debug test and remove dependency pandas

Author: liugangcode

README.md

@@ -56,6 +56,12 @@
 | BFGNNMolecularPredictor | torch-scatter |
 | GRINMolecularPredictor | torch-scatter |
 
+**For models that require `torch-scatter`: Install using the following command: `pip install torch-scatter -f https://data.pyg.org/whl/torch-${TORCH}+${CUDA}.html`, e.g.,
+
+> `pip install torch-scatter -f https://data.pyg.org/whl/torch-2.7.1+cu128.html`
+
+**For models that require `transformers`:** `pip install transformers`
+
 ## Usage
 
 Refer to the `tests` folder for more use cases.

pyproject.toml

@@ -19,7 +19,6 @@ dependencies = [
     "torch>=2.2.0",
     "torch-geometric>=2.6.1",
     "numpy",
-    "pandas>=2.2.3",
     "click",
     "huggingface_hub>=0.22.2",
     "joblib>=1.3.2",

tests/encoder/graphmae.py

@@ -1,8 +1,10 @@
 import numpy as np
-import pandas as pd
+import csv
 import os
 from torch_molecule import GraphMAEMolecularEncoder
 
+EPOCHS = 5
+
 def test_graphmae_encoder():
     # Load molecules from CSV file
     data_path = "data/molecule100.csv"
@@ -17,16 +19,20 @@ def test_graphmae_encoder():
             "CCN",      # Ethylamine
         ]
     else:
-        df = pd.read_csv(data_path)
-        molecules = df['smiles'].tolist()[:50]  # Use first 50 molecules
+        molecules = []
+        with open(data_path, 'r') as file:
+            csv_reader = csv.DictReader(file)
+            for i, row in enumerate(csv_reader):
+                if i >= 50:  # Use first 50 molecules
+                    break
+                molecules.append(row['smiles'])
         print(f"Loaded {len(molecules)} molecules from {data_path}")
-    
     # Initialize GraphMAE model
     model = GraphMAEMolecularEncoder(
         num_layer=3,
         hidden_size=128,
         batch_size=16,
-        epochs=30,  # Small number for testing
+        epochs=EPOCHS,  # Small number for testing
         mask_rate=0.15,
         verbose=True,
         # device="cpu"
@@ -79,16 +85,21 @@ def test_graphmae_with_edge_masking():
             "CCN",      # Ethylamine
         ]
     else:
-        df = pd.read_csv(data_path)
-        molecules = df['smiles'].tolist()[:50]  # Use first 50 molecules
+        molecules = []
+        with open(data_path, 'r') as file:
+            csv_reader = csv.DictReader(file)
+            for i, row in enumerate(csv_reader):
+                if i >= 50:  # Use first 50 molecules
+                    break
+                molecules.append(row['smiles'])
         print(f"Loaded {len(molecules)} molecules from {data_path}")
 
     # Initialize GraphMAE model with edge masking enabled
     model = GraphMAEMolecularEncoder(
         num_layer=3,
         hidden_size=128,
         batch_size=16,
-        epochs=30,  # Small number for testing
+        epochs=EPOCHS,  # Small number for testing
         mask_rate=0.15,
         mask_edge=True,  # Enable edge masking
         verbose=True,

tests/encoder/hfpretrained.py

@@ -24,7 +24,7 @@ def test_hf_pretrained_encoder():
         {"repo_id": "DeepChem/ChemBERTa-10M-MTR", "model_name": "ChemBERTa_10M_MTR"},
         {"repo_id": "DeepChem/ChemBERTa-10M-MLM", "model_name": "ChemBERTa_10M_MLM"},
         {"repo_id": "DeepChem/ChemBERTa-5M-MLM", "model_name": "ChemBERTa_5M_MLM"},
-        {"repo_id": "DeepChem/ChemBERTa-5M-MTR", "model_name": "ChemBERTa_5M_MTR"}
+        {"repo_id": "DeepChem/ChemBERTa-5M-MTR", "model_name": "ChemBERTa_5M_MTR"},
         {"repo_id": "seyonec/ChemBERTa-zinc-base-v1", "model_name": "ChemBERTa_zinc_base_v1"},
         {"repo_id": "unikei/bert-base-smiles", "model_name": "bert-base-smiles"}
     ]

tests/encoder/test_run_all.py

@@ -6,7 +6,7 @@
 from torch_molecule import DigressMolecularGenerator
 from torch_molecule.utils.search import ParameterType, ParameterSpec
 
-EPOCHS = 10
+EPOCHS = 5
 BATCH_SIZE = 32
 
 def test_digress_generator():
@@ -24,7 +24,6 @@ def test_digress_generator():
     model = DigressMolecularGenerator(
         hidden_size_X=256,
         hidden_size_E=128,
-        hidden_size_y=128,
         num_layer=5,
         dropout=0.1,
         timesteps=500,

tests/generator/digress.py

@@ -5,7 +5,7 @@
 import torch
 from torch_molecule import GDSSMolecularGenerator
 
-EPOCHS = 500
+EPOCHS = 5
 BATCH_SIZE = 16
 
 def test_gdss_generator():

tests/generator/gdss.py

@@ -4,7 +4,6 @@
 
 import torch
 from torch_molecule import GraphDITMolecularGenerator
-from torch_molecule.utils.search import ParameterType, ParameterSpec
 
 EPOCHS = 2
 BATCH_SIZE = 32

tests/generator/graphdit.py

@@ -1,6 +1,6 @@
 import os
 import numpy as np
-import pandas as pd
+import csv
 from tqdm import tqdm
 
 import torch
@@ -15,8 +15,12 @@ def test_jtvae_generator():
                             "data", "polymer100.csv")
     print(f"Loading data from: {data_path}")
 
-    df = pd.read_csv(data_path)
-    smiles_list = df['smiles'].tolist()
+    # Read CSV without pandas
+    smiles_list = []
+    with open(data_path, 'r', encoding='utf-8') as csvfile:
+        reader = csv.DictReader(csvfile)
+        for row in reader:
+            smiles_list.append(row['smiles'])
 
     print(f"Loaded {len(smiles_list)} molecules")
     print(f"First 3 SMILES: {smiles_list[:3]}")

tests/generator/jtvae.py

@@ -1,12 +1,13 @@
 import os
+import csv
 import numpy as np
-import pandas as pd
 from tqdm import tqdm
 
 import torch
 from torch_molecule.generator.lstm import LSTMMolecularGenerator
 
-EPOCHS = 1000  # Reduced for faster testing
+# EPOCHS = 1000  # Reduced for faster testing
+EPOCHS = 5
 BATCH_SIZE = 24
 
 def test_lstm_generator():
@@ -15,12 +16,21 @@ def test_lstm_generator():
                             "data", "polymer100.csv")
     print(f"Loading data from: {data_path}")
 
-    df = pd.read_csv(data_path)
-    smiles_list = df['smiles'].tolist()
+    # Read CSV without pandas
+    smiles_list = []
+    properties = []
+    property_columns = []
 
-    # Extract property columns (all columns except 'smiles')
-    property_columns = [col for col in df.columns if col != 'smiles']
-    properties = df[property_columns].values.tolist()
+    with open(data_path, 'r') as csvfile:
+        reader = csv.DictReader(csvfile)
+        # Get property columns (all columns except 'smiles')
+        property_columns = [col for col in reader.fieldnames if col != 'smiles']
+        
+        for row in reader:
+            smiles_list.append(row['smiles'])
+            # Extract property values for this row
+            row_properties = [float(row[col]) for col in property_columns]
+            properties.append(row_properties)
 
     print(f"Loaded {len(smiles_list)} molecules with {len(property_columns)} properties")
     print(f"Property columns: {property_columns}")