upgini 1.1.237a1__tar.gz → 1.1.237a2__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- {upgini-1.1.237a1/src/upgini.egg-info → upgini-1.1.237a2}/PKG-INFO +1 -1
- {upgini-1.1.237a1 → upgini-1.1.237a2}/setup.py +1 -1
- {upgini-1.1.237a1 → upgini-1.1.237a2}/src/upgini/utils/deduplicate_utils.py +2 -1
- {upgini-1.1.237a1 → upgini-1.1.237a2/src/upgini.egg-info}/PKG-INFO +1 -1
- {upgini-1.1.237a1 → upgini-1.1.237a2}/LICENSE +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/README.md +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/pyproject.toml +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/setup.cfg +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/src/upgini/__init__.py +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/src/upgini/ads.py +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/src/upgini/ads_management/__init__.py +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/src/upgini/ads_management/ads_manager.py +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/src/upgini/autofe/__init__.py +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/src/upgini/autofe/all_operands.py +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/src/upgini/autofe/binary.py +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/src/upgini/autofe/feature.py +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/src/upgini/autofe/groupby.py +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/src/upgini/autofe/operand.py +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/src/upgini/autofe/unary.py +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/src/upgini/autofe/vector.py +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/src/upgini/data_source/__init__.py +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/src/upgini/data_source/data_source_publisher.py +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/src/upgini/dataset.py +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/src/upgini/errors.py +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/src/upgini/features_enricher.py +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/src/upgini/fingerprint.js +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/src/upgini/http.py +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/src/upgini/mdc/__init__.py +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/src/upgini/mdc/context.py +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/src/upgini/metadata.py +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/src/upgini/metrics.py +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/src/upgini/normalizer/__init__.py +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/src/upgini/normalizer/phone_normalizer.py +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/src/upgini/resource_bundle/__init__.py +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/src/upgini/resource_bundle/exceptions.py +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/src/upgini/resource_bundle/strings.properties +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/src/upgini/sampler/__init__.py +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/src/upgini/sampler/base.py +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/src/upgini/sampler/random_under_sampler.py +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/src/upgini/sampler/utils.py +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/src/upgini/search_task.py +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/src/upgini/spinner.py +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/src/upgini/utils/__init__.py +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/src/upgini/utils/base_search_key_detector.py +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/src/upgini/utils/blocked_time_series.py +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/src/upgini/utils/country_utils.py +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/src/upgini/utils/custom_loss_utils.py +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/src/upgini/utils/cv_utils.py +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/src/upgini/utils/datetime_utils.py +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/src/upgini/utils/display_utils.py +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/src/upgini/utils/email_utils.py +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/src/upgini/utils/fallback_progress_bar.py +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/src/upgini/utils/features_validator.py +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/src/upgini/utils/format.py +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/src/upgini/utils/ip_utils.py +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/src/upgini/utils/phone_utils.py +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/src/upgini/utils/postal_code_utils.py +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/src/upgini/utils/progress_bar.py +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/src/upgini/utils/sklearn_ext.py +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/src/upgini/utils/target_utils.py +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/src/upgini/utils/track_info.py +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/src/upgini/utils/warning_counter.py +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/src/upgini/version_validator.py +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/src/upgini.egg-info/SOURCES.txt +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/src/upgini.egg-info/dependency_links.txt +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/src/upgini.egg-info/requires.txt +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/src/upgini.egg-info/top_level.txt +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/tests/test_binary_dataset.py +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/tests/test_blocked_time_series.py +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/tests/test_categorical_dataset.py +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/tests/test_continuous_dataset.py +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/tests/test_country_utils.py +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/tests/test_custom_loss_utils.py +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/tests/test_datetime_utils.py +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/tests/test_email_utils.py +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/tests/test_etalon_validation.py +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/tests/test_features_enricher.py +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/tests/test_metrics.py +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/tests/test_phone_utils.py +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/tests/test_postal_code_utils.py +0 -0
- {upgini-1.1.237a1 → upgini-1.1.237a2}/tests/test_widget.py +0 -0
|
@@ -49,10 +49,11 @@ def remove_fintech_duplicates(df: pd.DataFrame,
|
|
|
49
49
|
return df
|
|
50
50
|
|
|
51
51
|
def has_diff_target_within_60_days(rows):
|
|
52
|
-
rows = DateTimeSearchKeyConverter(date_col).convert(rows)
|
|
53
52
|
rows = rows.sort_values(by=date_col)
|
|
54
53
|
return len(rows[rows[TARGET].ne(rows[TARGET].shift()) & (rows[date_col].diff() < 60 * 24 * 60 * 60 * 1000)]) > 0
|
|
55
54
|
|
|
55
|
+
df = DateTimeSearchKeyConverter(date_col).convert(df)
|
|
56
|
+
grouped_by_personal_cols = df.groupby(personal_cols, group_keys=False)
|
|
56
57
|
rows_with_diff_target = grouped_by_personal_cols.filter(has_diff_target_within_60_days)
|
|
57
58
|
if len(rows_with_diff_target) > 0:
|
|
58
59
|
perc = len(rows_with_diff_target) * 100 / len(df)
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|