Open In Colab View Notebook on GitHub

German credit scoring [scikit-learn]

Giskard is an open-source framework for testing all ML models, from LLMs to tabular models. Don’t hesitate to give the project a star on GitHub ⭐️ if you find it useful!

In this notebook, you’ll learn how to create comprehensive test suites for your model in a few lines of code, thanks to Giskard’s open-source Python library.

Use-case:

  • Binary classification. Whether to give a customer credit or not.

  • Model: LogisticRegression

  • Dataset

Outline:

  • Detect vulnerabilities automatically with Giskard’s scan

  • Automatically generate & curate a comprehensive test suite to test your model beyond accuracy-related metrics

Install dependencies

Make sure to install the giskard

[ ]:
%pip install giskard --upgrade

Import libraries

[1]:
import pandas as pd
from sklearn.compose import ColumnTransformer
from sklearn.impute import SimpleImputer
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import classification_report
from sklearn.model_selection import train_test_split
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import OneHotEncoder, StandardScaler

from giskard import Model, Dataset, scan, testing

Define constants

[2]:
# Constants.
COLUMN_TYPES = {
    "account_check_status": "category",
    "duration_in_month": "numeric",
    "credit_history": "category",
    "purpose": "category",
    "credit_amount": "numeric",
    "savings": "category",
    "present_employment_since": "category",
    "installment_as_income_perc": "numeric",
    "sex": "category",
    "personal_status": "category",
    "other_debtors": "category",
    "present_residence_since": "numeric",
    "property": "category",
    "age": "category",
    "other_installment_plans": "category",
    "housing": "category",
    "credits_this_bank": "numeric",
    "job": "category",
    "people_under_maintenance": "numeric",
    "telephone": "category",
    "foreign_worker": "category",
}

TARGET_COLUMN_NAME = "default"

COLUMNS_TO_SCALE = [key for key in COLUMN_TYPES.keys() if COLUMN_TYPES[key] == "numeric"]
COLUMNS_TO_ENCODE = [key for key in COLUMN_TYPES.keys() if COLUMN_TYPES[key] == "category"]

# Paths.
DATA_URL = "https://raw.githubusercontent.com/Giskard-AI/giskard-examples/main/datasets/credit_scoring_classification_model_dataset/german_credit_prepared.csv"

Dataset preparation

Load data

[3]:
df = pd.read_csv(DATA_URL, keep_default_na=False, na_values=["_GSK_NA_"])

Train-test split

[4]:
X_train, X_test, Y_train, Y_test = train_test_split(df.drop(columns=TARGET_COLUMN_NAME), df[TARGET_COLUMN_NAME],
                                                    test_size=0.2, random_state=0, stratify=df[TARGET_COLUMN_NAME])

Wrap dataset with Giskard

To prepare for the vulnerability scan, make sure to wrap your dataset using Giskard’s Dataset class. More details here.

[ ]:
raw_data = pd.concat([X_test, Y_test], axis=1)
giskard_dataset = Dataset(
    df=raw_data,
    # A pandas.DataFrame that contains the raw data (before all the pre-processing steps) and the actual ground truth variable (target).
    target=TARGET_COLUMN_NAME,  # Ground truth variable.
    name='German credit scoring dataset',  # Optional.
    cat_columns=COLUMNS_TO_ENCODE
    # List of categorical columns. Optional, but is a MUST if available. Inferred automatically if not.
)

Model building

Define preprocessing pipeline

[6]:
numeric_transformer = Pipeline(steps=[
    ("imputer", SimpleImputer(strategy="median")),
    ("scaler", StandardScaler())
])

categorical_transformer = Pipeline([
    ("imputer", SimpleImputer(strategy="constant", fill_value="missing")),
    ("onehot", OneHotEncoder(handle_unknown="ignore", sparse_output=False)),
])

preprocessor = ColumnTransformer(transformers=[
    ("num", numeric_transformer, COLUMNS_TO_SCALE),
    ("cat", categorical_transformer, COLUMNS_TO_ENCODE),
])

Build estimator

[ ]:
pipeline = Pipeline(steps=[
    ("preprocessor", preprocessor),
    ("classifier", LogisticRegression(max_iter=100))
])

pipeline.fit(X_train, Y_train)

pred_train = pipeline.predict(X_train)
pred_test = pipeline.predict(X_test)

print(classification_report(Y_test, pred_test))

Wrap model with Giskard

To prepare for the vulnerability scan, make sure to wrap your model using Giskard’s Model class. You can choose to either wrap the prediction function (preferred option) or the model object. More details here.

[ ]:
giskard_model = Model(
    model=pipeline,
    # A prediction function that encapsulates all the data pre-processing steps and that could be executed with the dataset used by the scan.
    model_type="classification",  # Either regression, classification or text_generation.
    name="Credit scoring classifier",  # Optional.
    classification_labels=pipeline.classes_.tolist(),
    # Their order MUST be identical to the prediction_function's output order.
    feature_names=list(COLUMN_TYPES.keys()),  # Default: all columns of your dataset.
)

# Validate wrapped model.
print(classification_report(Y_test, pipeline.classes_[giskard_model.predict(giskard_dataset).raw_prediction]))

Detect vulnerabilities in your model

Scan your model for vulnerabilities with Giskard

Giskard’s scan allows you to detect vulnerabilities in your model automatically. These include performance biases, unrobustness, data leakage, stochasticity, underconfidence, ethical issues, and more. For detailed information about the scan feature, please refer to our scan documentation.

[ ]:
results = scan(giskard_model, giskard_dataset)
[10]:
display(results)

Generate comprehensive test suites automatically for your model

Generate test suites from the scan

The objects produced by the scan can be used as fixtures to generate a test suite that integrate all detected vulnerabilities. Test suites allow you to evaluate and validate your model’s performance, ensuring that it behaves as expected on a set of predefined test cases, and to identify any regressions or issues that might arise during development or updates.

[11]:
test_suite = results.generate_test_suite("My first test suite")
test_suite.run()
2024-05-29 11:45:25,982 pid:52370 MainThread giskard.datasets.base INFO     Casting dataframe columns from {'account_check_status': 'object', 'duration_in_month': 'int64', 'credit_history': 'object', 'purpose': 'object', 'credit_amount': 'int64', 'savings': 'object', 'present_employment_since': 'object', 'installment_as_income_perc': 'int64', 'sex': 'object', 'personal_status': 'object', 'other_debtors': 'object', 'present_residence_since': 'int64', 'property': 'object', 'age': 'int64', 'other_installment_plans': 'object', 'housing': 'object', 'credits_this_bank': 'int64', 'job': 'object', 'people_under_maintenance': 'int64', 'telephone': 'object', 'foreign_worker': 'object'} to {'account_check_status': 'object', 'duration_in_month': 'int64', 'credit_history': 'object', 'purpose': 'object', 'credit_amount': 'int64', 'savings': 'object', 'present_employment_since': 'object', 'installment_as_income_perc': 'int64', 'sex': 'object', 'personal_status': 'object', 'other_debtors': 'object', 'present_residence_since': 'int64', 'property': 'object', 'age': 'int64', 'other_installment_plans': 'object', 'housing': 'object', 'credits_this_bank': 'int64', 'job': 'object', 'people_under_maintenance': 'int64', 'telephone': 'object', 'foreign_worker': 'object'}
2024-05-29 11:45:25,986 pid:52370 MainThread giskard.utils.logging_utils INFO     Predicted dataset with shape (32, 22) executed in 0:00:00.014548
Executed 'Precision on data slice “`other_installment_plans` == "bank"”' with arguments {'model': <giskard.models.sklearn.SKLearnModel object at 0x15f6913c0>, 'dataset': <giskard.datasets.base.Dataset object at 0x15e4d30d0>, 'slicing_function': <giskard.slicing.slice.QueryBasedSliceFunction object at 0x316480910>, 'threshold': 0.7540625}:
               Test failed
               Metric: 0.6


2024-05-29 11:45:26,003 pid:52370 MainThread giskard.datasets.base INFO     Casting dataframe columns from {'account_check_status': 'object', 'duration_in_month': 'int64', 'credit_history': 'object', 'purpose': 'object', 'credit_amount': 'int64', 'savings': 'object', 'present_employment_since': 'object', 'installment_as_income_perc': 'int64', 'sex': 'object', 'personal_status': 'object', 'other_debtors': 'object', 'present_residence_since': 'int64', 'property': 'object', 'age': 'int64', 'other_installment_plans': 'object', 'housing': 'object', 'credits_this_bank': 'int64', 'job': 'object', 'people_under_maintenance': 'int64', 'telephone': 'object', 'foreign_worker': 'object'} to {'account_check_status': 'object', 'duration_in_month': 'int64', 'credit_history': 'object', 'purpose': 'object', 'credit_amount': 'int64', 'savings': 'object', 'present_employment_since': 'object', 'installment_as_income_perc': 'int64', 'sex': 'object', 'personal_status': 'object', 'other_debtors': 'object', 'present_residence_since': 'int64', 'property': 'object', 'age': 'int64', 'other_installment_plans': 'object', 'housing': 'object', 'credits_this_bank': 'int64', 'job': 'object', 'people_under_maintenance': 'int64', 'telephone': 'object', 'foreign_worker': 'object'}
2024-05-29 11:45:26,006 pid:52370 MainThread giskard.utils.logging_utils INFO     Predicted dataset with shape (58, 22) executed in 0:00:00.011488
Executed 'Precision on data slice “`account_check_status` == "0 <= ... < 200 DM"”' with arguments {'model': <giskard.models.sklearn.SKLearnModel object at 0x15f6913c0>, 'dataset': <giskard.datasets.base.Dataset object at 0x15e4d30d0>, 'slicing_function': <giskard.slicing.slice.QueryBasedSliceFunction object at 0x3164848e0>, 'threshold': 0.7540625}:
               Test failed
               Metric: 0.6


2024-05-29 11:45:26,019 pid:52370 MainThread giskard.datasets.base INFO     Casting dataframe columns from {'account_check_status': 'object', 'duration_in_month': 'int64', 'credit_history': 'object', 'purpose': 'object', 'credit_amount': 'int64', 'savings': 'object', 'present_employment_since': 'object', 'installment_as_income_perc': 'int64', 'sex': 'object', 'personal_status': 'object', 'other_debtors': 'object', 'present_residence_since': 'int64', 'property': 'object', 'age': 'int64', 'other_installment_plans': 'object', 'housing': 'object', 'credits_this_bank': 'int64', 'job': 'object', 'people_under_maintenance': 'int64', 'telephone': 'object', 'foreign_worker': 'object'} to {'account_check_status': 'object', 'duration_in_month': 'int64', 'credit_history': 'object', 'purpose': 'object', 'credit_amount': 'int64', 'savings': 'object', 'present_employment_since': 'object', 'installment_as_income_perc': 'int64', 'sex': 'object', 'personal_status': 'object', 'other_debtors': 'object', 'present_residence_since': 'int64', 'property': 'object', 'age': 'int64', 'other_installment_plans': 'object', 'housing': 'object', 'credits_this_bank': 'int64', 'job': 'object', 'people_under_maintenance': 'int64', 'telephone': 'object', 'foreign_worker': 'object'}
2024-05-29 11:45:26,021 pid:52370 MainThread giskard.utils.logging_utils INFO     Predicted dataset with shape (37, 22) executed in 0:00:00.008733
Executed 'Precision on data slice “`present_employment_since` == "... < 1 year"”' with arguments {'model': <giskard.models.sklearn.SKLearnModel object at 0x15f6913c0>, 'dataset': <giskard.datasets.base.Dataset object at 0x15e4d30d0>, 'slicing_function': <giskard.slicing.slice.QueryBasedSliceFunction object at 0x3164a61a0>, 'threshold': 0.7540625}:
               Test failed
               Metric: 0.65


2024-05-29 11:45:26,033 pid:52370 MainThread giskard.datasets.base INFO     Casting dataframe columns from {'account_check_status': 'object', 'duration_in_month': 'int64', 'credit_history': 'object', 'purpose': 'object', 'credit_amount': 'int64', 'savings': 'object', 'present_employment_since': 'object', 'installment_as_income_perc': 'int64', 'sex': 'object', 'personal_status': 'object', 'other_debtors': 'object', 'present_residence_since': 'int64', 'property': 'object', 'age': 'int64', 'other_installment_plans': 'object', 'housing': 'object', 'credits_this_bank': 'int64', 'job': 'object', 'people_under_maintenance': 'int64', 'telephone': 'object', 'foreign_worker': 'object'} to {'account_check_status': 'object', 'duration_in_month': 'int64', 'credit_history': 'object', 'purpose': 'object', 'credit_amount': 'int64', 'savings': 'object', 'present_employment_since': 'object', 'installment_as_income_perc': 'int64', 'sex': 'object', 'personal_status': 'object', 'other_debtors': 'object', 'present_residence_since': 'int64', 'property': 'object', 'age': 'int64', 'other_installment_plans': 'object', 'housing': 'object', 'credits_this_bank': 'int64', 'job': 'object', 'people_under_maintenance': 'int64', 'telephone': 'object', 'foreign_worker': 'object'}
2024-05-29 11:45:26,036 pid:52370 MainThread giskard.utils.logging_utils INFO     Predicted dataset with shape (68, 22) executed in 0:00:00.008518
Executed 'Recall on data slice “`personal_status` == "divorced"”' with arguments {'model': <giskard.models.sklearn.SKLearnModel object at 0x15f6913c0>, 'dataset': <giskard.datasets.base.Dataset object at 0x15e4d30d0>, 'slicing_function': <giskard.slicing.slice.QueryBasedSliceFunction object at 0x3164a5210>, 'threshold': 0.8617857142857143}:
               Test failed
               Metric: 0.8


2024-05-29 11:45:26,050 pid:52370 MainThread giskard.datasets.base INFO     Casting dataframe columns from {'account_check_status': 'object', 'duration_in_month': 'int64', 'credit_history': 'object', 'purpose': 'object', 'credit_amount': 'int64', 'savings': 'object', 'present_employment_since': 'object', 'installment_as_income_perc': 'int64', 'sex': 'object', 'personal_status': 'object', 'other_debtors': 'object', 'present_residence_since': 'int64', 'property': 'object', 'age': 'int64', 'other_installment_plans': 'object', 'housing': 'object', 'credits_this_bank': 'int64', 'job': 'object', 'people_under_maintenance': 'int64', 'telephone': 'object', 'foreign_worker': 'object'} to {'account_check_status': 'object', 'duration_in_month': 'int64', 'credit_history': 'object', 'purpose': 'object', 'credit_amount': 'int64', 'savings': 'object', 'present_employment_since': 'object', 'installment_as_income_perc': 'int64', 'sex': 'object', 'personal_status': 'object', 'other_debtors': 'object', 'present_residence_since': 'int64', 'property': 'object', 'age': 'int64', 'other_installment_plans': 'object', 'housing': 'object', 'credits_this_bank': 'int64', 'job': 'object', 'people_under_maintenance': 'int64', 'telephone': 'object', 'foreign_worker': 'object'}
2024-05-29 11:45:26,054 pid:52370 MainThread giskard.utils.logging_utils INFO     Predicted dataset with shape (112, 22) executed in 0:00:00.009998
Executed 'Precision on data slice “`duration_in_month` >= 16.500”' with arguments {'model': <giskard.models.sklearn.SKLearnModel object at 0x15f6913c0>, 'dataset': <giskard.datasets.base.Dataset object at 0x15e4d30d0>, 'slicing_function': <giskard.slicing.slice.QueryBasedSliceFunction object at 0x31635d9c0>, 'threshold': 0.7540625}:
               Test failed
               Metric: 0.71


2024-05-29 11:45:26,072 pid:52370 MainThread giskard.datasets.base INFO     Casting dataframe columns from {'account_check_status': 'object', 'duration_in_month': 'int64', 'credit_history': 'object', 'purpose': 'object', 'credit_amount': 'int64', 'savings': 'object', 'present_employment_since': 'object', 'installment_as_income_perc': 'int64', 'sex': 'object', 'personal_status': 'object', 'other_debtors': 'object', 'present_residence_since': 'int64', 'property': 'object', 'age': 'int64', 'other_installment_plans': 'object', 'housing': 'object', 'credits_this_bank': 'int64', 'job': 'object', 'people_under_maintenance': 'int64', 'telephone': 'object', 'foreign_worker': 'object'} to {'account_check_status': 'object', 'duration_in_month': 'int64', 'credit_history': 'object', 'purpose': 'object', 'credit_amount': 'int64', 'savings': 'object', 'present_employment_since': 'object', 'installment_as_income_perc': 'int64', 'sex': 'object', 'personal_status': 'object', 'other_debtors': 'object', 'present_residence_since': 'int64', 'property': 'object', 'age': 'int64', 'other_installment_plans': 'object', 'housing': 'object', 'credits_this_bank': 'int64', 'job': 'object', 'people_under_maintenance': 'int64', 'telephone': 'object', 'foreign_worker': 'object'}
2024-05-29 11:45:26,074 pid:52370 MainThread giskard.utils.logging_utils INFO     Predicted dataset with shape (69, 22) executed in 0:00:00.012084
Executed 'Precision on data slice “`property` == "if not A121/A122 : car or other, not in attribute 6"”' with arguments {'model': <giskard.models.sklearn.SKLearnModel object at 0x15f6913c0>, 'dataset': <giskard.datasets.base.Dataset object at 0x15e4d30d0>, 'slicing_function': <giskard.slicing.slice.QueryBasedSliceFunction object at 0x3164a4eb0>, 'threshold': 0.7540625}:
               Test failed
               Metric: 0.72


2024-05-29 11:45:26,087 pid:52370 MainThread giskard.datasets.base INFO     Casting dataframe columns from {'account_check_status': 'object', 'duration_in_month': 'int64', 'credit_history': 'object', 'purpose': 'object', 'credit_amount': 'int64', 'savings': 'object', 'present_employment_since': 'object', 'installment_as_income_perc': 'int64', 'sex': 'object', 'personal_status': 'object', 'other_debtors': 'object', 'present_residence_since': 'int64', 'property': 'object', 'age': 'int64', 'other_installment_plans': 'object', 'housing': 'object', 'credits_this_bank': 'int64', 'job': 'object', 'people_under_maintenance': 'int64', 'telephone': 'object', 'foreign_worker': 'object'} to {'account_check_status': 'object', 'duration_in_month': 'int64', 'credit_history': 'object', 'purpose': 'object', 'credit_amount': 'int64', 'savings': 'object', 'present_employment_since': 'object', 'installment_as_income_perc': 'int64', 'sex': 'object', 'personal_status': 'object', 'other_debtors': 'object', 'present_residence_since': 'int64', 'property': 'object', 'age': 'int64', 'other_installment_plans': 'object', 'housing': 'object', 'credits_this_bank': 'int64', 'job': 'object', 'people_under_maintenance': 'int64', 'telephone': 'object', 'foreign_worker': 'object'}
2024-05-29 11:45:26,089 pid:52370 MainThread giskard.utils.logging_utils INFO     Predicted dataset with shape (54, 22) executed in 0:00:00.009407
Executed 'Precision on data slice “`sex` == "female"”' with arguments {'model': <giskard.models.sklearn.SKLearnModel object at 0x15f6913c0>, 'dataset': <giskard.datasets.base.Dataset object at 0x15e4d30d0>, 'slicing_function': <giskard.slicing.slice.QueryBasedSliceFunction object at 0x3164a51b0>, 'threshold': 0.7540625}:
               Test failed
               Metric: 0.74


2024-05-29 11:45:26,093 pid:52370 MainThread giskard.core.suite INFO     Executed test suite 'My first test suite'
2024-05-29 11:45:26,093 pid:52370 MainThread giskard.core.suite INFO     result: failed
2024-05-29 11:45:26,094 pid:52370 MainThread giskard.core.suite INFO     Precision on data slice “`other_installment_plans` == "bank"” ({'model': <giskard.models.sklearn.SKLearnModel object at 0x15f6913c0>, 'dataset': <giskard.datasets.base.Dataset object at 0x15e4d30d0>, 'slicing_function': <giskard.slicing.slice.QueryBasedSliceFunction object at 0x316480910>, 'threshold': 0.7540625}): {failed, metric=0.6}
2024-05-29 11:45:26,094 pid:52370 MainThread giskard.core.suite INFO     Precision on data slice “`account_check_status` == "0 <= ... < 200 DM"” ({'model': <giskard.models.sklearn.SKLearnModel object at 0x15f6913c0>, 'dataset': <giskard.datasets.base.Dataset object at 0x15e4d30d0>, 'slicing_function': <giskard.slicing.slice.QueryBasedSliceFunction object at 0x3164848e0>, 'threshold': 0.7540625}): {failed, metric=0.6046511627906976}
2024-05-29 11:45:26,094 pid:52370 MainThread giskard.core.suite INFO     Precision on data slice “`present_employment_since` == "... < 1 year"” ({'model': <giskard.models.sklearn.SKLearnModel object at 0x15f6913c0>, 'dataset': <giskard.datasets.base.Dataset object at 0x15e4d30d0>, 'slicing_function': <giskard.slicing.slice.QueryBasedSliceFunction object at 0x3164a61a0>, 'threshold': 0.7540625}): {failed, metric=0.6521739130434783}
2024-05-29 11:45:26,094 pid:52370 MainThread giskard.core.suite INFO     Recall on data slice “`personal_status` == "divorced"” ({'model': <giskard.models.sklearn.SKLearnModel object at 0x15f6913c0>, 'dataset': <giskard.datasets.base.Dataset object at 0x15e4d30d0>, 'slicing_function': <giskard.slicing.slice.QueryBasedSliceFunction object at 0x3164a5210>, 'threshold': 0.8617857142857143}): {failed, metric=0.8048780487804879}
2024-05-29 11:45:26,095 pid:52370 MainThread giskard.core.suite INFO     Precision on data slice “`duration_in_month` >= 16.500” ({'model': <giskard.models.sklearn.SKLearnModel object at 0x15f6913c0>, 'dataset': <giskard.datasets.base.Dataset object at 0x15e4d30d0>, 'slicing_function': <giskard.slicing.slice.QueryBasedSliceFunction object at 0x31635d9c0>, 'threshold': 0.7540625}): {failed, metric=0.7125}
2024-05-29 11:45:26,095 pid:52370 MainThread giskard.core.suite INFO     Precision on data slice “`property` == "if not A121/A122 : car or other, not in attribute 6"” ({'model': <giskard.models.sklearn.SKLearnModel object at 0x15f6913c0>, 'dataset': <giskard.datasets.base.Dataset object at 0x15e4d30d0>, 'slicing_function': <giskard.slicing.slice.QueryBasedSliceFunction object at 0x3164a4eb0>, 'threshold': 0.7540625}): {failed, metric=0.7192982456140351}
2024-05-29 11:45:26,095 pid:52370 MainThread giskard.core.suite INFO     Precision on data slice “`sex` == "female"” ({'model': <giskard.models.sklearn.SKLearnModel object at 0x15f6913c0>, 'dataset': <giskard.datasets.base.Dataset object at 0x15e4d30d0>, 'slicing_function': <giskard.slicing.slice.QueryBasedSliceFunction object at 0x3164a51b0>, 'threshold': 0.7540625}): {failed, metric=0.7368421052631579}
[11]:
close Test suite failed.
Test Precision on data slice “`other_installment_plans` == "bank"”
Measured Metric = 0.6 close Failed
model Credit scoring classifier
dataset German credit scoring dataset
slicing_function `other_installment_plans` == "bank"
threshold 0.7540625
Test Precision on data slice “`account_check_status` == "0 <= ... < 200 DM"”
Measured Metric = 0.60465 close Failed
model Credit scoring classifier
dataset German credit scoring dataset
slicing_function `account_check_status` == "0 <= ... < 200 DM"
threshold 0.7540625
Test Precision on data slice “`present_employment_since` == "... < 1 year"”
Measured Metric = 0.65217 close Failed
model Credit scoring classifier
dataset German credit scoring dataset
slicing_function `present_employment_since` == "... < 1 year"
threshold 0.7540625
Test Recall on data slice “`personal_status` == "divorced"”
Measured Metric = 0.80488 close Failed
model Credit scoring classifier
dataset German credit scoring dataset
slicing_function `personal_status` == "divorced"
threshold 0.8617857142857143
Test Precision on data slice “`duration_in_month` >= 16.500”
Measured Metric = 0.7125 close Failed
model Credit scoring classifier
dataset German credit scoring dataset
slicing_function `duration_in_month` >= 16.500
threshold 0.7540625
Test Precision on data slice “`property` == "if not A121/A122 : car or other, not in attribute 6"”
Measured Metric = 0.7193 close Failed
model Credit scoring classifier
dataset German credit scoring dataset
slicing_function `property` == "if not A121/A122 : car or other, not in attribute 6"
threshold 0.7540625
Test Precision on data slice “`sex` == "female"”
Measured Metric = 0.73684 close Failed
model Credit scoring classifier
dataset German credit scoring dataset
slicing_function `sex` == "female"
threshold 0.7540625

Customize your suite by loading objects from the Giskard catalog

The Giskard open source catalog will enable to load:

  • Tests such as metamorphic, performance, prediction & data drift, statistical tests, etc

  • Slicing functions such as detectors of toxicity, hate, emotion, etc

  • Transformation functions such as generators of typos, paraphrase, style tune, etc

To create custom tests, refer to this page.

For demo purposes, we will load a simple unit test (test_f1) that checks if the test F1 score is above the given threshold. For more examples of tests and functions, refer to the Giskard catalog.

[ ]:
test_suite.add_test(testing.test_f1(model=giskard_model, dataset=giskard_dataset, threshold=0.7)).run()