# data.loc[(data.ttocvd <= TARGET_END) & (data.cvd == 0), 'label'] = 2
data = data_short_formatting(data, ['label', 'cvd', 'ttocvd'] + BASE_COVS +
INDICATORS, MARKERS, TRUNCATE_TIME)
FEATURE_LIST = data.columns[4:-3]
train_set, test_set = train_test_split(data, .3)
clf = LogisticRegression(solver='lbfgs').fit(
train_set.loc[:, FEATURE_LIST].values, train_set.loc[:,
'label'].values)
result = np.vstack(
(clf.predict_proba(test_set.loc[:, FEATURE_LIST].values)[:, 1],
test_set.loc[:, 'label'])).T
print("death ratio",
sum(test_set.loc[:, 'label'] == 1) / test_set.shape[0])
print(
"accuracy",
clf.score(test_set.loc[:, FEATURE_LIST].values,
test_set.loc[:, 'label'].values))
print(
"aucJM",
auc_jm(
torch.Tensor(test_set.loc[:, 'label'].values),
torch.Tensor(test_set.loc[:, 'ttocvd'].values),
torch.Tensor(
clf.predict_proba(test_set.loc[:, FEATURE_LIST].values)[:, 1]),
TARGET_END))
train_set, test_set = train_test_split(data, .3)
x_train, label_train = \
torch.from_numpy(train_set.loc[:, FEATURE_LIST].values).type(torch.FloatTensor), \
torch.from_numpy(train_set['label'].values).type(torch.LongTensor)
x_test, label_test = \
torch.from_numpy(test_set.loc[:, FEATURE_LIST].values).type(torch.FloatTensor), \
torch.from_numpy(test_set['label'].values).type(torch.LongTensor)
train_loss = []
test_loss = []
for epoch in range(n_epochs):
print("*************** new epoch ******************")
auc_test = auc_jm(
torch.from_numpy(test_set['cvd'].values).type(torch.IntTensor),
torch.from_numpy(test_set['ttocvd'].values).type(torch.IntTensor),
model(x_test)[:, 1], TARGET_TIME)
print("ten year auc:", auc_test)
label_pred = torch.exp(model(x_test))[:, 1].data > .5
label_true = test_set['label'].values
print("accuracy",
sum(label_pred.numpy() == label_true) * 1.0 / len(label_true))
scheduler.step()
for param_group in optimizer.param_groups:
print("learning rate:", param_group['lr'])
train_loss = train_loss + train(batch_size=batch_size)
test_loss = test_loss + test(batch_size=batch_size)
print("parameter change:", param_change(param, model))
torch.from_numpy(test_set.loc[:, FEATURE_LIST].values).type(torch.FloatTensor), \
torch.from_numpy(test_set['label'].values).type(torch.LongTensor), \
torch.from_numpy(test_set['cvd'].values).type(torch.LongTensor)
train_loss = []
test_loss = []
test_event = torch.from_numpy(test_set['cvd'].values).type(torch.IntTensor)
test_time = torch.from_numpy(test_set['ttocvd'].values).type(
torch.IntTensor)
for epoch in range(n_epochs):
print("*************** new epoch ******************")
pred = 1 - torch.cumprod(1 - model(x_test), dim=1)
print(torch.mean(model(x_test), dim=0))
auc_test = [
auc_jm(test_event, test_time, pred[:, 0], 20),
auc_jm(test_event, test_time, pred[:, 1], 25),
auc_jm(test_event, test_time, pred[:, 2], 30),
auc_jm(test_event, test_time, pred[:, 3], 40),
]
print("ten year auc:", auc_test)
scheduler.step()
for param_group in optimizer.param_groups:
print("learning rate:", param_group['lr'])
train_loss = train_loss + train(batch_size=batch_size)
test_loss = test_loss + test(batch_size=batch_size)
print("parameter change:", param_change(param, model))
param = deepcopy(model.state_dict())
torch.tensor(round(cox_complex_res.event_time)),
torch.tensor(cox_complex_res.hazard_ratio)))
jm_simple_res = pd.read_csv(os.path.join(DIR, 'jm_simple_res.csv'),
delimiter=',')
jm_complex_res = pd.read_csv(os.path.join(DIR, 'jm_complex_res.csv'),
delimiter=',')
# print(pd.concat([jm_simple_res, cox_simple_res['hazard_ratio']], axis=1))
for horizon in [20, 25, 30]:
print("horizon is", horizon)
print(
"simple",
# fitted result from JM package is survival probability
1 - auc_jm(torch.tensor(jm_simple_res.event),
torch.tensor(round(jm_simple_res.event_time)),
torch.tensor(jm_simple_res[str(horizon)]), horizon))
print(
"complex",
1 - auc_jm(torch.tensor(jm_complex_res.event),
torch.tensor(round(jm_complex_res.event_time)),
torch.tensor(jm_complex_res[str(horizon)]), horizon))
print(
c_index(torch.tensor(jm_simple_res.event),
torch.tensor(round(jm_simple_res.event_time)),
1 - torch.tensor(jm_simple_res[str(horizon)])))
print(
c_index(torch.tensor(jm_complex_res.event),
torch.tensor(round(jm_complex_res.event_time)),
1 - torch.tensor(jm_complex_res[str(horizon)])))
torch.from_numpy(test_set.loc[:, FEATURE_LIST].values).type(torch.FloatTensor), \
torch.from_numpy(test_set['label'].values).type(torch.LongTensor), \
torch.from_numpy(test_set['cvd'].values).type(torch.LongTensor)
train_loss = []
test_loss = []
test_event = torch.from_numpy(test_set['cvd'].values).type(torch.IntTensor)
test_time = torch.from_numpy(test_set['ttocvd'].values).type(torch.IntTensor)
for epoch in range(n_epochs):
print("*************** new epoch ******************")
pred = 1 - torch.cumprod(1 - model(x_test), dim=1)
# print(torch.mean(model(x_test), dim=0))
print(torch.mean(pred, dim=0)[[6, 11, 16, 26]])
auc_test = [
auc_jm(test_event, test_time, pred[:, 6], 20),
auc_jm(test_event, test_time, pred[:, 11], 25),
auc_jm(test_event, test_time, pred[:, 16], 30),
auc_jm(test_event, test_time, pred[:, 26], 40),
]
print("ten year auc:", auc_test)
cindex = [
c_index(test_event, test_time, pred[:, 6]),
c_index(test_event, test_time, pred[:, 11]),
c_index(test_event, test_time, pred[:, 16]),
c_index(test_event, test_time, pred[:, 26]),
]
print("c index:", cindex)
scheduler.step()
for param_group in optimizer.param_groups: