Minor changes.

ml4chem/data/preprocessing.py

@@ -86,8 +86,9 @@ def set(self, purpose):
             self.preprocessor = joblib.load(self.preprocessing)
 
         else:
-            logger.warning("Preprocessor is not supported.")
+            logger.warning("{} with {} is not supported.".format(self.preprocessing, self.kwargs))
             self.preprocessor = preprocessor_name = None
+
 
         if purpose == "training" and preprocessor_name is not None:
             logger.info("Data preprocessing")

ml4chem/data/visualization.py

@@ -261,10 +261,11 @@ def plot_atomic_features(latent_space, method="PCA", dimensions=2, backend="seab
         if dimensions == 3 and backend == "plotly":
             args["color"] = "Symbol"
             plt = px.scatter_3d(df, **args)
-            plt.update_traces(marker=dict(size=4))
+            plt.update_traces(marker=dict(size=2))
         elif dimensions == 2 and backend == "plotly":
             args["color"] = "Symbol"
             plt = px.scatter(df, **args)
+            plt.update_traces(marker=dict(size=2))
         elif dimensions == 3 and backend == "seaborn":
             raise ("This backend is for 2D visualization")
         elif dimensions == 2 and backend == "seaborn":
@@ -300,10 +301,11 @@ def plot_atomic_features(latent_space, method="PCA", dimensions=2, backend="seab
         if dimensions == 3 and backend == "plotly":
             args["color"] = "Symbol"
             plt = px.scatter_3d(df, **args)
-            plt.update_traces(marker=dict(size=4))
+            plt.update_traces(marker=dict(size=2))
         elif dimensions == 2 and backend == "plotly":
             args["color"] = "Symbol"
             plt = px.scatter(df, **args)
+            plt.update_traces(marker=dict(size=2))
         elif dimensions == 3 and backend == "seaborn":
             raise ("This backend is for 2D visualization")
         elif dimensions == 2 and backend == "seaborn":

ml4chem/potentials.py

@@ -40,6 +40,7 @@ class Potentials(Calculator, object):
     # This is a good way to make attributes available to the class. This can be
     # accessed as Potentials.attribute
     svm_models = ["KernelRidge", "GaussianProcess"]
+    autoencoders = ["AutoEncoder", "VAE"]
     module_names = {
         "PytorchPotentials": "neuralnetwork",
         "PytorchIonicPotentials": "ionic",
@@ -175,7 +176,7 @@ def save(model=None, features=None, path=None, label="ml4chem"):
 
                 torch.save(model.state_dict(), path + ".ml4c")
 
-                if model_name == "AutoEncoder":
+                if model_name in Potentials.autoencoders:
                     output_dimension = {"output_dimension": model.output_dimension}
                     params["model"].update(output_dimension)
         else: