Skip to content
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

Jump to bottom

added support to where method and tests #1

Open
wants to merge 4 commits into
base: master
Choose a base branch
from
Open

added support to where method and tests #1

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
f32db88
added support to where method and tests
Nov 16, 2023
78e8637
corrected method
Nov 22, 2023
70e9dbf
added tests and changed flow structure
Dec 5, 2023
5f1a81e
corrected failing test
Dec 5, 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
8 changes: 8 additions & 0 deletions pydeequ/checks.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -116,6 +116,14 @@ def addConstraint(self, constraint):
self.constraints.append(constraint)
self._Check = constraint._Check

def where(self, filter: str):
test = self._Check.getClass()
if self._Check.getClass().toString().endswith("CheckWithLastConstraintFilterable"):
choyrim marked this conversation as resolved.
Show resolved Hide resolved
self._Check = self._Check.where(filter)
else:
raise TypeError(f"Expected CheckWithLastConstraintFilterable class, not {self._Check.getClass()}")
return self

def addFilterableContstraint(self, creationFunc):
"""Adds a constraint that can subsequently be replaced with a filtered version
:param creationFunc:
Expand Down
30 changes: 30 additions & 0 deletions tests/test_checks.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -467,6 +467,12 @@ def hasNumberOfDistinctValues(self, column, assertion, binningUdf, maxBins, hint
df = VerificationResult.checkResultsAsDataFrame(self.spark, result)
return df.select("constraint_status").collect()

def where(self, assertion, filter, hint=None):
check = Check(self.spark, CheckLevel.Warning, "test where")
result = VerificationSuite(self.spark).onData(self.df).addCheck(check.hasSize(assertion, hint).where(filter)).run()
df = VerificationResult.checkResultsAsDataFrame(self.spark, result)
return df.select("constraint_status").collect()

def test_hasSize(self):
self.assertEqual(self.hasSize(lambda x: x == 3.0), [Row(constraint_status="Success")])
self.assertEqual(
Expand Down Expand Up @@ -1245,6 +1251,30 @@ def test_fail_isGreaterThanOrEqualTo(self):
)
self.assertEqual(self.isGreaterThanOrEqualTo("h", "f", lambda x: x == 1), [Row(constraint_status="Success")])

def test_where(self):
self.assertEqual(self.where(lambda x: x == 2.0, "boolean='true'", "column 'boolean' has two values true"),
[Row(constraint_status="Success")])
self.assertEqual(
self.where(lambda x: x == 3.0, "d=5", "column 'd' has three values 3"),
[Row(constraint_status="Success")],
)
self.assertEqual(
self.where(lambda x: x == 2.0, "ssn='000-00-0000'", "column 'ssn' has one value 000-00-0000"),
[Row(constraint_status="Failure")],
)

@pytest.mark.xfail(reason="@unittest.expectedFailure")
def test_fail_where(self):
self.assertEqual(self.where(lambda x: x == 2.0, "boolean='false'", "column 'boolean' has one value false"),
[Row(constraint_status="Success")])
self.assertEqual(
self.where(lambda x: x == 3.0, "a='bar'", "column 'a' has one value 'bar'"),
[Row(constraint_status="Success")],
)
self.assertEqual(
self.where(lambda x: x == 1.0, "f=1", "column 'f' has one value 1"),
[Row(constraint_status="Failure")],
)
# def test_hasNumberOfDistinctValues(self):
# #Todo: test binningUDf
# self.assertEqual(self.hasNumberOfDistinctValues('b', lambda x: x == 3, None, 3, "Column B has 3 distinct values"),
Expand Down