Update train.py DataLoader (#25)

Bug fix groupby action for categorical data to only show observed values in resulting DataFrame.
PMBio · Sep 26, 2023 · 7215b4e · 7215b4e
1 parent 284eb25
commit 7215b4e
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/deeprvat/deeprvat/train.py b/deeprvat/deeprvat/train.py
@@ -285,7 +285,7 @@ def __getitem__(self, index):
         start_idx = index * self.batch_size
         end_idx = min(self.total_samples, start_idx + self.batch_size)
         batch_samples = self.sample_order.iloc[start_idx:end_idx]
-        samples_by_pheno = batch_samples.groupby("phenotype")
+        samples_by_pheno = batch_samples.groupby("phenotype", observed=True)
 
         result = dict()
         for pheno, df in samples_by_pheno: