add check for time interval

Author: kierandidi

proteinworkshop/config/dataset/pdb.yaml

@@ -10,10 +10,10 @@ datamodule:
 
   pdb_dataset:
     _target_: "proteinworkshop.datasets.pdb_dataset.PDBData"
-    fraction: 1.0 # Fraction of dataset to use
+    fraction: 0.01 # Fraction of dataset to use
     molecule_type: "protein" # Type of molecule for which to select
     experiment_types: ["diffraction", "NMR", "EM", "other"] # All experiment types
-    max_length: 1000 # Exclude polypeptides greater than length 1000
+    max_length: 150 # Exclude polypeptides greater than length 1000
     min_length: 10 # Exclude peptides of length 10
     oligomeric_min: 1 # Include only monomeric proteins
     oligomeric_max: 5 # Include up to 5-meric proteins 

proteinworkshop/datasets/pdb_dataset.py

@@ -55,7 +55,13 @@ def __init__(
         self.split_type = split_type
         self.split_sequence_similarity = split_sequence_similiarity
         self.overwrite_sequence_clusters = overwrite_sequence_clusters
-        self.split_time_frames = [np.datetime64(date) for date in split_time_frames]
+        if split_time_frames is None:
+            self.split_time_frames = split_time_frames
+        else:
+            try:
+                self.split_time_frames = [np.datetime64(date) for date in split_time_frames]
+            except:
+                raise TypeError(f"{split_time_frames} does not contain valid dates for np.datetime64 format")
         self.splits = ["train", "val", "test"]
 
     def create_dataset(self):