def test_covariates_from_event_matrix_with_simple_addition(self):
base_df = pd.DataFrame(
[[1, 0, 5, 1], [2, 0, 4, 1], [3, 0, 8, 1], [4, 0, 4, 1]],
columns=["id", "start", "stop", "e"])
event_df = pd.DataFrame([[1, 1], [2, 2], [3, 3], [4, None]],
columns=["id", "poison"])
cv = utils.covariates_from_event_matrix(event_df, "id")
ldf = utils.add_covariate_to_timeline(base_df,
cv,
"id",
"duration",
"e",
cumulative_sum=True)
assert pd.notnull(ldf).all().all()
expected = pd.DataFrame(
[
(0.0, 0.0, 1.0, 1, False),
(1.0, 1.0, 5.0, 1, True),
(0.0, 0.0, 2.0, 2, False),
(2.0, 1.0, 4.0, 2, True),
(0.0, 0.0, 3.0, 3, False),
(3.0, 1.0, 8.0, 3, True),
(0.0, 0.0, 4.0, 4, True),
],
columns=["start", "cumsum_poison", "stop", "id", "e"],
)
assert_frame_equal(expected, ldf, check_dtype=False, check_like=True)
def test_covariates_from_event_matrix(self):
base_df = pd.DataFrame([
[1, 0, 5, 1],
[2, 0, 4, 1],
[3, 0, 8, 1],
[4, 0, 4, 1]
], columns=['id', 'start', 'stop', 'e'])
event_df = pd.DataFrame([
[1, 1, None, 2 ],
[2, None, 5, None],
[3, 3, 3, 7 ]
], columns=['id', 'promotion', 'movement', 'raise'])
cv = utils.covariates_from_event_matrix(event_df, 'id')
ldf = utils.add_covariate_to_timeline(base_df, cv, 'id', 'duration', 'e', cumulative_sum=True)
expected = pd.DataFrame.from_records([
{'cumsum_movement': 0.0, 'cumsum_promotion': 0.0, 'cumsum_raise': 0.0, 'e': 0.0, 'id': 1.0, 'start': 0.0, 'stop': 1.0},
{'cumsum_movement': 0.0, 'cumsum_promotion': 1.0, 'cumsum_raise': 0.0, 'e': 0.0, 'id': 1.0, 'start': 1.0, 'stop': 2.0},
{'cumsum_movement': 0.0, 'cumsum_promotion': 1.0, 'cumsum_raise': 1.0, 'e': 1.0, 'id': 1.0, 'start': 2.0, 'stop': 5.0},
{'cumsum_movement': 0.0, 'cumsum_promotion': 0.0, 'cumsum_raise': 0.0, 'e': 1.0, 'id': 2.0, 'start': 0.0, 'stop': 4.0},
{'cumsum_movement': 0.0, 'cumsum_promotion': 0.0, 'cumsum_raise': 0.0, 'e': 0.0, 'id': 3.0, 'start': 0.0, 'stop': 3.0},
{'cumsum_movement': 1.0, 'cumsum_promotion': 1.0, 'cumsum_raise': 0.0, 'e': 0.0, 'id': 3.0, 'start': 3.0, 'stop': 7.0},
{'cumsum_movement': 1.0, 'cumsum_promotion': 1.0, 'cumsum_raise': 1.0, 'e': 1.0, 'id': 3.0, 'start': 7.0, 'stop': 8.0},
{'cumsum_movement': None, 'cumsum_promotion': None, 'cumsum_raise': None, 'e': 1.0, 'id': 4.0, 'start': 0.0, 'stop': 4.0}
])
assert_frame_equal(expected, ldf, check_dtype=False, check_like=True)
def test_covariates_from_event_matrix(self):
df = pd.DataFrame([[1, 1, None, 2], [2, None, 5, None], [3, 3, 3, 7]],
columns=['id', 'promotion', 'movement', 'raise'])
ldf = pd.DataFrame(
[[1, 0, 5, 1], [2, 0, 4, 1], [3, 0, 8, 1], [4, 0, 4, 1]],
columns=['id', 'start', 'stop', 'e'])
cv = utils.covariates_from_event_matrix(df, 'id')
ldf = utils.add_covariate_to_timeline(ldf,
cv,
'id',
'duration',
'e',
cumulative_sum=True)
assert ldf.loc[ldf['id'] == 1]['cumsum_movement'].tolist() == [0, 0, 0]
assert ldf.loc[ldf['id'] == 1]['cumsum_promotion'].tolist() == [
0, 1, 1
]
assert ldf.loc[ldf['id'] == 1]['cumsum_raise'].tolist() == [0, 0, 1]
assert ldf.loc[ldf['id'] == 1]['start'].tolist() == [0, 1., 2.]
def test_covariates_from_event_matrix(self):
base_df = pd.DataFrame(
[[1, 0, 5, 1], [2, 0, 4, 1], [3, 0, 8, 1], [4, 0, 4, 1]], columns=["id", "start", "stop", "e"]
)
event_df = pd.DataFrame(
[[1, 1, None, 2], [2, None, 5, None], [3, 3, 3, 7]], columns=["id", "promotion", "movement", "raise"]
)
cv = utils.covariates_from_event_matrix(event_df, "id")
ldf = utils.add_covariate_to_timeline(base_df, cv, "id", "duration", "e", cumulative_sum=True)
expected = pd.DataFrame.from_records(
[
{
"cumsum_movement": 0.0,
"cumsum_promotion": 0.0,
"cumsum_raise": 0.0,
"e": 0.0,
"id": 1.0,
"start": 0.0,
"stop": 1.0,
},
{
"cumsum_movement": 0.0,
"cumsum_promotion": 1.0,
"cumsum_raise": 0.0,
"e": 0.0,
"id": 1.0,
"start": 1.0,
"stop": 2.0,
},
{
"cumsum_movement": 0.0,
"cumsum_promotion": 1.0,
"cumsum_raise": 1.0,
"e": 1.0,
"id": 1.0,
"start": 2.0,
"stop": 5.0,
},
{
"cumsum_movement": 0.0,
"cumsum_promotion": 0.0,
"cumsum_raise": 0.0,
"e": 1.0,
"id": 2.0,
"start": 0.0,
"stop": 4.0,
},
{
"cumsum_movement": 0.0,
"cumsum_promotion": 0.0,
"cumsum_raise": 0.0,
"e": 0.0,
"id": 3.0,
"start": 0.0,
"stop": 3.0,
},
{
"cumsum_movement": 1.0,
"cumsum_promotion": 1.0,
"cumsum_raise": 0.0,
"e": 0.0,
"id": 3.0,
"start": 3.0,
"stop": 7.0,
},
{
"cumsum_movement": 1.0,
"cumsum_promotion": 1.0,
"cumsum_raise": 1.0,
"e": 1.0,
"id": 3.0,
"start": 7.0,
"stop": 8.0,
},
{
"cumsum_movement": None,
"cumsum_promotion": None,
"cumsum_raise": None,
"e": 1.0,
"id": 4.0,
"start": 0.0,
"stop": 4.0,
},
]
)
assert_frame_equal(expected, ldf, check_dtype=False, check_like=True)
'E3': 2
}, {
'id': 2,
'E2': 5
}, {
'id': 3,
'E1': 3,
'E2': 5,
'E3': 7
}])
"""
id E1 E2 E3
0 1 1.0 NaN 2.0
1 2 NaN 5.0 NaN
2 3 3.0 5.0 7.0
"""
cv = covariates_from_event_matrix(base_df, 'id')
"""
event id duration E1 E2 E3
0 1 1.0 1 0 0
1 1 2.0 0 0 1
2 2 5.0 0 1 0
3 3 3.0 1 0 0
4 3 5.0 0 1 0
5 3 7.0 0 0 1
"""
#==============================================================================
#==============================================================================
