formatting

multidms/data.py

@@ -599,7 +599,6 @@ def targets(self) -> dict:
         """The functional scores for each variant in the training data."""
         return self._training_data["y"]
 
-    # TODO, rename mutparser
     @property
     def mutparser(self) -> MutationParser:
         """
@@ -608,7 +607,6 @@ def mutparser(self) -> MutationParser:
         """
         return self._mutparser
 
-    # TODO, rename
     @property
     def parse_mut(self) -> MutationParser:
         """
@@ -618,7 +616,6 @@ def parse_mut(self) -> MutationParser:
         """
         return self.mutparser.parse_mut
 
-    # TODO, document rename issue
     @property
     def parse_muts(self) -> partial:
         """
@@ -628,11 +625,6 @@ def parse_muts(self) -> partial:
         """
         return self._parse_muts
 
-    # TODO should this be cached? how does caching interact with the way in
-    # which we applying this function in parallel?
-    # although, unless the variants are un-collapsed, this cache will be
-    # pretty useless.
-    # although it could be useful for the Model.add_phenotypes_to_df method.
     def convert_subs_wrt_ref_seq(self, condition, aa_subs):
         """
         Covert amino acid substitutions to be with respect to the reference sequence.

multidms/model.py

@@ -209,7 +209,7 @@ def __init__(
         epistatic_model=multidms.biophysical.sigmoidal_global_epistasis,
         output_activation=multidms.biophysical.identity_activation,
         conditional_shifts=True,
-        alpha_d=False,  # TODO raise issue to be squashed in this PR
+        alpha_d=False,
         gamma_corrected=False,
         PRNGKey=0,
         init_beta_naught=0.0,
@@ -805,9 +805,9 @@ def add_phenotypes_to_df(
             if phenotype_as_effect:
                 latent_predictions -= wildtype_df.loc[condition, "predicted_latent"]
             latent_predictions[nan_variant_indices] = onp.nan
-            ret.loc[condition_df.index.values, latent_phenotype_col] = (
-                latent_predictions
-            )
+            ret.loc[
+                condition_df.index.values, latent_phenotype_col
+            ] = latent_predictions
 
             # func_score predictions on binary variants, X
             phenotype_predictions = onp.array(
@@ -819,9 +819,9 @@ def add_phenotypes_to_df(
                     condition, "predicted_func_score"
                 ]
             phenotype_predictions[nan_variant_indices] = onp.nan
-            ret.loc[condition_df.index.values, observed_phenotype_col] = (
-                phenotype_predictions
-            )
+            ret.loc[
+                condition_df.index.values, observed_phenotype_col
+            ] = phenotype_predictions
 
         return ret
 

multidms/model_collection.py

@@ -396,10 +396,6 @@ def __init__(self, fit_models):
             )
             all_mutations = set.union(all_mutations, set(fit.data.mutations))
 
-        # add the final training loss to the fit_models dataframe
-        # fit_models["training_loss"] = fit_models.step_loss.apply(lambda x: x[-1])
-        # TODO rename to fit_models_df
-
         # initialize empty columns for conditional loss
         fit_models.assign(
             **{
@@ -447,7 +443,6 @@ def all_mutations(self) -> tuple:
         """The mutations shared by each fitting dataset."""
         return self._all_mutations
 
-    # TODO remove verbose everywhere
     @lru_cache(maxsize=10)
     def split_apply_combine_muts(
         self,
@@ -1009,9 +1004,6 @@ def mut_type(mut):
             return "stop" if mut.endswith("*") else "nonsynonymous"
 
         # apply, drop, and melt
-        # TODO This throws deprecation warning
-        # because of the include_groups argument ...
-        # set to False, and lose the drop call after ...
         sparsity_df = (
             df.drop(columns=to_throw)
             .assign(mut_type=lambda x: x.mutation.apply(mut_type))