Amazon reviews 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:

Binary classification of product’s review ‘helpfulness’ (quality).
Reference notebook
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 string
from pathlib import Path
from urllib.request import urlretrieve

import numpy as np
import pandas as pd
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import roc_auc_score, balanced_accuracy_score
from sklearn.model_selection import train_test_split
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import FunctionTransformer

from giskard import Dataset, Model, scan, testing

Notebook-level settings¶

[2]:

# Disable chained assignment warning.
pd.options.mode.chained_assignment = None

Define constants¶

[3]:

# Constants.
RANDOM_SEED = 0
TEST_RATIO = 0.2

TARGET_THRESHOLD = 0.5
TARGET_NAME = "isHelpful"

# Paths.
DATA_URL = "ftp://sys.giskard.ai/pub/unit_test_resources/amazon_review_dataset/reviews.json"
DATA_PATH = Path.home() / ".giskard" / "amazon_review_dataset" / "reviews.json"

Dataset preparation¶

Load and preprocess data¶

[4]:

def fetch_from_ftp(url: str, file: Path) -> None:
    """Helper to fetch data from the FTP server."""
    if not file.parent.exists():
        file.parent.mkdir(parents=True, exist_ok=True)

    if not file.exists():
        print(f"Downloading data from {url}")
        urlretrieve(url, file)

    print(f"Data was loaded!")


def download_data(**kwargs) -> pd.DataFrame:
    """Download the dataset using URL."""
    fetch_from_ftp(DATA_URL, DATA_PATH)
    _df = pd.read_json(DATA_PATH, lines=True, **kwargs)
    return _df


def preprocess_data(df: pd.DataFrame) -> pd.DataFrame:
    """Perform data-preprocessing steps."""
    print(f"Start data preprocessing...")

    # Select columns.
    df = df[["reviewText", "helpful"]]

    # Remove Null-characters (x00) from the dataset.
    df.reviewText = df.reviewText.apply(lambda x: x.replace("\x00", ""))

    # Extract numbers of helpful and total votes.
    df['helpful_ratings'] = df.helpful.apply(lambda x: x[0])
    df['total_ratings'] = df.helpful.apply(lambda x: x[1])

    # Filter unreasonable comments.
    df = df[df.total_ratings > 10]

    # Create target column.
    df[TARGET_NAME] = np.where((df.helpful_ratings / df.total_ratings) > TARGET_THRESHOLD, 1, 0).astype(int)

    # Delete columns we don't need anymore.
    df.drop(columns=["helpful", 'helpful_ratings', 'total_ratings'], inplace=True)

    print("Data preprocessing finished!")

    return df

[ ]:

reviews_df = download_data()
reviews_df = preprocess_data(reviews_df)

Train-test split¶

[6]:

X_train, X_test, y_train, y_test = train_test_split(reviews_df[["reviewText"]], reviews_df[TARGET_NAME],
                                                    test_size=TEST_RATIO, random_state=RANDOM_SEED,
                                                    stratify=reviews_df[TARGET_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_NAME,  # Ground truth variable.
    name="reviews",  # Optional.
)

Model building¶

Define preprocessing pipeline¶

[8]:

def remove_punctuation(x):
    """Remove punctuation from input string."""
    x = x.reviewText.apply(lambda row: row.translate(str.maketrans('', '', string.punctuation)))
    return x


preprocessor = Pipeline(steps=[
    ("punctuation", FunctionTransformer(remove_punctuation)),
    ("vectorizer", TfidfVectorizer(stop_words='english', min_df=0.01))
])

Build estimator¶

[ ]:

pipeline = Pipeline(steps=[
    ("preprocessor", preprocessor),
    ("estimator", LogisticRegression(random_state=RANDOM_SEED, class_weight="balanced"))
])

pipeline.fit(X_train, y_train)

# ROC-AUC score.
train_metric = roc_auc_score(y_train, pipeline.predict_proba(X_train)[:, 1])
test_metric = roc_auc_score(y_test, pipeline.predict_proba(X_test)[:, 1])
print(f"Train ROC-AUC score: {train_metric:.2f}")
print(f"Test ROC-AUC score: {test_metric:.2f}")

# Balanced accuracy to account for imbalanced targets.
b_acc_train = balanced_accuracy_score(y_train, pipeline.predict(X_train))
b_acc_test = balanced_accuracy_score(y_test, pipeline.predict(X_test))
print(f"Train balanced accuracy: {b_acc_train:.2f}")
print(f"Test balanced accuracy: {b_acc_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.

[ ]:

# Wrap prediction function
def prediction_function(df):
    return pipeline.predict_proba(df)


giskard_model = Model(
    model=prediction_function,
    # 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="review_helpfulness_predictor",  # Optional.
    classification_labels=[0, 1],  # Their order MUST be identical to the prediction_function's output order.
    feature_names=["reviewText"],  # Default: all columns of your dataset.
)

# Validate wrapped model.
wrapped_predict = giskard_model.predict(giskard_dataset).raw[:, 1]
wrapped_test_metric = roc_auc_score(y_test, wrapped_predict)

print(f"Wrapped Test ROC-AUC 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)

[12]:

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.

[13]:

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

2024-05-29 11:31:46,497 pid:47376 MainThread giskard.datasets.base INFO     Casting dataframe columns from {'reviewText': 'object'} to {'reviewText': 'object'}
2024-05-29 11:31:46,501 pid:47376 MainThread giskard.utils.logging_utils INFO     Predicted dataset with shape (9587, 2) executed in 0:00:00.015202
2024-05-29 11:31:47,278 pid:47376 MainThread giskard.datasets.base INFO     Casting dataframe columns from {'reviewText': 'object'} to {'reviewText': 'object'}
2024-05-29 11:31:47,490 pid:47376 MainThread giskard.utils.logging_utils INFO     Predicted dataset with shape (9587, 2) executed in 0:00:00.246625
2024-05-29 11:31:47,499 pid:47376 MainThread giskard.utils.logging_utils INFO     Perturb and predict data executed in 0:00:01.872730
2024-05-29 11:31:47,500 pid:47376 MainThread giskard.utils.logging_utils INFO     Compare and predict the data executed in 0:00:00.000723
Executed 'Invariance to “Add typos”' with arguments {'model': <giskard.models.function.PredictionFunctionModel object at 0x107c5e110>, 'dataset': <giskard.datasets.base.Dataset object at 0x1634696c0>, 'transformation_function': <giskard.scanner.robustness.text_transformations.TextTypoTransformation object at 0x163469e70>, 'threshold': 0.95, 'output_sensitivity': 0.05}:
               Test failed
               Metric: 0.9
                - [INFO] 9515 rows were perturbed

2024-05-29 11:31:47,559 pid:47376 MainThread giskard.datasets.base INFO     Casting dataframe columns from {'reviewText': 'object'} to {'reviewText': 'object'}
2024-05-29 11:31:47,560 pid:47376 MainThread giskard.utils.logging_utils INFO     Predicted dataset with shape (1554, 2) executed in 0:00:00.013542
Executed 'Overconfidence on data slice “`reviewText` contains "don"”' with arguments {'model': <giskard.models.function.PredictionFunctionModel object at 0x107c5e110>, 'dataset': <giskard.datasets.base.Dataset object at 0x1634696c0>, 'slicing_function': <giskard.slicing.slice.QueryBasedSliceFunction object at 0x339cea860>, 'threshold': 0.20769479469770452, 'p_threshold': 0.5}:
               Test failed
               Metric: 0.27


2024-05-29 11:31:47,582 pid:47376 MainThread giskard.datasets.base INFO     Casting dataframe columns from {'reviewText': 'object'} to {'reviewText': 'object'}
2024-05-29 11:31:47,584 pid:47376 MainThread giskard.utils.logging_utils INFO     Predicted dataset with shape (4436, 2) executed in 0:00:00.016746
Executed 'Overconfidence on data slice “`text_length(reviewText)` < 174.500”' with arguments {'model': <giskard.models.function.PredictionFunctionModel object at 0x107c5e110>, 'dataset': <giskard.datasets.base.Dataset object at 0x1634696c0>, 'slicing_function': <giskard.slicing.text_slicer.MetadataSliceFunction object at 0x3a11fe1d0>, 'threshold': 0.20769479469770452, 'p_threshold': 0.5}:
               Test failed
               Metric: 0.21


2024-05-29 11:31:47,641 pid:47376 MainThread giskard.datasets.base INFO     Casting dataframe columns from {'reviewText': 'object'} to {'reviewText': 'object'}
2024-05-29 11:31:47,642 pid:47376 MainThread giskard.utils.logging_utils INFO     Predicted dataset with shape (734, 2) executed in 0:00:00.008658
Executed 'Underconfidence on data slice “`reviewText` contains "way"”' with arguments {'model': <giskard.models.function.PredictionFunctionModel object at 0x107c5e110>, 'dataset': <giskard.datasets.base.Dataset object at 0x1634696c0>, 'slicing_function': <giskard.slicing.slice.QueryBasedSliceFunction object at 0x33bcabd60>, 'threshold': 0.03912589965578388, 'p_threshold': 0.95}:
               Test failed
               Metric: 0.05


2024-05-29 11:31:47,698 pid:47376 MainThread giskard.datasets.base INFO     Casting dataframe columns from {'reviewText': 'object'} to {'reviewText': 'object'}
2024-05-29 11:31:47,699 pid:47376 MainThread giskard.utils.logging_utils INFO     Predicted dataset with shape (707, 2) executed in 0:00:00.008718
Executed 'Underconfidence on data slice “`reviewText` contains "better"”' with arguments {'model': <giskard.models.function.PredictionFunctionModel object at 0x107c5e110>, 'dataset': <giskard.datasets.base.Dataset object at 0x1634696c0>, 'slicing_function': <giskard.slicing.slice.QueryBasedSliceFunction object at 0x33b84efe0>, 'threshold': 0.03912589965578388, 'p_threshold': 0.95}:
               Test failed
               Metric: 0.04


2024-05-29 11:31:47,756 pid:47376 MainThread giskard.datasets.base INFO     Casting dataframe columns from {'reviewText': 'object'} to {'reviewText': 'object'}
2024-05-29 11:31:47,757 pid:47376 MainThread giskard.utils.logging_utils INFO     Predicted dataset with shape (849, 2) executed in 0:00:00.009271
Executed 'Underconfidence on data slice “`reviewText` contains "want"”' with arguments {'model': <giskard.models.function.PredictionFunctionModel object at 0x107c5e110>, 'dataset': <giskard.datasets.base.Dataset object at 0x1634696c0>, 'slicing_function': <giskard.slicing.slice.QueryBasedSliceFunction object at 0x3380c1ea0>, 'threshold': 0.03912589965578388, 'p_threshold': 0.95}:
               Test failed
               Metric: 0.04


2024-05-29 11:31:47,813 pid:47376 MainThread giskard.datasets.base INFO     Casting dataframe columns from {'reviewText': 'object'} to {'reviewText': 'object'}
2024-05-29 11:31:47,814 pid:47376 MainThread giskard.utils.logging_utils INFO     Predicted dataset with shape (733, 2) executed in 0:00:00.007101
Executed 'Underconfidence on data slice “`reviewText` contains "got"”' with arguments {'model': <giskard.models.function.PredictionFunctionModel object at 0x107c5e110>, 'dataset': <giskard.datasets.base.Dataset object at 0x1634696c0>, 'slicing_function': <giskard.slicing.slice.QueryBasedSliceFunction object at 0x3aaa19ed0>, 'threshold': 0.03912589965578388, 'p_threshold': 0.95}:
               Test failed
               Metric: 0.04


2024-05-29 11:31:47,868 pid:47376 MainThread giskard.datasets.base INFO     Casting dataframe columns from {'reviewText': 'object'} to {'reviewText': 'object'}
2024-05-29 11:31:47,869 pid:47376 MainThread giskard.utils.logging_utils INFO     Predicted dataset with shape (538, 2) executed in 0:00:00.006875
Executed 'Recall on data slice “`reviewText` contains "download"”' with arguments {'model': <giskard.models.function.PredictionFunctionModel object at 0x107c5e110>, 'dataset': <giskard.datasets.base.Dataset object at 0x1634696c0>, 'slicing_function': <giskard.slicing.slice.QueryBasedSliceFunction object at 0x339c7beb0>, 'threshold': 0.6419472738166567}:
               Test failed
               Metric: 0.59


2024-05-29 11:31:47,872 pid:47376 MainThread giskard.core.suite INFO     Executed test suite 'My first test suite'
2024-05-29 11:31:47,873 pid:47376 MainThread giskard.core.suite INFO     result: failed
2024-05-29 11:31:47,873 pid:47376 MainThread giskard.core.suite INFO     Invariance to “Add typos” ({'model': <giskard.models.function.PredictionFunctionModel object at 0x107c5e110>, 'dataset': <giskard.datasets.base.Dataset object at 0x1634696c0>, 'transformation_function': <giskard.scanner.robustness.text_transformations.TextTypoTransformation object at 0x163469e70>, 'threshold': 0.95, 'output_sensitivity': 0.05}): {failed, metric=0.9038360483447189}
2024-05-29 11:31:47,873 pid:47376 MainThread giskard.core.suite INFO     Overconfidence on data slice “`reviewText` contains "don"” ({'model': <giskard.models.function.PredictionFunctionModel object at 0x107c5e110>, 'dataset': <giskard.datasets.base.Dataset object at 0x1634696c0>, 'slicing_function': <giskard.slicing.slice.QueryBasedSliceFunction object at 0x339cea860>, 'threshold': 0.20769479469770452, 'p_threshold': 0.5}): {failed, metric=0.26622296173044924}
2024-05-29 11:31:47,873 pid:47376 MainThread giskard.core.suite INFO     Overconfidence on data slice “`text_length(reviewText)` < 174.500” ({'model': <giskard.models.function.PredictionFunctionModel object at 0x107c5e110>, 'dataset': <giskard.datasets.base.Dataset object at 0x1634696c0>, 'slicing_function': <giskard.slicing.text_slicer.MetadataSliceFunction object at 0x3a11fe1d0>, 'threshold': 0.20769479469770452, 'p_threshold': 0.5}): {failed, metric=0.21353196772191185}
2024-05-29 11:31:47,874 pid:47376 MainThread giskard.core.suite INFO     Underconfidence on data slice “`reviewText` contains "way"” ({'model': <giskard.models.function.PredictionFunctionModel object at 0x107c5e110>, 'dataset': <giskard.datasets.base.Dataset object at 0x1634696c0>, 'slicing_function': <giskard.slicing.slice.QueryBasedSliceFunction object at 0x33bcabd60>, 'threshold': 0.03912589965578388, 'p_threshold': 0.95}): {failed, metric=0.04904632152588556}
2024-05-29 11:31:47,874 pid:47376 MainThread giskard.core.suite INFO     Underconfidence on data slice “`reviewText` contains "better"” ({'model': <giskard.models.function.PredictionFunctionModel object at 0x107c5e110>, 'dataset': <giskard.datasets.base.Dataset object at 0x1634696c0>, 'slicing_function': <giskard.slicing.slice.QueryBasedSliceFunction object at 0x33b84efe0>, 'threshold': 0.03912589965578388, 'p_threshold': 0.95}): {failed, metric=0.042432814710042434}
2024-05-29 11:31:47,874 pid:47376 MainThread giskard.core.suite INFO     Underconfidence on data slice “`reviewText` contains "want"” ({'model': <giskard.models.function.PredictionFunctionModel object at 0x107c5e110>, 'dataset': <giskard.datasets.base.Dataset object at 0x1634696c0>, 'slicing_function': <giskard.slicing.slice.QueryBasedSliceFunction object at 0x3380c1ea0>, 'threshold': 0.03912589965578388, 'p_threshold': 0.95}): {failed, metric=0.04240282685512368}
2024-05-29 11:31:47,874 pid:47376 MainThread giskard.core.suite INFO     Underconfidence on data slice “`reviewText` contains "got"” ({'model': <giskard.models.function.PredictionFunctionModel object at 0x107c5e110>, 'dataset': <giskard.datasets.base.Dataset object at 0x1634696c0>, 'slicing_function': <giskard.slicing.slice.QueryBasedSliceFunction object at 0x3aaa19ed0>, 'threshold': 0.03912589965578388, 'p_threshold': 0.95}): {failed, metric=0.03956343792633015}
2024-05-29 11:31:47,875 pid:47376 MainThread giskard.core.suite INFO     Recall on data slice “`reviewText` contains "download"” ({'model': <giskard.models.function.PredictionFunctionModel object at 0x107c5e110>, 'dataset': <giskard.datasets.base.Dataset object at 0x1634696c0>, 'slicing_function': <giskard.slicing.slice.QueryBasedSliceFunction object at 0x339c7beb0>, 'threshold': 0.6419472738166567}): {failed, metric=0.5929203539823009}

[13]:

Test suite failed.

Test Invariance to “Add typos”

Measured Metric = 0.90384 Failed

model review_helpfulness_predictor

dataset reviews

transformation_function Add typos

threshold 0.95

output_sensitivity 0.05

Test Overconfidence on data slice “`reviewText` contains "don"”

Measured Metric = 0.26622 Failed

model review_helpfulness_predictor

dataset reviews

slicing_function `reviewText` contains "don"

threshold 0.20769479469770452

p_threshold 0.5

Test Overconfidence on data slice “`text_length(reviewText)` < 174.500”

Measured Metric = 0.21353 Failed

model review_helpfulness_predictor

dataset reviews

slicing_function `text_length(reviewText)` < 174.500

threshold 0.20769479469770452

p_threshold 0.5

Test Underconfidence on data slice “`reviewText` contains "way"”

Measured Metric = 0.04905 Failed

model review_helpfulness_predictor

dataset reviews

slicing_function `reviewText` contains "way"

threshold 0.03912589965578388

p_threshold 0.95

Test Underconfidence on data slice “`reviewText` contains "better"”

Measured Metric = 0.04243 Failed

model review_helpfulness_predictor

dataset reviews

slicing_function `reviewText` contains "better"

threshold 0.03912589965578388

p_threshold 0.95

Test Underconfidence on data slice “`reviewText` contains "want"”

Measured Metric = 0.0424 Failed

model review_helpfulness_predictor

dataset reviews

slicing_function `reviewText` contains "want"

threshold 0.03912589965578388

p_threshold 0.95

Test Underconfidence on data slice “`reviewText` contains "got"”

Measured Metric = 0.03956 Failed

model review_helpfulness_predictor

dataset reviews

slicing_function `reviewText` contains "got"

threshold 0.03912589965578388

p_threshold 0.95

Test Recall on data slice “`reviewText` contains "download"”

Measured Metric = 0.59292 Failed

model review_helpfulness_predictor

dataset reviews

slicing_function `reviewText` contains "download"

threshold 0.6419472738166567

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()