def test_aggregate(mock_save_results, mock_get_results, mock_fetch_data):
# run partial jobs
inputs_1 = t.inputs_regression(limit_from=0,
limit_to=8,
include_nominal=True)
mock_fetch_data.return_value = inputs_1
intermediate()
output_1 = mock_save_results.call_args[0][0]
inputs_2 = t.inputs_regression(limit_from=8,
limit_to=20,
include_nominal=True)
mock_fetch_data.return_value = inputs_2
intermediate()
output_2 = mock_save_results.call_args[0][0]
mock_get_results.side_effect = [
mock.MagicMock(data=output_1, error=''),
mock.MagicMock(data=output_2, error=''),
]
# run computations
aggregate(['1', '2'])
output_agg = json.loads(mock_save_results.call_args[0][0])
beta_agg = {k: v['coef'] for k, v in output_agg.items()}
# calculate coefficients from single-node regression
mock_fetch_data.return_value = t.inputs_regression(limit_to=20,
include_nominal=True)
main()
output_single = json.loads(mock_save_results.call_args[0][0])
beta_single = {k: v['coef'] for k, v in output_single.items()}
assert t.round_dict(beta_agg) == t.round_dict(beta_single)
def test_main_signular_matrix(mock_exit, mock_save_error, mock_fetch_data):
mock_fetch_data.return_value = t.inputs_regression(limit_to=1,
include_nominal=False)
main()
mock_save_error.assert_called_with(
'Too many factors (4) for too little data (1). Use less covariables or different design.'
)
def test_main(mock_save_results, mock_fetch_data):
mock_fetch_data.return_value = t.inputs_regression(include_nominal=False)
main()
result = json.loads(mock_save_results.call_args[0][0])
assert t.round_dict(result) == {
'Residual': {
'F': 'NaN',
'PR(>F)': 'NaN',
'df': 1.0,
'mean_sq': 0.019,
'sum_sq': 0.019
},
'minimentalstate': {
'F': 12.831,
'PR(>F)': 0.173,
'df': 1.0,
'mean_sq': 0.248,
'sum_sq': 0.248
},
'subjectage': {
'F': 0.958,
'PR(>F)': 0.507,
'df': 1.0,
'mean_sq': 0.019,
'sum_sq': 0.019
},
'subjectage:minimentalstate': {
'F': 0.096,
'PR(>F)': 0.808,
'df': 1.0,
'mean_sq': 0.002,
'sum_sq': 0.002
}
}
def test_compute_heatmap_continuous(mock_save_results, mock_fetch_data):
mock_fetch_data.return_value = t.inputs_regression(include_nominal=True)
compute('correlation_heatmap')
results = json.loads(mock_save_results.call_args[0][0])
assert t.round_dict(results) == {
'data': [{
'type':
'heatmap',
'x': ['lefthippocampus', 'subjectage', 'minimentalstate'],
'xaxis':
'x1',
'y': ['minimentalstate', 'subjectage', 'lefthippocampus'],
'yaxis':
'y1',
'z': [[0.959, -0.343, 1.0], [-0.254, 1.0, -0.343],
[1.0, -0.254, 0.959]],
'zmax':
1,
'zmin':
-1
}],
'layout': {
'title': 'Correlation heatmap'
}
}
def test_main_empty(mock_save_results, mock_fetch_data):
mock_fetch_data.return_value = t.inputs_regression(include_nominal=True,
limit_to=0)
main()
output = json.loads(mock_save_results.call_args[0][0])
assert output == {}
def test_compute_histograms():
inputs = t.inputs_regression(include_integer=True, include_nominal=True)
dep_var = inputs['data']['independent'][-2]
assert dep_var['name'] == 'minimentalstate'
histograms_results = compute_histograms(dep_var,
inputs['data']['independent'], 3)
assert histograms_results == [{
'chart': {
'type': 'column'
},
'label':
'Histogram',
'series': [{
'data': [0, 2, 3],
'name': 'all'
}],
'title': {
'text': 'MMSE Total scores histogram'
},
'xAxis': {
'categories': ['0 - 10', '10 - 20', '20 - 30']
},
'yAxis': {
'allowDecimals': False,
'min': 0,
'title': {
'text': 'Number of participants'
}
}
}, {
'chart': {
'type': 'column'
},
'label':
'Histogram - Age Group',
'series': [{
'data': [0, 1, 2],
'name': '-50y'
}, {
'data': [0, 1, 1],
'name': '50-59y'
}],
'title': {
'text': 'MMSE Total scores histogram by Age Group'
},
'xAxis': {
'categories': ['0 - 10', '10 - 20', '20 - 30']
},
'yAxis': {
'allowDecimals': False,
'min': 0,
'title': {
'text': 'Number of participants'
}
}
}]
def test_aggregate_single(mock_save_results, mock_get_results,
mock_fetch_data):
"""Aggregation on single node should give same results as ordinary linear regression."""
# run partial jobs
inputs = t.inputs_regression(limit_from=0, limit_to=20)
mock_fetch_data.return_value = inputs
intermediate()
output = mock_save_results.call_args[0][0]
mock_get_results.side_effect = [
mock.MagicMock(data=output, error=''),
]
# run computations
aggregate(['1'])
output_agg = json.loads(mock_save_results.call_args[0][0])
# calculate coefficients from single-node regression
mock_fetch_data.return_value = t.inputs_regression(limit_to=20)
main()
output_single = json.loads(mock_save_results.call_args[0][0])
assert t.round_dict(output_agg) == t.round_dict(output_single)
def test_intermediate_stats_real(mock_save_results, mock_fetch_data):
# input data with some null values
data = t.inputs_regression(include_nominal=True, add_null=True)
mock_fetch_data.return_value = data
intermediate_stats()
results = json.loads(mock_save_results.call_args[0][0])
assert len(results['data']) == 12
res = sorted(results['data'],
key=lambda d: (d['index'], tuple(d['group'])))
assert t.round_dict(res[:2]) == [{
'index': 'agegroup',
'label': 'Age Group',
'type': 'polynominal',
'group': ['-50y'],
'group_variables': ['Age Group'],
'count': 3,
'unique': 1,
'top': '-50y',
'frequency': {
'-50y': 3,
'50-59y': 0
},
'null_count': 0
}, {
'index': 'agegroup',
'label': 'Age Group',
'type': 'polynominal',
'group': ['50-59y'],
'group_variables': ['Age Group'],
'count': 2,
'unique': 1,
'top': '50-59y',
'frequency': {
'50-59y': 2,
'-50y': 0
},
'null_count': 0
}]
def test_intermediate_stats(mock_save_results, mock_fetch_data):
mock_fetch_data.return_value = t.inputs_regression(include_nominal=True)
intermediate_stats()
results = json.loads(mock_save_results.call_args[0][0])
assert t.round_dict(results) == {
'X^T * X': [[44.891, 1055.621,
317.732], [1055.621, 25462.015, 7279.928],
[317.732, 7279.928, 2354.0]],
'columns': ['lefthippocampus', 'subjectage', 'minimentalstate'],
'count':
5,
'crosstab': [{
'agegroup': '-50y',
'count': 3
}, {
'agegroup': '50-59y',
'count': 2
}],
'means': [2.987, 70.86, 20.8],
'nominal_columns': ['agegroup']
}
def test_main_empty_input(mock_exit, mock_save_error, mock_fetch_data):
mock_fetch_data.return_value = t.inputs_regression(limit_to=0)
main()
mock_exit.assert_called_once_with(1)
mock_save_error.assert_called_once()
def test_main(mock_parameters, mock_save_results, mock_get_results,
mock_fetch_data):
# create mock objects from database
mock_fetch_data.return_value = t.inputs_regression(include_nominal=False,
limit_to=5)
mock_get_results.return_value = None
main()
results = json.loads(mock_save_results.call_args[0][0])
assert t.round_dict(results) == {
'profile':
'tabular-data-resource',
'name':
'hinmine-features',
'data': [{
'f_1': 0.0,
'f_2': 0.51,
'f_3': 0.496,
'f_4': 0.49,
'f_5': 0.504,
'id': 0.0
}, {
'f_1': 0.509,
'f_2': 0.0,
'f_3': 0.496,
'f_4': 0.492,
'f_5': 0.503,
'id': 1.0
}, {
'f_1': 0.506,
'f_2': 0.506,
'f_3': 0.0,
'f_4': 0.484,
'f_5': 0.504,
'id': 2.0
}, {
'f_1': 0.505,
'f_2': 0.508,
'f_3': 0.49,
'f_4': 0.0,
'f_5': 0.497,
'id': 3.0
}, {
'f_1': 0.508,
'f_2': 0.508,
'f_3': 0.498,
'f_4': 0.486,
'f_5': 0.0,
'id': 4.0
}],
'schema': {
'fields': [{
'name': 'f_1',
'type': 'float'
}, {
'name': 'f_2',
'type': 'float'
}, {
'name': 'f_3',
'type': 'float'
}, {
'name': 'f_4',
'type': 'float'
}, {
'name': 'f_5',
'type': 'float'
}],
'primaryKey':
'id'
}
}
def test_main(mock_save_results, mock_fetch_data):
mock_fetch_data.return_value = t.inputs_regression(include_nominal=True)
main()
output = json.loads(mock_save_results.call_args[0][0])
assert t.round_dict(fx.output_regression()) == t.round_dict(output)