Addition of to_pandas() method for raw ASE data and general

improvements.

- Improved documentation about visualizing with plotly.
- Bumped version.
- ml4chem.data.utils:
    * Addition of `ase_to_xyz()` function.
- data.handler:
    * Addition of `to_pandas()` method.
    * Improved documentation.

docs/source/data.rst

@@ -3,7 +3,7 @@
 Introduction
 ==============
 Data is central in Machine Learning and ML4Chem provides some tools to
-prepare your Datas. We support the following:
+prepare your Datas. We support the following input formats:
 
 1. `Atomic Simulation Environment (ASE) <https://wiki.fysik.dtu.dk/ase/>`_.
 
@@ -62,3 +62,7 @@ created.
 .. raw:: html
    :file: _static/pca_visual.html
 
+To activate plotly in Jupyter or JupyterLab follow the instructions shown in
+`https://plot.ly/python/getting-started/#jupyter-notebook-support <https://plot.ly/python/getting-started/#jupyter-notebook-support>`_
+
+

ml4chem/__init__.py

@@ -2,4 +2,4 @@
 
 
 __all__ = ["Potentials"]
-__version__ = "0.0.5"
+__version__ = "0.0.6-dev"

ml4chem/data/handler.py

@@ -1,7 +1,9 @@
 from collections import OrderedDict
+from ml4chem.data.utils import ase_to_xyz
 from ml4chem.utils import get_hash
 import datetime
 import logging
+import pandas as pd
 
 logger = logging.getLogger()
 
@@ -51,13 +53,6 @@ def prepare_images(self, images, purpose=None):
             The purpose of the data so that structure is prepared accordingly.
             Supported are: 'training', 'inference'
 
-        Returns
-        -------
-        self.images : dict
-            Ordered dictionary of images corresponding to order of self.targets
-            list.
-        self.targets : list
-            Targets used for training the model.
         """
         logger.info("Preparing images for {}...".format(purpose))
         self.images = OrderedDict()
@@ -171,12 +166,21 @@ def get_unique_element_symbols(self, images=None, purpose=None):
         return self.unique_element_symbols
 
     def get_data(self, purpose=None):
-        """
+        """A method to get data
+
         Parameters
         ----------
         purpose : str
             The purpose of the data so that structure is prepared accordingly.
             Supported are: 'training', 'inference'
+
+        Returns
+        -------
+        self.images : dict
+            Ordered dictionary of images corresponding to order of self.targets
+            list.
+        self.targets : list
+            Targets used for training the model.
         """
 
         if purpose == "training":
@@ -185,7 +189,18 @@ def get_data(self, purpose=None):
             return self.images
 
     def get_total_number_atoms(self):
+        """Get the total number of atoms"""
         return sum(self.atoms_per_image)
 
     def to_pandas(self):
-        raise NotImplementedError
+        """Convert data to pandas DataFrame"""
+        images = OrderedDict()
+        columns = ["xyz"]
+
+        for key, atoms in self.images.items():
+            images[key] = ase_to_xyz(atoms, file=False)
+
+        df = pd.DataFrame.from_dict(images, orient="index", columns=columns)
+        df["energy"] = self.targets
+
+        return df

ml4chem/data/utils.py

@@ -1,8 +1,9 @@
 from ase.io import Trajectory
+from io import StringIO
 import random
 
 
-def split_Data(
+def split_data(
     images,
     training_name="training_images.traj",
     test_name="test_images.traj",
@@ -64,3 +65,22 @@ def split_Data(
 
         log.write(str(test_images))
     log.close()
+
+
+def ase_to_xyz(atoms, comment="", file=True):
+    """Convert ASE to xyz
+
+    This function is useful to save xyz to DataFrame.
+    """
+    xyz = StringIO()
+    symbols = atoms.get_chemical_symbols()
+    natoms = len(symbols)
+    xyz.write("%d\n%s\n" % (natoms, comment))
+
+    for s, (x, y, z) in zip(symbols, atoms.positions):
+        xyz.write("%-2s %22.15f %22.15f %22.15f\n" % (s, x, y, z))
+
+    if file:
+        return xyz
+    else:
+        return xyz.getvalue()