mirror of
https://github.com/open-metadata/OpenMetadata.git
synced 2025-12-04 19:44:58 +00:00
dddec06143
* Initial implementation for Dimensionality on Data Quality Tests * Fix ColumnValuesToBeUnique and create TestCaseResult API * Refactor dimension result * Initial E2E Implementation without Impact Score * Dimensionality Thin Slice * Update generated TypeScript types * Update generated TypeScript types * Removed useless method to use the one we already had * Fix Pandas Dimensionality checks * Remove useless comments * Implement PR comments, fix Tests * Improve the code a bit * Fix imports * Implement Dimensionality for ColumnMeanToBeBetween * Removed useless comments and improved minor things * Implement UnitTests * Fixes * Moved import pandas to type checking * Fix Min/Max being optional * Fix Unittests * small fixes * Fix Unittests * Fix Issue with counting total rows on mean * Improve code * Fix Merge * Removed unused type * Refactor to reduce code repetition and complexity * Fix conflict * Rename method * Refactor some metrics * Implement Dimensionality to ColumnLengthToBeBetween * Implement Dimensionality for ColumnMedianToBeBetween in Pandas * Implement Median Dimensionality for SQL * Add database tests * Fix median metric * Implement Dimensionality SumToBeBetween * Implement dimensionality for Column Values not In Set * Implement Dimensionality for ColumnValuestoMatchRegex and ColumnValuesToNotMatchRegex * Implement NotNull and MissingCount dimensionality * Implement columnValuesToBeBetween dimensionality * Fix test * Implement Pandas Dimensionality for ColumnValueStdDevToBeBetween * Implement Dimensionality for ColumnValuesStdDevToBeBetween * Fixed tests due to sqlite now supporting stddev --------- Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
77 lines
2.3 KiB
Python
77 lines
2.3 KiB
Python
import math
|
|
|
|
import sqlalchemy as sqa
|
|
from pytest import fixture
|
|
|
|
|
|
@fixture(scope="session", autouse=True)
|
|
def register_sqlite_math_functions():
|
|
"""
|
|
Register custom math functions for SQLite used in unit tests.
|
|
|
|
SQLite doesn't have built-in SQRT function, so we register Python's math.sqrt
|
|
to make it available for all SQLite connections in tests.
|
|
|
|
This runs automatically for all unit tests (autouse=True) and only once
|
|
per test session (scope="session").
|
|
"""
|
|
|
|
def safe_sqrt(x):
|
|
"""
|
|
Safe square root that handles floating-point precision issues.
|
|
|
|
When computing variance using AVG(x*x) - AVG(x)*AVG(x), floating-point
|
|
precision can result in slightly negative values (e.g., -1e-15) when
|
|
the true variance is zero. This function treats near-zero negative
|
|
values as zero, matching the behavior in stddev.py:254-256.
|
|
"""
|
|
if x is None:
|
|
return None
|
|
if x < 0:
|
|
if abs(x) < 1e-10:
|
|
return 0.0
|
|
raise ValueError(f"Cannot compute square root of negative number: {x}")
|
|
return math.sqrt(x)
|
|
|
|
@sqa.event.listens_for(sqa.engine.Engine, "connect")
|
|
def register_functions(dbapi_conn, connection_record):
|
|
if "sqlite" in str(type(dbapi_conn)):
|
|
dbapi_conn.create_function("SQRT", 1, safe_sqrt)
|
|
|
|
yield
|
|
|
|
# Clean up event listener after tests
|
|
sqa.event.remove(sqa.engine.Engine, "connect", register_functions)
|
|
|
|
|
|
def pytest_pycollect_makeitem(collector, name, obj):
|
|
try:
|
|
if obj.__name__ in ("TestSuiteSource", "TestSuiteInterfaceFactory"):
|
|
return []
|
|
if obj.__base__.__name__ in ("BaseModel", "Enum"):
|
|
return []
|
|
except AttributeError:
|
|
pass
|
|
|
|
|
|
def pytest_collection_modifyitems(session, config, items):
|
|
"""Reorder test items to ensure certain files run last."""
|
|
# List of test files that should run last
|
|
last_files = [
|
|
"test_dependency_injector.py",
|
|
# Add other files that should run last here
|
|
]
|
|
|
|
# Get all test items that should run last
|
|
last_items = []
|
|
other_items = []
|
|
|
|
for item in items:
|
|
if any(file in item.nodeid for file in last_files):
|
|
last_items.append(item)
|
|
else:
|
|
other_items.append(item)
|
|
|
|
# Reorder the items
|
|
items[:] = other_items + last_items
|