def test_add_columns_same_aliases_param_values_fail():
"""
(?)
Passing the same aliases to the attributes is allowed
"""
left_df = util.iris(['sepallength', 'sepalwidth'], size=10)
right_df = util.iris(['sepallength', 'sepalwidth'], size=10)
test_df = util.iris(
['sepallength', 'sepalwidth', 'sepallength', 'sepalwidth'], size=10)
arguments = {
'parameters': {'aliases': '_col,_col'},
'named_inputs': {
'input data 1': 'df1',
'input data 2': 'df2'
},
'named_outputs': {
'output data': 'out'
}
}
instance = AddColumnsOperation(**arguments)
result = util.execute(instance.generate_code(),
{'df1': left_df, 'df2': right_df})
test_df.columns = ['sepallength_col', 'sepalwidth_col',
'sepallength_col', 'sepalwidth_col']
assert result['out'].equals(test_df)
def test_add_columns_missing_input_implies_no_code_success():
arguments = {
'parameters': {},
'named_inputs': {
},
'named_outputs': {
'output data': 'out'
}
}
instance = AddColumnsOperation(**arguments)
assert instance.generate_code() is None
def test_add_columns_no_output_implies_no_code_success():
arguments = {
'parameters': {},
'named_inputs': {
'input data 1': 'df1',
'input data 2': 'df2'
},
'named_outputs': {
}
}
instance = AddColumnsOperation(**arguments)
assert instance.generate_code() is None
def test_add_columns_invalid_aliases_param_value_fail():
left_df = util.iris(['sepallength', 'sepalwidth'], size=10)
right_df = util.iris(['sepallength', 'sepalwidth'], size=10)
arguments = {
'parameters': {'aliases': 'invalid'},
'named_inputs': {
'input data 1': 'df1',
'input data 2': 'df2'
},
'named_outputs': {
'output data': 'out'
}
}
instance = AddColumnsOperation(**arguments)
with pytest.raises(IndexError) as idx_err:
util.execute(instance.generate_code(),
{'df1': left_df, 'df2': right_df})
assert 'list index out of range' in str(idx_err.value)
def test_add_columns_suffixes_params_success():
params = {AddColumnsOperation.ALIASES_PARAM: '_l,_r'}
n_in = {'input data 1': 'df1', 'input data 2': 'df2'}
n_out = {'output data': 'out'}
instance = AddColumnsOperation(parameters=params,
named_inputs=n_in,
named_outputs=n_out)
code = instance.generate_code()
expected_code = dedent("""
out = pd.merge(df1, df2, left_index=True,
right_index=True, suffixes=('_l', '_r'))
""".format(out=n_out['output data'],
in0=n_in['input data 1'],
in1=n_in['input data 2']))
result, msg = compare_ast(ast.parse(code), ast.parse(expected_code))
assert result, msg + format_code_comparison(code, expected_code)
def test_add_columns_success():
left_df = util.iris(['sepallength', 'sepalwidth'], size=10)
right_df = util.iris(['petallength', 'petalwidth', 'class'], size=10)
arguments = {
'parameters': {},
'named_inputs': {
'input data 1': 'df1',
'input data 2': 'df2'
},
'named_outputs': {
'output data': 'out'
}
}
instance = AddColumnsOperation(**arguments)
result = util.execute(instance.generate_code(),
{'df1': left_df, 'df2': right_df})
assert result['out'].equals(util.iris([
'sepallength', 'sepalwidth',
'petallength', 'petalwidth', 'class'], size=10))
def test_add_columns_aliases_param_success():
left_df = util.iris(['sepallength', 'sepalwidth'], size=10)
right_df = util.iris(['sepallength', 'sepalwidth'], size=10)
test_df = util.iris(
['sepallength', 'sepalwidth', 'sepallength', 'sepalwidth'], size=10)
arguments = {
'parameters': {'aliases': '_value0,_value1'},
'named_inputs': {
'input data 1': 'df1',
'input data 2': 'df2'
},
'named_outputs': {
'output data': 'out'
}
}
instance = AddColumnsOperation(**arguments)
result = util.execute(instance.generate_code(),
{'df1': left_df, 'df2': right_df})
test_df.columns = ['sepallength_value0', 'sepalwidth_value0',
'sepallength_value1', 'sepalwidth_value1']
assert result['out'].equals(test_df)
def test_add_columns_success():
slice_size = 10
left_df = ['df1', util.iris(['sepallength', 'sepalwidth'], slice_size)]
right_df = [
'df2',
util.iris(['petallength', 'petalwidth', 'class'], slice_size)
]
arguments = {
'parameters': {},
'named_inputs': {
'input data 1': left_df[0],
'input data 2': right_df[0]
},
'named_outputs': {
'output data': 'out'
}
}
instance = AddColumnsOperation(**arguments)
result = util.execute(instance.generate_code(), dict([left_df, right_df]))
assert result['out'].equals(util.iris(size=slice_size))
def test_add_columns_different_size_dataframes_success():
"""
In this case, AddColumnsOperation() returns a dataframe with the lowest
size passed.
"""
left_df = util.iris(['sepallength', 'sepalwidth'], size=10)
right_df = util.iris(['petallength', 'petalwidth', 'class'], size=5)
arguments = {
'parameters': {},
'named_inputs': {
'input data 1': 'df1',
'input data 2': 'df2'
},
'named_outputs': {
'output data': 'out'
}
}
instance = AddColumnsOperation(**arguments)
result = util.execute(instance.generate_code(),
{'df1': left_df, 'df2': right_df})
assert result['out'].equals(util.iris([
'sepallength', 'sepalwidth',
'petallength', 'petalwidth', 'class'], size=5))
def test_add_columns_repetead_column_names_success():
"""
AddColumnsOperation() automatically adds aliases to repetead column names
"""
left_df = util.iris(['sepallength', 'class'], size=10)
right_df = util.iris(['sepallength', 'class'], size=10)
test_df = util.iris(
['sepallength', 'class', 'sepallength', 'class'], size=10)
arguments = {
'parameters': {},
'named_inputs': {
'input data 1': 'df1',
'input data 2': 'df2'
},
'named_outputs': {
'output data': 'out'
}
}
instance = AddColumnsOperation(**arguments)
result = util.execute(instance.generate_code(),
{'df1': left_df, 'df2': right_df})
test_df.columns = ['sepallength_ds0', 'class_ds0',
'sepallength_ds1', 'class_ds1']
assert result['out'].equals(test_df)