diff --git a/README.md b/README.md
index e00d4c7..de30873 100644
--- a/README.md
+++ b/README.md
@@ -42,18 +42,18 @@ Now, you need to preprocess Elliptic2 to obtain the specific input format for ea
 
 #### GLASS and GNNSeg
 
-To preprocess for GLASS and GNNSeg, edit `DATAPATH` in `preprocess_glass.py` and run
+To preprocess for GLASS and GNNSeg, run (use `--datapath` if your data is not in `./dataset`)
 ```
 python preprocess_glass.py
 ```
 which will produce three files: `edge_list.txt`, `subgraph.pth`, `n2id.pkl`. 
 
-The first two files are the required inputs for GLASS, which should be move into `GLASS/dataset/elliptic`. The file `n2id.pkl` will store a dictionary that converts node id in Ellptic2 to node id in GLASS for reference. Note that the train/val split is fixed given the random seeds, but you can change the split size at the top of the python script.
+The first two files are the required inputs for GLASS, which should be move into `GLASS/dataset/elliptic`. The file `n2id.pkl` will store a dictionary that converts node id in Ellptic2 to node id in GLASS for reference. Note that the train/val/test split is fixed (roughly 80/10/10) by the deterministic per-subgraph assignment in the script.
 
 
 #### Sub2vec
 
-To preprocess for Sub2Vec, edit `DATAPATH` in `preprocess_sub2vec.py` and run
+To preprocess for Sub2Vec, run (use `--datapath` if needed)
 ```
 python preprocess_sub2vec.py
 ```
diff --git a/preprocess_glass.py b/preprocess_glass.py
index 1b4f243..ee73a76 100644
--- a/preprocess_glass.py
+++ b/preprocess_glass.py
@@ -3,15 +3,18 @@
 import random
 import time
 import pickle
+import argparse
+import os
 
 #Parameters
-DATAPATH = "./dataset/"
-train = 0.8 #percentage of training subgraph
-val = 0.1 #percentage of validation subgraph
+parser = argparse.ArgumentParser(description="Preprocess the Elliptic2 dataset for GLASS and GNNSeg.")
+parser.add_argument("--datapath", default=os.environ.get("ELLIPTIC2_DATAPATH", "./dataset"),
+                    help="Folder with the unzipped Elliptic2 CSV files (default: ./dataset).")
+DATAPATH = parser.parse_args().datapath
 
 #Read in nodes
 start = time.time()
-feat = pd.read_csv(DATAPATH+"/background_nodes.csv")
+feat = pd.read_csv(os.path.join(DATAPATH, "background_nodes.csv"))
 print(list(feat.columns[1:]))
 print(feat.head())
 print("load background node time", time.time()-start)
@@ -31,7 +34,7 @@
     pickle.dump(n2id, fp)
 
 #Read in edge list
-edge = pd.read_csv(DATAPATH+"/background_edges.csv",usecols=["clId1","clId2"])
+edge = pd.read_csv(os.path.join(DATAPATH, "background_edges.csv"),usecols=["clId1","clId2"])
 print("load background edge time", time.time()-start)
 print("total number of edge: ",len(edge))
 start = time.time()
@@ -42,7 +45,7 @@
     if n2id[c1] > maxid:
         print("WARNING NODE OUT OF RANGE:",c1,n2id[c1])
     if n2id[c2] > maxid:
-        print("WARNING NODE OUT OF RANGE:",c2,n2id[c1])
+        print("WARNING NODE OUT OF RANGE:",c2,n2id[c2])
     file.write(str(n2id[c1])+" "+str(n2id[c2])+"\n")
 file.close()
 print("time to store edgelist", time.time()-start)
@@ -51,9 +54,9 @@
 #Read in Subgraph
 
 start = time.time()
-cc = pd.read_csv(DATAPATH+"connected_components.csv")
-edge = pd.read_csv(DATAPATH+"edges.csv")
-node = pd.read_csv(DATAPATH+"nodes.csv")
+cc = pd.read_csv(os.path.join(DATAPATH, "connected_components.csv"))
+edge = pd.read_csv(os.path.join(DATAPATH, "edges.csv"))
+node = pd.read_csv(os.path.join(DATAPATH, "nodes.csv"))
 print("load rest time", time.time()-start)
 start = time.time()
 
diff --git a/preprocess_sub2vec.py b/preprocess_sub2vec.py
index c1e05cc..b4c768b 100644
--- a/preprocess_sub2vec.py
+++ b/preprocess_sub2vec.py
@@ -2,10 +2,14 @@
 import torch
 import pickle
 import numpy as np
-import os 
+import os
+import argparse
 
 #Parameters
-DATAPATH = "./dataset/"
+parser = argparse.ArgumentParser(description="Preprocess the Elliptic2 dataset for Sub2Vec.")
+parser.add_argument("--datapath", default=os.environ.get("ELLIPTIC2_DATAPATH", "./dataset"),
+                    help="Folder with the unzipped Elliptic2 CSV files (default: ./dataset).")
+DATAPATH = parser.parse_args().datapath
 
 #Read in Node ID
 n2id = {}
@@ -14,13 +18,13 @@
 
 #Read in Subgraph ID
 cc2id = {}
-cc = pd.read_csv(DATAPATH+"/connected_components.csv")
+cc = pd.read_csv(os.path.join(DATAPATH, "connected_components.csv"))
 for row in cc.itertuples(index=True):
     cc2id[int(row[1])] =int(row[0])
 
 #Read in Nodes in Subgraph
 sub = {}
-node = pd.read_csv(DATAPATH+"/nodes.csv")
+node = pd.read_csv(os.path.join(DATAPATH, "nodes.csv"))
 for row in node.itertuples(index=False):
     if cc2id[int(row[1])] in sub.keys():
         sub[cc2id[int(row[1])]].append(n2id[int(row[0])])