From 9c206182aca2fdd03bbbf164f6ac09680007603a Mon Sep 17 00:00:00 2001
From: Fontrodona Nicolas <nicolas.fontrodona@ens-lyon.fr>
Date: Tue, 11 Mar 2025 16:00:34 +0100
Subject: [PATCH] script to merge the communities together
---
src/location_pp/merge_nr_communities.py | 48 +++++++++++++++++++++++++
1 file changed, 48 insertions(+)
create mode 100644 src/location_pp/merge_nr_communities.py
diff --git a/src/location_pp/merge_nr_communities.py b/src/location_pp/merge_nr_communities.py
new file mode 100644
index 00000000..9092d8e1
--- /dev/null
+++ b/src/location_pp/merge_nr_communities.py
@@ -0,0 +1,48 @@
+#!/usr/bin/env python3
+
+# -*- coding: utf-8 -*-
+
+"""
+Description: The goal of this script is to merge multiple
+communities file together and remove redundant clusters, cluster
+with the same genes
+"""
+
+from pathlib import Path
+from typing import List
+
+import lazyparser as lp
+import polars as pl
+from loguru import logger
+
+from src.location_pp.config import ConfigLocation
+
+
+def load_communities(files: list[Path]) -> pl.DataFrame:
+ """Load communities from files."""
+ df = pl.concat(
+ [
+ pl.read_csv(file, separator="\t").select(
+ ["community", "nodes", "genes"]
+ )
+ for file in files
+ ]
+ )
+ row = df.shape[0]
+ df = df.unique(subset=["genes"], keep="first")
+ final = df.shape[0]
+ logger.info(
+ f" {row - final} / {row} communities were duplicated and removed"
+ )
+ return df
+
+
+@lp.parse(files="file")
+def main_merge(files: List[str], outname: str) -> pl.DataFrame:
+ """Merge communities from files."""
+ df = load_communities([Path(f) for f in files])
+ df.write_csv(ConfigLocation.output / f"{outname}.txt", separator="\t")
+
+
+if __name__ == "__main__":
+ main_merge()
--
GitLab