🔥 remove comments and code duplications

src/move/tasks/analyze_latent.py

@@ -406,16 +406,11 @@ def analyze_latent(config: MOVEConfig) -> None:
 
     for i, dataset_name in enumerate(config.data.continuous_names):
         logger.debug(f"Generating plot: feature importance '{dataset_name}'")
-        # NOT SURE IF IT WORKS THE SAME FOR CONTINUOUS FEATURES, CHECK THIS
-        # I did sth that did not work, I'll try again now.
         con_dataset_names = config.data.continuous_names
         target_idx = con_dataset_names.index(dataset_name)
-        # num_features = target_shape[0]
 
         num_features = test_dataset.con_shapes[target_idx]
 
-        # num_features = len(dataloaders)
-
         # We will use this inside the loop that iterates over all features:
         # We create one diff per dataset, to not store all of them in memory
         z = model.project(test_dataloader)

src/move/tasks/encode_data.py

@@ -59,12 +59,6 @@ def encode_data(config: DataConfig):
         )
         fig.savefig(fig_path)
 
-        values, mask_1d = preprocessing.scale(values)
-        names = names[mask_1d]
-        logger.debug(f"Columns with zero variance: {np.sum(~mask_1d)}")
-        io.dump_names(interim_data_path / f"{dataset_name}.txt", names)
-        np.save(interim_data_path / f"{dataset_name}.npy", values)
-
         # Plotting the value distribution for all continuous datasets:
         fig = plot_value_distributions(values)
         fig_path = str(output_path / f"Value_distribution_{dataset_name}.png")
@@ -74,5 +68,5 @@ def encode_data(config: DataConfig):
             values, mask_1d = preprocessing.scale(values, input_config.log2)
             names = names[mask_1d]
             logger.debug(f"Columns with zero variance: {np.sum(~mask_1d)}")
-        io.dump_names(interim_data_path / f"{input_config.name}.txt", names)
-        np.save(interim_data_path / f"{input_config.name}.npy", values)
+        io.dump_names(interim_data_path / f"{dataset_name}.txt", names)
+        np.save(interim_data_path / f"{dataset_name}.npy", values)