Renaming of modules and some classes:

- Renamed module fingerprints to features.
- Renamed DataSet class to Data.
- Renamed calculate_features method to calculate.

docs/source/data.rst

@@ -3,7 +3,7 @@
 Introduction
 ==============
 Data is central in Machine Learning and ML4Chem provides some tools to
-prepare your datasets. We support the following:
+prepare your Datas. We support the following:
 
 1. `Atomic Simulation Environment (ASE) <https://wiki.fysik.dtu.dk/ase/>`_.
 
@@ -21,15 +21,15 @@ right format to inter-operate with any other module of Ml4Chem.
 
 Its usage is very simple::
 
-    from ml4chem.data.handler import DataSet
+    from ml4chem.data.handler import Data
     from ase.io import Trajectory
 
     images = Trajectory("images.traj")
-    data_handler = DataSet(images, purpose="training")
+    data_handler = Data(images, purpose="training")
     traing_set, targets = data_handler.get_data(purpose="training")
 
 In the example above, an ASE trajectory file is loaded into memory and passed
-as an argument to instantiate the ``DataSet`` class with
+as an argument to instantiate the ``Data`` class with
 ``purpose="training"``. The ``.get_images()`` class method returns a hashed
 dictionary with the molecules in ``images.traj`` and the ``targets`` variable
 as a list of energies.

docs/source/ml4chem.fingerprints.rst

@@ -1,37 +1,37 @@
-ml4chem.fingerprints package
+ml4chem.features package
 ============================
 
 Submodules
 ----------
 
-ml4chem.fingerprints.autoencoders module
+ml4chem.features.autoencoders module
 ----------------------------------------
 
-.. automodule:: ml4chem.fingerprints.autoencoders
+.. automodule:: ml4chem.features.autoencoders
     :members:
     :undoc-members:
     :show-inheritance:
 
-ml4chem.fingerprints.cartesian module
+ml4chem.features.cartesian module
 -------------------------------------
 
-.. automodule:: ml4chem.fingerprints.cartesian
+.. automodule:: ml4chem.features.cartesian
     :members:
     :undoc-members:
     :show-inheritance:
 
-ml4chem.fingerprints.cutoff module
+ml4chem.features.cutoff module
 ----------------------------------
 
-.. automodule:: ml4chem.fingerprints.cutoff
+.. automodule:: ml4chem.features.cutoff
     :members:
     :undoc-members:
     :show-inheritance:
 
-ml4chem.fingerprints.gaussian module
+ml4chem.features.gaussian module
 ------------------------------------
 
-.. automodule:: ml4chem.fingerprints.gaussian
+.. automodule:: ml4chem.features.gaussian
     :members:
     :undoc-members:
     :show-inheritance:
@@ -40,7 +40,7 @@ ml4chem.fingerprints.gaussian module
 Module contents
 ---------------
 
-.. automodule:: ml4chem.fingerprints
+.. automodule:: ml4chem.features
     :members:
     :undoc-members:
     :show-inheritance:

docs/source/ml4chem.rst

@@ -8,7 +8,7 @@ Subpackages
 
     ml4chem.backends
     ml4chem.data
-    ml4chem.fingerprints
+    ml4chem.features
     ml4chem.models
     ml4chem.optim
 

docs/source/models.rst

@@ -115,12 +115,12 @@ predicting energy and atomic forces.
 
 ::
 
-    from ml4chem.fingerprints.gaussian import Gaussian
+    from ml4chem.features.gaussian import Gaussian
 
     features = Gaussian(cutoff=6.5, normalized=True, save_preprocessor="features.scaler")
 
 In the code snippet above we are building Gaussian type features using the
-:class:`ml4chem.fingerprints.gaussian.Gaussian` class. We use a ``cutoff``
+:class:`ml4chem.features.gaussian.Gaussian` class. We use a ``cutoff``
 radius of :math:`6.5` angstrom, we normalized by the squared cutoff raidous,
 and the preprocessing is saved to the file ``features.scaler`` (by default
 the preprocessing used is ``MinMaxScaler`` in a range :math:`(-1, 1)` as

examples/autoencoder/cu_inference.py

@@ -3,8 +3,8 @@
 sys.path.append("../../")
 from ase.io import Trajectory
 from dask.distributed import Client, LocalCluster
-from ml4chem.data.handler import DataSet
-from ml4chem.fingerprints import LatentFeatures
+from ml4chem.data.handler import Data
+from ml4chem.features import LatentFeatures
 from ml4chem.data.serialization import load
 from ml4chem.utils import logger
 import numpy as np
@@ -27,12 +27,12 @@ def autoencode():
     # Arguments for fingerprinting the images
     normalized = True
 
-    data_handler = DataSet(images, purpose=purpose)
+    data_handler = Data(images, purpose=purpose)
     images, energies = data_handler.get_data(purpose=purpose)
 
     preprocessor = ("MinMaxScaler", {"feature_range": (-1, 1)})
 
-    fingerprints = (
+    features = (
         "Gaussian",
         {
             "cutoff": 6.5,
@@ -43,19 +43,19 @@ def autoencode():
     )
     encoder = {"model": "ml4chem.ml4c", "params": "ml4chem.params"}
 
-    fingerprints = LatentFeatures(
-        features=fingerprints,
+    features = LatentFeatures(
+        features=features,
         encoder=encoder,
         preprocessor=None,
         save_preprocessor="latent_space_min_max.scaler",
     )
 
-    fingerprints = fingerprints.calculate_features(
+    features = features.calculate(
         images, purpose=purpose, data=data_handler, svm=True
     )
 
     latent_svm = []
-    for e in list(fingerprints.values()):
+    for e in list(features.values()):
         for symbol, features in e:
             latent_svm.append(features)
 

examples/autoencoder/cu_training.log

@@ -39,7 +39,7 @@ Adding atomic feature calculations to computational graph...
 Adding Dask array construction to computational graph...
 Calling feature scaler...
 Fingerprinting finished in 0 hours 0 minutes 13.72 seconds.
-Fingerprints saved to fingerprints.db.
+features saved to features.db.
 Model Training
 ==============
 Model name: AutoEncoder.

examples/autoencoder/cu_training.py

@@ -4,8 +4,8 @@
 from ase.io import Trajectory
 from dask.distributed import Client, LocalCluster
 from ml4chem import Potentials
-from ml4chem.data.handler import DataSet
-from ml4chem.fingerprints import Gaussian
+from ml4chem.data.handler import Data
+from ml4chem.features import Gaussian
 from ml4chem.models.autoencoders import AutoEncoder, train
 from ml4chem.data.serialization import dump
 from ml4chem.utils import logger
@@ -22,17 +22,17 @@ def autoencode():
     """
     Data Structure Preparation
     """
-    data_handler = DataSet(images, purpose=purpose)
+    data_handler = Data(images, purpose=purpose)
     training_set, energy_targets = data_handler.get_data(purpose=purpose)
 
     """
     Let's create the targets of the model
     """
-    fingerprints = Gaussian(
+    features = Gaussian(
         cutoff=6.5, normalized=normalized, save_preprocessor="cu_training.scaler"
     )
 
-    targets = fingerprints.calculate_features(
+    targets = features.calculate(
         training_set, data=data_handler, purpose=purpose, svm=False
     )
     output_dimension = len(list(targets.values())[0][0][1])

examples/gp_potentials/cu_inference.py

@@ -20,7 +20,7 @@ def main():
     )
 
     # Passage of fingerprint database with reference space
-    calc.reference_space = "fingerprints.db"
+    calc.reference_space = "features.db"
 
     for atoms in images:
         energy = calc.get_potential_energy(atoms)

examples/gp_potentials/cu_training.py

@@ -4,7 +4,7 @@
 
 sys.path.append("../../")
 from ml4chem import Potentials
-from ml4chem.fingerprints import Gaussian
+from ml4chem.features import Gaussian
 from ml4chem.models.gaussian_process import GaussianProcess
 from ml4chem.utils import logger
 
@@ -18,7 +18,7 @@ def train():
     batch_size = 160
 
     calc = Potentials(
-        fingerprints=Gaussian(
+        features=Gaussian(
             cutoff=6.5, normalized=normalized, save_preprocessor="cu_training.scaler"
         ),
         # model=GaussianProcess(batch_size=batch_size),

examples/krr_potentials/cu_inference.log

@@ -57,7 +57,7 @@ Symmetry function parameters for Cu atom:
 Adding atomic feature calculations to scheduler...
 ... finished in 0 hours 0 minutes 0.96 seconds.
 
-Computing fingerprints...
+Computing features...
 Fingerprinting finished in 0 hours 0 minutes 2.38 seconds.
 Computing energy...
 Data
@@ -92,7 +92,7 @@ Symmetry function parameters for Cu atom:
 Adding atomic feature calculations to scheduler...
 ... finished in 0 hours 0 minutes 0.06 seconds.
 
-Computing fingerprints...
+Computing features...
 Fingerprinting finished in 0 hours 0 minutes 1.10 seconds.
 Computing energy...
 Data
@@ -127,7 +127,7 @@ Symmetry function parameters for Cu atom:
 Adding atomic feature calculations to scheduler...
 ... finished in 0 hours 0 minutes 0.14 seconds.
 
-Computing fingerprints...
+Computing features...
 Fingerprinting finished in 0 hours 0 minutes 1.77 seconds.
 Computing energy...
 Data
@@ -162,7 +162,7 @@ Symmetry function parameters for Cu atom:
 Adding atomic feature calculations to scheduler...
 ... finished in 0 hours 0 minutes 0.07 seconds.
 
-Computing fingerprints...
+Computing features...
 Fingerprinting finished in 0 hours 0 minutes 1.14 seconds.
 Computing energy...
 Data
@@ -197,7 +197,7 @@ Symmetry function parameters for Cu atom:
 Adding atomic feature calculations to scheduler...
 ... finished in 0 hours 0 minutes 0.09 seconds.
 
-Computing fingerprints...
+Computing features...
 Fingerprinting finished in 0 hours 0 minutes 1.68 seconds.
 Computing energy...
 Data
@@ -232,7 +232,7 @@ Symmetry function parameters for Cu atom:
 Adding atomic feature calculations to scheduler...
 ... finished in 0 hours 0 minutes 0.11 seconds.
 
-Computing fingerprints...
+Computing features...
 Fingerprinting finished in 0 hours 0 minutes 1.32 seconds.
 Computing energy...
 Data
@@ -267,7 +267,7 @@ Symmetry function parameters for Cu atom:
 Adding atomic feature calculations to scheduler...
 ... finished in 0 hours 0 minutes 0.16 seconds.
 
-Computing fingerprints...
+Computing features...
 Fingerprinting finished in 0 hours 0 minutes 1.92 seconds.
 Computing energy...
 Data
@@ -302,7 +302,7 @@ Symmetry function parameters for Cu atom:
 Adding atomic feature calculations to scheduler...
 ... finished in 0 hours 0 minutes 0.11 seconds.
 
-Computing fingerprints...
+Computing features...
 Fingerprinting finished in 0 hours 0 minutes 0.92 seconds.
 Computing energy...
 Data
@@ -337,7 +337,7 @@ Symmetry function parameters for Cu atom:
 Adding atomic feature calculations to scheduler...
 ... finished in 0 hours 0 minutes 0.09 seconds.
 
-Computing fingerprints...
+Computing features...
 Fingerprinting finished in 0 hours 0 minutes 1.76 seconds.
 Computing energy...
 Data
@@ -372,6 +372,6 @@ Symmetry function parameters for Cu atom:
 Adding atomic feature calculations to scheduler...
 ... finished in 0 hours 0 minutes 0.11 seconds.
 
-Computing fingerprints...
+Computing features...
 Fingerprinting finished in 0 hours 0 minutes 1.10 seconds.
 Computing energy...

examples/krr_potentials/cu_inference.py

@@ -20,7 +20,7 @@ def main():
     )
 
     # Passage of fingerprint database with reference space
-    calc.reference_space = "fingerprints.db"
+    calc.reference_space = "features.db"
 
     for atoms in images:
         energy = calc.get_potential_energy(atoms)

examples/krr_potentials/cu_training.log

@@ -63,9 +63,9 @@ Options:
 Adding atomic feature calculations to scheduler...
 ... finished in 0 hours 0 minutes 1.87 seconds.
 
-Computing fingerprints...
+Computing features...
 Fingerprinting finished in 0 hours 0 minutes 12.67 seconds.
-Fingerprints saved to fingerprints.db.
+features saved to features.db.
 
 Model Training
 ==============

examples/krr_potentials/cu_training.params

@@ -14,7 +14,7 @@
         "batch_size": 160,
         "kwargs": {}
     },
-    "fingerprints": {
+    "features": {
         "name": "Gaussian",
         "cutoff": 6.5,
         "normalized": true,
@@ -23,7 +23,7 @@
             null
         ],
         "save_preprocessor": "cu_training.scaler",
-        "filename": "fingerprints.db",
+        "filename": "features.db",
         "angular_type": "G3",
         "weighted": false,
         "custom": {

examples/krr_potentials/cu_training.py

@@ -4,7 +4,7 @@
 
 sys.path.append("../../")
 from ml4chem import Potentials
-from ml4chem.fingerprints import Gaussian
+from ml4chem.features import Gaussian
 from ml4chem.models.kernelridge import KernelRidge
 from ml4chem.utils import logger
 
@@ -18,7 +18,7 @@ def train():
     batch_size = 160
 
     calc = Potentials(
-        fingerprints=Gaussian(
+        features=Gaussian(
             cutoff=6.5, normalized=normalized, save_preprocessor="cu_training.scaler"
         ),
         model=KernelRidge(batch_size=batch_size),