jacob-mathison/doczyai-pipelines
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Activity

few enhancement in the output needed

Browse Source
This commit is contained in:
Rahul Ailaboina
2026-02-03 13:50:06 -06:00
parent 8fbe64e42e
commit 1865e75c47
3 changed files with 27 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/parent_child/pipeline.py
+5 -1
View File
@@ -808,7 +808,11 @@ def assign_child_ranks(df, grouper_col="grouping_key"):
try:
amendment_val = int(float(raw))
except (ValueError, TypeError):
amendment_val = raw
raw_str = str(raw).strip()
if len(raw_str) == 1 and raw_str.isalpha():
amendment_val = ord(raw_str.upper()) - ord("A") + 1
else:
amendment_val = raw
rank_val = f"{parent_rank_str}.{amendment_val}.{i}"
children.loc[idx, "child_rank"] = rank_val
src/parent_child/qc.py
+4 -1
View File
@@ -2032,7 +2032,10 @@ class ParentChildEngine:
try:
return str(int(float(x)))
except (ValueError, TypeError):
return str(x).strip()
raw_str = str(x).strip()
if len(raw_str) == 1 and raw_str.isalpha():
return str(ord(raw_str.upper()) - ord("A") + 1)
return raw_str
return "0"
def prepare_output(self, df: pd.DataFrame) -> pd.DataFrame:
src/tests/test_parent_child.py
+18 -18
View File
@@ -776,7 +776,7 @@ class TestAssignChildRanksWithAmendmentNum(unittest.TestCase):
self.assertEqual(parent_rank, "1")
def test_children_use_character_amendment_num_in_rank(self):
"""Children with character amendment number (A, B, C) use it in rank."""
"""Children with character amendment number (A, B, C) convert to numeric (A=1, B=2, etc.)."""
df = pd.DataFrame(
{
"grouping_key": ["TIN:123", "TIN:123", "TIN:123"],
@@ -791,11 +791,11 @@ class TestAssignChildRanksWithAmendmentNum(unittest.TestCase):
child_df = result[result["parent"] == False].sort_values("fixed_effective_date")
ranks = child_df["child_rank"].tolist()
self.assertEqual(ranks[0], "1.A.1") # Amendment A, sequence 1
self.assertEqual(ranks[1], "1.B.2") # Amendment B, sequence 2
self.assertEqual(ranks[0], "1.1.1") # Amendment A=1, sequence 1
self.assertEqual(ranks[1], "1.2.2") # Amendment B=2, sequence 2
def test_orphans_use_character_amendment_num_in_rank(self):
"""Orphans with character amendment number get 0.amendment.seq format."""
"""Orphans with character amendment number convert to numeric (A=1, C=3)."""
df = pd.DataFrame(
{
"grouping_key": ["TIN:123", "TIN:123"],
@@ -808,8 +808,8 @@ class TestAssignChildRanksWithAmendmentNum(unittest.TestCase):
result = assign_child_ranks(df)
ranks = result["child_rank"].tolist()
self.assertEqual(ranks[0], "0.A.1")
self.assertEqual(ranks[1], "0.C.2")
self.assertEqual(ranks[0], "0.1.1") # A=1
self.assertEqual(ranks[1], "0.3.2") # C=3
def test_mixed_numeric_and_character_amendment_nums(self):
"""Mix of numeric and character amendment numbers in same group."""
@@ -833,7 +833,7 @@ class TestAssignChildRanksWithAmendmentNum(unittest.TestCase):
child_df = result[result["parent"] == False].sort_values("fixed_effective_date")
ranks = child_df["child_rank"].tolist()
self.assertEqual(ranks[0], "1.3.1") # numeric 3
self.assertEqual(ranks[1], "1.A.2") # character A
self.assertEqual(ranks[1], "1.1.2") # character A=1
self.assertEqual(ranks[2], "1.5.3") # numeric 5
@@ -962,7 +962,7 @@ class TestComputeRanksWithAmendmentNum(unittest.TestCase):
)
def test_child_rank_dest_with_character_amendment_num(self):
"""child_rank_dest handles character amendment values (A, B, C)."""
"""child_rank_dest converts character amendment values (A=1, B=2, C=3)."""
engine = self._make_engine()
df = self._make_base_df(
extra_cols={
@@ -971,13 +971,13 @@ class TestComputeRanksWithAmendmentNum(unittest.TestCase):
)
result = engine.compute_ranks(df)
# Index 2 (eff 2024-02-01, amendment=A) comes first -> seq 1
# Index 1 (eff 2024-03-01, amendment=B) comes second -> seq 2
self.assertEqual(result.at[2, "child_rank_dest"], "1.A.1")
self.assertEqual(result.at[1, "child_rank_dest"], "1.B.2")
# Index 2 (eff 2024-02-01, amendment=A=1) comes first -> seq 1
# Index 1 (eff 2024-03-01, amendment=B=2) comes second -> seq 2
self.assertEqual(result.at[2, "child_rank_dest"], "1.1.1")
self.assertEqual(result.at[1, "child_rank_dest"], "1.2.2")
def test_orphan_rank_dest_with_character_amendment_num(self):
"""orphan_rank_dest handles character amendment values."""
"""orphan_rank_dest converts character amendment values (A=1)."""
engine = self._make_engine()
df = self._make_base_df(
extra_cols={
@@ -986,7 +986,7 @@ class TestComputeRanksWithAmendmentNum(unittest.TestCase):
)
result = engine.compute_ranks(df)
self.assertEqual(result.at[3, "orphan_rank_dest"], "0.A.1")
self.assertEqual(result.at[3, "orphan_rank_dest"], "0.1.1") # A=1
def test_child_rank_dest_with_mixed_numeric_and_character_amendment(self):
"""child_rank_dest handles mix of numeric and character amendment values."""
@@ -999,11 +999,11 @@ class TestComputeRanksWithAmendmentNum(unittest.TestCase):
result = engine.compute_ranks(df)
# Index 2 (eff 2024-02-01, amendment=3) -> seq 1
# Index 1 (eff 2024-03-01, amendment=A) -> seq 2
# Index 1 (eff 2024-03-01, amendment=A=1) -> seq 2
self.assertEqual(result.at[2, "child_rank_dest"], "1.3.1")
self.assertEqual(result.at[1, "child_rank_dest"], "1.A.2")
# Index 3 is orphan with amendment=B
self.assertEqual(result.at[3, "orphan_rank_dest"], "0.B.1")
self.assertEqual(result.at[1, "child_rank_dest"], "1.1.2") # A=1
# Index 3 is orphan with amendment=B=2
self.assertEqual(result.at[3, "orphan_rank_dest"], "0.2.1") # B=2
if __name__ == "__main__":