def test_split_seed_param_success():
"""
Seeds higher than the integer limit and lower than zero will be set to 0
"""
df = util.iris(['sepallength', 'sepalwidth',
'petallength', 'petalwidth'], size=10)
test_out = df.copy()
test_out.index = [8, 4, 0, 7, 2, 9, 5, 6, 1, 3]
test_out.sort_index(axis=0, inplace=True)
test_out.index = [2, 8, 4, 9, 1, 6, 7, 3, 0, 5]
arguments = {
'parameters': {'seed': -1},
'named_inputs': {
'input data': 'df'
},
'named_outputs': {
'split 1': 'split_1_task_1',
'split 2': 'split_2_task_1'
}
}
instance = SplitOperation(**arguments)
result = util.execute(instance.generate_code(),
{'df': df})
assert len(result['split_1_task_1']) == 5
assert len(result['split_2_task_1']) == 5
assert test_out.iloc[:5, :].equals(result['split_1_task_1'])
assert test_out.iloc[5:10, :].equals(result['split_2_task_1'])
def test_split_no_output_implies_no_code_success():
arguments = {
'parameters': {},
'named_inputs': {
'input data': 'df',
},
'named_outputs': {
}
}
instance = SplitOperation(**arguments)
assert instance.generate_code() is None
def test_split_missing_input_implies_no_code_success():
arguments = {
'parameters': {},
'named_inputs': {
},
'named_outputs': {
'split 1': 'split_1_task_1',
'split 2': 'split_2_task_1'
}
}
instance = SplitOperation(**arguments)
assert instance.generate_code() is None
def test_random_split_params_success():
params = {'weights': '40.0', 'seed': '1234321'}
n_in = {'input data': 'df1'}
n_out = {'splitted data 1': 'out1', 'splitted data 2': 'out2'}
instance = SplitOperation(params, named_inputs=n_in, named_outputs=n_out)
code = instance.generate_code()
expected_code = """{out1}, {out2} = np.split({input}.sample(frac=1,
random_state={seed}), [int({weights}*len({input}))])
""".format(out1=n_out['splitted data 1'],
out2=n_out['splitted data 2'],
input=n_in['input data'],
weights='0.4',
seed=1234321)
result, msg = compare_ast(ast.parse(code), ast.parse(expected_code))
assert result, msg + format_code_comparison(code, expected_code)
def test_split_invalid_seed_param_fail():
df = util.iris(['sepallength', 'sepalwidth',
'petallength', 'petalwidth'], size=10)
arguments = {
'parameters': {'seed': 'invalid'},
'named_inputs': {
'input data': 'df'
},
'named_outputs': {
'split 1': 'split_1_task_1',
'split 2': 'split_2_task_1'
}
}
instance = SplitOperation(**arguments)
with pytest.raises(NameError) as nam_err:
util.execute(instance.generate_code(),
{'df': df})
assert "name 'invalid' is not defined" in str(nam_err.value)
def test_split_success():
slice_size = 10
df = [
'df',
util.iris(['sepallength', 'sepalwidth', 'petalwidth', 'petallength'],
slice_size)
]
arguments = {
'parameters': {},
'named_inputs': {
'input data': df[0],
},
'named_outputs': {
'output data': 'out'
}
}
instance = SplitOperation(**arguments)
result = util.execute(instance.generate_code(), dict([df]))
assert result['out'].equals(util.iris(size=slice_size))
def test_split_uneven_size_dataframe_success():
df = util.iris(['sepallength', 'sepalwidth',
'petallength', 'petalwidth'], size=13)
arguments = {
'parameters': {},
'named_inputs': {
'input data': 'df'
},
'named_outputs': {
'split 1': 'split_1_task_1',
'split 2': 'split_2_task_1'
}
}
instance = SplitOperation(**arguments)
result = util.execute(instance.generate_code(),
{'df': df})
assert len(result['split_1_task_1']) == 6
assert len(result['split_2_task_1']) == 7
def test_split_weights_param_success():
df = util.iris(['sepallength', 'sepalwidth',
'petallength', 'petalwidth'], size=50)
arguments = {
'parameters': {'weights': 36},
'named_inputs': {
'input data': 'df',
},
'named_outputs': {
'split 1': 'split_1_task_1',
'split 2': 'split_2_task_1'
}
}
instance = SplitOperation(**arguments)
result = util.execute(instance.generate_code(),
{'df': df})
assert len(result['split_1_task_1']) == 18
assert len(result['split_2_task_1']) == 32
def test_split_one_row_dataframe_success():
df = util.iris(['sepallength', 'sepalwidth',
'petallength', 'petalwidth'], size=1)
test_df = df.copy()
arguments = {
'parameters': {},
'named_inputs': {
'input data': 'df',
},
'named_outputs': {
'split 1': 'split_1_task_1',
'split 2': 'split_2_task_1'
}
}
instance = SplitOperation(**arguments)
result = util.execute(instance.generate_code(),
{'df': df})
assert result['split_2_task_1'].equals(test_df)
assert len(result['split_2_task_1']) == 1
def test_split_randomness_success():
df = util.iris(['sepallength', 'sepalwidth',
'petallength', 'petalwidth'], size=10)
test_df = df.copy()
arguments = {
'parameters': {},
'named_inputs': {
'input data': 'df',
},
'named_outputs': {
'split 1': 'split_1_task_1',
'split 2': 'split_2_task_1'
}
}
instance = SplitOperation(**arguments)
result = util.execute(instance.generate_code(),
{'df': df})
test_out = pd.concat(
[result['split_1_task_1'], result['split_2_task_1']])
assert not test_out.equals(test_df)