def test_time(input_folder):
seed = 2222
standardize_method = 'z'
is_cz = False
freq_list = [
'001', '002', '003', '004', '005', '006', '008', '009', '01', '011'
]
freq_to_trainFreq_map = {
'001': '001',
'002': '002',
'003': '004',
'004': '005',
'005': '007',
'006': '008',
'008': '01',
'009': '011',
'01': '013',
'011': '014'
}
nel_graph_length = 13
e = run.Experiment('%s/%s' % (input_folder, standardize_method),
'%s/dataset' % (input_folder), seed, is_cz,
standardize_method, freq_list, freq_to_trainFreq_map,
nel_graph_length)
for foldi in range(5):
ftrnel = "%s/mimic_train_fold%d.nel" % (e.cdn, foldi)
ftrnode = "%s/mimic_train_fold%d.node" % (e.cdn, foldi)
fnel = "%s/mimic_fold%d.nel" % (e.cdn, foldi)
fnode = "%s/mimic_fold%d.node" % (e.cdn, foldi)
e.subgraph_mining(tr_nel=ftrnel,
tr_te_nel=fnel,
freq_t='011',
foldi=foldi)
def check_interpolation_and_subgraphs():
ft = 'raw'
minp = 0.5
minc = 0.6
seed = 2222
standardize_method = "cz"
is_cz = True
# standardize_method = "z"
# is_cz = False
freq_list = [
'001', '002', '003', '004', '005', '006', '008', '009', '01', '011'
]
freq_to_trainFreq_map = {
'001': '001',
'002': '002',
'003': '004',
'004': '005',
'005': '007',
'006': '008',
'008': '01',
'009': '011',
'01': '013',
'011': '014'
}
nel_graph_length = 13
fout = '../observer/check_interpolation_and_subgraphs/seed%s_%s_mice_mp%s_mc%s_%s' % (
seed, ft, minp, minc, standardize_method)
cu.checkAndCreate(fout)
cu.checkAndCreate('../data/seed%s/%s/mice/mp%s_mc%s/%s' %
(seed, ft, minp, minc, standardize_method))
e = run.Experiment(
'../data/seed%s/%s/mice/mp%s_mc%s/%s' %
(seed, ft, minp, minc, standardize_method),
'../data/seed%s/%s/mice/mp%s_mc%s/dataset' % (seed, ft, minp, minc),
seed, is_cz, standardize_method, freq_list, freq_to_trainFreq_map,
nel_graph_length)
foldi = 2
train = e.ftrain % (e.dataset_folder, foldi, e.standardize_method)
test = e.ftest % (e.dataset_folder, foldi, e.standardize_method)
print train
print test
ftrnel = "%s/mimic_train_fold%d.nel" % (fout, foldi)
ftrnode = "%s/mimic_train_fold%d.node" % (fout, foldi)
fnel = "%s/mimic_fold%d.nel" % (fout, foldi)
fnode = "%s/mimic_fold%d.node" % (fout, foldi)
# e.interpolation(trcsv=train, tecsv=test, ftrnel=ftrnel, ftrnode=ftrnode, fnel=fnel, fnode=fnode)
e.subgraph_mining(tr_nel=ftrnel,
tr_te_nel=fnel,
freq_t='011',
foldi=foldi,
cfolder=fout)
def check_nmfClassify(input_folder, output_folder, isg, freq_t, nc, c, pl, cw,
ntestth):
seed = 2222
standardize_method = 'z'
is_cz = False
freq_list = [
'001', '002', '003', '004', '005', '006', '008', '009', '01', '011'
]
freq_to_trainFreq_map = {
'001': '001',
'002': '002',
'003': '004',
'004': '005',
'005': '007',
'006': '008',
'008': '01',
'009': '011',
'01': '013',
'011': '014'
}
nel_graph_length = 13
e = run.Experiment('%s/%s' % (input_folder, standardize_method),
'%s/dataset' % (input_folder), seed, is_cz,
standardize_method, freq_list, freq_to_trainFreq_map,
nel_graph_length)
res_list = []
for foldi in range(5):
prediction_matrics = e.read_prediction_matrics(
isg, freq_t, cfolder='%s/isg%d/same_freq_t/pt_sg_w' % (e.cdn, isg))
res = e.nmfClassify(
prediction_matrics['ptsg'][foldi],
prediction_matrics['ptwd'][foldi],
prediction_matrics['sgs'][foldi], prediction_matrics['pt'][foldi],
prediction_matrics['gt'][foldi],
'%s/isg%d/nmf_piks/nmf_%s_fold%d_%d_ramdon0-again.pik' %
(output_folder, isg, freq_t, foldi, nc), ntestth, foldi, nc, c, pl,
cw)
res_list.append(res)
(auc, tr_auc) = e.get_mean_auc(res_list)
print auc, tr_auc
def run_best_model(cdn):
ft = 'raw'
seed = 2222
standardize_method = 'z'
is_cz = False
cu.checkAndCreate('%s/seed%d' % (cdn, seed))
pp.split_nfolds('%s/alldata_readmit.csv' % cdn,
'%s/seed%d/alldata_readmit' % (cdn, seed),
shuffle=True,
seed=seed)
pp.split_by_feature_type(cdn='%s/seed%d' % (cdn, seed),
fn_prefix='%s/seed%d/alldata_readmit' %
(cdn, seed))
cu.checkAndCreate('%s/seed%d/raw/interp' % (cdn, seed))
cu.checkAndCreate('%s/seed%d/raw/interp/mean/dataset' % (cdn, seed))
for i in range(5):
pp.impute_by_interpolation_on_last12h(
'%s/seed%d/raw/test_fold%d.csv' % (cdn, seed, i),
'%s/seed%d/raw/interp/test_fold%d.csv' % (cdn, seed, i),
'%s/seed%d/raw/interp/extrapolation_log_test_fold%d.txt' %
(cdn, seed, i))
pp.impute_by_interpolation_on_last12h(
'%s/seed%d/raw/train_fold%d.csv' % (cdn, seed, i),
'%s/seed%d/raw/interp/train_fold%d.csv' % (cdn, seed, i),
'%s/seed%d/raw/interp/extrapolation_log_train_fold%d.txt' %
(cdn, seed, i))
pp.impute_by_mean(
'%s/seed%d/raw/interp/train_fold%d.csv' % (cdn, seed, i),
'%s/seed%d/raw/interp/test_fold%d.csv' % (cdn, seed, i),
'%s/seed%d/raw/interp/mean/dataset/train_fold%d.csv' %
(cdn, seed, i),
'%s/seed%d/raw/interp/mean/dataset/test_fold%d.csv' %
(cdn, seed, i))
pp.standardize_data(
'%s/seed%d/raw/interp/mean/dataset/train_fold%d.csv' %
(cdn, seed, i),
'%s/seed%d/raw/interp/mean/dataset/test_fold%d.csv' %
(cdn, seed, i),
'%s/seed%d/raw/interp/mean/dataset/train_fold%d_%s.csv' %
(cdn, seed, i, standardize_method),
'%s/seed%d/raw/interp/mean/dataset/test_fold%d_%s.csv' %
(cdn, seed, i, standardize_method))
# run temporal model
freq_list = ['011']
freq_to_trainFreq_map = {'011': '014'}
nel_graph_length = 13
cu.checkAndCreate('%s/seed%d/%s/interp/mean/%s' %
(cdn, seed, ft, standardize_method))
e = rn.Experiment(
'%s/seed%d/%s/interp/mean/%s' % (cdn, seed, ft, standardize_method),
'%s/seed%d/%s/interp/mean/dataset' % (cdn, seed, ft), seed, is_cz,
standardize_method, freq_list, freq_to_trainFreq_map, nel_graph_length)
isg = 0
freq_t = '011'
nc = 110
c = 2
pl = 'l1'
cw = 'balanced'
ntestth = 2
cu.checkAndCreate('%s/isg%d' % (e.cdn, isg))
cu.checkAndCreate('%s/isg%d/pt_sg_w' % (e.cdn, isg))
cu.checkAndCreate('%s/isg%d/res' % (e.cdn, isg))
cu.checkAndCreate('%s/isg%d/nmf_piks' % (e.cdn, isg))
for foldi in range(5):
train = e.ftrain % (e.dataset_folder, foldi, e.standardize_method)
test = e.ftest % (e.dataset_folder, foldi, e.standardize_method)
print train
print test
ftrnel = "%s/mimic_train_fold%d.nel" % (e.cdn, foldi)
ftrnode = "%s/mimic_train_fold%d.node" % (e.cdn, foldi)
fnel = "%s/mimic_fold%d.nel" % (e.cdn, foldi)
fnode = "%s/mimic_fold%d.node" % (e.cdn, foldi)
e.interpolation(trcsv=train,
tecsv=test,
ftrnel=ftrnel,
ftrnode=ftrnode,
fnel=fnel,
fnode=fnode)
e.get_freq_to_trainFreq_map(foldi)
for freq_t in e.moss_freq_threshold_list:
e.subgraph_mining(tr_nel=ftrnel,
tr_te_nel=fnel,
freq_t=freq_t,
foldi=foldi)
e.gen_pt_sg_files(isg, freq_t, foldi)
cu.checkAndCreate('%s/seed%d/raw/interp/mean/last_measures/dataset' %
(cdn, seed))
# run baseline model
for i in range(5):
pp.get_last_measurements(
'%s/seed%d/raw/interp/mean/dataset/train_fold%d_%s.csv' %
(cdn, seed, i, standardize_method),
'%s/seed%d/raw/interp/mean/last_measures/dataset/train_fold%d_%s.csv'
% (cdn, seed, i, standardize_method))
pp.get_last_measurements(
'%s/seed%d/raw/interp/mean/dataset/test_fold%d_%s.csv' %
(cdn, seed, i, standardize_method),
'%s/seed%d/raw/interp/mean/last_measures/dataset/test_fold%d_%s.csv'
% (cdn, seed, i, standardize_method))
best_features = rfe(
'%s/seed%d/raw/interp/mean/last_measures' % (cdn, seed), 50,
standardize_method, 5, 'l1', 'balanced')
print best_features
# best_features = ['urineByHrByWeight', 'HCT', 'INR', 'Platelets', 'RBC',
# 'DeliveredTidalVolume', 'PlateauPres', 'RAW', 'RSBI', 'mDBP', 'CV_HR',
# 'Art_BE', 'Art_CO2', 'Art_PaCO2', 'Art_pH', 'Cl', 'Mg', 'Anticoagulant',
# 'beta.Blocking_agent', 'Somatostatin_preparation', 'Vasodilating_agent',
# 'AIDS', 'MetCarcinoma']
baseline_auc = lr('%s/seed%d/raw/interp/mean/last_measures' % (cdn, seed),
standardize_method, 5, 'l1', 'balanced', 50)
print 'baseline AUC: %s' % baseline_auc
res_list = []
for foldi in range(5):
fnaddtr = '../data/seed2222/raw/interp/mean/last_measures/dataset/train_fold%d_%s.csv' % (
foldi, standardize_method)
fnaddte = '../data/seed2222/raw/interp/mean/last_measures/dataset/test_fold%d_%s.csv' % (
foldi, standardize_method)
prediction_matrics = e.read_prediction_matrics(isg, freq_t)
(res, gt_te, pt_te, res_baseline) = e.nmfClassify_ob(
prediction_matrics['ptsg'][foldi],
prediction_matrics['ptwd'][foldi],
prediction_matrics['sgs'][foldi], prediction_matrics['pt'][foldi],
prediction_matrics['gt'][foldi],
'%s/isg%d/nmf_piks/nmf_%s_fold%d_%d.pik' %
(e.cdn, isg, freq_t, foldi, nc), ntestth, foldi, nc, c, pl, cw,
fnaddtr, fnaddte, best_features)
res_list.append(res)
(auc, tr_auc) = e.get_mean_auc(res_list)
print auc, tr_auc
for i in range(len(res_list)):
with open(
'../data/seed2222/raw/interp/mean/z/isg0/res/c_pre_te_fold%d' %
i, 'wb') as f:
pickle.dump(res_list[i]['c_pre_te'], f)
with open('../data/seed2222/raw/interp/mean/z/isg0/res/res_fold%d' % i,
'wb') as f:
pickle.dump(res_list[i], f)
def get_res_and_oc(input_folder, output_folder):
seed = 2222
standardize_method = 'z'
is_cz = False
freq_list = [
'001', '002', '003', '004', '005', '006', '008', '009', '01', '011'
]
freq_to_trainFreq_map = {
'001': '001',
'002': '002',
'003': '004',
'004': '005',
'005': '007',
'006': '008',
'008': '01',
'009': '011',
'01': '013',
'011': '014'
}
nel_graph_length = 13
e = run.Experiment('%s/%s' % (input_folder, standardize_method),
'%s/dataset' % (input_folder), seed, is_cz,
standardize_method, freq_list, freq_to_trainFreq_map,
nel_graph_length)
isg = 0
freq_t = '011'
# foldi = 0
nc = 110
c = 2
pl = 'l1'
cw = 'balanced'
ntestth = 2
best_features = [
'urineByHrByWeight', 'HCT', 'INR', 'Platelets', 'RBC',
'DeliveredTidalVolume', 'PlateauPres', 'RAW', 'RSBI', 'mDBP', 'CV_HR',
'Art_BE', 'Art_CO2', 'Art_PaCO2', 'Art_pH', 'Cl', 'Mg',
'Anticoagulant', 'beta.Blocking_agent', 'Somatostatin_preparation',
'Vasodilating_agent', 'AIDS', 'MetCarcinoma'
]
# res_list = []
# oc_list = []
# oa = []
# for foldi in range(5):
# fnaddtr = '../../readmission_risk_baseline/data/seed2222/raw/interp/mean/last_measures/dataset/train_fold%d_%s.csv'%(foldi,standardize_method)
# fnaddte = '../../readmission_risk_baseline/data/seed2222/raw/interp/mean/last_measures/dataset/test_fold%d_%s.csv'%(foldi,standardize_method)
# prediction_matrics = e.read_prediction_matrics(isg,freq_t)
# (res, gt_te, pt_te) = e.nmfClassify_ob(prediction_matrics['ptsg'][foldi],
# prediction_matrics['ptwd'][foldi],
# prediction_matrics['sgs'][foldi],
# prediction_matrics['pt'][foldi],
# prediction_matrics['gt'][foldi],
# '%s/isg%d/nmf_piks/nmf_%s_fold%d_%d.pik'%(e.cdn,isg,freq_t,foldi,nc),
# ntestth, foldi, nc, c, pl, cw, fnaddtr, fnaddte, best_features)
# res_list.append(res)
# oc_list.append(gt_te)
# oa.append(res['n_pre_te'])
# (auc, tr_auc) = e.get_mean_auc(res_list)
# print auc, tr_auc
res_list = []
ob = []
for foldi in range(5):
prediction_matrics = e.read_prediction_matrics(isg, freq_t)
res = e.nmfClassify(
prediction_matrics['ptsg'][foldi],
prediction_matrics['ptwd'][foldi],
prediction_matrics['sgs'][foldi], prediction_matrics['pt'][foldi],
prediction_matrics['gt'][foldi],
'%s/isg%d/nmf_piks/nmf_%s_fold%d_%d.pik' %
(e.cdn, isg, freq_t, foldi, nc), ntestth, foldi, nc, c, pl, cw)
res_list.append(res)
ob.append(res['n_pre_te'])
(auc, tr_auc) = e.get_mean_auc(res_list)
print auc, tr_auc
def error_analysis(input_folder, output_folder):
ft = 'raw'
minp = 0.5
minc = 0.6
seed = 2222
standardize_method = 'z'
is_cz = False
freq_list = [
'001', '002', '003', '004', '005', '006', '008', '009', '01', '011'
]
freq_to_trainFreq_map = {
'001': '001',
'002': '002',
'003': '004',
'004': '005',
'005': '007',
'006': '008',
'008': '01',
'009': '011',
'01': '013',
'011': '014'
}
nel_graph_length = 13
# cu.checkAndCreate('../data/seed%s/%s/mice/mp%s_mc%s/%s'%(seed,ft,minp,minc,standardize_method))
e = run.Experiment('%s/%s' % (input_folder, standardize_method),
'%s/dataset' % (input_folder), seed, is_cz,
standardize_method, freq_list, freq_to_trainFreq_map,
nel_graph_length)
# e = run.Experiment('../data/seed%s/%s/mice/mp%s_mc%s/%s'%(seed,ft,minp,minc,standardize_method),
# '../data/seed%s/%s/mice/mp%s_mc%s/dataset'%(seed,ft,minp,minc),
# seed,is_cz,standardize_method,freq_list,freq_to_trainFreq_map,nel_graph_length)
# NMF:
isg = 0
freq_t = '011'
nc = 110
c = 2
pl = 'l1'
cw = 'balanced'
ntestth = 2
# DirClassify:
# isg = 0
# freq_t = '004'
# c = 1
# pl = 'l1'
# cw = 'balanced'
# ntestth = 2
best_features = [
'urineByHrByWeight', 'HCT', 'INR', 'Platelets', 'RBC',
'DeliveredTidalVolume', 'PlateauPres', 'RAW', 'RSBI', 'mDBP', 'CV_HR',
'Art_BE', 'Art_CO2', 'Art_PaCO2', 'Art_pH', 'Cl', 'Mg',
'Anticoagulant', 'beta.Blocking_agent', 'Somatostatin_preparation',
'Vasodilating_agent', 'AIDS', 'MetCarcinoma'
]
res_list = []
# res_baseline_list = []
for foldi in range(5):
fnaddtr = '../../readmission_risk_baseline/data/seed2222/raw/interp/mean/last_measures/dataset/train_fold%d_%s_t.csv' % (
foldi, standardize_method)
fnaddte = '../../readmission_risk_baseline/data/seed2222/raw/interp/mean/last_measures/dataset/test_fold%d_%s_t.csv' % (
foldi, standardize_method)
prediction_matrics = e.read_prediction_matrics(isg, freq_t)
(res, gt_te, pt_te, res_baseline) = e.nmfClassify_ob(
prediction_matrics['ptsg'][foldi],
# res = e.nmfClassify(prediction_matrics['ptsg'][foldi],
prediction_matrics['ptwd'][foldi],
prediction_matrics['sgs'][foldi],
prediction_matrics['pt'][foldi],
prediction_matrics['gt'][foldi],
'%s/isg%d/nmf_piks/nmf_%s_fold%d_%d.pik' %
(e.cdn, isg, freq_t, foldi, nc),
ntestth,
foldi,
nc,
c,
pl,
cw,
fnaddtr,
fnaddte,
best_features)
# res = e.dirClassify(prediction_matrics['ptsg'][foldi],
# # res = e.nmfClassify(prediction_matrics['ptsg'][foldi],
# prediction_matrics['ptwd'][foldi],
# prediction_matrics['sgs'][foldi],
# prediction_matrics['pt'][foldi],
# prediction_matrics['gt'][foldi],
# ntestth, foldi, c, pl, cw)
res_list.append(res)
# res_baseline_list.append(res_baseline)
# with open('%s/res_baseline_1170_list'%(output_folder),'wb') as f:
# pickle.dump(res_baseline_list,f)
(auc, tr_auc) = e.get_mean_auc(res_list)
print auc, tr_auc
# (auc, tr_auc) = e.get_mean_auc(res_baseline_list)
# print auc, tr_auc
# cu.checkAndCreate(output_folder)
for i in range(len(res_list)):
# i = 4
# with open('%s/gt_te_fold%d_t'%(output_folder,i),'wb') as f:
# pickle.dump(gt_te,f)
# with open('%s/pt_te_fold%d_t'%(output_folder,i),'wb') as f:
# pickle.dump(pt_te,f)
# with open('%s/pre_te_fold%d_t'%(output_folder,i),'wb') as f:
# pickle.dump(res_list[i]['n_pre_te'],f)
with open('%s/c_pre_te_fold%d' % (output_folder, i), 'wb') as f:
pickle.dump(res_list[i]['c_pre_te'], f)