def test_aaf_panel_dataset(self, block):
panel_dataset = load_panel_test()
aaf = AalenAdditiveFitter()
aaf.fit(panel_dataset, id_col="id", duration_col="t", event_col="E")
aaf.plot()
self.plt.title("test_aaf_panel_dataset")
self.plt.show(block=block)
return
def test_aalen_additive_fit_with_censor(self, block):
n = 2500
d = 6
timeline = np.linspace(0, 70, 10000)
hz, coef, X = generate_hazard_rates(n, d, timeline)
X.columns = coef.columns
cumulative_hazards = pd.DataFrame(cumulative_integral(
coef.values, timeline),
index=timeline,
columns=coef.columns)
T = generate_random_lifetimes(hz, timeline)
T[np.isinf(T)] = 10
X["T"] = T
X["E"] = np.random.binomial(1, 0.99, n)
aaf = AalenAdditiveFitter()
aaf.fit(X, "T", "E")
for i in range(d + 1):
ax = self.plt.subplot(d + 1, 1, i + 1)
col = cumulative_hazards.columns[i]
ax = cumulative_hazards[col].loc[:15].plot(ax=ax)
ax = aaf.plot(loc=slice(0, 15), ax=ax, columns=[col])
self.plt.title("test_aalen_additive_fit_with_censor")
self.plt.show(block=block)
return
def test_aalen_additive_plot(self, block):
# this is a visual test of the fitting the cumulative
# hazards.
n = 2500
d = 3
timeline = np.linspace(0, 70, 10000)
hz, coef, X = generate_hazard_rates(n, d, timeline)
T = generate_random_lifetimes(hz, timeline)
T[np.isinf(T)] = 10
C = np.random.binomial(1, 1.0, size=n)
X["T"] = T
X["E"] = C
# fit the aaf, no intercept as it is already built into X, X[2] is ones
aaf = AalenAdditiveFitter(coef_penalizer=0.1, fit_intercept=False)
aaf.fit(X, "T", "E")
ax = aaf.plot(iloc=slice(0, aaf.cumulative_hazards_.shape[0] - 100))
ax.set_xlabel("time")
ax.set_title("test_aalen_additive_plot")
self.plt.show(block=block)
return
#Survival Regression using the following covariates : Couple Race, Income Range, State and Marriage Date
X = patsy.dmatrix(
'State + Couple_Race + Household_Income_Range + Husband_Education + Husband_Race + Marriage_Date -1',
data,
return_type='dataframe')
aaf = AalenAdditiveFitter(coef_penalizer=1.0, fit_intercept=True)
X['T'] = data['Duration']
X['E'] = data['Divorce']
aaf.fit(X, 'T', event_col='E')
aaf.cumulative_hazards_.head()
sns.set()
aaf.plot(columns=[
'State[Alabama]', 'baseline', 'Couple_Race[T.Same-Race]',
'Household_Income_Range[T.42,830$ - 44,765$]'
],
ix=slice(1, 15))
plt.savefig(
'/home/raed/Dropbox/INSE - 6320/Final Project/Survival_Regression_for_Alabamae.pdf'
)
plt.show()
aaf.plot(columns=[
'State[Mississippi]', 'baseline', 'Couple_Race[T.Same-Race]',
'Household_Income_Range[T.42,830$ - 44,765$]'
],
ix=slice(1, 15))
plt.savefig(
'/home/raed/Dropbox/INSE - 6320/Final Project/Survival_Regression_for_Mississippi.pdf'
)
from lifelines.datasets import generate_regression_dataset regression_dataset = generate_regression_dataset() from lifelines import AalenAdditiveFitter, CoxPHFitter cf = CoxPHFitter() cf.fit(regression_dataset, duration_col='T', event_col='E') aaf = AalenAdditiveFitter(fit_intercept=False) aaf.fit(regression_dataset, duration_col='T', event_col='E') x = regression_dataset[regression_dataset.columns - ['E','T']] aaf.predict_survival_function(x.ix[10:12]).plot() aaf.plot()
df = df[df['Duration'] != 0]
df2 = df.loc[:, [
'DISTRIBUTION CHANNEL', 'GENDER', 'SMOKER STATUS', 'PremiumPattern',
'BENEFITS TYPE', 'BROKER COMM'
]]
#df2 = df.loc[:, ['GENDER', 'SMOKER STATUS', 'PremiumPattern']]
#df2 = df.loc[:, ['SMOKER STATUS', 'GENDER']]
df2 = pd.get_dummies(df2)
#T = df['Duration']
E = df['LapseIndicator'].apply(lambda x: True if x == 1 else False)
df2['E'] = E
df2['T'] = T
aaf = AalenAdditiveFitter()
aaf.fit(df2, 'T', event_col='E', show_progress=True)
pickle.dump(aaf, open('Smoker_Gender_All.pkl', 'wb'))
aaf.plot()
#cph = CoxPHFitter()
#cph.fit(df2, duration_col='T', event_col='E', show_progress=True, strata=['SMOKER STATUS_No','SMOKER STATUS_Yes',
# 'GENDER_F', 'GENDER_M'])
#pickle.dump(cph, open('Smoker_Gender_CPF.pkl', 'wb'))
#cph.plot()
