Skip to content

min max date #1825

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
SFJohnson24 merged 6 commits into from
Aug 19, 2026
Merged

min max date #1825

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
2ee2c0f
min max date
SFJohnson24 Aug 13, 2026
2eb5a8b
rework
SFJohnson24 Aug 13, 2026
cbc161c
update stale test
SFJohnson24 Aug 13, 2026
dc7ba52
fixes
SFJohnson24 Aug 13, 2026
4a3b5c3
blank guard
SFJohnson24 Aug 14, 2026
ca5db20
grouped NA protection
SFJohnson24 Aug 18, 2026
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
20 changes: 20 additions & 0 deletions cdisc_rules_engine/check_operators/helpers.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -334,6 +334,26 @@ def _truncate_by_precision(
)


def format_date_preserving_precision(original_str: str) -> str:
precision = detect_datetime_precision(original_str)
if precision is None:
return ""
dt = truncate_datetime_to_precision(original_str, precision)

if precision >= DatePrecision.second:
return dt.strftime("%Y-%m-%dT%H:%M:%S")
elif precision == DatePrecision.minute:
return dt.strftime("%Y-%m-%dT%H:%M")
elif precision == DatePrecision.hour:
return dt.strftime("%Y-%m-%dT%H")
elif precision == DatePrecision.day:
return dt.strftime("%Y-%m-%d")
elif precision == DatePrecision.month:
return dt.strftime("%Y-%m")
else: # year
return dt.strftime("%Y")


def _compare_with_inferred_precision(
operator_func,
target: str,
Expand Down
48 changes: 33 additions & 15 deletions cdisc_rules_engine/operations/max_date.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,26 +1,44 @@
import pandas as pd
from cdisc_rules_engine.operations.base_operation import BaseOperation
from cdisc_rules_engine.check_operators.helpers import format_date_preserving_precision


class MaxDate(BaseOperation):
def _execute_operation(self):
original = self.params.dataframe[self.params.target]
data = pd.to_datetime(original, format="ISO8601")

if not self.params.grouping:
data = pd.to_datetime(self.params.dataframe[self.params.target])
max_date = data.max()
if isinstance(max_date, pd._libs.tslibs.nattype.NaTType):
if data.isna().all():
result = ""
else:
result = max_date.isoformat()
max_idx = data.idxmax()
result = format_date_preserving_precision(original.loc[max_idx])
return pd.Series(result, index=self.evaluation_dataset.index)

grouping_cols = self.params.grouping
if isinstance(grouping_cols, str):
grouping_cols = [grouping_cols]

group_keys = [self.params.dataframe[col] for col in grouping_cols]
idx_of_max = data.groupby(group_keys).apply(
lambda s: s.idxmax() if s.notna().any() else pd.NA
)
max_dates = idx_of_max.apply(
lambda idx: (
""
if pd.isna(idx)
else format_date_preserving_precision(original.loc[idx])
)
)
if len(grouping_cols) == 1:
lookup_keys = self.evaluation_dataset[grouping_cols[0]]
else:
result = self.params.dataframe.groupby(
self.params.grouping, as_index=False, group_keys=False
).max()
if isinstance(result, pd.Series):
result = result.apply(lambda x: x.isoformat() if pd.notna(x) else "")
elif isinstance(result, pd.DataFrame):
for col in result.columns:
if pd.api.types.is_datetime64_any_dtype(result[col]):
result[col] = result[col].apply(
lambda x: x.isoformat() if pd.notna(x) else ""
)
lookup_keys = pd.Series(
list(zip(*[self.evaluation_dataset[c] for c in grouping_cols])),
index=self.evaluation_dataset.index,
)

result = lookup_keys.map(max_dates).fillna("")
result.index = self.evaluation_dataset.index
return result
41 changes: 34 additions & 7 deletions cdisc_rules_engine/operations/min_date.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,18 +1,45 @@
import pandas as pd
from cdisc_rules_engine.operations.base_operation import BaseOperation
from cdisc_rules_engine.check_operators.helpers import format_date_preserving_precision


class MinDate(BaseOperation):
def _execute_operation(self):
original = self.params.dataframe[self.params.target]
data = pd.to_datetime(original, format="ISO8601")

if not self.params.grouping:
data = pd.to_datetime(self.params.dataframe[self.params.target])
min_date = data.min()
if isinstance(min_date, pd._libs.tslibs.nattype.NaTType):
if data.isna().all():
result = ""
else:
result = min_date.isoformat()
min_idx = data.idxmin()
result = format_date_preserving_precision(original.loc[min_idx])
return pd.Series(result, index=self.evaluation_dataset.index)

grouping_cols = self.params.grouping
if isinstance(grouping_cols, str):
grouping_cols = [grouping_cols]

group_keys = [self.params.dataframe[col] for col in grouping_cols]
idx_of_min = data.groupby(group_keys).apply(
lambda s: s.idxmin() if s.notna().any() else pd.NA
)
min_dates = idx_of_min.apply(
lambda idx: (
""
if pd.isna(idx)
else format_date_preserving_precision(original.loc[idx])
)
)

if len(grouping_cols) == 1:
lookup_keys = self.evaluation_dataset[grouping_cols[0]]
else:
result = self.params.dataframe.groupby(
self.params.grouping, as_index=False
).min()
lookup_keys = pd.Series(
list(zip(*[self.evaluation_dataset[c] for c in grouping_cols])),
index=self.evaluation_dataset.index,
)

result = lookup_keys.map(min_dates).fillna("")
result.index = self.evaluation_dataset.index
return result
88 changes: 85 additions & 3 deletions tests/unit/test_operations/test_max_date.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,7 @@
from cdisc_rules_engine.models.dataset.pandas_dataset import PandasDataset
from cdisc_rules_engine.operations.max_date import MaxDate
from cdisc_rules_engine.models.operation_params import OperationParams
import pandas as pd
from cdisc_rules_engine.check_operators.helpers import format_date_preserving_precision
import pytest

from cdisc_rules_engine.services.cache.cache_service_factory import CacheServiceFactory
Expand All @@ -17,14 +17,14 @@
[
(
{"dates": ["2001-01-01", "", "2022-01-05"]},
pd.to_datetime("2022-01-05").isoformat(),
format_date_preserving_precision("2022-01-05"),
PandasDataset,
None,
),
({"dates": [None, None]}, "", PandasDataset, None),
(
{"dates": ["2001-01-01", "", "2022-01-05"]},
pd.to_datetime("2022-01-05").isoformat(),
format_date_preserving_precision("2022-01-05"),
DaskDataset,
None,
),
Expand Down Expand Up @@ -93,6 +93,88 @@
DaskDataset,
["USUBJID"],
),
(
{
"dates": [
"2025-10-10",
"2025-10-15",
"2025-12-02",
"2025-12-11",
"",
"",
],
"USUBJID": ["00002", "00002", "00003", "00003", "00004", "00004"],
},
PandasDataset.from_records(
[
{
"dates": "2025-10-10",
"USUBJID": "00002",
"operation_id": "2025-10-15",
},
{
"dates": "2025-10-15",
"USUBJID": "00002",
"operation_id": "2025-10-15",
},
{
"dates": "2025-12-02",
"USUBJID": "00003",
"operation_id": "2025-12-11",
},
{
"dates": "2025-12-11",
"USUBJID": "00003",
"operation_id": "2025-12-11",
},
{"dates": "", "USUBJID": "00004", "operation_id": ""},
{"dates": "", "USUBJID": "00004", "operation_id": ""},
]
),
PandasDataset,
["USUBJID"],
),
(
{
"dates": [
"2025-10-10",
"2025-10-15",
"2025-12-02",
"2025-12-11",
"",
"",
],
"USUBJID": ["00002", "00002", "00003", "00003", "00004", "00004"],
},
DaskDataset.from_records(
[
{
"dates": "2025-10-10",
"USUBJID": "00002",
"operation_id": "2025-10-15",
},
{
"dates": "2025-10-15",
"USUBJID": "00002",
"operation_id": "2025-10-15",
},
{
"dates": "2025-12-02",
"USUBJID": "00003",
"operation_id": "2025-12-11",
},
{
"dates": "2025-12-11",
"USUBJID": "00003",
"operation_id": "2025-12-11",
},
{"dates": "", "USUBJID": "00004", "operation_id": ""},
{"dates": "", "USUBJID": "00004", "operation_id": ""},
]
),
DaskDataset,
["USUBJID"],
),
],
)
def test_max_date(
Expand Down
Loading
Loading