def test_sample_or_partition_seed_success():
"""
seeds 4294967296 or higher (integer limit) will be set to 0
seeds lower than 0 will be set to 0
"""
df = util.iris(['sepallength', 'sepalwidth', 'petalwidth', 'petallength'],
size=10)
test_df = df.copy()
arguments = {
'parameters': {
'type': 'value',
'seed': 4294967296,
'value': 10
},
'named_inputs': {
'input data': 'df',
},
'named_outputs': {
'sampled data': 'out'
}
}
instance = SampleOrPartitionOperation(**arguments)
result = util.execute(instance.generate_code(), {'df': df})
test_out = test_df.sample(n=10, random_state=0)
assert result['out'].equals(test_out)
def test_sample_or_partition_fraction_percentage_success():
params = {'fraction': 45}
n_in = {'input data': 'input_1'}
n_out = {'sampled data': 'output_1'}
instance = SampleOrPartitionOperation(params,
named_inputs=n_in,
named_outputs=n_out)
code = instance.generate_code()
expected_code = "output_1 = input_1.sample(frac={}, random_state={})"\
.format(params['fraction'] * 0.01, 'None')
result, msg = compare_ast(ast.parse(code), ast.parse(expected_code))
assert result, msg
def test_sample_or_partition_minimal_params_success():
params = {'fraction': '3', 'seed': '0'}
n_in = {'input data': 'input_1'}
n_out = {'sampled data': 'output_1'}
instance = SampleOrPartitionOperation(params,
named_inputs=n_in,
named_outputs=n_out)
code = instance.generate_code()
expected_code = "output_1 = input_1.sample(frac={}, random_state={})"\
.format('0.03', params['seed'])
result, msg = compare_ast(ast.parse(code), ast.parse(expected_code))
assert result, msg
def test_sample_or_partition_no_output_implies_no_code_success():
arguments = {
'parameters': {
'type': 'percent',
'fraction': 60
},
'named_inputs': {
'input data': 'df',
},
'named_outputs': {}
}
instance = SampleOrPartitionOperation(**arguments)
assert instance.generate_code() is None
def test_sample_or_partition_type_head_success():
params = {
'value': 365,
'seed': 0,
'type': SampleOrPartitionOperation.TYPE_HEAD
}
n_in = {'input data': 'input_1'}
n_out = {'sampled data': 'output_1'}
instance = SampleOrPartitionOperation(params,
named_inputs=n_in,
named_outputs=n_out)
code = instance.generate_code()
expected_code = "output_1 = input_1.head({})".format(params['value'])
result, msg = compare_ast(ast.parse(code), ast.parse(expected_code))
assert result, msg
def test_sample_or_partition_type_value_success():
params = {
'value': '400',
'seed': '0',
'type': SampleOrPartitionOperation.TYPE_VALUE
}
n_in = {'input data': 'input_1'}
n_out = {'sampled data': 'output_1'}
instance = SampleOrPartitionOperation(params,
named_inputs=n_in,
named_outputs=n_out)
code = instance.generate_code()
expected_code = "output_1 = input_1.sample(n={}, random_state=0)"\
.format(params['value'])
result, msg = compare_ast(ast.parse(code), ast.parse(expected_code))
assert result, msg
def test_sample_or_partition_fraction_missing_failure():
params = {'seed': '0'}
with pytest.raises(ValueError):
n_in = {'input data': 'input_1'}
n_out = {'output data': 'output_1'}
SampleOrPartitionOperation(params,
named_inputs=n_in,
named_outputs=n_out)
def test_sample_or_partition_head_success():
df = util.iris(['sepallength', 'sepalwidth', 'petalwidth', 'petallength'],
size=10)
test_df = df.copy()
arguments = {
'parameters': {
'type': 'head',
'value': 2
},
'named_inputs': {
'input data': 'df',
},
'named_outputs': {
'sampled data': 'out'
}
}
instance = SampleOrPartitionOperation(**arguments)
result = util.execute(instance.generate_code(), {'df': df})
assert len(result['out']) == 2
assert result['out'].equals(test_df.iloc[:2, :])
def test_sample_or_partition_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 = SampleOrPartitionOperation(**arguments)
result = util.execute(instance.generate_code(), dict([df]))
assert result['out'].equals(util.iris(size=slice_size))
def test_sample_or_partition_invalid_value_failure():
params = {
'value': -365,
'seed': '0',
'type': SampleOrPartitionOperation.TYPE_HEAD
}
with pytest.raises(ValueError):
n_in = {'input data': 'input_1'}
n_out = {'output data': 'output_1'}
SampleOrPartitionOperation(params,
named_inputs=n_in,
named_outputs=n_out)
def test_sample_or_partition_missing_parameters_fail():
arguments = {
'parameters': {},
'named_inputs': {
'input data': 'df',
},
'named_outputs': {
'sampled data': 'out'
}
}
with pytest.raises(ValueError) as val_err:
SampleOrPartitionOperation(**arguments)
assert "Parameter 'fraction' must be 0<=x<=1 if is using the current type of" \
" sampling in task" in str(val_err)
def test_sample_or_partition_invalid_value_param_fail():
arguments = {
'parameters': {
'type': 'head',
'value': -1
},
'named_inputs': {
'input data': 'df',
},
'named_outputs': {
'sampled data': 'out'
}
}
with pytest.raises(ValueError) as val_err:
SampleOrPartitionOperation(**arguments)
assert "Parameter 'value' must be [x>=0] if is using the current type of" \
" sampling in task" in str(val_err.value)
def test_sample_or_partition_invalid_fraction_param_fail():
arguments = {
'parameters': {
'type': 'percent',
'fraction': 110
},
'named_inputs': {
'input data': 'df',
},
'named_outputs': {
'sampled data': 'out'
}
}
with pytest.raises(ValueError) as val_err:
SampleOrPartitionOperation(**arguments)
assert "Parameter 'fraction' must be 0<=x<=1 if is using the current type" \
" of sampling in task" in str(val_err.value)