def temporal(self, dct, now, args):
needs_processing = {k : bool(v.get()) for k, v in dct['temporal_specific'].iteritems()}
out_dir = dct['out_dir'].get() + '/' + now + '/data/'
util.make_dir(out_dir)
min_sup = float(dct['temporal_specific']['support'].get())
if not dct['temporal_specific']['sequences_available'].get():
# if enrichment is enabled, we create a different object instance than usual
if dct['enrich'].get():
seq_p = SequenceEnrichProcess(*args, mapping_files_dir=dct['mapping_dir'].get())
name = 'sequences_enriched'
elif dct['temporal_specific']['anti-knowledge-driven'].get():
seq_p = NonMarshallSequenceProcess(*args)
name = 'sequences_excl_marshall'
else:
seq_p = SequenceProcess(*args)
name = 'sequences'
seq_p.process(needs_processing)
seq_p.sort_sequences()
seq_p.save_output(sequence_file=True, sub_dir='data/tmprl', name=name)
generate_pattern_occurrences_per_patient(out_dir, seq_p.id2data, min_sup, dct['mapping_dir'].get())
sequence_f = out_dir + '/tmprl/{}.csv'.format(name)
else:
sequence_f = dct['temporal_specific']['sequence_file'].get()
generate_pattern_occurrences_per_patient(out_dir, sequence_f, min_sup, dct['mapping_dir'].get())
def export(self, out_dir): '''export results''' util.make_dir(out_dir) io.dict2csv(self.code2indications, out_dir + 'indication.csv') io.dict2csv(self.code2effects, out_dir + 'effect.csv') io.dict2csv(self.code2ingredients, out_dir + 'ingredient.csv')
def export(self, out_dir):
'''export results'''
util.make_dir(out_dir)
io.dict2csv(self.code2manifestation_of,
out_dir + 'manifestationof.csv')
io.dict2csv(self.code2association, out_dir + 'association.csv')
def export(self, out_dir):
'''export results'''
util.make_dir(out_dir)
io.dict2csv(self.code2indications, out_dir + 'indication.csv')
io.dict2csv(self.code2effects, out_dir + 'effect.csv')
io.dict2csv(self.code2ingredients, out_dir + 'ingredient.csv')
def save_statistics(self, sub_dir='data', name='unnamed'):
out_dir = self.out_dir + '/' + sub_dir + '/'
util.make_dir(out_dir)
f_out = out_dir + name + '.csv'
with open(f_out, 'w') as f:
for key, value in self.statistics.items():
f.write('%s:%s\n' % (key, value))
def go(self, button):
'''initiates the associated algorithms '''
dct = self.user_input
button.config(text='Running', state=DISABLED)
if dct['in_dir'].get() == 'input folder':
dct['in_dir'].set('sql')
if dct['delimiter'].get() == '':
dct['delimiter'].set(',')
if dct['out_dir'].get() == 'output folder':
dct['out_dir'].set('./out')
if dct['min_age'].get() == '':
dct['min_age'].set(30)
if dct['max_age'].get() == '':
dct['max_age'].set(150)
if dct['begin_interval'].get() == '':
dct['begin_interval'].set(int(365./52*26+1))
if dct['end_interval'].get() == '':
dct['end_interval'].set(int(365./52*0+1))
if dct['ID_column'].get() == '':
dct['ID_column'].set('patientnummer')
if dct['temporal_specific']['support'].get() == '':
dct['temporal_specific']['support'].set(0.1)
if dct['mapping_dir'].get() == 'semantic enrichment dir':
dct['mapping_dir'].set('./out/semantics/')
self.master.update_idletasks()
now = util.get_current_datetime()
util.make_dir(dct['out_dir'].get() + '/' + now + '/')
HISes = [dct['PMO'].get(), dct['MDM'].get(), dct['LUMC'].get(),
dct['VUMH'].get(), dct['VUMD'].get(), dct['VUSC'].get()]
args = [dct['in_dir'].get(),
dct['delimiter'].get(),
dct['out_dir'].get() + '/' + now,
dct['ID_column'].get(),
int(dct['min_age'].get()),
int(dct['max_age'].get()),
[int(dct['end_interval'].get()), int(dct['begin_interval'].get())],
True if dct['in_dir'].get().lower() == 'sql' else False,
HISes]
if dct['process_temporal'].get(): # process temporally
self.temporal(dct, now, args)
else: # process atemporally
self.regular(dct, now, args)
pretty_dct = util.tkinter2var(dct)
try:
io.pprint_to_file(dct['out_dir'].get() + '/' + now + '/settings.txt', pretty_dct)
except IOError, e:
print e
def save_output(self,
benchmark=False,
sequence_file=False,
sub_dir='',
name='unnamed',
target=False):
'''saves processed data to the specified output directory'''
print('...saving processed data'
) # to {}'.format('sql' if self.from_sql else 'file')
headers = self.headers
# print (self.id2data.values())
# print('x')
# if we didn't get the data from sql database, just save to .csv
if True or not self.from_sql:
# possibly make new directories
out_dir = self.out_dir + '/' + sub_dir + '/'
util.make_dir(out_dir)
f_out = out_dir + name + '.csv'
out = write_csv(f_out)
# write headers where required
if benchmark:
out.writerow(headers[0:3])
elif target:
out.writerow([headers[0], headers[-1]])
elif sequence_file:
pass
else:
out.writerow([headers[0]] + headers[3:-1])
# write data
for value in self.id2data.values():
data = value['data']
if benchmark:
data = data[0:3]
data[2] = 1 if data[2] == 'V' else 0
elif target:
if self.survival == False:
data = [data[0], 0 if data[-1] == 'negative' else 1]
else:
data = [data[0], data[-1]]
elif sequence_file:
pass
else:
data = [data[0]] + data[3:-1]
out.writerow(data)
def temporal(self, dct, now, args):
needs_processing = {
k: bool(v.get())
for k, v in dct['temporal_specific'].items()
}
out_dir = dct['out_dir'].get() + '/' + now + '/data/'
util.make_dir(out_dir)
# minimal support is set here
min_sup = float(dct['temporal_specific']['support'].get())
# if there are no sequences available
if not dct['temporal_specific']['sequences_available'].get():
# if enrichment is enabled, we create a different object instance than usual
# if enriched
# if dct['enrich'].get():
# seq_p = SequenceEnrichProcess(*args, mapping_files_dir=dct['mapping_dir'].get())
# name = 'sequences_enriched'
# if not enriched and no marshall predictors
if dct['temporal_specific']['anti-knowledge-driven'].get():
seq_p = NonMarshallSequenceProcess(*args)
name = 'sequences_excl_marshall'
else:
seq_p = SequenceProcess(*args)
name = 'sequences'
seq_p.process(needs_processing)
seq_p.sort_sequences()
seq_p.save_output(sequence_file=True,
sub_dir='data/tmprl',
name=name)
generate_pattern_occurrences_per_patient(out_dir, seq_p.id2data,
min_sup,
dct['mapping_dir'].get())
sequence_f = out_dir + '/tmprl/{}.csv'.format(name)
else:
sequence_f = dct['temporal_specific']['sequence_file'].get()
generate_pattern_occurrences_per_patient(out_dir, sequence_f,
min_sup,
dct['mapping_dir'].get())
def go(self, button):
'''initiates the associated algorithms '''
dct = self.user_input
button.config(text='Running', state=DISABLED)
if dct['in_dir'].get() == 'input folder':
dct['in_dir'].set('/Users/Reiny/Documents/UI_CRC/playground')
if dct['delimiter'].get() == '':
dct['delimiter'].set(',')
if dct['out_dir'].get() == 'output folder':
dct['out_dir'].set('/Users/Reiny/Documents/UI_CRC/out')
self.master.update_idletasks()
util.make_dir(dct['out_dir'].get() + '/')
HISes = [
dct['PMO'].get(), dct['MDM'].get(), dct['LUMC'].get(),
dct['VUMH'].get(), dct['VUMD'].get(), dct['VUSC'].get()
]
args = [
dct['in_dir'].get(), dct['delimiter'].get(),
dct['out_dir'].get() + '/' + dct['output_id'].get() + '.csv',
dct['age+gender'].get(), dct['counts_med'].get(),
dct['counts_med_enrich'].get(), dct['counts_consult'].get(),
dct['counts_consult_enrich'].get(), dct['counts_referral'].get(),
dct['counts_lab'].get(), dct['tmprl'].get(),
dct['enriched_tmprl'].get(), dct['knowledge_driven'].get(),
dct['anti_knowledge_driven'].get(),
dct['anti_knowledge_driven_tmprl'].get(), dct['separate'].get(),
HISes
]
# merge
combine.execute(*args)
button.config(text='Done')
self.master.update_idletasks()
time.sleep(0.5)
button.config(text='Run!', state=NORMAL)
def go(self, button):
'''initiates the associated algorithms '''
dct = self.user_input
button.config(text='Running', state=DISABLED)
self.master.update_idletasks()
util.make_dir(dct['f_out'].get())
report = Report(dct['f_general'].get(), dct['f_data'].get(),
dct['f_predictors'].get(), dct['f_out'].get(),
float(dct['feature-threshold'].get()))
report.compile()
report.export()
print '### Done processing ###'
button.config(text='Done')
self.master.update_idletasks()
time.sleep(0.5)
button.config(text='Run!', state=NORMAL)
def go(self, button): '''initiates the associated algorithms ''' dct = self.user_input button.config(text='Running', state=DISABLED) self.master.update_idletasks() util.make_dir(dct['f_out'].get()) report = Report(dct['f_general'].get(), dct['f_data'].get(), dct['f_predictors'].get(), dct['f_out'].get(), float(dct['feature-threshold'].get()) ) report.compile() report.export() print '### Done processing ###' button.config(text='Done') self.master.update_idletasks() time.sleep(0.5) button.config(text='Run!', state=NORMAL)
def go(self, button):
'''initiates the associated algorithms '''
dct = self.user_input
button.config(text='Running', state=DISABLED)
if dct['in_dir'].get() == 'input folder':
dct['in_dir'].set('sql')
if dct['delimiter'].get() == '':
dct['delimiter'].set(',')
if dct['out_dir'].get() == 'output folder':
dct['out_dir'].set('./out')
if dct['min_age'].get() == '':
dct['min_age'].set(30)
if dct['max_age'].get() == '':
dct['max_age'].set(150)
if dct['begin_interval'].get() == '':
dct['begin_interval'].set(int(365. / 52 * 26 + 1))
if dct['end_interval'].get() == '':
dct['end_interval'].set(int(365. / 52 * 0 + 1))
if dct['ID_column'].get() == '':
dct['ID_column'].set('patientnummer')
if dct['temporal_specific']['support'].get() == '':
dct['temporal_specific']['support'].set(0.1)
# if dct['mapping_dir'].get() == 'semantic enrichment dir':
# dct['mapping_dir'].set('./out/semantics/')
self.master.update_idletasks()
now = util.get_current_datetime()
util.make_dir(dct['out_dir'].get() + '/' + now + '/')
# HISes = [dct['PMO'].get(), dct['MDM'].get(), dct['LUMC'].get(),
# dct['VUMH'].get(), dct['VUMD'].get(), dct['VUSC'].get()]
args = [
dct['in_dir'].get(), dct['delimiter'].get(),
dct['out_dir'].get() + '/' + now, dct['ID_column'].get(),
int(dct['min_age'].get()),
int(dct['max_age'].get()),
[int(dct['end_interval'].get()),
int(dct['begin_interval'].get())],
True if dct['in_dir'].get().lower() == 'sql' else False, False,
dct['survival'].get(), dct['already_processed'].get()
]
if dct['process_temporal'].get(): # process temporally
self.temporal(dct, now, args)
else: # process atemporally
self.regular(dct, now, args)
pretty_dct = util.tkinter2var(dct)
try:
io.pprint_to_file(
dct['out_dir'].get() + '/' + now + '/settings.txt', pretty_dct)
except IOError as e:
print(e)
print('### Done processing ###')
button.config(text='Done')
self.master.update_idletasks()
time.sleep(0.5)
button.config(text='Run!', state=NORMAL)
def execute(in_dir, out_dir, record_id, target_id, day_id, day, algorithms, feature_selection, separate_testset, in_dir_test):
'''executes the learning task on the data in in_dir with the algorithms in algorithms.
The results are written to out_dir and subdirectories,
and the record_ and target_ids are used to differentiate attributes and non-attributes'''
print '### executing learning algorithms on... ###'
# get the files
files = util.list_dir_csv(in_dir)
# stop if no files found
if not files:
print 'No appropriate csv files found. Select an input directory with appropriate files'
return
if separate_testset:
files_test = util.list_dir_csv(in_dir_test)
else:
files_test = files
# create directory
util.make_dir(out_dir)
# execute each algorithm
for alg in algorithms:
print '...{}'.format(alg)
util.make_dir(out_dir+'/'+alg+'/')
results_list = []
if separate_testset:
results_list2 = []
util.make_dir(out_dir+'/'+alg+'_test/')
# list which will contain the results
# run algorithm alg for each file f
for f, f_test in zip(files,files_test):
fname = in_out.get_file_name(f, extension=False)
print ' ...{}'.format(fname)
# get data, split in features/target. If invalid stuff happened --> exit
X, y, headers = in_out.import_data(f, record_id, target_id) # assumption: first column is patientnumber and is pruned, last is target
if type(X) == bool: return
# if separate_testset:
# X, X_te = X
# y, y_te = y
# print ' ...train instances: {}, attributes: {}'.format(X.shape[0], X.shape[1])
# print ' ...test instances: {}, attributes: {}'.format(X_te.shape[0], X_te.shape[1])
# else:
# Now remove the ones without a relevant day:
new_headers = [h for h in headers if not h == day_id]
day_index = headers.index(day_id)
new_X = np.zeros((0, len(headers)))
new_y = []
for i in range(0, X.shape[0]):
if X[i,headers.index(day_id)] == day:
row = np.array(X[i,:]).reshape(-1)
new_X = np.append(new_X, np.column_stack(row), axis=0)
new_y.append(int(y[i]))
new_X = np.delete(new_X, day_index, 1)
X = new_X
y = np.squeeze(np.asarray(new_y))
print ' ...instances: {}, attributes: {}'.format(X.shape[0], X.shape[1])
model, best_features, results = execute_with_algorithm(alg, X, y, fname, headers, out_dir+'/'+alg+'/', record_id, target_id, feature_selection)
results_list.append(results)
if separate_testset:
X, y, headers = in_out.import_data(f_test, record_id, target_id) # assumption: first column is patientnumber and is pruned, last is target
if type(X) == bool: return
print ' ...instances: {}, attributes: {} (test set)'.format(X.shape[0], X.shape[1])
results = predict_separate(X, y, fname, out_dir+'/'+alg+'_test/', record_id, target_id, feature_selection, model, best_features)
results_list2.append(results)
try:
in_out.save_ROC(out_dir+'/'+alg+'/'+"roc.png", results_list, title='ROC curve')
except IndexError:
pass
try:
in_out.save_ROC(out_dir+'/'+alg+'_test/'+"roc.png", results_list2, title='ROC curve')
except NameError:
pass
# notify user
print '## Learning Finished ##'
def execute(in_dir, out_dir, record_id, target_id, algorithms, feature_selection, separate_testset, in_dir_test, survival, oversampling, undersampling, aggregation):
'''executes the learning task on the data in in_dir with the algorithms in algorithms.
The results are written to out_dir and subdirectories,
and the record_ and target_ids are used to differentiate attributes and non-attributes'''
print ('### executing learning algorithms on... ###')
# get the files
files = util.list_dir_csv(in_dir)
# stop if no files found
if not files:
print ('No appropriate csv files found. Select an input directory with appropriate files')
return
if separate_testset:
files_test = util.list_dir_csv(in_dir_test)
else:
files_test = files
# create directory
util.make_dir(out_dir)
# execute each algorithm
for alg in algorithms:
print ('...{}'.format(alg))
util.make_dir(out_dir+'/'+alg+'/')
results_list = []
if separate_testset:
results_list2 = []
util.make_dir(out_dir+'/'+alg+'_test/')
# list which will contain the results
# run algorithm alg for each file f
for f, f_test in zip(files,files_test):
fname = in_out.get_file_name(f, extension=False)
print (' ...{}'.format(fname))
# get data, split in features/target. If invalid stuff happened --> exit
X, y, headers, target_list = in_out.import_data(f, record_id, target_id, survival) # assumption: first column is patientnumber and is pruned, last is target
if type(X) == bool: return
if aggregation == True:
X, headers = aggregations(f, target_list, survival)
print (' ...instances: {}, attributes: {}'.format(X.shape[0], X.shape[1]))
model, best_features, results = execute_with_algorithm(alg, X, y, fname, headers, out_dir+'/'+alg+'/', record_id, target_id, feature_selection, oversampling, survival, undersampling, aggregation)
results_list.append(results)
if separate_testset:
X, y, headers = in_out.import_data(f_test, record_id, target_id) # assumption: first column is patientnumber and is pruned, last is target
if type(X) == bool: return
print (' ...instances: {}, attributes: {} (test set)'.format(X.shape[0], X.shape[1]))
results = predict_separate(X, y, fname, out_dir+'/'+alg+'_test/', record_id, target_id, feature_selection, model, best_features)
results_list2.append(results)
try:
in_out.save_ROC(out_dir+'/'+alg+'/'+"roc.png", results_list, title='ROC curve')
except IndexError:
pass
try:
in_out.save_ROC(out_dir+'/'+alg+'_test/'+"roc.png", results_list2, title='ROC curve')
except NameError:
pass
# notify user
print ('## Learning Finished ##')
def execute_knn(in_dir, out_dir, record_id, target_id, day_id, day, k):
'''executes the learning task on the data in in_dir with the algorithms in algorithms.
The results are written to out_dir and sub_directories,
and the record_ and target_ids are used to differentiate attributes and non-attributes'''
print '### executing learning algorithms on... ###'
# get the files
files = util.list_dir_csv(in_dir)
# stop if no files found
if not files:
print 'No appropriate csv files found. Select an input directory with appropriate files'
return
# create directory
util.make_dir(out_dir)
# execute each algorithm
# run algorithm alg for each file f
for f in files:
results_list = []
fname = in_out.get_file_name(f, extension=False)
print ' ...{}'.format(fname)
# get data, split in features/target. If invalid stuff happened --> exit
X, y, headers = in_out.import_data(
f, record_id, target_id,
True) # assumption: first column is patientnumber
if type(X) == bool: return
day_index = headers.index(day_id)
new_X = np.zeros((0, len(headers)))
new_y = []
IDs = []
IDrows = {}
# ordering of time points and complete data (filled with nan's if not available) assumed!
# features_to_be_removed = [ "pvc_bin","pnc_bin","pac_bin","ect_freq_bin","full_code_bin","comfort_meas_bin","other_code_bin","no_cpr_bin",
# "dnr_bin","dni_bin","fall_risk_bin","orientation_ord","orient_unable_ass_bin","riker_sas_ord","vent_bin",
# "vent_mode_ord","pacemaker_bin","trach_bin","flush_skin_bin","jaundice_skin_bin","pale_skin_bin","impaired_skin_bin",
# "iabp_ord","iabp_bin","svnsicu_bin","svcsicu_bin","svcsru_bin","svmicu_bin","svmsicu_bin","svother_bin","svccu_bin",
# "gender"]
exclude = [
146, 140, 95, 123, 88, 133, 22, 65, 49, 114, 178, 55, 133, 138, 34,
186, 20, 73
]
new_index = 0
for i in range(0, X.shape[0]):
if X[i, headers.index(day_id)] == day or day == -1:
row = np.array(X[i, :]).reshape(-1)
if not row[0] in IDs and not row[0] in exclude:
IDs.append(row[0])
new_y.append(int(y[i]))
IDrows[row[0]] = [new_index]
elif not row[0] in exclude:
IDrows[row[0]].append(new_index)
new_X = np.append(new_X, np.column_stack(row), axis=0)
new_index += 1
ID_column = new_X[:, 0]
# Remove the id, the day, and the time stamp from the data and headers.
new_X = np.delete(new_X, 2, 1)
new_X = np.delete(new_X, 1, 1)
new_X = np.delete(new_X, 0, 1)
new_headers = headers[3:len(headers)]
dtw_attr = ['hr', 'resp', 'nbp', 'sbp', 'dbp', 'so2']
X = new_X
print len(X)
non_singular_rows = [
i for i in range(0, X.shape[1])
if len(set(util.get_non_nans(X[:, i].tolist()))) > 1
]
#print str(len(non_singular_rows)) + ' ' + str(X.shape[1])
#print non_singular_rows
X = X[:, non_singular_rows]
new_headers = np.array(new_headers)[non_singular_rows].tolist()
print str(
len(new_headers)) + "length new headers after non singular rows"
print new_headers
print "Removed columns with only nan of 1 value"
max_values = np.nanmax(X, axis=0)
min_values = np.nanmin(X, axis=0)
ranges = []
for i in range(0, len(min_values)):
diff = max_values[i] - min_values[i]
if diff == 0:
print 'difference of zero encountered in ' + str(i)
print 'Max values: ' + str(max_values[i])
print 'Min values: ' + str(min_values[i])
ranges.append(1)
else:
ranges.append(diff)
# Now do some scaling to get the values to the same order or magnitude
scaled_X = (X - min_values) / (max_values - min_values)
X = scaled_X
y = np.squeeze(np.asarray(new_y))
print "Scaling done!"
new_IDrows = {}
for ID in IDs:
IDrows[ID] = {
'first_row': min(IDrows[ID]),
'last_row': max(IDrows[ID])
}
print ' ...instances: {}, attributes: {}'.format(
X.shape[0], X.shape[1])
# Now we are going to build the similarity matrix. We are also going to store how many attributes
# we actually able to make a comparison for.
similarity_matrix = np.ones((len(IDs), len(IDs)))
matching_number_matrix = np.ones((len(IDs), len(IDs)))
for attr in range(0, len(new_headers)):
print str(attr) + "attribute in KNN loop"
print str(attr) + "/" + str(len(new_headers))
temp = np.ones((len(IDs), len(IDs)))
temp[:] = 2
for i in range(0, len(IDs)):
for j in range(i + 1, len(IDs)):
i_data = X[IDrows[IDs[i]]['first_row']:
IDrows[IDs[i]]['last_row'] + 1, attr].tolist()
j_data = X[IDrows[IDs[j]]['first_row']:
IDrows[IDs[j]]['last_row'] + 1, attr].tolist()
if new_headers[attr] in dtw_attr:
dtw_distance = dtw.lb_keogh(i_data, j_data, window)
if not dtw_distance == -1:
temp[i, j] += dtw_distance
matching_number_matrix[i, j] += 1
matching_number_matrix[
j, i] = matching_number_matrix[i, j]
temp[j, i] = temp[i, j]
else:
i_data = util.get_non_nans(i_data)
j_data = util.get_non_nans(j_data)
if len(i_data) > 0 and len(j_data) > 0:
simple_distance = math.pow(
np.mean(i_data) - np.mean(j_data), 2)
temp[i, j] += simple_distance
matching_number_matrix[i, j] += 1
matching_number_matrix[
j, i] = matching_number_matrix[i, j]
temp[j, i] = temp[i, j]
if np.max(temp) != 0:
temp = temp / np.max(temp)
similarity_matrix += temp
# We calculate the average score per item matched
# Best might be to apply a weighting scheme now.
similarity_matrix = (similarity_matrix / matching_number_matrix) + (
1 / matching_number_matrix)
print len(IDs)
results = perform_classification(similarity_matrix, y, out_dir, k)
results_list.append(results)
print results
in_out.save_results(out_dir + str(k) + '.csv',
["fpr", "tpr", "auc", "cm"],
results[1:len(results)], [sum(y), len(y)])
in_out.save_ROC(out_dir + '/roc.png', results_list, title='ROC curve')
# notify user
print '## Learning Finished ##'
print similarity_matrix
def execute(in_dir, delim, out_file, age_gender=False, counts_med=False,
counts_med_enrich=False, counts_consult=False, counts_consult_enrich=False,
counts_referral=False, counts_lab=False, tmprl=False,
enriched_tmprl=False, knowledge_driven=False, counts_no_knowledge=False, tmprl_no_knowledge=False,
separate=False, HISes=[]):
'''merge the in files to produce the out file'''
merged = defaultdict(list)
headers = ['ID']
# we may not need this.
ID2HIS = {}
merged_test = defaultdict(list)
# if we wish to separate, get dictionary of patient HIS sources using SQL.
if separate:
c = util.sql_connect().cursor()
HISes_str = "','".join(HISes)
q = '''SELECT patientnummer
FROM patienten
WHERE PRAKTIJKCODE IN ('{}')'''.format(HISes_str)
c.execute(q)
ID2HIS = {row[0] : row[0] for row in c}
if age_gender:
headers = merge_file(in_dir+'/AG.csv', merged, headers, delim, separate, ID2HIS, merged_test)
if counts_med:
headers = merge_file(in_dir+'/C_M.csv', merged, headers, delim, separate, ID2HIS, merged_test)
if counts_med_enrich:
headers = merge_file(in_dir+'/C_M_enrich.csv', merged, headers, delim, separate, ID2HIS, merged_test)
if counts_consult:
headers = merge_file(in_dir+'/C_C.csv', merged, headers, delim, separate, ID2HIS, merged_test)
if counts_consult_enrich:
headers = merge_file(in_dir+'/C_C_enrich.csv', merged, headers, delim, separate, ID2HIS, merged_test)
if counts_referral:
headers = merge_file(in_dir+'/C_R.csv', merged, headers, delim, separate, ID2HIS, merged_test)
if counts_lab:
headers = merge_file(in_dir+'/C_L.csv', merged, headers, delim, separate, ID2HIS, merged_test)
if tmprl:
headers = merge_file(in_dir+'/T.csv', merged, headers, delim, separate, ID2HIS, merged_test)
if enriched_tmprl:
headers = merge_file(in_dir+'/T_enrich.csv', merged, headers, delim, separate, ID2HIS, merged_test)
if knowledge_driven:
headers = merge_file(in_dir+'/K.csv', merged, headers, delim, separate, ID2HIS, merged_test)
if counts_no_knowledge:
headers = merge_file(in_dir+'/C_NK.csv', merged, headers, delim, separate, ID2HIS, merged_test)
if tmprl_no_knowledge:
headers = merge_file(in_dir+'/T_NK.csv', merged, headers, delim, separate, ID2HIS, merged_test)
headers = merge_file(in_dir+'/CRC.csv', merged, headers, delim, separate, ID2HIS, merged_test)
# now write to new file (also check whether all results have same length)
make_dir(out_file)
out = io.write_csv(out_file)
out.writerow(headers)
skip=0
for key in merged:
if len(headers) != 1+len(merged[key]):
print 'unequal to header amount ({} vs {})! watch out.'.format(len(headers),len(merged[key]))
# skip+=1
# continue
out.writerow([key] + merged[key])
if separate:
out_file_test = out_file[:out_file.rfind('/')+1] + 'test' + out_file[out_file.rfind('/'):]
make_dir(out_file_test)
out = io.write_csv(out_file_test)
out.writerow(headers)
for key in merged_test:
if len(headers) != 1+len(merged_test[key]):
print 'unequal to header amount ({} vs {})! watch out.'.format(len(headers),len(merged_test[key]))
# skip+=1
# continue
out.writerow([key] + merged_test[key])
print '## Done Merging ##'
def execute(in_dir,
delim,
out_file,
age_gender=False,
counts_med=False,
counts_med_enrich=False,
counts_consult=False,
counts_consult_enrich=False,
counts_referral=False,
counts_lab=False,
all_counts=False,
tmprl=False,
enriched_tmprl=False,
knowledge_driven=False,
counts_no_knowledge=False,
tmprl_no_knowledge=False,
separate=False,
HISes=[]):
'''merge the in files to produce the out file'''
merged = defaultdict(list)
headers = ['ID']
# we may not need this.
ID2HIS = {}
merged_test = defaultdict(list)
# if we wish to separate, get dictionary of patient HIS sources using SQL.
if separate:
c = util.sql_connect().cursor()
HISes_str = "','".join(HISes)
q = '''SELECT patientnummer
FROM patienten
WHERE PRAKTIJKCODE IN ('{}')'''.format(HISes_str)
c.execute(q)
ID2HIS = {row[0]: row[0] for row in c}
if age_gender:
headers = merge_file(in_dir + '/AG.csv', merged, headers, delim,
separate, ID2HIS, merged_test)
if counts_med:
headers = merge_file(in_dir + '/C_M.csv', merged, headers, delim,
separate, ID2HIS, merged_test)
if counts_med_enrich:
headers = merge_file(in_dir + '/C_M_enrich.csv', merged, headers,
delim, separate, ID2HIS, merged_test)
if counts_consult:
headers = merge_file(in_dir + '/C_C.csv', merged, headers, delim,
separate, ID2HIS, merged_test)
if counts_consult_enrich:
headers = merge_file(in_dir + '/C_C_enrich.csv', merged, headers,
delim, separate, ID2HIS, merged_test)
if counts_referral:
headers = merge_file(in_dir + '/C_R.csv', merged, headers, delim,
separate, ID2HIS, merged_test)
if counts_lab:
headers = merge_file(in_dir + '/C_L.csv', merged, headers, delim,
separate, ID2HIS, merged_test)
if tmprl:
headers = merge_file(in_dir + '/T.csv', merged, headers, delim,
separate, ID2HIS, merged_test)
if enriched_tmprl:
headers = merge_file(in_dir + '/T_enrich.csv', merged, headers, delim,
separate, ID2HIS, merged_test)
if knowledge_driven:
headers = merge_file(in_dir + '/K.csv', merged, headers, delim,
separate, ID2HIS, merged_test)
if counts_no_knowledge:
headers = merge_file(in_dir + '/C_NK.csv', merged, headers, delim,
separate, ID2HIS, merged_test)
if tmprl_no_knowledge:
headers = merge_file(in_dir + '/T_NK.csv', merged, headers, delim,
separate, ID2HIS, merged_test)
if all_counts:
print('ja')
headers = merge_file(in_dir + '/counts.csv', merged, headers, delim,
separate, ID2HIS, merged_test)
headers = merge_file(in_dir + '/stroke.csv', merged, headers, delim,
separate, ID2HIS, merged_test)
# now write to new file (also check whether all results have same length)
make_dir(out_file)
out = io.write_csv(out_file)
out.writerow(headers)
skip = 0
for key in merged:
if len(headers) != 1 + len(merged[key]):
print('unequal to header amount ({} vs {})! watch out.'.format(
len(headers), len(merged[key])))
# skip+=1
# continue
out.writerow([key] + merged[key])
if separate:
out_file_test = out_file[:out_file.rfind('/') +
1] + 'test' + out_file[out_file.rfind('/'):]
make_dir(out_file_test)
out = io.write_csv(out_file_test)
out.writerow(headers)
for key in merged_test:
if len(headers) != 1 + len(merged_test[key]):
print('unequal to header amount ({} vs {})! watch out.'.format(
len(headers), len(merged_test[key])))
# skip+=1
# continue
out.writerow([key] + merged_test[key])
print('## Done Merging ##')
def execute_knn(in_dir, out_dir, record_id, target_id, day_id, day, k):
'''executes the learning task on the data in in_dir with the algorithms in algorithms.
The results are written to out_dir and subdirectories,
and the record_ and target_ids are used to differentiate attributes and non-attributes'''
print '### executing learning algorithms on... ###'
# get the files
files = util.list_dir_csv(in_dir)
# stop if no files found
if not files:
print 'No appropriate csv files found. Select an input directory with appropriate files'
return
# create directory
util.make_dir(out_dir)
# execute each algorithm
# run algorithm alg for each file f
for f in files:
results_list = []
fname = in_out.get_file_name(f, extension=False)
print ' ...{}'.format(fname)
# get data, split in features/target. If invalid stuff happened --> exit
X, y, headers = in_out.import_data(
f, record_id, target_id,
True) # assumption: first column is patientnumber
if type(X) == bool: return
day_index = headers.index(day_id)
new_X = np.zeros((0, len(headers)))
new_y = []
IDs = []
IDrows = {}
# ordering of time points and complete data (filled with nan's if not available) assumed!
# Select the right day and normalize the columns
new_index = 0
for i in range(0, X.shape[0]):
if X[i, headers.index(day_id)] == day or day == -1:
row = np.array(X[i, :]).reshape(-1)
if not row[0] in IDs:
IDs.append(row[0])
new_y.append(int(y[i]))
IDrows[row[0]] = [new_index]
else:
IDrows[row[0]].append(new_index)
new_X = np.append(new_X, np.column_stack(row), axis=0)
new_index += 1
# Remove the id, the day, and the time stamp from the data and headers.
new_X = np.delete(new_X, 2, 1)
new_X = np.delete(new_X, 1, 1)
new_X = np.delete(new_X, 0, 1)
new_headers = headers[3:len(headers)]
X = new_X
# Remove columns with only a single value or all nans
non_singular_rows = [
i for i in range(0, X.shape[1])
if len(set(util.get_non_nans(X[:, i].tolist()))) > 1
]
#print str(len(non_singular_rows)) + ' ' + str(X.shape[1])
#print non_singular_rows
X = X[:, non_singular_rows]
new_headers = np.array(new_headers)[non_singular_rows].tolist()
max_values = np.nanmax(X, axis=0)
min_values = np.nanmin(X, axis=0)
ranges = []
for i in range(0, len(min_values)):
diff = max_values[i] - min_values[i]
if diff == 0:
print 'difference of zero encountered in ' + str(i)
print 'Max values: ' + str(max_values[i])
print 'Min values: ' + str(min_values[i])
ranges.append(1)
else:
ranges.append(diff)
# Now do some scaling to get the values to the same order or magnitude
scaled_X = (X - min_values) / (max_values - min_values)
X = scaled_X
y = np.squeeze(np.asarray(new_y))
new_IDrows = {}
for ID in IDs:
IDrows[ID] = {
'first_row': min(IDrows[ID]),
'last_row': max(IDrows[ID])
}
print ' ...instances: {}, attributes: {}'.format(
X.shape[0], X.shape[1])
# Now we are going to build the similarity matrix. We are also going to store how many attributes
# we actually able to make a comparison for.
similarity_matrix = np.zeros((len(IDs), len(IDs)))
matching_number_matrix = np.ones((len(IDs), len(IDs)))
for i in range(0, len(IDs)):
for j in range(i + 1, len(IDs)):
for attr in range(0, len(new_headers)):
i_data = X[IDrows[IDs[i]]['first_row']:
IDrows[IDs[i]]['last_row'] + 1, attr].tolist()
j_data = X[IDrows[IDs[j]]['first_row']:
IDrows[IDs[j]]['last_row'] + 1, attr].tolist()
#print i_data
#print j_data
if new_headers[attr] in dtw_attr:
dtw_distance = dtw.lb_keogh(i_data, j_data, window)
# print dtw_distance
if not dtw_distance == -1:
similarity_matrix[i, j] += dtw_distance
matching_number_matrix[i, j] += 1
else:
i_data = util.get_non_nans(i_data)
j_data = util.get_non_nans(j_data)
if len(i_data) > 0 and len(j_data) > 0:
simple_distance = math.pow(
np.mean(i_data) - np.mean(j_data), 2)
similarity_matrix[i, j] += simple_distance
matching_number_matrix[i, j] += 1
similarity_matrix[j, i] = similarity_matrix[i, j]
matching_number_matrix[j, i] = matching_number_matrix[i, j]
similarity_matrix = similarity_matrix / matching_number_matrix # We calculate the average score per item matched
# Best might be to apply a weighting scheme now.
results = perform_classification(similarity_matrix, y, out_dir, k)
results_list.append(results)
in_out.save_results(out_dir + str(k) + '.csv',
["fpr", "tpr", "auc", "cm"],
results[1:len(results)], [sum(y), len(y)])
in_out.save_ROC(out_dir + '/roc.png', results_list, title='ROC curve')
# notify user
print '## Learning Finished ##'
def export(self, out_dir): '''export results''' util.make_dir(out_dir) io.dict2csv(self.code2manifestation_of, out_dir + 'manifestationof.csv') io.dict2csv(self.code2association, out_dir + 'association.csv')
def execute(in_dir, out_dir, record_id, target_id, algorithms, feature_selection, separate_testset, in_dir_test):
'''executes the learning task on the data in in_dir with the algorithms in algorithms.
The results are written to out_dir and subdirectories,
and the record_ and target_ids are used to differentiate attributes and non-attributes'''
print '### executing learning algorithms on... ###'
# get the files
files = util.list_dir_csv(in_dir)
# stop if no files found
if not files:
print 'No appropriate csv files found. Select an input directory with appropriate files'
return
if separate_testset:
files_test = util.list_dir_csv(in_dir_test)
else:
files_test = files
# create directory
util.make_dir(out_dir)
# execute each algorithm
for alg in algorithms:
print '...{}'.format(alg)
util.make_dir(out_dir+'/'+alg+'/')
results_list = []
if separate_testset:
results_list2 = []
util.make_dir(out_dir+'/'+alg+'_test/')
# list which will contain the results
# run algorithm alg for each file f
for f, f_test in zip(files,files_test):
fname = in_out.get_file_name(f, extension=False)
print ' ...{}'.format(fname)
# get data, split in features/target. If invalid stuff happened --> exit
X, y, headers = in_out.import_data(f, record_id, target_id) # assumption: first column is patientnumber and is pruned, last is target
if type(X) == bool: return
# if separate_testset:
# X, X_te = X
# y, y_te = y
# print ' ...train instances: {}, attributes: {}'.format(X.shape[0], X.shape[1])
# print ' ...test instances: {}, attributes: {}'.format(X_te.shape[0], X_te.shape[1])
# else:
print ' ...instances: {}, attributes: {}'.format(X.shape[0], X.shape[1])
model, best_features, results = execute_with_algorithm(alg, X, y, fname, headers, out_dir+'/'+alg+'/', record_id, target_id, feature_selection)
results_list.append(results)
if separate_testset:
X, y, headers = in_out.import_data(f_test, record_id, target_id) # assumption: first column is patientnumber and is pruned, last is target
if type(X) == bool: return
print ' ...instances: {}, attributes: {} (test set)'.format(X.shape[0], X.shape[1])
results = predict_separate(X, y, fname, out_dir+'/'+alg+'_test/', record_id, target_id, feature_selection, model, best_features)
results_list2.append(results)
try:
in_out.save_ROC(out_dir+'/'+alg+'/'+"roc.png", results_list, title='ROC curve')
except IndexError:
pass
try:
in_out.save_ROC(out_dir+'/'+alg+'_test/'+"roc.png", results_list2, title='ROC curve')
except NameError:
pass
# notify user
print '## Learning Finished ##'