def test_save_fig_to_path():
"""
Tests whether the .py version of the inspector works
"""
extracted_dag = get_expected_dag_adult_easy_py()
filename = os.path.join(str(get_project_root()), "test", "pipelines",
"adult_easy.png")
save_fig_to_path(extracted_dag, filename)
assert os.path.isfile(filename)
def test_save_fig_to_path():
"""
Tests whether the .py version of the inspector works
"""
extracted_dag = get_expected_dag_adult_easy("<string-source>")
filename = os.path.join(str(get_project_root()), "example_pipelines",
"adult_simple", "adult_simple.png")
save_fig_to_path(extracted_dag, filename)
assert os.path.isfile(filename)
"""
COMPAS pipeline
"""
import os
import pandas as pd
from sklearn.compose import ColumnTransformer
from sklearn.impute import SimpleImputer
from sklearn.linear_model import LogisticRegression
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import OneHotEncoder, KBinsDiscretizer, label_binarize
from mlinspect.utils import get_project_root
train_file = os.path.join(str(get_project_root()), "experiments",
"user_interviews", "compas_train_modified.csv")
train = pd.read_csv(train_file, na_values='?', index_col=0)
test_file = os.path.join(str(get_project_root()), "example_pipelines",
"compas", "compas_test.csv")
test = pd.read_csv(test_file, na_values='?', index_col=0)
train = train[[
'sex', 'dob', 'age', 'c_charge_degree', 'race', 'score_text',
'priors_count', 'days_b_screening_arrest', 'decile_score', 'is_recid',
'two_year_recid', 'c_jail_in', 'c_jail_out'
]]
test = test[[
'sex', 'dob', 'age', 'c_charge_degree', 'race', 'score_text',
'priors_count', 'days_b_screening_arrest', 'decile_score', 'is_recid',
'two_year_recid', 'c_jail_in', 'c_jail_out'
]]
"""
Tests whether the MaterializeFirstRowsInspection works
"""
import os
from testfixtures import compare, RangeComparison
from numpy.ma import array
from mlinspect.inspections.inspection_input import InspectionInputRow
from mlinspect.inspections.materialize_first_rows_inspection import MaterializeFirstRowsInspection
from mlinspect.instrumentation.dag_node import DagNode, OperatorType, CodeReference
from mlinspect.pipeline_inspector import PipelineInspector
from mlinspect.utils import get_project_root
FILE_PY = os.path.join(str(get_project_root()), "test", "pipelines", "adult_easy.py")
def test_materialize_first_rows_inspection():
"""
Tests whether the MaterializeFirstRowsInspection works
"""
inspector_result = PipelineInspector \
.on_pipeline_from_py_file(FILE_PY) \
.add_inspection(MaterializeFirstRowsInspection(2)) \
.execute()
inspection_result = inspector_result.inspection_to_annotations
assert MaterializeFirstRowsInspection(2) in inspection_result
result = inspection_result[MaterializeFirstRowsInspection(2)]
compare(result, get_expected_result())
"""
An example pipeline
"""
import os
import pandas as pd
from sklearn.compose import ColumnTransformer
from sklearn.impute import SimpleImputer
from sklearn.linear_model import LogisticRegression
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import OneHotEncoder, KBinsDiscretizer, label_binarize
from mlinspect.utils import get_project_root
train_file = os.path.join(str(get_project_root()), "example_pipelines", "compas", "compas_train.csv")
train_data = pd.read_csv(train_file, na_values='?', index_col=0)
test_file = os.path.join(str(get_project_root()), "example_pipelines", "compas", "compas_test.csv")
test_data = pd.read_csv(test_file, na_values='?', index_col=0)
train_data = train_data[
['sex', 'dob', 'age', 'c_charge_degree', 'race', 'score_text', 'priors_count', 'days_b_screening_arrest',
'decile_score', 'is_recid', 'two_year_recid', 'c_jail_in', 'c_jail_out']]
test_data = test_data[
['sex', 'dob', 'age', 'c_charge_degree', 'race', 'score_text', 'priors_count', 'days_b_screening_arrest',
'decile_score', 'is_recid', 'two_year_recid', 'c_jail_in', 'c_jail_out']]
train_data = train_data[(train_data['days_b_screening_arrest'] <= 30) & (train_data['days_b_screening_arrest'] >= -30)]
train_data = train_data[train_data['is_recid'] != -1]
train_data = train_data[train_data['c_charge_degree'] != "O"]
train_data = train_data[train_data['score_text'] != 'N/A']
"""
Tests whether the adult_easy test pipeline works
"""
import ast
import os
import nbformat
from nbconvert import PythonExporter
from mlinspect.utils import get_project_root
FILE_PY = os.path.join(str(get_project_root()), "test", "pipelines",
"adult_easy.py")
FILE_NB = os.path.join(str(get_project_root()), "test", "pipelines",
"adult_easy.ipynb")
def test_py_pipeline_runs():
"""
Tests whether the .py version of the pipeline works
"""
with open(FILE_PY) as file:
text = file.read()
parsed_ast = ast.parse(text)
exec(compile(parsed_ast, filename="<ast>", mode="exec"))
def test_nb_pipeline_runs():
"""
Tests whether the .ipynb version of the pipeline works
"""
with open(FILE_NB) as file:
notebook = nbformat.reads(file.read(), nbformat.NO_CONVERT)
"""
Some useful utils for the project
"""
import os
from mlinspect.utils import get_project_root
ADULT_SIMPLE_PY = os.path.join(str(get_project_root()), "example_pipelines",
"adult_simple", "adult_simple.py")
ADULT_SIMPLE_IPYNB = os.path.join(str(get_project_root()), "example_pipelines",
"adult_simple", "adult_simple.ipynb")
ADULT_SIMPLE_PNG = os.path.join(str(get_project_root()), "example_pipelines",
"adult_simple", "adult_simple.png")
ADULT_COMPLEX_PY = os.path.join(str(get_project_root()), "example_pipelines",
"adult_complex", "adult_complex.py")
ADULT_COMPLEX_PNG = os.path.join(str(get_project_root()), "example_pipelines",
"adult_complex", "adult_complex.png")
COMPAS_PY = os.path.join(str(get_project_root()), "example_pipelines",
"compas", "compas.py")
COMPAS_PNG = os.path.join(str(get_project_root()), "example_pipelines",
"compas", "compas.png")
HEALTHCARE_PY = os.path.join(str(get_project_root()), "example_pipelines",
"healthcare", "healthcare.py")
HEALTHCARE_PNG = os.path.join(str(get_project_root()), "example_pipelines",
"healthcare", "healthcare.png")
"""
Adult income pipeline
"""
import os
import pandas as pd
from sklearn import compose, preprocessing, tree, pipeline
from mlinspect.utils import get_project_root
print('pipeline start')
train_file_a = os.path.join(str(get_project_root()), "experiments",
"user_interviews", "adult_simple_train_a.csv")
raw_data_a = pd.read_csv(train_file_a, na_values='?', index_col=0)
train_file_b = os.path.join(str(get_project_root()), "experiments",
"user_interviews", "adult_simple_train_b.csv")
raw_data_b = pd.read_csv(train_file_b, na_values='?', index_col=0)
merged_raw_data = raw_data_a.merge(raw_data_b, on="id")
data = merged_raw_data.dropna()
labels = preprocessing.label_binarize(data['income-per-year'],
classes=['>50K', '<=50K'])
column_transformer = compose.ColumnTransformer(
transformers=[('categorical',
preprocessing.OneHotEncoder(handle_unknown='ignore'),
['education', 'workclass']),
('numeric', preprocessing.StandardScaler(),
from sklearn.compose import ColumnTransformer
from sklearn.impute import SimpleImputer
from sklearn.model_selection import train_test_split
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import OneHotEncoder, StandardScaler
from tensorflow.keras.wrappers.scikit_learn import KerasClassifier
from example_pipelines.healthcare.healthcare_utils import MyW2VTransformer, create_model
from mlinspect.utils import get_project_root
# FutureWarning: Given feature/column names or counts do not match the ones for the data given during fit
warnings.filterwarnings('ignore')
COUNTIES_OF_INTEREST = ['county2', 'county3']
# load input data sources (data generated with https://www.mockaroo.com as a single file and then split into two)
patients = pd.read_csv(os.path.join(str(get_project_root()),
"example_pipelines", "healthcare",
"healthcare_patients.csv"),
na_values='?')
histories = pd.read_csv(os.path.join(str(get_project_root()),
"example_pipelines", "healthcare",
"healthcare_histories.csv"),
na_values='?')
# combine input data into a single table
data = patients.merge(histories, on=['ssn'])
# compute mean complications per age group, append as column
complications = data.groupby('age_group').agg(
mean_complications=('complications', 'mean'))
"""
Tests whether the healthcare demo works
"""
import os
from importnb import Notebook
import matplotlib
from mlinspect.utils import get_project_root
DEMO_NB_FILE = os.path.join(str(get_project_root()), "demo",
"feature_overview", "feature_overview.ipynb")
def test_demo_nb():
"""
Tests whether the demo notebook works
"""
matplotlib.use(
"template") # Disable plt.show when executing nb as part of this test
Notebook.load(DEMO_NB_FILE)
"""
Tests whether the healthcare demo works
"""
import os
from importnb import Notebook
import matplotlib
from mlinspect.utils import get_project_root
ADULT_SIMPLE_TASK_NB = os.path.join(str(get_project_root()), "experiments",
"user_interviews",
"example-task-with-solution.ipynb")
COMPAS_TASK_NB = os.path.join(str(get_project_root()), "experiments",
"user_interviews", "task-1-solution.ipynb")
HEALTHCARE_TASK_NB = os.path.join(str(get_project_root()), "experiments",
"user_interviews", "task-2-solution.ipynb")
def test_adult_simple_task_nb():
"""
Tests whether this task notebook works
"""
matplotlib.use(
"template") # Disable plt.show when executing nb as part of this test
Notebook.load(ADULT_SIMPLE_TASK_NB)
def test_compas_task_nb():
"""
Tests whether this task notebook works
"""
Tests whether the performance benchmark notebook works
"""
import os
import matplotlib
from importnb import Notebook
from mlinspect.utils import get_project_root
EXPERIMENT_NB_FILE = os.path.join(str(get_project_root()), "experiments",
"performance",
"performance_benchmarks.ipynb")
def test_experiment_nb():
"""
Tests whether the experiment notebook works
"""
matplotlib.use(
"template") # Disable plt.show when executing nb as part of this test
Notebook.load(EXPERIMENT_NB_FILE)
def test_get_project_root():
"""
Tests whether get_project_root works
"""
assert get_project_root() == Path(__file__).parent.parent
"""
Tests whether the healthcare demo works
"""
import ast
import os
from importnb import Notebook
from mlinspect.utils import get_project_root
ADULT_EASY_FILE_PY = os.path.join(str(get_project_root()), "test", "pipelines",
"adult_easy.py")
FILE_NB = os.path.join(str(get_project_root()), "test", "pipelines",
"adult_easy.ipynb")
PIPELINE_FILE_PY = os.path.join(str(get_project_root()), "demo", "healthcare",
"healthcare.py")
DEMO_NB_FILE = os.path.join(str(get_project_root()), "demo", "healthcare",
"healthcare_demo.ipynb")
def test_py_pipeline_runs():
"""
Tests whether the .py version of the pipeline works
"""
with open(PIPELINE_FILE_PY) as file:
healthcare_code = file.read()
parsed_ast = ast.parse(healthcare_code)
exec(compile(parsed_ast, filename="<ast>", mode="exec"))
"""
An example pipeline
"""
import os
import pandas as pd
from sklearn import compose, preprocessing, tree, pipeline
from mlinspect.utils import get_project_root
print('pipeline start')
train_file = os.path.join(str(get_project_root()), "test", "data",
"adult_train.csv")
raw_data = pd.read_csv(train_file, na_values='?', index_col=0)
data = raw_data.dropna()
labels = preprocessing.label_binarize(data['income-per-year'],
classes=['>50K', '<=50K'])
feature_transformation = compose.ColumnTransformer(
transformers=[('categorical',
preprocessing.OneHotEncoder(handle_unknown='ignore'),
['education', 'workclass']),
('numeric', preprocessing.StandardScaler(),
['age', 'hours-per-week'])])
income_pipeline = pipeline.Pipeline([('features', feature_transformation),
('classifier',
tree.DecisionTreeClassifier())])
income_pipeline.fit(data, labels)
"""
An example pipeline
"""
import os
import pandas as pd
from sklearn import compose, preprocessing, tree, pipeline
from mlinspect.utils import get_project_root
print('pipeline start')
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)
data = raw_data.dropna()
labels = preprocessing.label_binarize(data['income-per-year'], classes=['>50K', '<=50K'])
feature_transformation = compose.ColumnTransformer(transformers=[
('categorical', preprocessing.OneHotEncoder(handle_unknown='ignore'), ['education', 'workclass']),
('numeric', preprocessing.StandardScaler(), ['age', 'hours-per-week'])
])
income_pipeline = pipeline.Pipeline([
('features', feature_transformation),
('classifier', tree.DecisionTreeClassifier())])
income_pipeline.fit(data, labels)
print('pipeline finished')
