adjust comments

schnellerereETL.py

@@ -3,9 +3,9 @@ import pandas as pd
 from pathlib import Path
 from collections import defaultdict
 
-# ==============================
+
 # KONFIGURATION
-# ==============================
+
 INPUT_JSON = "hetionet-v1.0.json"
 OUTPUT_DIR = Path("neo4j_csv")
 OUTPUT_DIR.mkdir(exist_ok=True)
@@ -14,9 +14,8 @@ print("="*60)
 print("HETIONET ETL PIPELINE")
 print("="*60)
 
-# ==============================
 # EXTRACT
-# ==============================
+
 print("\nPHASE 1: EXTRACTION")
 print("-"*60)
 print("Loading JSON data...")
@@ -30,9 +29,8 @@ edges_raw = data["edges"]
 print(f"Nodes loaded: {len(nodes_raw):,}")
 print(f"Edges loaded: {len(edges_raw):,}")
 
-# ==============================
 # TRANSFORM – NODES
-# ==============================
+
 print("\n PHASE 2: TRANSFORM NODES")
 print("-"*60)
 
@@ -91,9 +89,8 @@ for kind in nodes_df["kind"].unique():
     df_kind.to_csv(filename, index=False)
     print(f"   {filename.name} ({len(df_kind):,} rows)")
 
-# ==============================
 # TRANSFORM – EDGES
-# ==============================
+
 print("\nPHASE 3: TRANSFORM EDGES")
 print("-"*60)
 
@@ -127,9 +124,9 @@ for edge_type in ['associates', 'treats', 'presents', 'causes', 'regulates', 'up
     if len(edges_by_type[edge_type]) > 0:
         print(f"   - {edge_type}: {len(edges_by_type[edge_type]):,}")
 
-# ==============================
+
 # ANALYSES
-# ==============================
+
 print("\n" + "="*60)
 print("PHASE 4: ANALYSES")
 print("="*60)
@@ -438,9 +435,7 @@ network_edges_df.to_csv(OUTPUT_DIR / "network_edges.csv", index=False)
 
 print(f"Network: {len(network_nodes_df)} nodes, {len(network_edges_df)} edges")
 
-# ==============================
-# SUMMARY
-# ==============================
+
 print("\n" + "="*60)
 print("ETL PIPELINE COMPLETED SUCCESSFULLY")
 print("="*60)