def test_cohort_estimator_counts(self):
dataset_path = source_path + "datasets/"
data = pd.read_csv(dataset_path + 'synthetic_data5.csv')
event_count = data[data['Timestep'] < 4]['ID'].count()
definition = [('0', "Stage 1"), ('1', "Stage 2"), ('2', "Stage 3")]
myState = tm.StateSpace(definition)
sorted_data = data.sort_values(['ID', 'Timestep'], ascending=[True, True])
myEstimator = es.CohortEstimator(states=myState, ci={'method': 'goodman', 'alpha': 0.05})
result = myEstimator.fit(sorted_data)
self.assertEqual(event_count, myEstimator.counts)
def test_roundtrip_identity(self):
definition = [('0', "A"), ('1', "B"), ('2', "C"), ('3', "D")]
myState = tm.StateSpace(definition)
input_data = dataset_generators.long_format(myState,
Identity,
n=100,
timesteps=2,
mode='Canonical')
compact_data = to_compact(input_data)
cohort_data, cohort_bounds = tm.utils.bin_timestamps(compact_data,
cohorts=1)
sorted_data = cohort_data.sort_values(['ID', 'Time'],
ascending=[True, True])
myEstimator = es.CohortEstimator(states=myState,
cohort_bounds=cohort_bounds,
ci={
'method': 'goodman',
'alpha': 0.05
})
result = myEstimator.fit(sorted_data,
labels={
'Time': 'Time',
'State': 'State',
'ID': 'ID'
})
myMatrix = tm.TransitionMatrix(myEstimator.average_matrix)
self.assertAlmostEqual(myMatrix[0, 0],
1.0,
places=ACCURATE_DIGITS,
msg=None,
delta=None)
self.assertAlmostEqual(myMatrix[1, 1],
1.0,
places=ACCURATE_DIGITS,
msg=None,
delta=None)
self.assertAlmostEqual(myMatrix[2, 2],
1.0,
places=ACCURATE_DIGITS,
msg=None,
delta=None)
self.assertAlmostEqual(myMatrix[2, 2],
1.0,
places=ACCURATE_DIGITS,
msg=None,
delta=None)
def test_cohort_estimator_counts(self):
"""
Test that the total counts constructed by the estimator is the same as the event count in the dataset
"""
dataset_path = source_path + "datasets/"
data = pd.read_csv(dataset_path + 'synthetic_data5.csv')
event_count = data['ID'].count()
# event_count = data[data['Time'] < 4]['ID'].count()
definition = [('0', "Stage 1"), ('1', "Stage 2"), ('2', "Stage 3")]
myState = tm.StateSpace(definition)
sorted_data = data.sort_values(['ID', 'Time'], ascending=[True, True])
myEstimator = es.CohortEstimator(states=myState,
cohort_bounds=[0, 1, 2, 3, 4],
ci={
'method': 'goodman',
'alpha': 0.05
})
result = myEstimator.fit(sorted_data)
self.assertEqual(event_count, myEstimator.counts)
('4', "BB"), ('5', "B"), ('6', "CCC"), ('7', "D")]
myState = tm.StateSpace(description)
myState.describe()
print(myState.get_states())
print(myState.get_state_labels())
data = pd.read_csv(dataset_path + 'synthetic_data4.csv',
dtype={'State': str})
sorted_data = data.sort_values(['ID', 'Timestep'], ascending=[True, True])
print(myState.validate_dataset(dataset=sorted_data))
# compute confidence interval using goodman method at 95% confidence level
myEstimator = es.CohortEstimator(states=myState,
ci={
'method': 'goodman',
'alpha': 0.05
})
result = myEstimator.fit(sorted_data)
# Print confidence intervals
myEstimator.summary()
# Print the estimated results
myMatrixSet = tm.TransitionMatrixSet(values=result,
temporal_type='Incremental')
print(myMatrixSet.temporal_type)
myMatrixSet.print()
elif example == 2:
# Example: IFRS 9 Style Migration Matrix
def test_cohort_estimator_matrix(self):
"""
Test that the estimated matrix is same as the matrix that was used to generate the data
matrix = [[0.8, 0.15, 0.05],
[0.1, 0.7, 0.2],
[0.0, 0.0, 1.0]]
"""
dataset_path = source_path + "datasets/"
data = pd.read_csv(dataset_path + 'synthetic_data5.csv')
definition = [('0', "Stage 1"), ('1', "Stage 2"), ('2', "Stage 3")]
myState = tm.StateSpace(definition)
sorted_data = data.sort_values(['ID', 'Time'], ascending=[True, True])
myEstimator = es.CohortEstimator(states=myState,
cohort_bounds=[0, 1, 2, 3, 4],
ci={
'method': 'goodman',
'alpha': 0.05
})
result = myEstimator.fit(sorted_data)
am = myEstimator.average_matrix
self.assertAlmostEqual(am[0, 0],
0.8,
places=ACCURATE_DIGITS,
msg=None,
delta=None)
self.assertAlmostEqual(am[0, 1],
0.15,
places=ACCURATE_DIGITS,
msg=None,
delta=None)
self.assertAlmostEqual(am[0, 2],
0.05,
places=ACCURATE_DIGITS,
msg=None,
delta=None)
self.assertAlmostEqual(am[1, 0],
0.1,
places=ACCURATE_DIGITS,
msg=None,
delta=None)
self.assertAlmostEqual(am[1, 1],
0.7,
places=ACCURATE_DIGITS,
msg=None,
delta=None)
self.assertAlmostEqual(am[1, 2],
0.2,
places=ACCURATE_DIGITS,
msg=None,
delta=None)
self.assertAlmostEqual(am[2, 0],
0.0,
places=ACCURATE_DIGITS,
msg=None,
delta=None)
self.assertAlmostEqual(am[2, 1],
0.0,
places=ACCURATE_DIGITS,
msg=None,
delta=None)
self.assertAlmostEqual(am[2, 2],
1.0,
places=ACCURATE_DIGITS,
msg=None,
delta=None)