Open In Colab View Notebook on GitHub

ENRON email classification [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:

  • Multinomial classification of the email’s category.

  • 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 glob
import email
from string import punctuation
from collections import defaultdict

import nltk
import pandas as pd
from dateutil import parser
from nltk.corpus import stopwords
from nltk.stem import PorterStemmer
from sklearn import model_selection
from sklearn.pipeline import Pipeline
from sklearn.metrics import accuracy_score
from sklearn.compose import ColumnTransformer
from sklearn.linear_model import LogisticRegression
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.feature_extraction.text import TfidfTransformer

from giskard import Dataset, Model, scan, testing

Define constants

[2]:

TEXT_COLUMN = "Content"
TARGET_COLUMN = "Target"

COLUMN_TYPES = {TEXT_COLUMN: "text"}
COLUMNS_NAMES = ["Target", "Subject", "Content", "Week_day", "Year", "Month", "Hour", "Nb_of_forwarded_msg"]

RANDOM_STATE = 0

IDX_TO_CAT = {
    1: "REGULATION",
    2: "INTERNAL",
    3: "INFLUENCE",
    4: "INFLUENCE",
    5: "INFLUENCE",
    6: "CALIFORNIA CRISIS",
    7: "INTERNAL",
    8: "INTERNAL",
    9: "INFLUENCE",
    10: "REGULATION",
    11: "talking points",
    12: "meeting minutes",
    13: "trip reports",
}

LABEL_CAT = 3

Dataset preparation

Load and preprocess data

[ ]:

!wget https://bailando.berkeley.edu/enron/enron_with_categories.tar.gz
!tar zxf enron_with_categories.tar.gz
!rm enron_with_categories.tar.gz

[ ]:

nltk.download("punkt")
nltk.download("stopwords")

stoplist = list(set(stopwords.words("english") + list(punctuation)))
stemmer = PorterStemmer()


def get_labels(filename):
    with open(filename + ".cats") as f:
        labels = defaultdict(dict)
        line = f.readline()

        while line:
            line = line.split(",")
            top_cat, sub_cat, freq = int(line[0]), int(line[1]), int(line[2])
            labels[top_cat][sub_cat] = freq
            line = f.readline()

    return dict(labels)


data = pd.DataFrame(columns=COLUMNS_NAMES)

email_files = [f.replace(".cats", "") for f in glob.glob("enron_with_categories/*/*.cats")]
for email_file in email_files:
    values_to_add = {}

    # Target is the sub-category with maximum frequency
    if LABEL_CAT in get_labels(email_file):
        sub_cat_dict = get_labels(email_file)[LABEL_CAT]
        target_int = max(sub_cat_dict, key=sub_cat_dict.get)
        values_to_add[TARGET_COLUMN] = str(IDX_TO_CAT[target_int])

    # Features are metadata from the email object
    filename = email_file + ".txt"
    with open(filename) as f:
        message = email.message_from_string(f.read())

        values_to_add["Subject"] = str(message["Subject"])
        values_to_add[TEXT_COLUMN] = str(message.get_payload())

        date_time_obj = parser.parse(message["Date"])
        values_to_add["Week_day"] = date_time_obj.strftime("%A")
        values_to_add["Year"] = date_time_obj.strftime("%Y")
        values_to_add["Month"] = date_time_obj.strftime("%B")
        values_to_add["Hour"] = int(date_time_obj.strftime("%H"))

        # Count number of forwarded mails
        number_of_messages = 0
        for line in message.get_payload().split("\n"):
            if ("forwarded" in line.lower() or "original" in line.lower()) and "--" in line:
                number_of_messages += 1
        values_to_add["Nb_of_forwarded_msg"] = number_of_messages

    row_to_add = pd.Series(values_to_add)
    data = pd.concat([data, pd.DataFrame([row_to_add])], ignore_index=True)


data_filtered = data[data[TARGET_COLUMN].notnull()]

# Exclude target category with very few rows.
excluded_category = [IDX_TO_CAT[i] for i in [11, 12, 13]]
data_filtered = data_filtered[data_filtered["Target"].isin(excluded_category) == False]
num_classes = len(data_filtered[TARGET_COLUMN].value_counts())

# Keep only the email column and the target
data_filtered = data_filtered[[TEXT_COLUMN, TARGET_COLUMN]]

Train-test split

[6]:

Y = data_filtered[TARGET_COLUMN]
X = data_filtered.drop(columns=[TARGET_COLUMN])[list(COLUMN_TYPES.keys())]
X_train, X_test, Y_train, Y_test = model_selection.train_test_split(X, Y, random_state=RANDOM_STATE, stratify=Y)

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",  # Ground truth variable.
    name="Emails of different categories",  # Optional.
)

Model building

Build estimator

[ ]:

text_transformer = Pipeline([("vect", CountVectorizer(stop_words=stoplist)), ("tfidf", TfidfTransformer())])

preprocessor = ColumnTransformer(transformers=[("text_Mail", text_transformer, "Content")])

clf = Pipeline(steps=[("preprocessor", preprocessor), ("classifier", LogisticRegression())])
clf.fit(X_train, Y_train)

print(f"Train Accuracy score: {clf.score(X_train, Y_train):.2f}")
print(f"Test Accuracy score: {clf.score(X_test, Y_test):.2f}")

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=clf,  # 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="Email category classifier",  # Optional.
    classification_labels=clf.classes_.tolist(),  # Their order MUST be identical to the prediction_function's output order.
    feature_names=COLUMN_TYPES.keys(),  # Default: all columns of your dataset.
)

# Validate wrapped model.
y_test_pred_wrapped = giskard_model.predict(giskard_dataset).prediction
wrapped_test_metric = accuracy_score(Y_test, y_test_pred_wrapped)

print(f"Wrapped Test Accuracy score: {wrapped_test_metric:.2f}")

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)

[11]:

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.

[12]:

test_suite = results.generate_test_suite("My first test suite")
test_suite.run()

2024-05-29 11:56:58,129 pid:53166 MainThread giskard.datasets.base INFO     Casting dataframe columns from {'Content': 'object'} to {'Content': 'object'}
2024-05-29 11:56:58,130 pid:53166 MainThread giskard.utils.logging_utils INFO     Predicted dataset with shape (213, 2) executed in 0:00:00.018116
2024-05-29 11:57:01,545 pid:53166 MainThread giskard.datasets.base INFO     Casting dataframe columns from {'Content': 'object'} to {'Content': 'object'}
2024-05-29 11:57:01,546 pid:53166 MainThread giskard.utils.logging_utils INFO     Predicted dataset with shape (213, 2) executed in 0:00:00.022507
2024-05-29 11:57:01,552 pid:53166 MainThread giskard.utils.logging_utils INFO     Perturb and predict data executed in 0:00:03.448961
2024-05-29 11:57:01,554 pid:53166 MainThread giskard.utils.logging_utils INFO     Compare and predict the data executed in 0:00:00.000496
Executed 'Invariance to “Transform numbers to words”' with arguments {'model': <giskard.models.sklearn.SKLearnModel object at 0x30c9ed030>, 'dataset': <giskard.datasets.base.Dataset object at 0x30bf54070>, 'transformation_function': <giskard.scanner.robustness.text_transformations.TextNumberToWordTransformation object at 0x3345b7f40>, 'threshold': 0.95, 'output_sensitivity': 0.05}:
               Test failed
               Metric: 0.92
                - [INFO] 192 rows were perturbed

2024-05-29 11:57:01,567 pid:53166 MainThread giskard.datasets.base INFO     Casting dataframe columns from {'Content': 'object'} to {'Content': 'object'}
2024-05-29 11:57:01,568 pid:53166 MainThread giskard.utils.logging_utils INFO     Predicted dataset with shape (213, 2) executed in 0:00:00.008830
2024-05-29 11:57:03,985 pid:53166 MainThread giskard.datasets.base INFO     Casting dataframe columns from {'Content': 'object'} to {'Content': 'object'}
2024-05-29 11:57:04,121 pid:53166 MainThread giskard.utils.logging_utils INFO     Predicted dataset with shape (213, 2) executed in 0:00:00.155254
2024-05-29 11:57:04,123 pid:53166 MainThread giskard.utils.logging_utils INFO     Perturb and predict data executed in 0:00:02.564476
2024-05-29 11:57:04,124 pid:53166 MainThread giskard.utils.logging_utils INFO     Compare and predict the data executed in 0:00:00.000349
Executed 'Invariance to “Add typos”' with arguments {'model': <giskard.models.sklearn.SKLearnModel object at 0x30c9ed030>, 'dataset': <giskard.datasets.base.Dataset object at 0x30bf54070>, 'transformation_function': <giskard.scanner.robustness.text_transformations.TextTypoTransformation object at 0x3356608b0>, 'threshold': 0.95, 'output_sensitivity': 0.05}:
               Test failed
               Metric: 0.93
                - [INFO] 213 rows were perturbed

2024-05-29 11:57:04,161 pid:53166 MainThread giskard.datasets.base INFO     Casting dataframe columns from {'Content': 'object'} to {'Content': 'object'}
2024-05-29 11:57:04,162 pid:53166 MainThread giskard.utils.logging_utils INFO     Predicted dataset with shape (21, 2) executed in 0:00:00.017651
Executed 'Precision on data slice “`Content` contains "gives"”' with arguments {'model': <giskard.models.sklearn.SKLearnModel object at 0x30c9ed030>, 'dataset': <giskard.datasets.base.Dataset object at 0x30bf54070>, 'slicing_function': <giskard.slicing.slice.QueryBasedSliceFunction object at 0x339d3fc40>, 'threshold': 0.544131455399061}:
               Test failed
               Metric: 0.29


2024-05-29 11:57:04,199 pid:53166 MainThread giskard.datasets.base INFO     Casting dataframe columns from {'Content': 'object'} to {'Content': 'object'}
2024-05-29 11:57:04,199 pid:53166 MainThread giskard.utils.logging_utils INFO     Predicted dataset with shape (20, 2) executed in 0:00:00.017908
Executed 'Precision on data slice “`Content` contains "delay"”' with arguments {'model': <giskard.models.sklearn.SKLearnModel object at 0x30c9ed030>, 'dataset': <giskard.datasets.base.Dataset object at 0x30bf54070>, 'slicing_function': <giskard.slicing.slice.QueryBasedSliceFunction object at 0x339e01db0>, 'threshold': 0.544131455399061}:
               Test failed
               Metric: 0.3


2024-05-29 11:57:04,232 pid:53166 MainThread giskard.datasets.base INFO     Casting dataframe columns from {'Content': 'object'} to {'Content': 'object'}
2024-05-29 11:57:04,233 pid:53166 MainThread giskard.utils.logging_utils INFO     Predicted dataset with shape (23, 2) executed in 0:00:00.018628
Executed 'Precision on data slice “`Content` contains "sacramento"”' with arguments {'model': <giskard.models.sklearn.SKLearnModel object at 0x30c9ed030>, 'dataset': <giskard.datasets.base.Dataset object at 0x30bf54070>, 'slicing_function': <giskard.slicing.slice.QueryBasedSliceFunction object at 0x339ea4670>, 'threshold': 0.544131455399061}:
               Test failed
               Metric: 0.3


2024-05-29 11:57:04,272 pid:53166 MainThread giskard.datasets.base INFO     Casting dataframe columns from {'Content': 'object'} to {'Content': 'object'}
2024-05-29 11:57:04,272 pid:53166 MainThread giskard.utils.logging_utils INFO     Predicted dataset with shape (23, 2) executed in 0:00:00.008717
Executed 'Precision on data slice “`Content` contains "dasovich"”' with arguments {'model': <giskard.models.sklearn.SKLearnModel object at 0x30c9ed030>, 'dataset': <giskard.datasets.base.Dataset object at 0x30bf54070>, 'slicing_function': <giskard.slicing.slice.QueryBasedSliceFunction object at 0x339ea05b0>, 'threshold': 0.544131455399061}:
               Test failed
               Metric: 0.3


2024-05-29 11:57:04,312 pid:53166 MainThread giskard.datasets.base INFO     Casting dataframe columns from {'Content': 'object'} to {'Content': 'object'}
2024-05-29 11:57:04,313 pid:53166 MainThread giskard.utils.logging_utils INFO     Predicted dataset with shape (21, 2) executed in 0:00:00.016500
Executed 'Precision on data slice “`Content` contains "pro"”' with arguments {'model': <giskard.models.sklearn.SKLearnModel object at 0x30c9ed030>, 'dataset': <giskard.datasets.base.Dataset object at 0x30bf54070>, 'slicing_function': <giskard.slicing.slice.QueryBasedSliceFunction object at 0x339eb14b0>, 'threshold': 0.544131455399061}:
               Test failed
               Metric: 0.33


2024-05-29 11:57:04,350 pid:53166 MainThread giskard.datasets.base INFO     Casting dataframe columns from {'Content': 'object'} to {'Content': 'object'}
2024-05-29 11:57:04,352 pid:53166 MainThread giskard.utils.logging_utils INFO     Predicted dataset with shape (53, 2) executed in 0:00:00.017631
Executed 'Precision on data slice “`Content` contains "jeff"”' with arguments {'model': <giskard.models.sklearn.SKLearnModel object at 0x30c9ed030>, 'dataset': <giskard.datasets.base.Dataset object at 0x30bf54070>, 'slicing_function': <giskard.slicing.slice.QueryBasedSliceFunction object at 0x33a81a470>, 'threshold': 0.544131455399061}:
               Test failed
               Metric: 0.34


2024-05-29 11:57:04,390 pid:53166 MainThread giskard.datasets.base INFO     Casting dataframe columns from {'Content': 'object'} to {'Content': 'object'}
2024-05-29 11:57:04,391 pid:53166 MainThread giskard.utils.logging_utils INFO     Predicted dataset with shape (28, 2) executed in 0:00:00.013602
Executed 'Precision on data slice “`Content` contains "alan"”' with arguments {'model': <giskard.models.sklearn.SKLearnModel object at 0x30c9ed030>, 'dataset': <giskard.datasets.base.Dataset object at 0x30bf54070>, 'slicing_function': <giskard.slicing.slice.QueryBasedSliceFunction object at 0x33aba4eb0>, 'threshold': 0.544131455399061}:
               Test failed
               Metric: 0.36


2024-05-29 11:57:04,426 pid:53166 MainThread giskard.datasets.base INFO     Casting dataframe columns from {'Content': 'object'} to {'Content': 'object'}
2024-05-29 11:57:04,427 pid:53166 MainThread giskard.utils.logging_utils INFO     Predicted dataset with shape (21, 2) executed in 0:00:00.017925
Executed 'Precision on data slice “`Content` contains "judge"”' with arguments {'model': <giskard.models.sklearn.SKLearnModel object at 0x30c9ed030>, 'dataset': <giskard.datasets.base.Dataset object at 0x30bf54070>, 'slicing_function': <giskard.slicing.slice.QueryBasedSliceFunction object at 0x339ea6470>, 'threshold': 0.544131455399061}:
               Test failed
               Metric: 0.38


2024-05-29 11:57:04,458 pid:53166 MainThread giskard.datasets.base INFO     Casting dataframe columns from {'Content': 'object'} to {'Content': 'object'}
2024-05-29 11:57:04,459 pid:53166 MainThread giskard.utils.logging_utils INFO     Predicted dataset with shape (21, 2) executed in 0:00:00.019073
Executed 'Precision on data slice “`Content` contains "blackouts"”' with arguments {'model': <giskard.models.sklearn.SKLearnModel object at 0x30c9ed030>, 'dataset': <giskard.datasets.base.Dataset object at 0x30bf54070>, 'slicing_function': <giskard.slicing.slice.QueryBasedSliceFunction object at 0x339e3f730>, 'threshold': 0.544131455399061}:
               Test failed
               Metric: 0.38


2024-05-29 11:57:04,498 pid:53166 MainThread giskard.datasets.base INFO     Casting dataframe columns from {'Content': 'object'} to {'Content': 'object'}
2024-05-29 11:57:04,499 pid:53166 MainThread giskard.utils.logging_utils INFO     Predicted dataset with shape (23, 2) executed in 0:00:00.017635
Executed 'Precision on data slice “`Content` contains "push"”' with arguments {'model': <giskard.models.sklearn.SKLearnModel object at 0x30c9ed030>, 'dataset': <giskard.datasets.base.Dataset object at 0x30bf54070>, 'slicing_function': <giskard.slicing.slice.QueryBasedSliceFunction object at 0x339e50bb0>, 'threshold': 0.544131455399061}:
               Test failed
               Metric: 0.39


2024-05-29 11:57:04,535 pid:53166 MainThread giskard.datasets.base INFO     Casting dataframe columns from {'Content': 'object'} to {'Content': 'object'}
2024-05-29 11:57:04,536 pid:53166 MainThread giskard.utils.logging_utils INFO     Predicted dataset with shape (23, 2) executed in 0:00:00.019982
Executed 'Precision on data slice “`Content` contains "emergency"”' with arguments {'model': <giskard.models.sklearn.SKLearnModel object at 0x30c9ed030>, 'dataset': <giskard.datasets.base.Dataset object at 0x30bf54070>, 'slicing_function': <giskard.slicing.slice.QueryBasedSliceFunction object at 0x339ea8f70>, 'threshold': 0.544131455399061}:
               Test failed
               Metric: 0.39


2024-05-29 11:57:04,568 pid:53166 MainThread giskard.datasets.base INFO     Casting dataframe columns from {'Content': 'object'} to {'Content': 'object'}
2024-05-29 11:57:04,568 pid:53166 MainThread giskard.utils.logging_utils INFO     Predicted dataset with shape (35, 2) executed in 0:00:00.019893
Executed 'Precision on data slice “`Content` contains "governor"”' with arguments {'model': <giskard.models.sklearn.SKLearnModel object at 0x30c9ed030>, 'dataset': <giskard.datasets.base.Dataset object at 0x30bf54070>, 'slicing_function': <giskard.slicing.slice.QueryBasedSliceFunction object at 0x33ab1c850>, 'threshold': 0.544131455399061}:
               Test failed
               Metric: 0.4


2024-05-29 11:57:04,609 pid:53166 MainThread giskard.datasets.base INFO     Casting dataframe columns from {'Content': 'object'} to {'Content': 'object'}
2024-05-29 11:57:04,609 pid:53166 MainThread giskard.utils.logging_utils INFO     Predicted dataset with shape (25, 2) executed in 0:00:00.018383
Executed 'Precision on data slice “`Content` contains "duke"”' with arguments {'model': <giskard.models.sklearn.SKLearnModel object at 0x30c9ed030>, 'dataset': <giskard.datasets.base.Dataset object at 0x30bf54070>, 'slicing_function': <giskard.slicing.slice.QueryBasedSliceFunction object at 0x33ab6a650>, 'threshold': 0.544131455399061}:
               Test failed
               Metric: 0.4


2024-05-29 11:57:04,648 pid:53166 MainThread giskard.datasets.base INFO     Casting dataframe columns from {'Content': 'object'} to {'Content': 'object'}
2024-05-29 11:57:04,649 pid:53166 MainThread giskard.utils.logging_utils INFO     Predicted dataset with shape (20, 2) executed in 0:00:00.018559
Executed 'Precision on data slice “`Content` contains "fair"”' with arguments {'model': <giskard.models.sklearn.SKLearnModel object at 0x30c9ed030>, 'dataset': <giskard.datasets.base.Dataset object at 0x30bf54070>, 'slicing_function': <giskard.slicing.slice.QueryBasedSliceFunction object at 0x339e4a2f0>, 'threshold': 0.544131455399061}:
               Test failed
               Metric: 0.4


2024-05-29 11:57:04,686 pid:53166 MainThread giskard.datasets.base INFO     Casting dataframe columns from {'Content': 'object'} to {'Content': 'object'}
2024-05-29 11:57:04,687 pid:53166 MainThread giskard.utils.logging_utils INFO     Predicted dataset with shape (42, 2) executed in 0:00:00.020775
Executed 'Precision on data slice “`Content` contains "friday"”' with arguments {'model': <giskard.models.sklearn.SKLearnModel object at 0x30c9ed030>, 'dataset': <giskard.datasets.base.Dataset object at 0x30bf54070>, 'slicing_function': <giskard.slicing.slice.QueryBasedSliceFunction object at 0x335662e60>, 'threshold': 0.544131455399061}:
               Test failed
               Metric: 0.4


2024-05-29 11:57:04,689 pid:53166 MainThread giskard.core.suite INFO     Executed test suite 'My first test suite'
2024-05-29 11:57:04,689 pid:53166 MainThread giskard.core.suite INFO     result: failed
2024-05-29 11:57:04,690 pid:53166 MainThread giskard.core.suite INFO     Invariance to “Transform numbers to words” ({'model': <giskard.models.sklearn.SKLearnModel object at 0x30c9ed030>, 'dataset': <giskard.datasets.base.Dataset object at 0x30bf54070>, 'transformation_function': <giskard.scanner.robustness.text_transformations.TextNumberToWordTransformation object at 0x3345b7f40>, 'threshold': 0.95, 'output_sensitivity': 0.05}): {failed, metric=0.921875}
2024-05-29 11:57:04,690 pid:53166 MainThread giskard.core.suite INFO     Invariance to “Add typos” ({'model': <giskard.models.sklearn.SKLearnModel object at 0x30c9ed030>, 'dataset': <giskard.datasets.base.Dataset object at 0x30bf54070>, 'transformation_function': <giskard.scanner.robustness.text_transformations.TextTypoTransformation object at 0x3356608b0>, 'threshold': 0.95, 'output_sensitivity': 0.05}): {failed, metric=0.9342723004694836}
2024-05-29 11:57:04,690 pid:53166 MainThread giskard.core.suite INFO     Precision on data slice “`Content` contains "gives"” ({'model': <giskard.models.sklearn.SKLearnModel object at 0x30c9ed030>, 'dataset': <giskard.datasets.base.Dataset object at 0x30bf54070>, 'slicing_function': <giskard.slicing.slice.QueryBasedSliceFunction object at 0x339d3fc40>, 'threshold': 0.544131455399061}): {failed, metric=0.2857142857142857}
2024-05-29 11:57:04,690 pid:53166 MainThread giskard.core.suite INFO     Precision on data slice “`Content` contains "delay"” ({'model': <giskard.models.sklearn.SKLearnModel object at 0x30c9ed030>, 'dataset': <giskard.datasets.base.Dataset object at 0x30bf54070>, 'slicing_function': <giskard.slicing.slice.QueryBasedSliceFunction object at 0x339e01db0>, 'threshold': 0.544131455399061}): {failed, metric=0.3}
2024-05-29 11:57:04,691 pid:53166 MainThread giskard.core.suite INFO     Precision on data slice “`Content` contains "sacramento"” ({'model': <giskard.models.sklearn.SKLearnModel object at 0x30c9ed030>, 'dataset': <giskard.datasets.base.Dataset object at 0x30bf54070>, 'slicing_function': <giskard.slicing.slice.QueryBasedSliceFunction object at 0x339ea4670>, 'threshold': 0.544131455399061}): {failed, metric=0.30434782608695654}
2024-05-29 11:57:04,691 pid:53166 MainThread giskard.core.suite INFO     Precision on data slice “`Content` contains "dasovich"” ({'model': <giskard.models.sklearn.SKLearnModel object at 0x30c9ed030>, 'dataset': <giskard.datasets.base.Dataset object at 0x30bf54070>, 'slicing_function': <giskard.slicing.slice.QueryBasedSliceFunction object at 0x339ea05b0>, 'threshold': 0.544131455399061}): {failed, metric=0.30434782608695654}
2024-05-29 11:57:04,691 pid:53166 MainThread giskard.core.suite INFO     Precision on data slice “`Content` contains "pro"” ({'model': <giskard.models.sklearn.SKLearnModel object at 0x30c9ed030>, 'dataset': <giskard.datasets.base.Dataset object at 0x30bf54070>, 'slicing_function': <giskard.slicing.slice.QueryBasedSliceFunction object at 0x339eb14b0>, 'threshold': 0.544131455399061}): {failed, metric=0.3333333333333333}
2024-05-29 11:57:04,691 pid:53166 MainThread giskard.core.suite INFO     Precision on data slice “`Content` contains "jeff"” ({'model': <giskard.models.sklearn.SKLearnModel object at 0x30c9ed030>, 'dataset': <giskard.datasets.base.Dataset object at 0x30bf54070>, 'slicing_function': <giskard.slicing.slice.QueryBasedSliceFunction object at 0x33a81a470>, 'threshold': 0.544131455399061}): {failed, metric=0.33962264150943394}
2024-05-29 11:57:04,692 pid:53166 MainThread giskard.core.suite INFO     Precision on data slice “`Content` contains "alan"” ({'model': <giskard.models.sklearn.SKLearnModel object at 0x30c9ed030>, 'dataset': <giskard.datasets.base.Dataset object at 0x30bf54070>, 'slicing_function': <giskard.slicing.slice.QueryBasedSliceFunction object at 0x33aba4eb0>, 'threshold': 0.544131455399061}): {failed, metric=0.35714285714285715}
2024-05-29 11:57:04,692 pid:53166 MainThread giskard.core.suite INFO     Precision on data slice “`Content` contains "judge"” ({'model': <giskard.models.sklearn.SKLearnModel object at 0x30c9ed030>, 'dataset': <giskard.datasets.base.Dataset object at 0x30bf54070>, 'slicing_function': <giskard.slicing.slice.QueryBasedSliceFunction object at 0x339ea6470>, 'threshold': 0.544131455399061}): {failed, metric=0.38095238095238093}
2024-05-29 11:57:04,692 pid:53166 MainThread giskard.core.suite INFO     Precision on data slice “`Content` contains "blackouts"” ({'model': <giskard.models.sklearn.SKLearnModel object at 0x30c9ed030>, 'dataset': <giskard.datasets.base.Dataset object at 0x30bf54070>, 'slicing_function': <giskard.slicing.slice.QueryBasedSliceFunction object at 0x339e3f730>, 'threshold': 0.544131455399061}): {failed, metric=0.38095238095238093}
2024-05-29 11:57:04,693 pid:53166 MainThread giskard.core.suite INFO     Precision on data slice “`Content` contains "push"” ({'model': <giskard.models.sklearn.SKLearnModel object at 0x30c9ed030>, 'dataset': <giskard.datasets.base.Dataset object at 0x30bf54070>, 'slicing_function': <giskard.slicing.slice.QueryBasedSliceFunction object at 0x339e50bb0>, 'threshold': 0.544131455399061}): {failed, metric=0.391304347826087}
2024-05-29 11:57:04,693 pid:53166 MainThread giskard.core.suite INFO     Precision on data slice “`Content` contains "emergency"” ({'model': <giskard.models.sklearn.SKLearnModel object at 0x30c9ed030>, 'dataset': <giskard.datasets.base.Dataset object at 0x30bf54070>, 'slicing_function': <giskard.slicing.slice.QueryBasedSliceFunction object at 0x339ea8f70>, 'threshold': 0.544131455399061}): {failed, metric=0.391304347826087}
2024-05-29 11:57:04,694 pid:53166 MainThread giskard.core.suite INFO     Precision on data slice “`Content` contains "governor"” ({'model': <giskard.models.sklearn.SKLearnModel object at 0x30c9ed030>, 'dataset': <giskard.datasets.base.Dataset object at 0x30bf54070>, 'slicing_function': <giskard.slicing.slice.QueryBasedSliceFunction object at 0x33ab1c850>, 'threshold': 0.544131455399061}): {failed, metric=0.4}
2024-05-29 11:57:04,694 pid:53166 MainThread giskard.core.suite INFO     Precision on data slice “`Content` contains "duke"” ({'model': <giskard.models.sklearn.SKLearnModel object at 0x30c9ed030>, 'dataset': <giskard.datasets.base.Dataset object at 0x30bf54070>, 'slicing_function': <giskard.slicing.slice.QueryBasedSliceFunction object at 0x33ab6a650>, 'threshold': 0.544131455399061}): {failed, metric=0.4}
2024-05-29 11:57:04,695 pid:53166 MainThread giskard.core.suite INFO     Precision on data slice “`Content` contains "fair"” ({'model': <giskard.models.sklearn.SKLearnModel object at 0x30c9ed030>, 'dataset': <giskard.datasets.base.Dataset object at 0x30bf54070>, 'slicing_function': <giskard.slicing.slice.QueryBasedSliceFunction object at 0x339e4a2f0>, 'threshold': 0.544131455399061}): {failed, metric=0.4}
2024-05-29 11:57:04,695 pid:53166 MainThread giskard.core.suite INFO     Precision on data slice “`Content` contains "friday"” ({'model': <giskard.models.sklearn.SKLearnModel object at 0x30c9ed030>, 'dataset': <giskard.datasets.base.Dataset object at 0x30bf54070>, 'slicing_function': <giskard.slicing.slice.QueryBasedSliceFunction object at 0x335662e60>, 'threshold': 0.544131455399061}): {failed, metric=0.40476190476190477}

[12]:
close Test suite failed.
Test Invariance to “Transform numbers to words”
Measured Metric = 0.92188 close Failed
model Email category classifier
dataset Emails of different categories
transformation_function Transform numbers to words
threshold 0.95
output_sensitivity 0.05
Test Invariance to “Add typos”
Measured Metric = 0.93427 close Failed
model Email category classifier
dataset Emails of different categories
transformation_function Add typos
threshold 0.95
output_sensitivity 0.05
Test Precision on data slice “`Content` contains "gives"”
Measured Metric = 0.28571 close Failed
model Email category classifier
dataset Emails of different categories
slicing_function `Content` contains "gives"
threshold 0.544131455399061
Test Precision on data slice “`Content` contains "delay"”
Measured Metric = 0.3 close Failed
model Email category classifier
dataset Emails of different categories
slicing_function `Content` contains "delay"
threshold 0.544131455399061
Test Precision on data slice “`Content` contains "sacramento"”
Measured Metric = 0.30435 close Failed
model Email category classifier
dataset Emails of different categories
slicing_function `Content` contains "sacramento"
threshold 0.544131455399061
Test Precision on data slice “`Content` contains "dasovich"”
Measured Metric = 0.30435 close Failed
model Email category classifier
dataset Emails of different categories
slicing_function `Content` contains "dasovich"
threshold 0.544131455399061
Test Precision on data slice “`Content` contains "pro"”
Measured Metric = 0.33333 close Failed
model Email category classifier
dataset Emails of different categories
slicing_function `Content` contains "pro"
threshold 0.544131455399061
Test Precision on data slice “`Content` contains "jeff"”
Measured Metric = 0.33962 close Failed
model Email category classifier
dataset Emails of different categories
slicing_function `Content` contains "jeff"
threshold 0.544131455399061
Test Precision on data slice “`Content` contains "alan"”
Measured Metric = 0.35714 close Failed
model Email category classifier
dataset Emails of different categories
slicing_function `Content` contains "alan"
threshold 0.544131455399061
Test Precision on data slice “`Content` contains "judge"”
Measured Metric = 0.38095 close Failed
model Email category classifier
dataset Emails of different categories
slicing_function `Content` contains "judge"
threshold 0.544131455399061
Test Precision on data slice “`Content` contains "blackouts"”
Measured Metric = 0.38095 close Failed
model Email category classifier
dataset Emails of different categories
slicing_function `Content` contains "blackouts"
threshold 0.544131455399061
Test Precision on data slice “`Content` contains "push"”
Measured Metric = 0.3913 close Failed
model Email category classifier
dataset Emails of different categories
slicing_function `Content` contains "push"
threshold 0.544131455399061
Test Precision on data slice “`Content` contains "emergency"”
Measured Metric = 0.3913 close Failed
model Email category classifier
dataset Emails of different categories
slicing_function `Content` contains "emergency"
threshold 0.544131455399061
Test Precision on data slice “`Content` contains "governor"”
Measured Metric = 0.4 close Failed
model Email category classifier
dataset Emails of different categories
slicing_function `Content` contains "governor"
threshold 0.544131455399061
Test Precision on data slice “`Content` contains "duke"”
Measured Metric = 0.4 close Failed
model Email category classifier
dataset Emails of different categories
slicing_function `Content` contains "duke"
threshold 0.544131455399061
Test Precision on data slice “`Content` contains "fair"”
Measured Metric = 0.4 close Failed
model Email category classifier
dataset Emails of different categories
slicing_function `Content` contains "fair"
threshold 0.544131455399061
Test Precision on data slice “`Content` contains "friday"”
Measured Metric = 0.40476 close Failed
model Email category classifier
dataset Emails of different categories
slicing_function `Content` contains "friday"
threshold 0.544131455399061

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()