Skip to content

feat: add descriptive statistics module #331

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

Draft
LauraBoenchenLB wants to merge 7 commits into
base: epic/157-create-an-evaluatorcomparer
Choose a base branch
from
Draft

feat: add descriptive statistics module #331

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
7b0c19e
refactor overview and add tests
LauraBoenchenLB Feb 10, 2025
5df982f
Merge branch 'epic/157-create-an-evaluatorcomparer' into 215-descript…
LauraBoenchenLB Feb 12, 2025
ee1e7d9
added datatype from type
LauraBoenchenLB Feb 13, 2025
5c90531
update summary functions
LauraBoenchenLB Feb 17, 2025
d7965e4
added concept analysis
LauraBoenchenLB Feb 17, 2025
f26c391
fix linting errors
LauraBoenchenLB Feb 18, 2025
932bc46
added functionality attribute values
LauraBoenchenLB Feb 18, 2025
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
258 changes: 0 additions & 258 deletions medmodels/medrecord/_overview.py
View file
Open in desktop

This file was deleted.

15 changes: 12 additions & 3 deletions medmodels/medrecord/medrecord.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,7 +18,6 @@
import polars as pl

from medmodels._medmodels import PyMedRecord
from medmodels.medrecord._overview import extract_attribute_summary, prettify_table
from medmodels.medrecord.builder import MedRecordBuilder
from medmodels.medrecord.indexers import EdgeIndexer, NodeIndexer
from medmodels.medrecord.querying import EdgeOperand, EdgeQuery, NodeOperand, NodeQuery
Expand Down Expand Up @@ -52,6 +51,12 @@
is_polars_node_dataframe_input,
is_polars_node_dataframe_input_list,
)
from medmodels.statistic_evaluations.statistical_analysis.attribute_analysis import (
extract_attribute_summary,
)
from medmodels.statistic_evaluations.statistical_analysis.statistics_display import (
prettify_table,
)


def process_nodes_dataframe(
Expand Down Expand Up @@ -1345,7 +1350,9 @@ def _describe_group_nodes(

nodes_info[group] = {
"count": len(nodes),
"attribute": extract_attribute_summary(self.node[nodes], schema=schema),
"attribute": extract_attribute_summary(
self.node[nodes], schema=schema, summary_type="short"
),
}

if not add_ungrouped:
Expand Down Expand Up @@ -1397,7 +1404,9 @@ def _describe_group_edges(

edges_info[group] = {
"count": len(edges),
"attribute": extract_attribute_summary(self.edge[edges], schema=schema),
"attribute": extract_attribute_summary(
self.edge[edges], schema=schema, summary_type="short"
),
}

if not add_ungrouped:
Expand Down
39 changes: 20 additions & 19 deletions medmodels/medrecord/tests/test_medrecord.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1683,9 +1683,9 @@ def test_describe_group_nodes(self) -> None:
1: {
"count": 2,
"attribute": {
"adipiscing": {"type": "Categorical", "values": "Values: elit"},
"dolor": {"type": "Categorical", "values": "Values: sit"},
"lorem": {"type": "Categorical", "values": "Values: ipsum"},
"adipiscing": {"type": "Unstructured", "values": "Values: elit"},
"dolor": {"type": "Unstructured", "values": "Values: sit"},
"lorem": {"type": "Unstructured", "values": "Values: ipsum"},
},
},
"Float": {"count": 0, "attribute": {}},
Expand All @@ -1703,7 +1703,7 @@ def test_describe_group_nodes(self) -> None:
"Odd": {
"count": 2,
"attribute": {
"amet": {"type": "Categorical", "values": "Values: consectetur"}
"amet": {"type": "Unstructured", "values": "Values: consectetur"}
},
},
}
Expand All @@ -1717,9 +1717,9 @@ def test_describe_group_edges(self) -> None:
"Even": {
"count": 2,
"attribute": {
"eiusmod": {"type": "Categorical", "values": "Values: tempor"},
"incididunt": {"type": "Categorical", "values": "Values: ut"},
"sed": {"type": "Categorical", "values": "Values: do"},
"eiusmod": {"type": "Unstructured", "values": "Values: tempor"},
"incididunt": {"type": "Unstructured", "values": "Values: ut"},
"sed": {"type": "Unstructured", "values": "Values: do"},
},
},
"Ungrouped Edges": {"count": 2, "attribute": {}},
Expand All @@ -1730,9 +1730,9 @@ def test_describe_group_edges(self) -> None:
"Even": {
"count": 2,
"attribute": {
"eiusmod": {"type": "Categorical", "values": "Values: tempor"},
"incididunt": {"type": "Categorical", "values": "Values: ut"},
"sed": {"type": "Categorical", "values": "Values: do"},
"eiusmod": {"type": "Unstructured", "values": "Values: tempor"},
"incididunt": {"type": "Unstructured", "values": "Values: ut"},
"sed": {"type": "Unstructured", "values": "Values: do"},
},
},
}
Expand All @@ -1742,15 +1742,16 @@ def test_overview_edges(self) -> None:

assert "\n".join(
[
"--------------------------------------------------------------------------",
"Edges Group Count Attribute Type Data ",
"--------------------------------------------------------------------------",
"patient_diagnosis 60 duration_days Continuous min: 0.00 ",
" max: 3416.00 ",
" mean: 405.02 ",
" time Temporal min: 1962-10-21 00:00:00 ",
" max: 2024-04-12 00:00:00 ",
"--------------------------------------------------------------------------",
"---------------------------------------------------------------------------",
"Edges Group Count Attribute Type Data ",
"---------------------------------------------------------------------------",
"patient_diagnosis 60 duration_days Continuous min: 0.00 ",
" max: 3416.00 ",
" mean: 405.02 ",
" time Temporal min: 1962-10-21 00:00:00 ",
" max: 2024-04-12 00:00:00 ",
" mean: 2012-01-25 11:12:00 ",
"---------------------------------------------------------------------------",
]
) == str(medrecord.overview_edges("patient_diagnosis"))

Expand Down
Loading