int(round(2 * float(params.maxrad)))
n = 5
dmin = int(dmin) / n * n
dmax = int(dmax) / n * n + n
bins = np.linspace(dmin, dmax, num=(dmax - dmin) / n + 1)
bins = np.int_(bins)
stat['Diameter, $\mu m$'] = stat.Diameter
stat['Volume, x 1000 $\mu m^3$'] = stat.Volume / 1000
x = 'Diameter, $\mu m$'
if absvalues:
y = 'Number of glomeruli'
else:
y = 'Frequency'
distr = pd.DataFrame()
for img in stat.Image_name.unique():
curstat = stat[stat.Image_name == img]
curdistr = pd.DataFrame()
for i in range(1, len(bins)):
curstat0 = curstat[(curstat[x] >= bins[i - 1])
& (curstat[x] < bins[i])]
if absvalues:
fr = len(curstat0)
else:
fr = len(curstat0) * 1. / len(curstat)
curdistr = curdistr.append(pd.Series({
x:
bins[i - 1] + (bins[i] - bins[i - 1]) / 2.,
y:
fr
}),
ignore_index=True)
curdistr['Image_name'] = curstat.Image_name.iloc[0]
distr = pd.concat([distr, curdistr], ignore_index=True)
distr = filelib.extract_groups(distr)
distr.to_csv(params.inputfolder +
'../statistics/diameter_distribution.csv',
sep='\t')
maxvol = int(round(4. / 3 * np.pi * float(params.maxrad)**3))
minvol = int(round(4. / 3 * np.pi * float(params.minrad)**3))
n = 32
dmin = int(minvol / 1000) / n * n
dmax = int(maxvol / 1000 * 0.4) / n * n + n
bins = np.linspace(dmin, dmax, num=(dmax - dmin) / n + 1)
bins = np.int_(bins)
x = 'Volume, x 1000 $\mu m^3$'
distr = pd.DataFrame()
for img in stat.Image_name.unique():
curstat = stat[stat.Image_name == img]
curdistr = pd.DataFrame()
for i in range(1, len(bins)):
curstat0 = curstat[(curstat[x] >= bins[i - 1])
& (curstat[x] < bins[i])]
if absvalues:
fr = len(curstat0)
else:
fr = len(curstat0) * 1. / len(curstat)
curdistr = curdistr.append(pd.Series({
x:
bins[i - 1] + (bins[i] - bins[i - 1]) / 2.,
y:
fr
}),
ignore_index=True)
curdistr['Image_name'] = curstat.Image_name.iloc[0]
distr = pd.concat([distr, curdistr], ignore_index=True)
distr = filelib.extract_groups(distr)
distr.to_csv(params.inputfolder + '../statistics/volume_distribution.csv',
sep='\t')