def test_summary(self):
# smoke test
np.random.seed(34234)
time = 50 * np.random.uniform(size=200)
status = np.random.randint(0, 2, 200).astype(np.float64)
exog = np.random.normal(size=(200,4))
mod = PHReg(time, exog, status)
rslt = mod.fit()
smry = rslt.summary()
strata = np.kron(np.arange(50), np.ones(4))
mod = PHReg(time, exog, status, strata=strata)
rslt = mod.fit()
smry = rslt.summary()
msg = "3 strata dropped for having no events"
assert_(msg in str(smry))
groups = np.kron(np.arange(25), np.ones(8))
mod = PHReg(time, exog, status)
rslt = mod.fit(groups=groups)
smry = rslt.summary()
entry = np.random.uniform(0.1, 0.8, 200) * time
mod = PHReg(time, exog, status, entry=entry)
rslt = mod.fit()
smry = rslt.summary()
msg = "200 observations have positive entry times"
assert_(msg in str(smry))
def test_summary(self):
# smoke test
np.random.seed(34234)
time = 50 * np.random.uniform(size=200)
status = np.random.randint(0, 2, 200).astype(np.float64)
exog = np.random.normal(size=(200, 4))
mod = PHReg(time, exog, status)
rslt = mod.fit()
smry = rslt.summary()
strata = np.kron(np.arange(50), np.ones(4))
mod = PHReg(time, exog, status, strata=strata)
rslt = mod.fit()
smry = rslt.summary()
msg = "3 strata dropped for having no events"
assert_(msg in str(smry))
groups = np.kron(np.arange(25), np.ones(8))
mod = PHReg(time, exog, status)
rslt = mod.fit(groups=groups)
smry = rslt.summary()
entry = np.random.uniform(0.1, 0.8, 200) * time
mod = PHReg(time, exog, status, entry=entry)
rslt = mod.fit()
smry = rslt.summary()
msg = "200 observations have positive entry times"
assert_(msg in str(smry))
def test_formula(self):
np.random.seed(34234)
time = 50 * np.random.uniform(size=200)
status = np.random.randint(0, 2, 200).astype(np.float64)
exog = np.random.normal(size=(200,4))
entry = np.zeros_like(time)
entry[0:10] = time[0:10] / 2
df = pd.DataFrame({"time": time, "status": status,
"exog1": exog[:, 0], "exog2": exog[:, 1],
"exog3": exog[:, 2], "exog4": exog[:, 3],
"entry": entry})
mod1 = PHReg(time, exog, status, entry=entry)
rslt1 = mod1.fit()
fml = "time ~ 0 + exog1 + exog2 + exog3 + exog4"
mod2 = PHReg.from_formula(fml, df, status=status,
entry=entry)
rslt2 = mod2.fit()
mod3 = PHReg.from_formula(fml, df, status="status",
entry="entry")
rslt3 = mod3.fit()
assert_allclose(rslt1.params, rslt2.params)
assert_allclose(rslt1.params, rslt3.params)
assert_allclose(rslt1.bse, rslt2.bse)
assert_allclose(rslt1.bse, rslt3.bse)
def test_offset(self):
np.random.seed(34234)
time = 50 * np.random.uniform(size=200)
status = np.random.randint(0, 2, 200).astype(np.float64)
exog = np.random.normal(size=(200, 4))
mod1 = PHReg(time, exog, status)
rslt1 = mod1.fit()
offset = exog[:, 0] * rslt1.params[0]
exog = exog[:, 1:]
mod2 = PHReg(time, exog, status, offset=offset)
rslt2 = mod2.fit()
assert_allclose(rslt2.params, rslt1.params[1:])
def test_offset(self):
np.random.seed(34234)
time = 50 * np.random.uniform(size=200)
status = np.random.randint(0, 2, 200).astype(np.float64)
exog = np.random.normal(size=(200,4))
mod1 = PHReg(time, exog, status)
rslt1 = mod1.fit()
offset = exog[:,0] * rslt1.params[0]
exog = exog[:, 1:]
mod2 = PHReg(time, exog, status, offset=offset)
rslt2 = mod2.fit()
assert_allclose(rslt2.params, rslt1.params[1:])
def test_formula(self):
np.random.seed(34234)
time = 50 * np.random.uniform(size=200)
status = np.random.randint(0, 2, 200).astype(np.float64)
exog = np.random.normal(size=(200, 4))
entry = np.zeros_like(time)
entry[0:10] = time[0:10] / 2
df = pd.DataFrame({
"time": time,
"status": status,
"exog1": exog[:, 0],
"exog2": exog[:, 1],
"exog3": exog[:, 2],
"exog4": exog[:, 3],
"entry": entry
})
mod1 = PHReg(time, exog, status, entry=entry)
rslt1 = mod1.fit()
fml = "time ~ 0 + exog1 + exog2 + exog3 + exog4"
mod2 = PHReg.from_formula(fml, df, status=status, entry=entry)
rslt2 = mod2.fit()
mod3 = PHReg.from_formula(fml, df, status="status", entry="entry")
rslt3 = mod3.fit()
assert_allclose(rslt1.params, rslt2.params)
assert_allclose(rslt1.params, rslt3.params)
assert_allclose(rslt1.bse, rslt2.bse)
assert_allclose(rslt1.bse, rslt3.bse)
def test_summary(self):
# smoke test
np.random.seed(34234)
time = 50 * np.random.uniform(size=200)
status = np.random.randint(0, 2, 200).astype(np.float64)
exog = np.random.normal(size=(200, 4))
mod = PHReg(time, exog, status)
rslt = mod.fit()
rslt.summary()
def test_summary(self):
# smoke test
np.random.seed(34234)
time = 50 * np.random.uniform(size=200)
status = np.random.randint(0, 2, 200).astype(np.float64)
exog = np.random.normal(size=(200,4))
mod = PHReg(time, exog, status)
rslt = mod.fit()
rslt.summary()
def test_post_estimation(self):
# All regression tests
np.random.seed(34234)
time = 50 * np.random.uniform(size=200)
status = np.random.randint(0, 2, 200).astype(np.float64)
exog = np.random.normal(size=(200, 4))
mod = PHReg(time, exog, status)
rslt = mod.fit()
mart_resid = rslt.martingale_residuals
assert_allclose(np.abs(mart_resid).sum(), 120.72475743348433)
w_avg = rslt.weighted_covariate_averages
assert_allclose(
np.abs(w_avg[0]).sum(0), np.r_[7.31008415, 9.77608674, 10.89515885,
13.1106801])
bc_haz = rslt.baseline_cumulative_hazard
v = [np.mean(np.abs(x)) for x in bc_haz[0]]
w = np.r_[23.482841556421608, 0.44149255358417017, 0.68660114081275281]
assert_allclose(v, w)
score_resid = rslt.score_residuals
v = np.r_[0.50924792, 0.4533952, 0.4876718, 0.5441128]
w = np.abs(score_resid).mean(0)
assert_allclose(v, w)
groups = np.random.randint(0, 3, 200)
mod = PHReg(time, exog, status)
rslt = mod.fit(groups=groups)
robust_cov = rslt.cov_params()
v = [0.00513432, 0.01278423, 0.00810427, 0.00293147]
w = np.abs(robust_cov).mean(0)
assert_allclose(v, w, rtol=1e-6)
s_resid = rslt.schoenfeld_residuals
ii = np.flatnonzero(np.isfinite(s_resid).all(1))
s_resid = s_resid[ii, :]
v = np.r_[0.85154336, 0.72993748, 0.73758071, 0.78599333]
assert_allclose(np.abs(s_resid).mean(0), v)
def test_post_estimation(self):
# All regression tests
np.random.seed(34234)
time = 50 * np.random.uniform(size=200)
status = np.random.randint(0, 2, 200).astype(np.float64)
exog = np.random.normal(size=(200,4))
mod = PHReg(time, exog, status)
rslt = mod.fit()
mart_resid = rslt.martingale_residuals
assert_allclose(np.abs(mart_resid).sum(), 120.72475743348433)
w_avg = rslt.weighted_covariate_averages
assert_allclose(np.abs(w_avg[0]).sum(0),
np.r_[7.31008415, 9.77608674,10.89515885, 13.1106801])
bc_haz = rslt.baseline_cumulative_hazard
v = [np.mean(np.abs(x)) for x in bc_haz[0]]
w = np.r_[23.482841556421608, 0.44149255358417017,
0.68660114081275281]
assert_allclose(v, w)
score_resid = rslt.score_residuals
v = np.r_[ 0.50924792, 0.4533952, 0.4876718, 0.5441128]
w = np.abs(score_resid).mean(0)
assert_allclose(v, w)
groups = np.random.randint(0, 3, 200)
mod = PHReg(time, exog, status)
rslt = mod.fit(groups=groups)
robust_cov = rslt.cov_params()
v = [0.00513432, 0.01278423, 0.00810427, 0.00293147]
w = np.abs(robust_cov).mean(0)
assert_allclose(v, w, rtol=1e-6)
s_resid = rslt.schoenfeld_residuals
ii = np.flatnonzero(np.isfinite(s_resid).all(1))
s_resid = s_resid[ii, :]
v = np.r_[0.85154336, 0.72993748, 0.73758071, 0.78599333]
assert_allclose(np.abs(s_resid).mean(0), v)
def test_predict(self):
# All smoke tests. We should be able to convert the lhr and hr
# tests into real tests against R. There are many options to
# this function that may interact in complicated ways. Only a
# few key combinations are tested here.
np.random.seed(34234)
endog = 50 * np.random.uniform(size=200)
status = np.random.randint(0, 2, 200).astype(np.float64)
exog = np.random.normal(size=(200, 4))
mod = PHReg(endog, exog, status)
rslt = mod.fit()
rslt.predict()
for pred_type in "lhr", "hr", "cumhaz", "surv":
rslt.predict(pred_type=pred_type)
rslt.predict(endog=endog[0:10], pred_type=pred_type)
rslt.predict(endog=endog[0:10], exog=exog[0:10, :], pred_type=pred_type)
def do1(self, fname, ties, entry_f, strata_f):
# Read the test data.
time, status, entry, exog = self.load_file(fname)
n = len(time)
vs = fname.split("_")
n = int(vs[2])
p = int(vs[3].split(".")[0])
ties1 = ties[0:3]
# Needs to match the kronecker statement in survival.R
strata = np.kron(range(5), np.ones(n // 5))
# No stratification or entry times
mod = PHReg(time, exog, status, ties=ties)
phrb = mod.fit(**args)
coef_r, se_r, time_r, hazard_r = get_results(n, p, None, ties1)
assert_allclose(phrb.params, coef_r, rtol=1e-3)
assert_allclose(phrb.bse, se_r, rtol=1e-4)
time_h, cumhaz, surv = phrb.baseline_cumulative_hazard[0]
# Entry times but no stratification
phrb = PHReg(time, exog, status, entry=entry,
ties=ties).fit(**args)
coef, se, time_r, hazard_r = get_results(n, p, "et", ties1)
assert_allclose(phrb.params, coef, rtol=1e-3)
assert_allclose(phrb.bse, se, rtol=1e-3)
# Stratification but no entry times
phrb = PHReg(time, exog, status, strata=strata,
ties=ties).fit(**args)
coef, se, time_r, hazard_r = get_results(n, p, "st", ties1)
assert_allclose(phrb.params, coef, rtol=1e-4)
assert_allclose(phrb.bse, se, rtol=1e-4)
# Stratification and entry times
phrb = PHReg(time, exog, status, entry=entry,
strata=strata, ties=ties).fit(**args)
coef, se, time_r, hazard_r = get_results(n, p, "et_st", ties1)
assert_allclose(phrb.params, coef, rtol=1e-3)
assert_allclose(phrb.bse, se, rtol=1e-4)
#smoke test
time_h, cumhaz, surv = phrb.baseline_cumulative_hazard[0]
def do1(fname, ties, entry_f, strata_f):
# Read the test data.
time, status, entry, exog = TestPHReg.load_file(fname)
n = len(time)
vs = fname.split("_")
n = int(vs[2])
p = int(vs[3].split(".")[0])
ties1 = ties[0:3]
# Needs to match the kronecker statement in survival.R
strata = np.kron(range(5), np.ones(n // 5))
# No stratification or entry times
mod = PHReg(time, exog, status, ties=ties)
phrb = mod.fit(**args)
coef_r, se_r, time_r, hazard_r = get_results(n, p, None, ties1)
assert_allclose(phrb.params, coef_r, rtol=1e-3)
assert_allclose(phrb.bse, se_r, rtol=1e-4)
time_h, cumhaz, surv = phrb.baseline_cumulative_hazard[0]
# Entry times but no stratification
phrb = PHReg(time, exog, status, entry=entry,
ties=ties).fit(**args)
coef, se, time_r, hazard_r = get_results(n, p, "et", ties1)
assert_allclose(phrb.params, coef, rtol=1e-3)
assert_allclose(phrb.bse, se, rtol=1e-3)
# Stratification but no entry times
phrb = PHReg(time, exog, status, strata=strata,
ties=ties).fit(**args)
coef, se, time_r, hazard_r = get_results(n, p, "st", ties1)
assert_allclose(phrb.params, coef, rtol=1e-4)
assert_allclose(phrb.bse, se, rtol=1e-4)
# Stratification and entry times
phrb = PHReg(time, exog, status, entry=entry,
strata=strata, ties=ties).fit(**args)
coef, se, time_r, hazard_r = get_results(n, p, "et_st", ties1)
assert_allclose(phrb.params, coef, rtol=1e-3)
assert_allclose(phrb.bse, se, rtol=1e-4)
#smoke test
time_h, cumhaz, surv = phrb.baseline_cumulative_hazard[0]
def test_get_distribution(self):
# Smoke test
np.random.seed(34234)
exog = np.random.normal(size=(200, 2))
lin_pred = exog.sum(1)
elin_pred = np.exp(-lin_pred)
time = -elin_pred * np.log(np.random.uniform(size=200))
mod = PHReg(time, exog)
rslt = mod.fit()
dist = rslt.get_distribution()
fitted_means = dist.mean()
true_means = elin_pred
fitted_var = dist.var()
fitted_sd = dist.std()
sample = dist.rvs()
def test_predict(self):
# All smoke tests. We should be able to convert the lhr and hr
# tests into real tests against R. There are many options to
# this function that may interact in complicated ways. Only a
# few key combinations are tested here.
np.random.seed(34234)
endog = 50 * np.random.uniform(size=200)
status = np.random.randint(0, 2, 200).astype(np.float64)
exog = np.random.normal(size=(200,4))
mod = PHReg(endog, exog, status)
rslt = mod.fit()
rslt.predict()
for pred_type in 'lhr', 'hr', 'cumhaz', 'surv':
rslt.predict(pred_type=pred_type)
rslt.predict(endog=endog[0:10], pred_type=pred_type)
rslt.predict(endog=endog[0:10], exog=exog[0:10,:],
pred_type=pred_type)
def test_get_distribution(self):
# Smoke test
np.random.seed(34234)
exog = np.random.normal(size=(200, 2))
lin_pred = exog.sum(1)
elin_pred = np.exp(-lin_pred)
time = -elin_pred * np.log(np.random.uniform(size=200))
mod = PHReg(time, exog)
rslt = mod.fit()
dist = rslt.get_distribution()
fitted_means = dist.mean()
true_means = elin_pred
fitted_var = dist.var()
fitted_sd = dist.std()
sample = dist.rvs()
def test_get_distribution(self):
np.random.seed(34234)
n = 200
exog = np.random.normal(size=(n, 2))
lin_pred = exog.sum(1)
elin_pred = np.exp(-lin_pred)
time = -elin_pred * np.log(np.random.uniform(size=n))
status = np.ones(n)
status[0:20] = 0
strata = np.kron(range(5), np.ones(n // 5))
mod = PHReg(time, exog, status=status, strata=strata)
rslt = mod.fit()
dist = rslt.get_distribution()
fitted_means = dist.mean()
true_means = elin_pred
fitted_var = dist.var()
fitted_sd = dist.std()
sample = dist.rvs()
def test_get_distribution(self):
np.random.seed(34234)
n = 200
exog = np.random.normal(size=(n, 2))
lin_pred = exog.sum(1)
elin_pred = np.exp(-lin_pred)
time = -elin_pred * np.log(np.random.uniform(size=n))
status = np.ones(n)
status[0:20] = 0
strata = np.kron(range(5), np.ones(n // 5))
mod = PHReg(time, exog, status=status, strata=strata)
rslt = mod.fit()
dist = rslt.get_distribution()
fitted_means = dist.mean()
true_means = elin_pred
fitted_var = dist.var()
fitted_sd = dist.std()
sample = dist.rvs()
def core(X, Y1, Y2, Z=None):
'''
Y1: pd.Series,生存时间， 定量数据
Y2: pd.Series,生存状态， 定类数据， 只能为0或者1， 1表示活， 0 表示死
X： pd.DataFrame,药物组合的类型、年龄等等定类或者定量数据
Z: pd.Series, 分层项，定类数据
'''
X = X.reset_index(drop=True)
if type(Y1) == np.ndarray:
Y1 = pd.Series(Y1, name='futime')
else:
Y1 = Y1.reset_index(drop=True)
if type(Y2) == np.ndarray:
Y2 = pd.Series(Y2, name='death')
else:
Y2 = Y2.reset_index(drop=True)
if type(Z) == np.ndarray:
Z = pd.Series(Z, name='class')
elif type(Z) == pd.Series:
Z = Z.reset_index(drop=True)
else:
Z = pd.Series(['' for i in range(len(Y1))], name='class')
mod = PHReg(Y1, X, status=Y2)
res = mod.fit()
tables = res.summary().tables
dfinfo1 = tables[1]
dfinfo1.index.name = '项'
dfinfo1.columns.name = '参数类型'
dfinfo1.columns = [
'回归系数', '标准误差SE', '风险比HR', 'Z值', 'p值', '95%CI(下限)', '95%CI(上限)'
]
dfinfo1['or值'] = np.exp(res.params)
dfinfo1 = dfinfo1.round(3)
tb2 = {'df': res.df_model, '似然比卡方值': res.llf}
dfinfo2 = pd.DataFrame([tb2]).round(3)
dfinfo2 = dfinfo2.set_index('似然比卡方值')
## 生存率曲线
D = Y1.to_frame(name='futime').join(Y2.to_frame(name='death')).join(
Z.to_frame(name='class'))
gb = D.groupby("class")
classes = []
for g in gb:
sf = sm.SurvfuncRight(g[1]["futime"], g[1]["death"]).summary()
sl = sf['Surv prob']
sl.index.name = '生存时间'
sl.name = str(g[0]) + '_生存率'
classes.append(sl.to_frame())
df_sl = pd.concat(classes, axis=1)
rr = {'生存函数曲线': df_sl, 'Cox回归模型分析结果汇总': dfinfo1, 'Cox回归模型似然比检验结果': dfinfo2}
return rr