add torch dependency, fix 3dzd embedding test (#16)

training/requirements.txt

@@ -1,10 +1,9 @@
 pandas
 pillow
-keras
+torch
 scikit-learn
 matplotlib
 numpy
-pandas
 pyyaml
 kaleido
 faiss-cpu

training/tests/test_create_embedding.py

@@ -2,12 +2,10 @@
 import re
 import tempfile
 from pathlib import Path
-
 import pandas as pd
 import pytest
 from alphafind_training.create_embedding import create_embedding
 
-
 @pytest.fixture(scope="function")
 def output_file():
     # Setup: Define the output file path
@@ -32,17 +30,15 @@ def test_create_embedding():
     with tempfile.TemporaryDirectory() as tmpdir:
         cif_path = "./data/cifs"
         output_path = f"{tmpdir}/embedding.pkl"
-        granularity = 10
 
-        # 45 features for each protein - (10x10 - 10) / 2
-        expected_dimensionality = 45
+        expected_dimensionality = 121
 
-        create_embedding(Path(cif_path), Path(output_path), granularity)
+        create_embedding(Path(cif_path), Path(output_path))
 
         assert os.path.exists(output_path)
         assert os.path.getsize(output_path) > 0
         # load embedding.pkl and check if it has the correct shape
-        df = pd.read_pickle(output_path)
+        df = pd.read_parquet(output_path)
         assert df.shape[0] == len(os.listdir(cif_path))
         assert df.shape[1] == expected_dimensionality
 

training/tests/test_create_kmeans.py

@@ -10,8 +10,7 @@
 def _setup(tempdir: str):
     create_embedding(
         input_path=Path("./data/cifs"),
-        output_path=Path(f"{tempdir}/embedding.pkl"),
-        granularity=10
+        output_path=Path(f"{tempdir}/embedding.pkl")
     )
 
 

training/tests/test_model_creation.py

@@ -11,8 +11,7 @@
 def _setup(tempdir: str):
     create_embedding(
         input_path=Path("./data/cifs"),
-        output_path=Path(f"{tempdir}/embedding.pkl"),
-        granularity=10
+        output_path=Path(f"{tempdir}/embedding.pkl")
     )
 
     create_kmeans(