def test_predict_method_returns_gives_values_prior_to_the_value_in_the_survival_function(
self):
T = [1, 2, 3]
kmf = KaplanMeierFitter()
kmf.fit(T)
assert abs(kmf.predict(0.5) -
kmf.survival_function_.ix[0].values) < 10e-8
assert abs(kmf.predict(1.9999) -
kmf.survival_function_.ix[1].values) < 10e-8
def test_predict_method_returns_exact_value_if_given_an_observed_time(
self):
T = [1, 2, 3]
kmf = KaplanMeierFitter()
kmf.fit(T)
time = 1
assert abs(kmf.predict(time) -
kmf.survival_function_.ix[time].values) < 10e-8
#median survival in months
print("median survival: " + str(kmf.median_) + " months")
#print(kmf.survival_function_)
coordinates = []
survival_fx = (kmf.survival_function_)
coordinates_y = list(survival_fx.values.flatten())
coordinates_x = []
for row in survival_fx.iterrows():
timeline, km_estimate = row
coordinates_x.append(timeline.tolist())
for (x, y) in zip(coordinates_x, coordinates_y):
coordinates.append([x, y])
print("curve coordinates:")
print(coordinates)
#calculate the survival probability for t=1 year
surv_for_1 = kmf.predict(12)
print("probability of survival for 1 year: " + str(surv_for_1))
#caluclate the survival probability for t=3 years
surv_for_3 = kmf.predict(36)
print("probability of survival for 3 years: " + str(surv_for_3))
#calculate the survival probability for t=5
surv_for_5 = kmf.predict(60)
print("probability of survival for 5 years: " + str(surv_for_5))
def test_predict_methods_returns_a_scalar_or_a_array_depending_on_input(self, sample_lifetimes):
kmf = KaplanMeierFitter()
kmf.fit(sample_lifetimes[0])
assert not isinstance(kmf.predict(1), Iterable)
assert isinstance(kmf.predict([1, 2]), Iterable)
def progression_free_analysis(data):
list_patients = []
for patient, data in data.items():
v_status = data['VitalStatus']
d_progression = data['DiseaseProgression']
s_time = data['SurvivalTime']
patient_info = []
if d_progression != None:
if v_status != None:
if v_status == 'Alive' or d_progression == 'False':
#patient disease did not progress
progression_status = 0
else:
progression_status = 1
#patient disease did progress
patient_info.append(progression_status)
if type(s_time) != str:
patient_info.append(s_time)
list_patients.append(patient_info)
df = pd.DataFrame(list_patients)
num_patients = len(df)
df.columns = ['Event', 'Duration']
kmf = KaplanMeierFitter()
kmf.fit(durations=df.Duration, event_observed=df.Event)
coordinates = []
survival_fx = kmf.survival_function_
coordinates_y = list(survival_fx.values.flatten())
coordinates_x = []
for row in survival_fx.iterrows():
timeline, km_estimate = row
coordinates_x.append(timeline.tolist())
for (x, y) in zip(coordinates_x, coordinates_y):
coordinates.append([x, y])
#calculate the progression free survival probability for t=1 year
surv_for_1 = kmf.predict(12)
#calculate the progression free survival probability for t=3 years
surv_for_3 = kmf.predict(36)
#calculate the progression free survival probability for t=5 years
surv_for_5 = kmf.predict(60)
surv_median = int(round(kmf.median_))
year_1_surv = int(round(surv_for_1 * 100))
year_3_surv = int(round(surv_for_3 * 100))
year_5_surv = int(round(surv_for_5 * 100))
prog_free_stats = {}
prog_free_stats['Coordinates'] = coordinates
prog_free_stats['Median'] = surv_median
prog_free_stats['1Year'] = year_1_surv
prog_free_stats['3Year'] = year_3_surv
prog_free_stats['5Year'] = year_5_surv
return prog_free_stats
def overall_survival_analysis(data):
list_patients = []
for patient, data in data.items():
patient_info = []
v_status = data['VitalStatus']
s_time = data['SurvivalTime']
if v_status == 'Alive' or 'Dead':
if v_status == 'Alive':
v_status = 0
else:
v_status = 1
patient_info.append(v_status)
if type(s_time) != str:
patient_info.append(s_time)
list_patients.append(patient_info)
df = pd.DataFrame(list_patients)
num_patients = len(df)
df.columns = ['Event', 'Duration']
kmf = KaplanMeierFitter()
kmf.fit(durations=df.Duration, event_observed=df.Event)
#print(kmf.survival_function_)
coordinates = []
survival_fx = (kmf.survival_function_)
coordinates_y = list(survival_fx.values.flatten())
coordinates_x = []
for row in survival_fx.iterrows():
timeline, km_estimate = row
coordinates_x.append(timeline.tolist())
for (x, y) in zip(coordinates_x, coordinates_y):
coordinates.append([x, y])
#calculate the survival probability for t=1 year
surv_for_1 = kmf.predict(12)
#caluclate the survival probability for t=3 years
surv_for_3 = kmf.predict(36)
#calculate the survival probability for t=5
surv_for_5 = kmf.predict(60)
surv_median = int(round(kmf.median_))
year_1_surv = int(round(surv_for_1 * 100))
year_3_surv = int(round(surv_for_3 * 100))
year_5_surv = int(round(surv_for_5 * 100))
overall_surv_stats = {}
overall_surv_stats['Coordinates'] = coordinates
overall_surv_stats['Median'] = surv_median
overall_surv_stats['1Year'] = year_1_surv
overall_surv_stats['3Year'] = year_3_surv
overall_surv_stats['5Year'] = year_5_surv
return overall_surv_stats
def test_predict_method_returns_gives_values_prior_to_the_value_in_the_survival_function(self):
T = [1, 2, 3]
kmf = KaplanMeierFitter()
kmf.fit(T)
assert abs(kmf.predict(0.5) - kmf.survival_function_.ix[0].values) < 10e-8
assert abs(kmf.predict(1.9999) - kmf.survival_function_.ix[1].values) < 10e-8
def test_predict_method_returns_exact_value_if_given_an_observed_time(self):
T = [1, 2, 3]
kmf = KaplanMeierFitter()
kmf.fit(T)
time = 1
assert abs(kmf.predict(time) - kmf.survival_function_.ix[time].values) < 10e-8
def test_predict_methods_returns_a_scalar_or_a_array_depending_on_input(self, sample_lifetimes):
kmf = KaplanMeierFitter()
kmf.fit(sample_lifetimes[0])
assert not isinstance(kmf.predict(1), Iterable)
assert isinstance(kmf.predict([1, 2]), Iterable)
