phjacoby/ETL_Datamanagement
1
1
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

visual fixes

Browse Source
This commit is contained in:
Philipp Jacoby
2026-02-10 18:07:49 +01:00
parent 8965b04a61
commit 9b8f9a87e7
1 changed files with 1 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
etl.py
View File

@@ -10,9 +10,7 @@ INPUT_JSON = "hetionet-v1.0.json"
OUTPUT_DIR = Path("neo4j_csv") OUTPUT_DIR = Path("neo4j_csv")
OUTPUT_DIR.mkdir(exist_ok=True) OUTPUT_DIR.mkdir(exist_ok=True)
print("="*60)
print("HETIONET ETL PIPELINE (OPTIMIZED + SPLIT EDGES)") print("HETIONET ETL PIPELINE (OPTIMIZED + SPLIT EDGES)")
print("="*60)
# extract # extract
@@ -146,9 +144,8 @@ for edge_type in sorted(edge_types):
print(f" - {edge_type:20s}: {count:>10,} ({pct:>5.1f}%)") print(f" - {edge_type:20s}: {count:>10,} ({pct:>5.1f}%)")
print("\n" + "="*60)
print("PHASE 4: ANALYSES") print("PHASE 4: ANALYSES")
print("="*60)
# analysis 1: hotspot genes # analysis 1: hotspot genes
print("\nAnalysis 1: Hotspot Genes") print("\nAnalysis 1: Hotspot Genes")