def test_frame_merge_sorted():
"""
Tests whether the monkey patching of ('pandas.core.frame', 'merge') works if the sort option is set to True
"""
test_code = cleandoc("""
import pandas as pd
df_a = pd.DataFrame({'A': [0, 2, 4, 8, 5], 'B': [7, 5, 4, 2, 1]})
df_b = pd.DataFrame({'B': [1, 4, 3, 2, 5], 'C': [1, 5, 4, 11, None]})
df_merged = df_a.merge(df_b, on='B', sort=True)
df_expected = pd.DataFrame({'A': [5, 8, 4, 2], 'B': [1, 2, 4, 5], 'C': [1, 11, 5, None]})
pd.testing.assert_frame_equal(df_merged, df_expected)
""")
inspector_result = _pipeline_executor.singleton.run(
python_code=test_code,
track_code_references=True,
inspections=[RowLineage(5)])
inspector_result.dag.remove_node(list(inspector_result.dag.nodes)[3])
expected_dag = networkx.DiGraph()
expected_a = DagNode(
0, BasicCodeLocation("<string-source>", 3),
OperatorContext(OperatorType.DATA_SOURCE,
FunctionInfo('pandas.core.frame', 'DataFrame')),
DagNodeDetails(None, ['A', 'B']),
OptionalCodeInfo(
CodeReference(3, 7, 3, 65),
"pd.DataFrame({'A': [0, 2, 4, 8, 5], 'B': [7, 5, 4, 2, 1]})"))
expected_b = DagNode(
1, BasicCodeLocation("<string-source>", 4),
OperatorContext(OperatorType.DATA_SOURCE,
FunctionInfo('pandas.core.frame', 'DataFrame')),
DagNodeDetails(None, ['B', 'C']),
OptionalCodeInfo(
CodeReference(4, 7, 4, 69),
"pd.DataFrame({'B': [1, 4, 3, 2, 5], 'C': [1, 5, 4, 11, None]})"))
expected_join = DagNode(
2, BasicCodeLocation("<string-source>", 5),
OperatorContext(OperatorType.JOIN,
FunctionInfo('pandas.core.frame', 'merge')),
DagNodeDetails("on 'B'", ['A', 'B', 'C']),
OptionalCodeInfo(CodeReference(5, 12, 5, 47),
"df_a.merge(df_b, on='B', sort=True)"))
expected_dag.add_edge(expected_a, expected_join)
expected_dag.add_edge(expected_b, expected_join)
compare(networkx.to_dict_of_dicts(inspector_result.dag),
networkx.to_dict_of_dicts(expected_dag))
inspection_results_data_source = inspector_result.dag_node_to_inspection_results[
expected_join]
lineage_output = inspection_results_data_source[RowLineage(5)]
expected_lineage_df = DataFrame(
[[5, 1, 1., {LineageId(0, 4), LineageId(1, 0)}],
[8, 2, 11., {LineageId(0, 3), LineageId(1, 3)}],
[4, 4, 5., {LineageId(0, 2), LineageId(1, 1)}],
[2, 5, math.nan, {LineageId(0, 1), LineageId(1, 4)}]],
columns=['A', 'B', 'C', 'mlinspect_lineage'])
pandas.testing.assert_frame_equal(
lineage_output.reset_index(drop=True),
expected_lineage_df.reset_index(drop=True))
def test_black_box_operation():
"""
Tests whether the monkey patching of pandas function works
"""
test_code = cleandoc("""
import pandas
from mlinspect.testing._testing_helper_utils import black_box_df_op
df = black_box_df_op()
df = df.dropna()
print("df")
""")
extracted_dag = _pipeline_executor.singleton.run(
python_code=test_code, track_code_references=True).dag
expected_dag = networkx.DiGraph()
expected_missing_op = DagNode(
-1, BasicCodeLocation("<string-source>", 5),
OperatorContext(OperatorType.MISSING_OP, None),
DagNodeDetails(
'Warning! Operator <string-source>:5 (df.dropna()) encountered a '
'DataFrame resulting from an operation without mlinspect support!',
['A']), OptionalCodeInfo(CodeReference(5, 5, 5, 16),
'df.dropna()'))
expected_select = DagNode(
0, BasicCodeLocation("<string-source>", 5),
OperatorContext(OperatorType.SELECTION,
FunctionInfo('pandas.core.frame', 'dropna')),
DagNodeDetails('dropna', ['A']),
OptionalCodeInfo(CodeReference(5, 5, 5, 16), 'df.dropna()'))
expected_dag.add_edge(expected_missing_op, expected_select)
compare(networkx.to_dict_of_dicts(extracted_dag),
networkx.to_dict_of_dicts(expected_dag))
def test_func_defs_and_loops():
"""
Tests whether the monkey patching of pandas function works
"""
test_code = get_test_code_with_function_def_and_for_loop()
extracted_dag = _pipeline_executor.singleton.run(
python_code=test_code, track_code_references=True).dag
expected_dag = networkx.DiGraph()
expected_data_source = DagNode(
0, BasicCodeLocation("<string-source>", 4),
OperatorContext(OperatorType.DATA_SOURCE,
FunctionInfo('pandas.core.frame', 'DataFrame')),
DagNodeDetails(None, ['A']),
OptionalCodeInfo(CodeReference(4, 9, 4, 44),
"pd.DataFrame([0, 1], columns=['A'])"))
expected_select_1 = DagNode(
1, BasicCodeLocation("<string-source>", 8),
OperatorContext(OperatorType.SELECTION,
FunctionInfo('pandas.core.frame', 'dropna')),
DagNodeDetails('dropna', ['A']),
OptionalCodeInfo(CodeReference(8, 9, 8, 20), 'df.dropna()'))
expected_dag.add_edge(expected_data_source, expected_select_1)
expected_select_2 = DagNode(
2, BasicCodeLocation("<string-source>", 8),
OperatorContext(OperatorType.SELECTION,
FunctionInfo('pandas.core.frame', 'dropna')),
DagNodeDetails('dropna', ['A']),
OptionalCodeInfo(CodeReference(8, 9, 8, 20), 'df.dropna()'))
expected_dag.add_edge(expected_select_1, expected_select_2)
compare(networkx.to_dict_of_dicts(extracted_dag),
networkx.to_dict_of_dicts(expected_dag))
def test_statsmodels_add_constant():
"""
Tests whether the monkey patching of ('statsmodel.api', 'add_constant') works
"""
test_code = cleandoc("""
import numpy as np
import statsmodels.api as sm
np.random.seed(42)
test = np.random.random(100)
test = sm.add_constant(test)
assert len(test) == 100
""")
inspector_result = _pipeline_executor.singleton.run(
python_code=test_code,
track_code_references=True,
inspections=[RowLineage(2)])
expected_dag = networkx.DiGraph()
expected_random = DagNode(
0, BasicCodeLocation("<string-source>", 4),
OperatorContext(OperatorType.DATA_SOURCE,
FunctionInfo('numpy.random', 'random')),
DagNodeDetails('random', ['array']),
OptionalCodeInfo(CodeReference(4, 7, 4, 28), "np.random.random(100)"))
expected_constant = DagNode(
1, BasicCodeLocation("<string-source>", 5),
OperatorContext(OperatorType.PROJECTION_MODIFY,
FunctionInfo('statsmodel.api', 'add_constant')),
DagNodeDetails('Adds const column', ['array']),
OptionalCodeInfo(CodeReference(5, 7, 5, 28), "sm.add_constant(test)"))
expected_dag.add_edge(expected_random, expected_constant)
compare(networkx.to_dict_of_dicts(inspector_result.dag),
networkx.to_dict_of_dicts(expected_dag))
inspection_results_data_source = inspector_result.dag_node_to_inspection_results[
expected_random]
lineage_output = inspection_results_data_source[RowLineage(2)]
expected_lineage_df = DataFrame(
[[0.5, {LineageId(0, 0)}], [0.5, {LineageId(0, 1)}]],
columns=['array', 'mlinspect_lineage'])
pandas.testing.assert_frame_equal(
lineage_output.reset_index(drop=True),
expected_lineage_df.reset_index(drop=True),
atol=1)
inspection_results_data_source = inspector_result.dag_node_to_inspection_results[
expected_constant]
lineage_output = inspection_results_data_source[RowLineage(2)]
expected_lineage_df = DataFrame(
[[numpy.array([0.5, 1.]), {LineageId(0, 0)}],
[numpy.array([0.5, 1.]), {LineageId(0, 1)}]],
columns=['array', 'mlinspect_lineage'])
pandas.testing.assert_frame_equal(
lineage_output.reset_index(drop=True),
expected_lineage_df.reset_index(drop=True),
atol=1)
def test_frame__setitem__():
"""
Tests whether the monkey patching of ('pandas.core.frame', '__setitem__') works
"""
test_code = cleandoc("""
import pandas as pd
pandas_df = pd.DataFrame({'foo': ['one', 'one', 'one', 'two', 'two', 'two'],
'bar': ['A', 'B', 'C', 'A', 'B', 'C'],
'baz': [1, 2, 3, 4, 5, 6],
'zoo': ['x', 'y', 'z', 'q', 'w', 't']})
pandas_df['baz'] = pandas_df['baz'] + 1
df_expected = pd.DataFrame({'foo': ['one', 'one', 'one', 'two', 'two', 'two'],
'bar': ['A', 'B', 'C', 'A', 'B', 'C'],
'baz': [2, 3, 4, 5, 6, 7],
'zoo': ['x', 'y', 'z', 'q', 'w', 't']})
pd.testing.assert_frame_equal(pandas_df, df_expected)
""")
inspector_result = _pipeline_executor.singleton.run(python_code=test_code, track_code_references=True,
inspections=[RowLineage(2)])
inspector_result.dag.remove_node(list(inspector_result.dag.nodes)[3])
expected_dag = networkx.DiGraph()
expected_data_source = DagNode(0,
BasicCodeLocation("<string-source>", 3),
OperatorContext(OperatorType.DATA_SOURCE,
FunctionInfo('pandas.core.frame', 'DataFrame')),
DagNodeDetails(None, ['foo', 'bar', 'baz', 'zoo']),
OptionalCodeInfo(CodeReference(3, 12, 6, 53),
"pd.DataFrame({'foo': ['one', 'one', 'one', 'two', "
"'two', 'two'],\n"
" 'bar': ['A', 'B', 'C', 'A', 'B', 'C'],\n"
" 'baz': [1, 2, 3, 4, 5, 6],\n"
" 'zoo': ['x', 'y', 'z', 'q', 'w', 't']})"))
expected_project = DagNode(1,
BasicCodeLocation("<string-source>", 7),
OperatorContext(OperatorType.PROJECTION,
FunctionInfo('pandas.core.frame', '__getitem__')),
DagNodeDetails("to ['baz']", ['baz']),
OptionalCodeInfo(CodeReference(7, 19, 7, 35), "pandas_df['baz']"))
expected_dag.add_edge(expected_data_source, expected_project)
expected_project_modify = DagNode(2,
BasicCodeLocation("<string-source>", 7),
OperatorContext(OperatorType.PROJECTION_MODIFY,
FunctionInfo('pandas.core.frame', '__setitem__')),
DagNodeDetails("modifies ['baz']", ['foo', 'bar', 'baz', 'zoo']),
OptionalCodeInfo(CodeReference(7, 0, 7, 39),
"pandas_df['baz'] = pandas_df['baz'] + 1"))
expected_dag.add_edge(expected_data_source, expected_project_modify)
compare(networkx.to_dict_of_dicts(inspector_result.dag), networkx.to_dict_of_dicts(expected_dag))
inspection_results_data_source = inspector_result.dag_node_to_inspection_results[expected_project_modify]
lineage_output = inspection_results_data_source[RowLineage(2)]
expected_lineage_df = DataFrame([['one', 'A', 2, 'x', {LineageId(0, 0)}],
['one', 'B', 3, 'y', {LineageId(0, 1)}]],
columns=['foo', 'bar', 'baz', 'zoo', 'mlinspect_lineage'])
pandas.testing.assert_frame_equal(lineage_output.reset_index(drop=True), expected_lineage_df.reset_index(drop=True))
def test_my_word_to_vec_transformer():
"""
Tests whether the monkey patching of ('example_pipelines.healthcare.healthcare_utils', 'MyW2VTransformer') works
"""
test_code = cleandoc("""
import pandas as pd
from example_pipelines.healthcare.healthcare_utils import MyW2VTransformer
import numpy as np
df = pd.DataFrame({'A': ['cat_a', 'cat_b', 'cat_a', 'cat_c']})
word_to_vec = MyW2VTransformer(min_count=2, size=2, workers=1)
encoded_data = word_to_vec.fit_transform(df)
assert encoded_data.shape == (4, 2)
""")
inspector_result = _pipeline_executor.singleton.run(
python_code=test_code,
track_code_references=True,
inspections=[RowLineage(3)],
custom_monkey_patching=[custom_monkeypatching])
expected_dag = networkx.DiGraph()
expected_data_source = DagNode(
0, BasicCodeLocation("<string-source>", 5),
OperatorContext(OperatorType.DATA_SOURCE,
FunctionInfo('pandas.core.frame', 'DataFrame')),
DagNodeDetails(None, ['A']),
OptionalCodeInfo(
CodeReference(5, 5, 5, 62),
"pd.DataFrame({'A': ['cat_a', 'cat_b', 'cat_a', 'cat_c']})"))
expected_estimator = DagNode(
1, BasicCodeLocation("<string-source>", 6),
OperatorContext(
OperatorType.TRANSFORMER,
FunctionInfo('example_pipelines.healthcare.healthcare_utils',
'MyW2VTransformer')),
DagNodeDetails('Word2Vec', ['array']),
OptionalCodeInfo(CodeReference(6, 14, 6, 62),
'MyW2VTransformer(min_count=2, size=2, workers=1)'))
expected_dag.add_edge(expected_data_source, expected_estimator)
compare(networkx.to_dict_of_dicts(inspector_result.dag),
networkx.to_dict_of_dicts(expected_dag))
inspection_results_data_source = inspector_result.dag_node_to_inspection_results[
expected_estimator]
lineage_output = inspection_results_data_source[RowLineage(3)]
expected_lineage_df = DataFrame(
[[numpy.array([0.0, 0.0, 0.0]), {LineageId(0, 0)}],
[numpy.array([0.0, 0.0, 0.0]), {LineageId(0, 1)}],
[numpy.array([0.0, 0.0, 0.0]), {LineageId(0, 2)}]],
columns=['array', 'mlinspect_lineage'])
pandas.testing.assert_series_equal(
lineage_output["mlinspect_lineage"],
expected_lineage_df["mlinspect_lineage"])
assert expected_lineage_df.iloc[0, 0].shape == (3, )
def test_frame__getitem__selection():
"""
Tests whether the monkey patching of ('pandas.core.frame', '__getitem__') works for filtering
"""
test_code = cleandoc("""
import pandas as pd
df = pd.DataFrame({'A': [0, 2, 4, 8, 5], 'B': [1, 5, 4, 11, None]})
df_selection = df[df['A'] > 3]
df_expected = pd.DataFrame({'A': [4, 8, 5], 'B': [4, 11, None]})
pd.testing.assert_frame_equal(df_selection.reset_index(drop=True), df_expected.reset_index(drop=True))
""")
inspector_result = _pipeline_executor.singleton.run(
python_code=test_code,
track_code_references=True,
inspections=[RowLineage(2)])
inspector_result.dag.remove_node(list(inspector_result.dag.nodes)[3])
expected_dag = networkx.DiGraph()
expected_data_source = DagNode(
0, BasicCodeLocation("<string-source>", 3),
OperatorContext(OperatorType.DATA_SOURCE,
FunctionInfo('pandas.core.frame', 'DataFrame')),
DagNodeDetails(None, ['A', 'B']),
OptionalCodeInfo(
CodeReference(3, 5, 3, 67),
"pd.DataFrame({'A': [0, 2, 4, 8, 5], 'B': [1, 5, 4, 11, None]})"))
expected_projection = DagNode(
1, BasicCodeLocation("<string-source>", 4),
OperatorContext(OperatorType.PROJECTION,
FunctionInfo('pandas.core.frame', '__getitem__')),
DagNodeDetails("to ['A']", ['A']),
OptionalCodeInfo(CodeReference(4, 18, 4, 25), "df['A']"))
expected_dag.add_edge(expected_data_source, expected_projection)
expected_selection = DagNode(
2, BasicCodeLocation("<string-source>", 4),
OperatorContext(OperatorType.SELECTION,
FunctionInfo('pandas.core.frame', '__getitem__')),
DagNodeDetails("Select by Series: df[df['A'] > 3]", ['A', 'B']),
OptionalCodeInfo(CodeReference(4, 15, 4, 30), "df[df['A'] > 3]"))
expected_dag.add_edge(expected_data_source, expected_selection)
compare(networkx.to_dict_of_dicts(inspector_result.dag),
networkx.to_dict_of_dicts(expected_dag))
inspection_results_data_source = inspector_result.dag_node_to_inspection_results[
expected_selection]
lineage_output = inspection_results_data_source[RowLineage(2)]
expected_lineage_df = DataFrame(
[[4, 4., {LineageId(0, 2)}], [8, 11., {LineageId(0, 3)}]],
columns=['A', 'B', 'mlinspect_lineage'])
pandas.testing.assert_frame_equal(
lineage_output.reset_index(drop=True),
expected_lineage_df.reset_index(drop=True))
def test_groupby_agg():
"""
Tests whether the monkey patching of ('pandas.core.frame', 'groupby') and ('pandas.core.groupbygeneric', 'agg')
works.
"""
test_code = cleandoc("""
import pandas as pd
df = pd.DataFrame({'group': ['A', 'B', 'A', 'C', 'B'], 'value': [1, 2, 1, 3, 4]})
df_groupby_agg = df.groupby('group').agg(mean_value=('value', 'mean'))
df_expected = pd.DataFrame({'group': ['A', 'B', 'C'], 'mean_value': [1, 3, 3]})
pd.testing.assert_frame_equal(df_groupby_agg.reset_index(drop=False), df_expected.reset_index(drop=True))
""")
inspector_result = _pipeline_executor.singleton.run(
python_code=test_code,
track_code_references=True,
inspections=[RowLineage(2)])
inspector_result.dag.remove_node(list(inspector_result.dag.nodes)[2])
expected_dag = networkx.DiGraph()
expected_data = DagNode(
0, BasicCodeLocation("<string-source>", 3),
OperatorContext(OperatorType.DATA_SOURCE,
FunctionInfo('pandas.core.frame', 'DataFrame')),
DagNodeDetails(None, ['group', 'value']),
OptionalCodeInfo(
CodeReference(3, 5, 3, 81),
"pd.DataFrame({'group': ['A', 'B', 'A', 'C', 'B'], "
"'value': [1, 2, 1, 3, 4]})"))
expected_groupby_agg = DagNode(
1, BasicCodeLocation("<string-source>", 4),
OperatorContext(OperatorType.GROUP_BY_AGG,
FunctionInfo('pandas.core.groupby.generic', 'agg')),
DagNodeDetails(
"Groupby 'group', Aggregate: '{'mean_value': ('value', 'mean')}'",
['group', 'mean_value']),
OptionalCodeInfo(
CodeReference(4, 17, 4, 70),
"df.groupby('group').agg(mean_value=('value', 'mean'))"))
expected_dag.add_edge(expected_data, expected_groupby_agg)
compare(networkx.to_dict_of_dicts(inspector_result.dag),
networkx.to_dict_of_dicts(expected_dag))
inspection_results_data_source = inspector_result.dag_node_to_inspection_results[
expected_groupby_agg]
lineage_output = inspection_results_data_source[RowLineage(2)]
expected_lineage_df = DataFrame(
[["A", 1, {LineageId(1, 0)}], ['B', 3, {LineageId(1, 1)}]],
columns=['group', 'mean_value', 'mlinspect_lineage'])
pandas.testing.assert_frame_equal(
lineage_output.reset_index(drop=True),
expected_lineage_df.reset_index(drop=True))
def test_frame__getitem__frame():
"""
Tests whether the monkey patching of ('pandas.core.frame', '__getitem__') works for multiple string arguments
"""
test_code = cleandoc("""
import pandas as pd
df = pd.DataFrame([[0, None, 2], [1, 2, 3], [4, None, 2], [9, 2, 3], [6, 1, 2], [1, 2, 3]],
columns=['A', 'B', 'C'])
df_projection = df[['A', 'C']]
df_expected = pd.DataFrame([[0, 2], [1, 3], [4, 2], [9, 3], [6, 2], [1, 3]], columns=['A', 'C'])
pd.testing.assert_frame_equal(df_projection, df_expected)
""")
inspector_result = _pipeline_executor.singleton.run(
python_code=test_code,
track_code_references=True,
inspections=[RowLineage(2)])
inspector_result.dag.remove_node(list(inspector_result.dag.nodes)[2])
expected_dag = networkx.DiGraph()
expected_data_source = DagNode(
0, BasicCodeLocation("<string-source>", 3),
OperatorContext(OperatorType.DATA_SOURCE,
FunctionInfo('pandas.core.frame', 'DataFrame')),
DagNodeDetails(None, ['A', 'B', 'C']),
OptionalCodeInfo(
CodeReference(3, 5, 4, 28),
"pd.DataFrame([[0, None, 2], [1, 2, 3], [4, None, 2], "
"[9, 2, 3], [6, 1, 2], [1, 2, 3]], \n"
" columns=['A', 'B', 'C'])"))
expected_project = DagNode(
1, BasicCodeLocation("<string-source>", 5),
OperatorContext(OperatorType.PROJECTION,
FunctionInfo('pandas.core.frame', '__getitem__')),
DagNodeDetails("to ['A', 'C']", ['A', 'C']),
OptionalCodeInfo(CodeReference(5, 16, 5, 30), "df[['A', 'C']]"))
expected_dag.add_edge(expected_data_source, expected_project)
compare(networkx.to_dict_of_dicts(inspector_result.dag),
networkx.to_dict_of_dicts(expected_dag))
inspection_results_data_source = inspector_result.dag_node_to_inspection_results[
expected_project]
lineage_output = inspection_results_data_source[RowLineage(2)]
expected_lineage_df = DataFrame(
[[0, 2, {LineageId(0, 0)}], [1, 3, {LineageId(0, 1)}]],
columns=['A', 'C', 'mlinspect_lineage'])
pandas.testing.assert_frame_equal(
lineage_output.reset_index(drop=True),
expected_lineage_df.reset_index(drop=True))
def test_frame_replace():
"""
Tests whether the monkey patching of ('pandas.core.frame', 'replace') works
"""
test_code = cleandoc("""
import pandas as pd
df = pd.DataFrame(['Low', 'Medium', 'Low', 'High', None], columns=['A'])
df_replace = df.replace('Medium', 'Low')
df_expected = pd.DataFrame(['Low', 'Low', 'Low', 'High', None], columns=['A'])
pd.testing.assert_frame_equal(df_replace.reset_index(drop=True), df_expected.reset_index(drop=True))
""")
inspector_result = _pipeline_executor.singleton.run(
python_code=test_code,
track_code_references=True,
inspections=[RowLineage(2)])
inspector_result.dag.remove_node(list(inspector_result.dag.nodes)[2])
expected_dag = networkx.DiGraph()
expected_data_source = DagNode(
0, BasicCodeLocation("<string-source>", 3),
OperatorContext(OperatorType.DATA_SOURCE,
FunctionInfo('pandas.core.frame', 'DataFrame')),
DagNodeDetails(None, ['A']),
OptionalCodeInfo(
CodeReference(3, 5, 3, 72),
"pd.DataFrame(['Low', 'Medium', 'Low', 'High', None], "
"columns=['A'])"))
expected_modify = DagNode(
1, BasicCodeLocation("<string-source>", 4),
OperatorContext(OperatorType.PROJECTION_MODIFY,
FunctionInfo('pandas.core.frame', 'replace')),
DagNodeDetails("Replace 'Medium' with 'Low'", ['A']),
OptionalCodeInfo(CodeReference(4, 13, 4, 40),
"df.replace('Medium', 'Low')"))
expected_dag.add_edge(expected_data_source, expected_modify)
compare(networkx.to_dict_of_dicts(inspector_result.dag),
networkx.to_dict_of_dicts(expected_dag))
inspection_results_data_source = inspector_result.dag_node_to_inspection_results[
expected_modify]
lineage_output = inspection_results_data_source[RowLineage(2)]
expected_lineage_df = DataFrame(
[['Low', {LineageId(0, 0)}], ['Low', {LineageId(0, 1)}]],
columns=['A', 'mlinspect_lineage'])
pandas.testing.assert_frame_equal(
lineage_output.reset_index(drop=True),
expected_lineage_df.reset_index(drop=True))
def add_test_label_node(test_label_arg, caller_filename, function_info, lineno,
optional_code_reference, optional_source_code):
"""Add a Test Label DAG Node for a estimator.score call"""
# pylint: disable=too-many-arguments
operator_context = OperatorContext(OperatorType.TEST_LABELS, function_info)
input_info_test_labels = get_input_info(test_label_arg, caller_filename,
lineno, function_info,
optional_code_reference,
optional_source_code)
test_label_op_id = _pipeline_executor.singleton.get_next_op_id()
test_labels_dag_node = DagNode(
test_label_op_id, BasicCodeLocation(caller_filename,
lineno), operator_context,
DagNodeDetails(None, get_column_names(test_label_arg)),
get_optional_code_info_or_none(optional_code_reference,
optional_source_code))
input_infos = SklearnBackend.before_call(
operator_context, [input_info_test_labels.annotated_dfobject])
label_backend_result = SklearnBackend.after_call(operator_context,
input_infos,
test_label_arg)
add_dag_node(test_labels_dag_node, [input_info_test_labels.dag_node],
label_backend_result)
test_labels_result = label_backend_result.annotated_dfobject.result_data
return label_backend_result, test_labels_dag_node, test_labels_result
def test_numpy_random():
"""
Tests whether the monkey patching of ('numpy.random', 'random') works
"""
test_code = cleandoc("""
import numpy as np
np.random.seed(42)
test = np.random.random(100)
assert len(test) == 100
""")
inspector_result = _pipeline_executor.singleton.run(
python_code=test_code,
track_code_references=True,
inspections=[RowLineage(2)])
extracted_node: DagNode = list(inspector_result.dag.nodes)[0]
expected_node = DagNode(
0, BasicCodeLocation("<string-source>", 3),
OperatorContext(OperatorType.DATA_SOURCE,
FunctionInfo('numpy.random', 'random')),
DagNodeDetails('random', ['array']),
OptionalCodeInfo(CodeReference(3, 7, 3, 28), "np.random.random(100)"))
compare(extracted_node, expected_node)
inspection_results_data_source = inspector_result.dag_node_to_inspection_results[
extracted_node]
lineage_output = inspection_results_data_source[RowLineage(2)]
expected_lineage_df = DataFrame(
[[0.5, {LineageId(0, 0)}], [0.5, {LineageId(0, 1)}]],
columns=['array', 'mlinspect_lineage'])
pandas.testing.assert_frame_equal(
lineage_output.reset_index(drop=True),
expected_lineage_df.reset_index(drop=True),
atol=1)
def add_train_data_node(estimator, train_data_arg, function_info):
"""Add a Train Label DAG Node for a estimator.fit call"""
input_info_train_data = get_input_info(
train_data_arg, estimator.mlinspect_caller_filename,
estimator.mlinspect_lineno, function_info,
estimator.mlinspect_optional_code_reference,
estimator.mlinspect_optional_source_code)
train_data_op_id = _pipeline_executor.singleton.get_next_op_id()
operator_context = OperatorContext(OperatorType.TRAIN_DATA, function_info)
train_data_dag_node = DagNode(
train_data_op_id,
BasicCodeLocation(estimator.mlinspect_caller_filename,
estimator.mlinspect_lineno), operator_context,
DagNodeDetails(None, ["array"]),
get_optional_code_info_or_none(
estimator.mlinspect_optional_code_reference,
estimator.mlinspect_optional_source_code))
input_infos = SklearnBackend.before_call(
operator_context, [input_info_train_data.annotated_dfobject])
data_backend_result = SklearnBackend.after_call(operator_context,
input_infos,
train_data_arg)
add_dag_node(train_data_dag_node, [input_info_train_data.dag_node],
data_backend_result)
train_data_result = data_backend_result.annotated_dfobject.result_data
return data_backend_result, train_data_dag_node, train_data_result
def patched_fit_transform(self, *args, **kwargs):
""" Patch for ('example_pipelines.healthcare.healthcare_utils.MyW2VTransformer', 'fit_transform') """
# pylint: disable=no-method-argument
self.mlinspect_fit_transform_active = True # pylint: disable=attribute-defined-outside-init
original = gorilla.get_original_attribute(
healthcare_utils.MyW2VTransformer, 'fit_transform')
function_info = FunctionInfo(
'example_pipelines.healthcare.healthcare_utils',
'MyW2VTransformer')
input_info = get_input_info(args[0], self.mlinspect_caller_filename,
self.mlinspect_lineno, function_info,
self.mlinspect_optional_code_reference,
self.mlinspect_optional_source_code)
operator_context = OperatorContext(OperatorType.TRANSFORMER,
function_info)
input_infos = SklearnBackend.before_call(
operator_context, [input_info.annotated_dfobject])
result = original(self, input_infos[0].result_data, *args[1:],
**kwargs)
backend_result = SklearnBackend.after_call(operator_context,
input_infos, result)
new_return_value = backend_result.annotated_dfobject.result_data
assert isinstance(new_return_value, MlinspectNdarray)
dag_node = DagNode(
singleton.get_next_op_id(),
BasicCodeLocation(self.mlinspect_caller_filename,
self.mlinspect_lineno), operator_context,
DagNodeDetails("Word2Vec: fit_transform", ['array']),
get_optional_code_info_or_none(
self.mlinspect_optional_code_reference,
self.mlinspect_optional_source_code))
add_dag_node(dag_node, [input_info.dag_node], backend_result)
self.mlinspect_fit_transform_active = False # pylint: disable=attribute-defined-outside-init
return new_return_value
def test_frame__init__():
"""
Tests whether the monkey patching of ('pandas.core.frame', 'DataFrame') works
"""
test_code = cleandoc("""
import pandas as pd
df = pd.DataFrame([0, 1, 2], columns=['A'])
assert len(df) == 3
""")
inspector_result = _pipeline_executor.singleton.run(
python_code=test_code,
track_code_references=True,
inspections=[RowLineage(2)])
extracted_node: DagNode = list(inspector_result.dag.nodes)[0]
expected_node = DagNode(
0, BasicCodeLocation("<string-source>", 3),
OperatorContext(OperatorType.DATA_SOURCE,
FunctionInfo('pandas.core.frame', 'DataFrame')),
DagNodeDetails(None, ['A']),
OptionalCodeInfo(CodeReference(3, 5, 3, 43),
"pd.DataFrame([0, 1, 2], columns=['A'])"))
compare(extracted_node, expected_node)
inspection_results_data_source = inspector_result.dag_node_to_inspection_results[
extracted_node]
lineage_output = inspection_results_data_source[RowLineage(2)]
expected_lineage_df = DataFrame(
[[0, {LineageId(0, 0)}], [1, {LineageId(0, 1)}]],
columns=['A', 'mlinspect_lineage'])
pandas.testing.assert_frame_equal(
lineage_output.reset_index(drop=True),
expected_lineage_df.reset_index(drop=True))
def test_get_rdataset():
"""
Tests whether the monkey patching of ('statsmodels.datasets', 'get_rdataset') works
"""
test_code = cleandoc("""
import statsmodels.api as sm
dat = sm.datasets.get_rdataset("Guerry", "HistData").data
assert len(dat) == 86
""")
inspector_result = _pipeline_executor.singleton.run(
python_code=test_code,
track_code_references=True,
inspections=[RowLineage(2)])
extracted_node: DagNode = list(inspector_result.dag.nodes)[0]
expected_node = DagNode(
0, BasicCodeLocation("<string-source>", 3),
OperatorContext(OperatorType.DATA_SOURCE,
FunctionInfo('statsmodels.datasets', 'get_rdataset')),
DagNodeDetails(
'Data from A.-M. Guerry, "Essay on the Moral Statistics of France"',
[
'dept', 'Region', 'Department', 'Crime_pers', 'Crime_prop',
'Literacy', 'Donations', 'Infants', 'Suicides', 'MainCity',
'Wealth', 'Commerce', 'Clergy', 'Crime_parents', 'Infanticide',
'Donation_clergy', 'Lottery', 'Desertion', 'Instruction',
'Prostitutes', 'Distance', 'Area', 'Pop1831'
]),
OptionalCodeInfo(CodeReference(3, 6, 3, 52),
"""sm.datasets.get_rdataset("Guerry", "HistData")"""))
compare(extracted_node, expected_node)
inspection_results_data_source = inspector_result.dag_node_to_inspection_results[
extracted_node]
lineage_output = inspection_results_data_source[RowLineage(2)]
expected_lineage_df = DataFrame(
[[
1, 'E', 'Ain', 28870, 15890, 37, 5098, 33120, 35039, '2:Med', 73,
58, 11, 71, 60, 69, 41, 55, 46, 13, 218.372, 5762, 346.03,
{LineageId(0, 0)}
],
[
2, 'N', 'Aisne', 26226, 5521, 51, 8901, 14572, 12831, '2:Med', 22,
10, 82, 4, 82, 36, 38, 82, 24, 327, 65.945, 7369, 513.0,
{LineageId(0, 1)}
]],
columns=[
'dept', 'Region', 'Department', 'Crime_pers', 'Crime_prop',
'Literacy', 'Donations', 'Infants', 'Suicides', 'MainCity',
'Wealth', 'Commerce', 'Clergy', 'Crime_parents', 'Infanticide',
'Donation_clergy', 'Lottery', 'Desertion', 'Instruction',
'Prostitutes', 'Distance', 'Area', 'Pop1831', 'mlinspect_lineage'
])
pandas.testing.assert_frame_equal(
lineage_output.reset_index(drop=True),
expected_lineage_df.reset_index(drop=True))
def test_read_csv():
"""
Tests whether the monkey patching of ('pandas.io.parsers', 'read_csv') works
"""
test_code = cleandoc("""
import os
import pandas as pd
from mlinspect.utils import get_project_root
train_file = os.path.join(str(get_project_root()), "example_pipelines", "adult_complex", "adult_train.csv")
raw_data = pd.read_csv(train_file, na_values='?', index_col=0)
assert len(raw_data) == 22792
""")
inspector_result = _pipeline_executor.singleton.run(
python_code=test_code,
track_code_references=True,
inspections=[RowLineage(2)])
extracted_node: DagNode = list(inspector_result.dag.nodes)[0]
expected_node = DagNode(
0, BasicCodeLocation("<string-source>", 6),
OperatorContext(OperatorType.DATA_SOURCE,
FunctionInfo('pandas.io.parsers', 'read_csv')),
DagNodeDetails(StringComparison(r".*\.csv"), [
'age', 'workclass', 'fnlwgt', 'education', 'education-num',
'marital-status', 'occupation', 'relationship', 'race', 'sex',
'capital-gain', 'capital-loss', 'hours-per-week', 'native-country',
'income-per-year'
]),
OptionalCodeInfo(
CodeReference(6, 11, 6, 62),
"pd.read_csv(train_file, na_values='?', index_col=0)"))
compare(extracted_node, expected_node)
inspection_results_data_source = inspector_result.dag_node_to_inspection_results[
extracted_node]
lineage_output = inspection_results_data_source[RowLineage(2)]
expected_lineage_df = DataFrame(
[[
46, 'Private', 128645, 'Some-college', 10, 'Divorced',
'Prof-specialty', 'Not-in-family', 'White', 'Female', 0, 0, 40,
'United-States', '<=50K', {LineageId(0, 0)}
],
[
29, 'Local-gov', 115585, 'Some-college', 10, 'Never-married',
'Handlers-cleaners', 'Not-in-family', 'White', 'Male', 0, 0, 50,
'United-States', '<=50K', {LineageId(0, 1)}
]],
columns=[
'age', 'workclass', 'fnlwgt', 'education', 'education-num',
'marital-status', 'occupation', 'relationship', 'race', 'sex',
'capital-gain', 'capital-loss', 'hours-per-week', 'native-country',
'income-per-year', 'mlinspect_lineage'
])
pandas.testing.assert_frame_equal(
lineage_output.reset_index(drop=True),
expected_lineage_df.reset_index(drop=True))
def test_frame_dropna():
"""
Tests whether the monkey patching of ('pandas.core.frame', 'dropna') works
"""
test_code = cleandoc("""
import pandas as pd
df = pd.DataFrame([0, 2, 4, 5, None], columns=['A'])
assert len(df) == 5
df = df.dropna()
assert len(df) == 4
""")
inspector_result = _pipeline_executor.singleton.run(
python_code=test_code,
track_code_references=True,
inspections=[RowLineage(2)])
expected_dag = networkx.DiGraph()
expected_data_source = DagNode(
0, BasicCodeLocation("<string-source>", 3),
OperatorContext(OperatorType.DATA_SOURCE,
FunctionInfo('pandas.core.frame', 'DataFrame')),
DagNodeDetails(None, ['A']),
OptionalCodeInfo(CodeReference(3, 5, 3, 52),
"pd.DataFrame([0, 2, 4, 5, None], columns=['A'])"))
expected_select = DagNode(
1, BasicCodeLocation("<string-source>", 5),
OperatorContext(OperatorType.SELECTION,
FunctionInfo('pandas.core.frame', 'dropna')),
DagNodeDetails('dropna', ['A']),
OptionalCodeInfo(CodeReference(5, 5, 5, 16), 'df.dropna()'))
expected_dag.add_edge(expected_data_source, expected_select)
compare(networkx.to_dict_of_dicts(inspector_result.dag),
networkx.to_dict_of_dicts(expected_dag))
inspection_results_data_source = inspector_result.dag_node_to_inspection_results[
expected_select]
lineage_output = inspection_results_data_source[RowLineage(2)]
expected_lineage_df = DataFrame(
[[0., {LineageId(0, 0)}], [2., {LineageId(0, 1)}]],
columns=['A', 'mlinspect_lineage'])
pandas.testing.assert_frame_equal(
lineage_output.reset_index(drop=True),
expected_lineage_df.reset_index(drop=True))
def get_input_info(df_object, caller_filename, lineno, function_info, optional_code_reference, optional_source_code) \
-> InputInfo:
"""
Uses the patched _mlinspect_dag_node attribute and the singleton.op_id_to_dag_node map to find the parent DAG node
for the DAG node we want to insert in the next step.
"""
# pylint: disable=too-many-arguments, unused-argument, protected-access, unused-variable, too-many-locals
if isinstance(df_object, DataFrame):
columns = list(df_object.columns) # TODO: Update this for numpy arrays etc. later
elif isinstance(df_object, Series):
columns = [df_object.name]
elif isinstance(df_object, (csr_matrix, numpy.ndarray)):
columns = ['array']
else:
raise NotImplementedError("TODO: Mlinspect info storage for type: '{}'".format(type(df_object)))
if hasattr(df_object, "_mlinspect_annotation"):
input_op_id = df_object._mlinspect_dag_node
input_dag_node = singleton.op_id_to_dag_node[input_op_id]
annotation_df = df_object._mlinspect_annotation
input_info = InputInfo(input_dag_node, AnnotatedDfObject(df_object, annotation_df))
else:
operator_context = OperatorContext(OperatorType.DATA_SOURCE, function_info)
backend_result = execute_inspection_visits_data_source(operator_context, df_object)
if optional_code_reference:
code_reference = "({})".format(optional_source_code)
else:
code_reference = ""
description = "Warning! Operator {}:{} {} encountered a DataFrame resulting from an operation " \
"without mlinspect support!".format(caller_filename, lineno, code_reference)
missing_op_id = singleton.get_next_missing_op_id()
input_dag_node = DagNode(missing_op_id,
BasicCodeLocation(caller_filename, lineno),
OperatorContext(OperatorType.MISSING_OP, None),
DagNodeDetails(description, columns),
OptionalCodeInfo(optional_code_reference, optional_source_code))
add_dag_node(input_dag_node, [], backend_result)
annotation_df = backend_result.annotated_dfobject.result_annotation
input_info = InputInfo(input_dag_node, AnnotatedDfObject(df_object, annotation_df))
return input_info
def get_expected_dag_adult_easy_py():
"""
Get the expected DAG for the adult_easy pipeline
"""
# pylint: disable=too-many-locals
expected_graph = networkx.DiGraph()
expected_data_source = DagNode(18, OperatorType.DATA_SOURCE, CodeReference(12, 11, 12, 62),
('pandas.io.parsers', 'read_csv'),
"adult_train.csv",
['age', 'workclass', 'fnlwgt', 'education', 'education-num', 'marital-status',
'occupation', 'relationship', 'race', 'sex', 'capital-gain', 'capital-loss',
'hours-per-week', 'native-country', 'income-per-year'],
"pd.read_csv(train_file, na_values='?', index_col=0)")
expected_graph.add_node(expected_data_source)
expected_select = DagNode(20, OperatorType.SELECTION, CodeReference(14, 7, 14, 24), ('pandas.core.frame', 'dropna'),
"dropna", ['age', 'workclass', 'fnlwgt', 'education', 'education-num', 'marital-status',
'occupation', 'relationship', 'race', 'sex', 'capital-gain', 'capital-loss',
'hours-per-week', 'native-country', 'income-per-year'],
'raw_data.dropna()')
expected_graph.add_edge(expected_data_source, expected_select)
expected_train_data = DagNode(56, OperatorType.TRAIN_DATA, CodeReference(24, 18, 26, 51),
('sklearn.pipeline', 'fit', 'Train Data'), None,
['age', 'workclass', 'fnlwgt', 'education', 'education-num',
'marital-status', 'occupation', 'relationship', 'race', 'sex', 'capital-gain',
'capital-loss', 'hours-per-week', 'native-country', 'income-per-year'],
'income_pipeline.fit(data, labels)'
)
expected_graph.add_edge(expected_select, expected_train_data)
pipeline_str = "compose.ColumnTransformer(transformers=[\n" \
" ('categorical', preprocessing.OneHotEncoder(handle_unknown='ignore'), " \
"['education', 'workclass']),\n" \
" ('numeric', preprocessing.StandardScaler(), ['age', 'hours-per-week'])\n" \
"])"
expected_pipeline_project_one = DagNode(34, OperatorType.PROJECTION, CodeReference(18, 25, 21, 2),
('sklearn.compose._column_transformer', 'ColumnTransformer',
'Projection'),
"to ['education'] (ColumnTransformer)", ['education'], pipeline_str)
expected_graph.add_edge(expected_train_data, expected_pipeline_project_one)
expected_pipeline_project_two = DagNode(35, OperatorType.PROJECTION, CodeReference(18, 25, 21, 2),
('sklearn.compose._column_transformer', 'ColumnTransformer',
'Projection'),
"to ['workclass'] (ColumnTransformer)", ['workclass'], pipeline_str)
expected_graph.add_edge(expected_train_data, expected_pipeline_project_two)
expected_pipeline_project_three = DagNode(40, OperatorType.PROJECTION, CodeReference(18, 25, 21, 2),
('sklearn.compose._column_transformer', 'ColumnTransformer',
'Projection'),
"to ['age'] (ColumnTransformer)", ['age'], pipeline_str)
expected_graph.add_edge(expected_train_data, expected_pipeline_project_three)
expected_pipeline_project_four = DagNode(41, OperatorType.PROJECTION, CodeReference(18, 25, 21, 2),
('sklearn.compose._column_transformer', 'ColumnTransformer',
'Projection'),
"to ['hours-per-week'] (ColumnTransformer)", ['hours-per-week'],
pipeline_str)
expected_graph.add_edge(expected_train_data, expected_pipeline_project_four)
expected_pipeline_transformer_one = DagNode(34, OperatorType.TRANSFORMER, CodeReference(19, 20, 19, 72),
('sklearn.preprocessing._encoders', 'OneHotEncoder', 'Pipeline'),
"Categorical Encoder (OneHotEncoder), Column: 'education'",
['education'],
"preprocessing.OneHotEncoder(handle_unknown='ignore')")
expected_graph.add_edge(expected_pipeline_project_one, expected_pipeline_transformer_one)
expected_pipeline_transformer_two = DagNode(35, OperatorType.TRANSFORMER, CodeReference(19, 20, 19, 72),
('sklearn.preprocessing._encoders', 'OneHotEncoder', 'Pipeline'),
"Categorical Encoder (OneHotEncoder), Column: 'workclass'",
['workclass'], "preprocessing.OneHotEncoder(handle_unknown='ignore')")
expected_graph.add_edge(expected_pipeline_project_two, expected_pipeline_transformer_two)
expected_pipeline_transformer_three = DagNode(40, OperatorType.TRANSFORMER, CodeReference(20, 16, 20, 46),
('sklearn.preprocessing._data', 'StandardScaler', 'Pipeline'),
"Numerical Encoder (StandardScaler), Column: 'age'", ['age'],
'preprocessing.StandardScaler()')
expected_graph.add_edge(expected_pipeline_project_three, expected_pipeline_transformer_three)
expected_pipeline_transformer_four = DagNode(41, OperatorType.TRANSFORMER, CodeReference(20, 16, 20, 46),
('sklearn.preprocessing._data', 'StandardScaler', 'Pipeline'),
"Numerical Encoder (StandardScaler), Column: 'hours-per-week'",
['hours-per-week'], 'preprocessing.StandardScaler()')
expected_graph.add_edge(expected_pipeline_project_four, expected_pipeline_transformer_four)
expected_pipeline_concatenation = DagNode(46, OperatorType.CONCATENATION, CodeReference(18, 25, 21, 2),
('sklearn.compose._column_transformer', 'ColumnTransformer',
'Concatenation'), None, ['array'], pipeline_str)
expected_graph.add_edge(expected_pipeline_transformer_one, expected_pipeline_concatenation)
expected_graph.add_edge(expected_pipeline_transformer_two, expected_pipeline_concatenation)
expected_graph.add_edge(expected_pipeline_transformer_three, expected_pipeline_concatenation)
expected_graph.add_edge(expected_pipeline_transformer_four, expected_pipeline_concatenation)
expected_estimator = DagNode(51, OperatorType.ESTIMATOR, CodeReference(26, 19, 26, 48),
('sklearn.tree._classes', 'DecisionTreeClassifier', 'Pipeline'),
"Decision Tree", source_code='tree.DecisionTreeClassifier()')
expected_graph.add_edge(expected_pipeline_concatenation, expected_estimator)
expected_pipeline_fit = DagNode(56, OperatorType.FIT, CodeReference(24, 18, 26, 51),
('sklearn.pipeline', 'fit', 'Pipeline'),
source_code='income_pipeline.fit(data, labels)')
expected_graph.add_edge(expected_estimator, expected_pipeline_fit)
expected_project = DagNode(23, OperatorType.PROJECTION, CodeReference(16, 38, 16, 61),
('pandas.core.frame', '__getitem__', 'Projection'), "to ['income-per-year']",
['income-per-year'], "data['income-per-year']")
expected_graph.add_edge(expected_select, expected_project)
expected_project_modify = DagNode(28, OperatorType.PROJECTION_MODIFY, CodeReference(16, 9, 16, 89),
('sklearn.preprocessing._label', 'label_binarize'),
"label_binarize, classes: ['>50K', '<=50K']", ['array'],
"preprocessing.label_binarize(data['income-per-year'], "
"classes=['>50K', '<=50K'])")
expected_graph.add_edge(expected_project, expected_project_modify)
expected_train_labels = DagNode(56, OperatorType.TRAIN_LABELS, CodeReference(24, 18, 26, 51),
('sklearn.pipeline', 'fit', 'Train Labels'), None, ['array'],
'income_pipeline.fit(data, labels)')
expected_graph.add_edge(expected_project_modify, expected_train_labels)
expected_graph.add_edge(expected_train_labels, expected_pipeline_fit)
return expected_graph
def get_expected_dag_adult_easy(caller_filename: str,
line_offset: int = 0,
with_code_references=True):
"""
Get the expected DAG for the adult_easy pipeline
"""
# pylint: disable=too-many-locals
# The line numbers differ slightly between the .py file and the.ipynb file
expected_graph = networkx.DiGraph()
expected_data_source = DagNode(
0, BasicCodeLocation(caller_filename, 12 + line_offset),
OperatorContext(OperatorType.DATA_SOURCE,
FunctionInfo('pandas.io.parsers', 'read_csv')),
DagNodeDetails('adult_train.csv', [
'age', 'workclass', 'fnlwgt', 'education', 'education-num',
'marital-status', 'occupation', 'relationship', 'race', 'sex',
'capital-gain', 'capital-loss', 'hours-per-week', 'native-country',
'income-per-year'
]),
OptionalCodeInfo(
CodeReference(12 + line_offset, 11, 12 + line_offset, 62),
"pd.read_csv(train_file, na_values='?', index_col=0)"))
expected_graph.add_node(expected_data_source)
expected_select = DagNode(
1, BasicCodeLocation(caller_filename, 14 + line_offset),
OperatorContext(OperatorType.SELECTION,
FunctionInfo('pandas.core.frame', 'dropna')),
DagNodeDetails('dropna', [
'age', 'workclass', 'fnlwgt', 'education', 'education-num',
'marital-status', 'occupation', 'relationship', 'race', 'sex',
'capital-gain', 'capital-loss', 'hours-per-week', 'native-country',
'income-per-year'
]),
OptionalCodeInfo(
CodeReference(14 + line_offset, 7, 14 + line_offset, 24),
'raw_data.dropna()'))
expected_graph.add_edge(expected_data_source, expected_select)
pipeline_str = "compose.ColumnTransformer(transformers=[\n" \
" ('categorical', preprocessing.OneHotEncoder(handle_unknown='ignore'), " \
"['education', 'workclass']),\n" \
" ('numeric', preprocessing.StandardScaler(), ['age', 'hours-per-week'])\n" \
"])"
expected_pipeline_project_one = DagNode(
4, BasicCodeLocation(caller_filename, 18 + line_offset),
OperatorContext(
OperatorType.PROJECTION,
FunctionInfo('sklearn.compose._column_transformer',
'ColumnTransformer')),
DagNodeDetails("to ['education', 'workclass']",
['education', 'workclass']),
OptionalCodeInfo(
CodeReference(18 + line_offset, 25, 21 + line_offset, 2),
pipeline_str))
expected_graph.add_edge(expected_select, expected_pipeline_project_one)
expected_pipeline_project_two = DagNode(
6, BasicCodeLocation(caller_filename, 18 + line_offset),
OperatorContext(
OperatorType.PROJECTION,
FunctionInfo('sklearn.compose._column_transformer',
'ColumnTransformer')),
DagNodeDetails("to ['age', 'hours-per-week']",
['age', 'hours-per-week']),
OptionalCodeInfo(
CodeReference(18 + line_offset, 25, 21 + line_offset, 2),
pipeline_str))
expected_graph.add_edge(expected_select, expected_pipeline_project_two)
expected_pipeline_transformer_one = DagNode(
5, BasicCodeLocation(caller_filename, 19 + line_offset),
OperatorContext(
OperatorType.TRANSFORMER,
FunctionInfo('sklearn.preprocessing._encoders', 'OneHotEncoder')),
DagNodeDetails('One-Hot Encoder: fit_transform', ['array']),
OptionalCodeInfo(
CodeReference(19 + line_offset, 20, 19 + line_offset, 72),
"preprocessing.OneHotEncoder(handle_unknown='ignore')"))
expected_pipeline_transformer_two = DagNode(
7, BasicCodeLocation(caller_filename, 20 + line_offset),
OperatorContext(
OperatorType.TRANSFORMER,
FunctionInfo('sklearn.preprocessing._data', 'StandardScaler')),
DagNodeDetails('Standard Scaler: fit_transform', ['array']),
OptionalCodeInfo(
CodeReference(20 + line_offset, 16, 20 + line_offset, 46),
'preprocessing.StandardScaler()'))
expected_graph.add_edge(expected_pipeline_project_one,
expected_pipeline_transformer_one)
expected_graph.add_edge(expected_pipeline_project_two,
expected_pipeline_transformer_two)
expected_pipeline_concatenation = DagNode(
8, BasicCodeLocation(caller_filename, 18 + line_offset),
OperatorContext(
OperatorType.CONCATENATION,
FunctionInfo('sklearn.compose._column_transformer',
'ColumnTransformer')),
DagNodeDetails(None, ['array']),
OptionalCodeInfo(
CodeReference(18 + line_offset, 25, 21 + line_offset, 2),
pipeline_str))
expected_graph.add_edge(expected_pipeline_transformer_one,
expected_pipeline_concatenation)
expected_graph.add_edge(expected_pipeline_transformer_two,
expected_pipeline_concatenation)
expected_train_data = DagNode(
9, BasicCodeLocation(caller_filename, 26 + line_offset),
OperatorContext(
OperatorType.TRAIN_DATA,
FunctionInfo('sklearn.tree._classes', 'DecisionTreeClassifier')),
DagNodeDetails(None, ['array']),
OptionalCodeInfo(
CodeReference(26 + line_offset, 19, 26 + line_offset, 48),
'tree.DecisionTreeClassifier()'))
expected_graph.add_edge(expected_pipeline_concatenation,
expected_train_data)
expected_project = DagNode(
2, BasicCodeLocation(caller_filename, 16 + line_offset),
OperatorContext(OperatorType.PROJECTION,
FunctionInfo('pandas.core.frame', '__getitem__')),
DagNodeDetails("to ['income-per-year']", ['income-per-year']),
OptionalCodeInfo(
CodeReference(16 + line_offset, 38, 16 + line_offset, 61),
"data['income-per-year']"))
expected_graph.add_edge(expected_select, expected_project)
expected_project_modify = DagNode(
3, BasicCodeLocation(caller_filename, 16 + line_offset),
OperatorContext(
OperatorType.PROJECTION_MODIFY,
FunctionInfo('sklearn.preprocessing._label', 'label_binarize')),
DagNodeDetails("label_binarize, classes: ['>50K', '<=50K']",
['array']),
OptionalCodeInfo(
CodeReference(16 + line_offset, 9, 16 + line_offset, 89),
"preprocessing.label_binarize(data['income-per-year'], "
"classes=['>50K', '<=50K'])"))
expected_graph.add_edge(expected_project, expected_project_modify)
expected_train_labels = DagNode(
10, BasicCodeLocation(caller_filename, 26 + line_offset),
OperatorContext(
OperatorType.TRAIN_LABELS,
FunctionInfo('sklearn.tree._classes', 'DecisionTreeClassifier')),
DagNodeDetails(None, ['array']),
OptionalCodeInfo(
CodeReference(26 + line_offset, 19, 26 + line_offset, 48),
'tree.DecisionTreeClassifier()'))
expected_graph.add_edge(expected_project_modify, expected_train_labels)
expected_estimator = DagNode(
11, BasicCodeLocation(caller_filename, 26 + line_offset),
OperatorContext(
OperatorType.ESTIMATOR,
FunctionInfo('sklearn.tree._classes', 'DecisionTreeClassifier')),
DagNodeDetails('Decision Tree', []),
OptionalCodeInfo(
CodeReference(26 + line_offset, 19, 26 + line_offset, 48),
'tree.DecisionTreeClassifier()'))
expected_graph.add_edge(expected_train_data, expected_estimator)
expected_graph.add_edge(expected_train_labels, expected_estimator)
if not with_code_references:
for dag_node in expected_graph.nodes:
dag_node.optional_code_info = None
return expected_graph
def test_ols_fit():
"""
Tests whether the monkey patching of ('statsmodels.regression.linear_model.OLS', 'fit') works
"""
test_code = cleandoc("""
import numpy as np
import statsmodels.api as sm
np.random.seed(42)
nobs = 100
X = np.random.random((nobs, 2))
X = sm.add_constant(X)
beta = [1, .1, .5]
e = np.random.random(nobs)
y = np.dot(X, beta) + e
results = sm.OLS(y, X).fit()
assert results.summary() is not None
""")
inspector_result = _pipeline_executor.singleton.run(
python_code=test_code,
track_code_references=True,
inspections=[RowLineage(3)])
inspector_result.dag.remove_nodes_from(
list(inspector_result.dag.nodes)[0:4])
inspector_result.dag.remove_node(list(inspector_result.dag.nodes)[1])
expected_dag = networkx.DiGraph()
expected_train_data = DagNode(
3, BasicCodeLocation("<string-source>", 10),
OperatorContext(OperatorType.TRAIN_DATA,
FunctionInfo('statsmodel.api.OLS', 'fit')),
DagNodeDetails(None, ['array']),
OptionalCodeInfo(CodeReference(10, 10, 10, 22), 'sm.OLS(y, X)'))
expected_train_labels = DagNode(
4, BasicCodeLocation("<string-source>", 10),
OperatorContext(OperatorType.TRAIN_LABELS,
FunctionInfo('statsmodel.api.OLS', 'fit')),
DagNodeDetails(None, ['array']),
OptionalCodeInfo(CodeReference(10, 10, 10, 22), 'sm.OLS(y, X)'))
expected_ols = DagNode(
5, BasicCodeLocation("<string-source>", 10),
OperatorContext(OperatorType.ESTIMATOR,
FunctionInfo('statsmodel.api.OLS', 'fit')),
DagNodeDetails('Decision Tree', []),
OptionalCodeInfo(CodeReference(10, 10, 10, 22), 'sm.OLS(y, X)'))
expected_dag.add_edge(expected_train_data, expected_ols)
expected_dag.add_edge(expected_train_labels, expected_ols)
compare(networkx.to_dict_of_dicts(inspector_result.dag),
networkx.to_dict_of_dicts(expected_dag))
inspection_results_data_source = inspector_result.dag_node_to_inspection_results[
expected_train_data]
lineage_output = inspection_results_data_source[RowLineage(3)]
expected_lineage_df = DataFrame(
[[
numpy.array([1.0, 0.3745401188473625, 0.9507143064099162]),
{LineageId(3, 0)}
],
[
numpy.array([1.0, 0.7319939418114051, 0.5986584841970366]),
{LineageId(3, 1)}
],
[
numpy.array([1.0, 0.15601864044243652, 0.15599452033620265]),
{LineageId(3, 2)}
]],
columns=['array', 'mlinspect_lineage'])
pandas.testing.assert_frame_equal(
lineage_output.reset_index(drop=True),
expected_lineage_df.reset_index(drop=True),
atol=0.1)
inspection_results_data_source = inspector_result.dag_node_to_inspection_results[
expected_train_labels]
lineage_output = inspection_results_data_source[RowLineage(3)]
expected_lineage_df = DataFrame([[2.154842811243982, {LineageId(5, 0)}],
[1.4566686012747074, {LineageId(5, 1)}],
[1.2552278383069588, {LineageId(5, 2)}]],
columns=['array', 'mlinspect_lineage'])
pandas.testing.assert_frame_equal(
lineage_output.reset_index(drop=True),
expected_lineage_df.reset_index(drop=True),
atol=0.1)
inspection_results_data_source = inspector_result.dag_node_to_inspection_results[
expected_ols]
lineage_output = inspection_results_data_source[RowLineage(3)]
expected_lineage_df = DataFrame(
[[{LineageId(5, 0), LineageId(3, 0)}],
[{LineageId(5, 1), LineageId(3, 1)}],
[{LineageId(5, 2), LineageId(3, 2)}]],
columns=['mlinspect_lineage'])
pandas.testing.assert_frame_equal(
lineage_output.reset_index(drop=True),
expected_lineage_df.reset_index(drop=True),
check_column_type=False)
def get_expected_result():
"""
Get the expected PrintFirstRowsAnalyzer(2) result for the adult_easy example
"""
pipeline_str = "compose.ColumnTransformer(transformers=[\n " \
"('categorical', preprocessing.OneHotEncoder(handle_unknown='ignore'), " \
"['education', 'workclass']),\n " \
"('numeric', preprocessing.StandardScaler(), ['age', 'hours-per-week'])\n])"
expected_result = {
DagNode(node_id=18, operator_type=OperatorType.DATA_SOURCE, module=('pandas.io.parsers', 'read_csv'),
code_reference=CodeReference(12, 11, 12, 62), description='adult_train.csv',
columns=['age', 'workclass', 'fnlwgt', 'education', 'education-num', 'marital-status',
'occupation', 'relationship', 'race', 'sex', 'capital-gain', 'capital-loss',
'hours-per-week', 'native-country', 'income-per-year'],
source_code="pd.read_csv(train_file, na_values='?', index_col=0)"):
DataFrame([[46, 'Private', 128645, 'Some-college', 10, 'Divorced', 'Prof-specialty',
'Not-in-family', 'White', 'Female', 0, 0, 40, 'United-States', '<=50K'],
[29, 'Local-gov', 115585, 'Some-college', 10, 'Never-married', 'Handlers-cleaners',
'Not-in-family', 'White', 'Male', 0, 0, 50, 'United-States', '<=50K']],
columns=['age', 'workclass', 'fnlwgt', 'education', 'education-num', 'marital-status',
'occupation', 'relationship', 'race', 'sex', 'capital-gain', 'capital-loss',
'hours-per-week', 'native-country', 'income-per-year']),
DagNode(node_id=20, operator_type=OperatorType.SELECTION, module=('pandas.core.frame', 'dropna'),
code_reference=CodeReference(14, 7, 14, 24), description='dropna',
columns=['age', 'workclass', 'fnlwgt', 'education', 'education-num',
'marital-status', 'occupation', 'relationship', 'race', 'sex',
'capital-gain', 'capital-loss', 'hours-per-week',
'native-country', 'income-per-year'],
source_code='raw_data.dropna()'
):
DataFrame([[46, 'Private', 128645, 'Some-college', 10, 'Divorced', 'Prof-specialty',
'Not-in-family', 'White', 'Female', 0, 0, 40, 'United-States', '<=50K'],
[29, 'Local-gov', 115585, 'Some-college', 10, 'Never-married', 'Handlers-cleaners',
'Not-in-family', 'White', 'Male', 0, 0, 50, 'United-States', '<=50K']],
columns=['age', 'workclass', 'fnlwgt', 'education', 'education-num',
'marital-status', 'occupation', 'relationship', 'race', 'sex',
'capital-gain', 'capital-loss', 'hours-per-week',
'native-country', 'income-per-year']),
DagNode(node_id=23, operator_type=OperatorType.PROJECTION, module=('pandas.core.frame', '__getitem__',
'Projection'),
code_reference=CodeReference(16, 38, 16, 61), description="to ['income-per-year']",
columns=['income-per-year'], source_code="data['income-per-year']"):
DataFrame([['<=50K'], ['<=50K']], columns=['array']),
DagNode(node_id=28, operator_type=OperatorType.PROJECTION_MODIFY,
module=('sklearn.preprocessing._label', 'label_binarize'),
code_reference=CodeReference(16, 9, 16, 89),
description="label_binarize, classes: ['>50K', '<=50K']", columns=['array'],
source_code="preprocessing.label_binarize(data['income-per-year'], classes=['>50K', '<=50K'])"):
DataFrame([[array(1)], [array(1)]], columns=['array']),
DagNode(node_id=56, operator_type=OperatorType.TRAIN_DATA, module=('sklearn.pipeline', 'fit', 'Train Data'),
code_reference=CodeReference(24, 18, 26, 51), description=None,
columns=['age', 'workclass', 'fnlwgt', 'education', 'education-num', 'marital-status',
'occupation', 'relationship', 'race', 'sex', 'capital-gain', 'capital-loss',
'hours-per-week', 'native-country', 'income-per-year'],
source_code='income_pipeline.fit(data, labels)'):
DataFrame([
[46, 'Private', 128645, 'Some-college', 10, 'Divorced', 'Prof-specialty',
'Not-in-family', 'White', 'Female', 0, 0, 40, 'United-States', '<=50K'],
[29, 'Local-gov', 115585, 'Some-college', 10, 'Never-married', 'Handlers-cleaners',
'Not-in-family', 'White', 'Male', 0, 0, 50, 'United-States', '<=50K']],
columns=['age', 'workclass', 'fnlwgt', 'education', 'education-num', 'marital-status',
'occupation', 'relationship', 'race', 'sex', 'capital-gain', 'capital-loss',
'hours-per-week', 'native-country', 'income-per-year']),
DagNode(node_id=56, operator_type=OperatorType.TRAIN_LABELS, module=('sklearn.pipeline', 'fit', 'Train Labels'),
code_reference=CodeReference(24, 18, 26, 51), description=None, columns=['array'],
source_code='income_pipeline.fit(data, labels)'):
DataFrame([[array(1)], [array(1)]], columns=['array']),
DagNode(node_id=40, operator_type=OperatorType.PROJECTION, code_reference=CodeReference(18, 25, 21, 2),
module=('sklearn.compose._column_transformer', 'ColumnTransformer', 'Projection'),
description="to ['age'] (ColumnTransformer)", columns=['age'], source_code=pipeline_str):
DataFrame([[46], [29]], columns=['age']),
DagNode(node_id=34, operator_type=OperatorType.PROJECTION, code_reference=CodeReference(18, 25, 21, 2),
module=('sklearn.compose._column_transformer', 'ColumnTransformer', 'Projection'),
description="to ['education'] (ColumnTransformer)", columns=['education'], source_code=pipeline_str):
DataFrame([['Some-college'], ['Some-college']], columns=['education']),
DagNode(node_id=41, operator_type=OperatorType.PROJECTION, code_reference=CodeReference(18, 25, 21, 2),
module=('sklearn.compose._column_transformer', 'ColumnTransformer', 'Projection'),
description="to ['hours-per-week'] (ColumnTransformer)", columns=['hours-per-week'],
source_code=pipeline_str):
DataFrame([[40], [50]], columns=['hours-per-week']),
DagNode(node_id=35, operator_type=OperatorType.PROJECTION, code_reference=CodeReference(18, 25, 21, 2),
module=('sklearn.compose._column_transformer', 'ColumnTransformer', 'Projection'),
description="to ['workclass'] (ColumnTransformer)", columns=['workclass'], source_code=pipeline_str):
DataFrame([['Private'], ['Local-gov']], columns=['workclass']),
DagNode(node_id=40, operator_type=OperatorType.TRANSFORMER, code_reference=CodeReference(20, 16, 20, 46),
module=('sklearn.preprocessing._data', 'StandardScaler', 'Pipeline'),
description="Numerical Encoder (StandardScaler), Column: 'age'", columns=['age'],
source_code='preprocessing.StandardScaler()'):
DataFrame([[array(RangeComparison(0.5, 0.6))], [array(RangeComparison(-0.8, -0.7))]], columns=['age']),
DagNode(node_id=41, operator_type=OperatorType.TRANSFORMER, code_reference=CodeReference(20, 16, 20, 46),
module=('sklearn.preprocessing._data', 'StandardScaler', 'Pipeline'),
description="Numerical Encoder (StandardScaler), Column: 'hours-per-week'", columns=['hours-per-week'],
source_code='preprocessing.StandardScaler()'):
DataFrame([[array(RangeComparison(-0.09, -0.08))], [array(RangeComparison(0.7, 0.8))]],
columns=['hours-per-week']),
DagNode(node_id=34, operator_type=OperatorType.TRANSFORMER, code_reference=CodeReference(19, 20, 19, 72),
module=('sklearn.preprocessing._encoders', 'OneHotEncoder', 'Pipeline'),
description="Categorical Encoder (OneHotEncoder), Column: 'education'", columns=['education'],
source_code="preprocessing.OneHotEncoder(handle_unknown='ignore')"):
DataFrame([[array([0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 1.])],
[array([0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 1.])]],
columns=['education']),
DagNode(node_id=35, operator_type=OperatorType.TRANSFORMER, code_reference=CodeReference(19, 20, 19, 72),
module=('sklearn.preprocessing._encoders', 'OneHotEncoder', 'Pipeline'),
description="Categorical Encoder (OneHotEncoder), Column: 'workclass'", columns=['workclass'],
source_code="preprocessing.OneHotEncoder(handle_unknown='ignore')"):
DataFrame([[array([0., 0., 1., 0., 0., 0., 0.])], [array([0., 1., 0., 0., 0., 0., 0.])]],
columns=['workclass']),
DagNode(node_id=46, operator_type=OperatorType.CONCATENATION, code_reference=CodeReference(18, 25, 21, 2),
module=('sklearn.compose._column_transformer', 'ColumnTransformer', 'Concatenation'),
description=None, columns=['array'], source_code=pipeline_str):
DataFrame([[array([0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,
0., 0., 0., 0., 0., 1., 0., 0., 1., 0.,
0., 0., 0., RangeComparison(0.5, 0.6),
RangeComparison(-0.09, -0.08)])],
[array([0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,
0., 0., 0., 0., 0., 1., 0., 1., 0., 0.,
0., 0., 0., RangeComparison(-0.8, -0.7),
RangeComparison(0.7, 0.8)])]],
columns=['array']),
DagNode(node_id=51, operator_type=OperatorType.ESTIMATOR, code_reference=CodeReference(26, 19, 26, 48),
module=('sklearn.tree._classes', 'DecisionTreeClassifier', 'Pipeline'),
description='Decision Tree', source_code='tree.DecisionTreeClassifier()'): None
}
return expected_result
