def test_survival_prediction_is_the_same_indp_of_scale(self, regression_dataset):
df = regression_dataset.copy()
df_scaled = regression_dataset.copy()
df_scaled[['var1', 'var2', 'var3']] = df_scaled[['var1', 'var2', 'var3']] * 10.0
cp1 = CoxPHFitter()
cp1.fit(df, event_col='E', duration_col='T')
cp2 = CoxPHFitter()
cp2.fit(df_scaled, event_col='E', duration_col='T')
assert_frame_equal(
cp1.predict_survival_function(df.ix[[0]][['var1', 'var2', 'var3']]),
cp2.predict_survival_function(df_scaled.ix[[0]][['var1', 'var2', 'var3']])
)
kaplen_meier.fit(time_of_event, timeline=time, event_observed=event, label='All patients') kaplen_meier.plot() plt.show() #stratify Congestive Heart Complications history = df['chf'] == 1; kaplen_meier = KaplanMeierFitter() kaplen_meier.fit(time_of_event[history], timeline=time, event_observed=event[history], label='Congestive heart complications') ax = kaplen_meier.plot() kaplen_meier.fit(time_of_event[~history], timeline=time, event_observed=event[~history], label='No congestive heart complications') kaplen_meier.plot(ax=ax, c="b") plt.show() #Cox proportional hazard ph_data = df[["fstat", "lenfol", "bmi", "age"]] ph = CoxPHFitter() ph.fit(ph_data, 'lenfol', event_col='fstat') ph.print_summary() print(ph.baseline_hazard_.head()) #use predict_survival_function to get probability x = ph_data[ph_data.columns.difference(['lenfol', 'fstat'])].ix[23:25] print(x) ph.predict_survival_function(x).plot() plt.show()
