def read_measurements_from_cvs(filename):
"""
Created a dict from the sample measurements file. For compatibility with the library, the dict has to have the
{ <rid> : { <viscode> : { DX.scan : <diagnosis> }
{ scantime : <days after bl> }
{ <biomarker1> : <volume> }
... }
{ <viscode> : ... }}
:param filename: filename of the *.csv file
:rtype: dict
:return: the generated dict with the measurements
"""
scantime_dict = {'bl': 0, 'm12': 365, 'm24': 730, 'm36': 1095}
biomarkers = set()
measurements = {0: {}}
with open(filename) as csvfile:
reader = csv.DictReader(csvfile)
visits = reader.fieldnames[1:]
for visit in visits:
measurements[0].update({visit: {'scantime': scantime_dict[visit], 'DX.scan': 'UNKNOWN'}})
for row in reader:
biomarker = row['Biomarker Name']
if biomarker in DataHandler.get_all_biomarker_names():
for visit in visits:
try:
measurements[0][visit].update({biomarker: float(row[visit])})
biomarkers.add(biomarker)
except ValueError:
pass
return measurements, list(biomarkers)
def main():
# Collect data for test
data_handler = DataHandler.get_data_handler()
biomarkers = DataHandler.get_all_biomarker_names()
mean_changes = {}
for biomarker in biomarkers:
measurements = data_handler.get_measurements_as_dict(
visits=['bl', 'm12'], biomarkers=[biomarker], select_complete=True)
mean_changes_biomarker = {0.0: 0.0, 0.25: 0.0, 0.75: 0.0, 1.0: 0.0}
num_subjects = {0.0: 0, 0.25: 0, 0.75: 0, 1.0: 0}
for rid in measurements:
diagnosis = measurements[rid]['bl']['DX.scan']
value_bl = measurements[rid]['bl'][biomarker]
value_y1 = measurements[rid]['m12'][biomarker]
scantime_bl = measurements[rid]['bl']['scantime']
scantime_y1 = measurements[rid]['m12']['scantime']
change = (value_y1 - value_bl) / (scantime_y1 - scantime_bl)
mean_changes_biomarker[diagnosis] += change
num_subjects[diagnosis] += 1
mean_change_mci_ad = mean_changes_biomarker[
0.25] + mean_changes_biomarker[0.75] + mean_changes_biomarker[1.0]
num_subjects_mci_ad = num_subjects[0.25] + num_subjects[
0.75] + num_subjects[1.0]
for diagnosis in mean_changes_biomarker:
mean_changes_biomarker[diagnosis] /= num_subjects[diagnosis]
mean_changes_biomarker.update(
{0.66: mean_change_mci_ad / num_subjects_mci_ad})
mean_changes.update({biomarker: mean_changes_biomarker})
print log.RESULT, '{0} CN: {1}, (n={2})'.format(
biomarker, mean_changes_biomarker[0.0], num_subjects[0.0])
print log.RESULT, '{0} EMCI: {1}, (n={2})'.format(
biomarker, mean_changes_biomarker[0.25], num_subjects[0.25])
print log.RESULT, '{0} LMCI: {1}, (n={2})'.format(
biomarker, mean_changes_biomarker[0.75], num_subjects[0.75])
print log.RESULT, '{0} AD: {1}, (n={2})'.format(
biomarker, mean_changes_biomarker[1.0], num_subjects[1.0])
mean_changes_file = os.path.join(data_handler.get_eval_folder(),
'mean_changes.p')
pickle.dump(mean_changes, open(mean_changes_file, 'wb'))
def main():
# Collect data for test
data_handler = DataHandler.get_data_handler()
biomarkers = DataHandler.get_all_biomarker_names()
mean_changes = {}
for biomarker in biomarkers:
measurements = data_handler.get_measurements_as_dict(visits=['bl', 'm12'],
biomarkers=[biomarker],
select_complete=True)
mean_changes_biomarker = {0.0: 0.0, 0.25: 0.0, 0.75: 0.0, 1.0: 0.0}
num_subjects = {0.0: 0, 0.25: 0, 0.75: 0, 1.0: 0}
for rid in measurements:
diagnosis = measurements[rid]['bl']['DX.scan']
value_bl = measurements[rid]['bl'][biomarker]
value_y1 = measurements[rid]['m12'][biomarker]
scantime_bl = measurements[rid]['bl']['scantime']
scantime_y1 = measurements[rid]['m12']['scantime']
change = (value_y1 - value_bl) / (scantime_y1 - scantime_bl)
mean_changes_biomarker[diagnosis] += change
num_subjects[diagnosis] += 1
mean_change_mci_ad = mean_changes_biomarker[0.25] + mean_changes_biomarker[0.75] + mean_changes_biomarker[1.0]
num_subjects_mci_ad = num_subjects[0.25] + num_subjects[0.75] + num_subjects[1.0]
for diagnosis in mean_changes_biomarker:
mean_changes_biomarker[diagnosis] /= num_subjects[diagnosis]
mean_changes_biomarker.update({0.66: mean_change_mci_ad / num_subjects_mci_ad})
mean_changes.update({biomarker: mean_changes_biomarker})
print log.RESULT, '{0} CN: {1}, (n={2})'.format(biomarker, mean_changes_biomarker[0.0], num_subjects[0.0])
print log.RESULT, '{0} EMCI: {1}, (n={2})'.format(biomarker, mean_changes_biomarker[0.25], num_subjects[0.25])
print log.RESULT, '{0} LMCI: {1}, (n={2})'.format(biomarker, mean_changes_biomarker[0.75], num_subjects[0.75])
print log.RESULT, '{0} AD: {1}, (n={2})'.format(biomarker, mean_changes_biomarker[1.0], num_subjects[1.0])
mean_changes_file = os.path.join(data_handler.get_eval_folder(), 'mean_changes.p')
pickle.dump(mean_changes, open(mean_changes_file, 'wb'))
def read_measurements_from_cvs(filename):
"""
Created a dict from the sample measurements file. For compatibility with the library, the dict has to have the
{ <rid> : { <viscode> : { DX.scan : <diagnosis> }
{ scantime : <days after bl> }
{ <biomarker1> : <volume> }
... }
{ <viscode> : ... }}
:param filename: filename of the *.csv file
:rtype: dict
:return: the generated dict with the measurements
"""
scantime_dict = {'bl': 0, 'm12': 365, 'm24': 730, 'm36': 1095}
biomarkers = set()
measurements = {0: {}}
with open(filename) as csvfile:
reader = csv.DictReader(csvfile)
visits = reader.fieldnames[1:]
for visit in visits:
measurements[0].update({
visit: {
'scantime': scantime_dict[visit],
'DX.scan': 'UNKNOWN'
}
})
for row in reader:
biomarker = row['Biomarker Name']
if biomarker in DataHandler.get_all_biomarker_names():
for visit in visits:
try:
measurements[0][visit].update(
{biomarker: float(row[visit])})
biomarkers.add(biomarker)
except ValueError:
pass
return measurements, list(biomarkers)
