Skip to content

Split train and test set in fraud detection fixtures #1235

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 3 commits into from
Jul 7, 2023
Merged

Split train and test set in fraud detection fixtures #1235

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
53baf51
Split train and test set in fraud detection fixtures
mattbit Jul 6, 2023
25d8fb9
Merge branch 'main' into task/fix-fraud-detector-fixtures
mattbit Jul 6, 2023
06e7716
Merge branch 'main' into task/fix-fraud-detector-fixtures
mattbit Jul 7, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
28 changes: 20 additions & 8 deletions python-client/tests/fixtures/fraud_detection__binary_classification.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,9 +1,10 @@
import os
from pathlib import Path

import pytest
import pandas as pd
import pytest
from pandas.api.types import union_categoricals
from sklearn.model_selection import train_test_split

from giskard import Dataset, Model
from tests.url_utils import fetch_from_ftp
Expand Down Expand Up @@ -135,25 +136,36 @@ def preprocess_dataset(train_set, test_set):
# Remove useless columns.
united.drop("TransactionDT", axis=1, inplace=True)

return united
# Split in train/test sets
train_set, test_set = train_test_split(united, test_size=0.5, random_state=41)

return train_set, test_set


@pytest.fixture()
def fraud_detection_data() -> Dataset:
# Download dataset.
raw_data = preprocess_dataset(*read_dataset())
_, test_set = preprocess_dataset(*read_dataset())
wrapped_dataset = Dataset(
test_set, name="fraud_detection_adversarial_dataset", target=TARGET_COLUMN, cat_columns=CATEGORICALS
)
return wrapped_dataset


@pytest.fixture()
def fraud_detection_train_data() -> Dataset:
train_set, _ = preprocess_dataset(*read_dataset())
wrapped_dataset = Dataset(
raw_data, name="fraud_detection_adversarial_dataset", target=TARGET_COLUMN, cat_columns=CATEGORICALS
train_set, name="fraud_detection_adversarial_dataset", target=TARGET_COLUMN, cat_columns=CATEGORICALS
)
return wrapped_dataset


@pytest.fixture()
def fraud_detection_model(fraud_detection_data: Dataset) -> Model:
def fraud_detection_model(fraud_detection_train_data: Dataset) -> Model:
from lightgbm import LGBMClassifier

x = fraud_detection_data.df.drop(TARGET_COLUMN, axis=1)
y = fraud_detection_data.df[TARGET_COLUMN]
x = fraud_detection_train_data.df.drop(TARGET_COLUMN, axis=1)
y = fraud_detection_train_data.df[TARGET_COLUMN]

estimator = LGBMClassifier()
estimator.fit(x, y)
Expand Down