def test_join_match_case_param_success():
"""
Match case converts a column to lower then, it adds a _lower to the column
name and finally it drops the column. (Seems redundant...)
"""
df1 = util.titanic(['name', 'embarked'], size=10)
df2 = util.titanic(['homedest', 'name'], size=10)
test_df = util.titanic(['name', 'embarked', 'homedest'], size=10)
arguments = {
'parameters': {
'keep_right_keys': False,
'match_case': False,
'join_type': 'inner',
'left_attributes': ['name'],
'right_attributes': ['name']
},
'named_inputs': {
'input data 1': 'df1',
'input data 2': 'df2'
},
'named_outputs': {
'output data': 'out'
}
}
instance = JoinOperation(**arguments)
result = util.execute(instance.generate_code(), {'df1': df1, 'df2': df2})
test_df.columns = ['name_l', 'embarked_l', 'homedest_r']
assert result['out'].equals(test_df)
def test_join_krk_param_success():
df1 = util.titanic(['name', 'homedest'], size=10)
df2 = util.titanic(['embarked', 'name'], size=10)
test_df = util.titanic(['name', 'homedest', 'embarked', 'name'], size=10)
arguments = {
'parameters': {
'keep_right_keys': 1,
'match_case': '1',
'join_type': 'inner',
'left_attributes': ['name'],
'right_attributes': ['name']
},
'named_inputs': {
'input data 1': 'df1',
'input data 2': 'df2'
},
'named_outputs': {
'output data': 'out'
}
}
instance = JoinOperation(**arguments)
result = util.execute(instance.generate_code(), {'df1': df1, 'df2': df2})
test_df.columns = ['name_l', 'homedest_l', 'embarked_r', 'name_r']
assert result['out'].equals(test_df)
def test_join_outer_replace_success():
"""
This only happens when you pass '_outer'
"""
df1 = util.titanic(['name', 'homedest'], size=10)
df2 = util.titanic(['embarked', 'name'], size=10)
arguments = {
'parameters': {
'keep_right_keys': False,
'match_case': True,
'join_type': '_outer',
'left_attributes': ['homedest'],
'right_attributes': ['embarked']
},
'named_inputs': {
'input data 1': 'df1',
'input data 2': 'df2'
},
'named_outputs': {
'output data': 'out'
}
}
instance = JoinOperation(**arguments)
with pytest.raises(KeyError) as key_err:
util.execute(instance.generate_code(), {'df1': df1, 'df2': df2})
assert '' in str(key_err.value)
def test_join_custom_suffixes_success():
df1 = util.titanic(['name', 'homedest'], size=10)
df2 = util.titanic(['embarked', 'name'], size=10)
test_df = util.titanic(['name', 'homedest', 'embarked'], size=10)
arguments = {
'parameters': {
'keep_right_keys': False,
'match_case': True,
'join_type': 'inner',
'left_attributes': ['name'],
'right_attributes': ['name'],
'aliases': '_esquerdo,_direito'
},
'named_inputs': {
'input data 1': 'df1',
'input data 2': 'df2'
},
'named_outputs': {
'output data': 'out'
}
}
instance = JoinOperation(**arguments)
result = util.execute(instance.generate_code(), {'df1': df1, 'df2': df2})
test_df.columns = [
'name_esquerdo', 'homedest_esquerdo', 'embarked_direito'
]
assert result['out'].equals(test_df)
def test_aggregation_non_numeric_attributes_success():
df = util.titanic(['homedest'], size=150)
test_out = df.copy()
arguments = {
'parameters': {
'attributes': ['homedest'],
'function': return_funcs('homedest', drop='avg')
},
'named_inputs': {
'input data': 'df'
},
'named_outputs': {
'output data': 'out'
}
}
instance = AggregationOperation(**arguments)
result = util.execute(instance.generate_code(), {'df': df})
test_out = test_out.groupby(['homedest']).agg(
home_collect_list=('homedest', _collect_list),
home_collect_set=('homedest', _collect_set),
home_count=('homedest', 'count'),
home_first=('homedest', 'first'),
home_last=('homedest', 'last'),
home_max=('homedest', 'max'),
home_min=('homedest', 'min'),
home_sum=('homedest', 'sum'),
home_size=('homedest', 'size')).reset_index()
assert result['out'].equals(test_out)
def test_join_merge_outer_parameter_success():
"""
there's a line of code that replaces '_outer' to ''
"""
df1 = util.titanic(['name', 'homedest'], size=10)
df2 = util.titanic(['embarked', 'name'], size=10)
test_df1 = df1.copy()
test_df2 = df2.copy()
arguments = {
'parameters': {
'keep_right_keys': False,
'match_case': True,
'join_type': 'outer',
'left_attributes': ['homedest'],
'right_attributes': ['embarked']
},
'named_inputs': {
'input data 1': 'df1',
'input data 2': 'df2'
},
'named_outputs': {
'output data': 'out'
}
}
instance = JoinOperation(**arguments)
result = util.execute(instance.generate_code(), {'df1': df1, 'df2': df2})
cols1 = [c + '_l' for c in test_df1.columns]
cols2 = [c + '_r' for c in test_df2.columns]
test_df1.columns = cols1
test_df2.columns = cols2
keys1 = [c + '_l' for c in ['homedest']]
keys2 = [c + '_r' for c in ['embarked']]
test_out = pd.merge(test_df1,
test_df2,
how='outer',
suffixes=['_l', '_r'],
left_on=keys1,
right_on=keys2)
cols_to_remove = keys2
test_out.drop(cols_to_remove, axis=1, inplace=True)
assert result['out'].equals(test_out)
def test_join_invalid_right_attributes_param_fail():
df1 = util.titanic(['name', 'homedest'], size=10)
df2 = util.titanic(['embarked', 'name'], size=10)
arguments = {
'parameters': {
'keep_right_keys': False,
'match_case': False,
'join_type': 'inner',
'left_attributes': ['homedest'],
'right_attributes': 'invalid'
},
'named_inputs': {
'input data 1': 'df1',
'input data 2': 'df2'
},
'named_outputs': {
'output data': 'out'
}
}
instance = JoinOperation(**arguments)
with pytest.raises(NameError) as nam_err:
util.execute(instance.generate_code(), {'df1': df1, 'df2': df2})
assert "invalid" in str(nam_err.value)
def test_aggregation_non_numeric_attributes_fail():
df = util.titanic(['homedest'], size=150)
arguments = {
'parameters': {
'attributes': ['homedest'],
'function': return_funcs('homedest')
},
'named_inputs': {
'input data': 'df'
},
'named_outputs': {
'output data': 'out'
}
}
instance = AggregationOperation(**arguments)
with pytest.raises(pd.core.base.DataError) as data_err:
util.execute(instance.generate_code(), {'df': df})
assert "No numeric types to aggregate" in str(data_err.value)