def test_maxabsscaler_minimum_operation_success():
params = {
MaxAbsScalerOperation.ATTRIBUTE_PARAM: ['col'],
}
n_in = {'input data': 'input_1'}
n_out = {'output data': 'output_1'}
in1 = n_in['input data']
out = n_out['output data']
instance = MaxAbsScalerOperation(params,
named_inputs=n_in,
named_outputs=n_out)
code = instance.generate_code()
expected_code = dedent("""
output_1 = input_1
from sklearn.preprocessing import MaxAbsScaler
scaler = MaxAbsScaler()
X_train = input_1['col'].values.tolist()
output_1['col_norm'] = scaler.fit_transform(X_train).tolist()
""")
result, msg = compare_ast(ast.parse(code), ast.parse(expected_code))
assert result, msg + format_code_comparison(code, expected_code)
def test_max_abs_scaler_success():
df = util.iris(['sepalwidth', 'petalwidth'], size=10)
test_df = df.copy()
arguments = {
'parameters': {
'attribute': ['sepalwidth', 'petalwidth'],
'multiplicity': {
'input data': 0
}
},
'named_inputs': {
'input data': 'df',
},
'named_outputs': {
'output data': 'out'
}
}
instance = MaxAbsScalerOperation(**arguments)
result = util.execute(instance.generate_code(), {'df': df})
data = {'scaled_1': scaler(df, ['sepalwidth', 'petalwidth'])}
data = pd.DataFrame(data)
assert test_df.max()['sepalwidth'] == 3.9
assert test_df.max()['petalwidth'] == 0.4
assert result['out'].loc[:, 'scaled_1'].equals(data.loc[:, 'scaled_1'])
def test_max_abs_scaler_missing_input_implies_no_code_success():
arguments = {
'parameters': {
'attribute': ['sepalwidth', 'petalwidth'],
'multiplicity': {
'input data': 0
}
},
'named_inputs': {},
'named_outputs': {
'output data': 'out'
}
}
instance = MaxAbsScalerOperation(**arguments)
assert instance.generate_code() is None
def test_max_abs_scaler_alias_param_success():
df = util.iris(['sepalwidth', 'petalwidth'], size=10)
arguments = {
'parameters': {
'attribute': ['sepalwidth', 'petalwidth'],
'multiplicity': {
'input data': 0
},
'alias': 'test_pass'
},
'named_inputs': {
'input data': 'df',
},
'named_outputs': {
'output data': 'out'
}
}
instance = MaxAbsScalerOperation(**arguments)
result = util.execute(instance.generate_code(), {'df': df})
assert result['out'].iloc[:, 2].name == 'test_pass'
def test_max_abs_scaler_missing_attributes_param_fail():
arguments = {
'parameters': {
'multiplicity': {
'input data': 0
}
},
'named_inputs': {
'input data': 'df',
},
'named_outputs': {
'output data': 'out'
}
}
with pytest.raises(ValueError) as val_err:
MaxAbsScalerOperation(**arguments)
assert "Parameters 'attribute' must be informed for task" in str(
val_err.value)
def test_maxabsscaler_operation_failure():
params = {MaxAbsScalerOperation.ALIAS_PARAM: 'c'}
with pytest.raises(ValueError):
n_in = {'input data': 'input_1'}
n_out = {'output data': 'output_1'}
MaxAbsScalerOperation(params, named_inputs=n_in, named_outputs=n_out)