Merge pull request #511 from mala-project/code_formatting_standard

Adopting a code formatting standard

.github/workflows/cpu-tests.yml

@@ -155,7 +155,7 @@ jobs:
           conda env export -n mala-cpu > env_1.yml
 
           # install mala package
-          pip --no-cache-dir install -e .[opt,test]
+          pip --no-cache-dir install -e .[opt,test] --no-build-isolation
 
       - name: Check if Conda environment meets the specified requirements
         shell: 'bash -c "docker exec -i mala-cpu bash < {0}"'

docs/source/CONTRIBUTE.md

@@ -90,6 +90,14 @@ the core development team.
 * If you're adding code that should be tested, add tests
 * If you're adding or modifying examples, make sure to add them to `test_examples.py`
 
+### Formatting code
+
+* MALA uses [`black`](https://github.com/psf/black) for code formatting
+* The `black` configuration is located in `pyproject.toml`
+* Currently, no automatic code reformatting will be done in the CI, thus
+  please ensure that your code is properly formatted before creating a pull 
+  request
+
 ### Adding dependencies
 
 If you add additional dependencies, make sure to add them to `requirements.txt`
@@ -98,7 +106,6 @@ they are not.
 Further, in order for them to be available during the CI tests, make sure to 
 add _required_ dependencies to the appropriate environment files in folder `install/` and _extra_ requirements directly in the `Dockerfile` for the `conda` environment build.
 
-
 ## Pull Requests
 We actively welcome pull requests.
 1. Fork the repo and create your branch from `develop`

examples/advanced/ex01_checkpoint_training.py

@@ -4,6 +4,7 @@
 from mala import printout
 
 from mala.datahandling.data_repo import data_repo_path
+
 data_path = os.path.join(data_repo_path, "Be2")
 
 """
@@ -35,15 +36,27 @@ def initial_setup():
     parameters.running.checkpoint_name = "ex01_checkpoint"
 
     data_handler = mala.DataHandler(parameters)
-    data_handler.add_snapshot("Be_snapshot0.in.npy", data_path,
-                              "Be_snapshot0.out.npy", data_path, "tr")
-    data_handler.add_snapshot("Be_snapshot1.in.npy", data_path,
-                              "Be_snapshot1.out.npy", data_path, "va")
+    data_handler.add_snapshot(
+        "Be_snapshot0.in.npy",
+        data_path,
+        "Be_snapshot0.out.npy",
+        data_path,
+        "tr",
+    )
+    data_handler.add_snapshot(
+        "Be_snapshot1.in.npy",
+        data_path,
+        "Be_snapshot1.out.npy",
+        data_path,
+        "va",
+    )
     data_handler.prepare_data()
 
-    parameters.network.layer_sizes = [data_handler.input_dimension,
-                                      100,
-                                      data_handler.output_dimension]
+    parameters.network.layer_sizes = [
+        data_handler.input_dimension,
+        100,
+        data_handler.output_dimension,
+    ]
 
     test_network = mala.Network(parameters)
     test_trainer = mala.Trainer(parameters, test_network, data_handler)
@@ -52,12 +65,12 @@ def initial_setup():
 
 
 if mala.Trainer.run_exists("ex01_checkpoint"):
-    parameters, network, datahandler, trainer = \
-        mala.Trainer.load_run("ex01_checkpoint")
+    parameters, network, datahandler, trainer = mala.Trainer.load_run(
+        "ex01_checkpoint"
+    )
     printout("Starting resumed training.")
 else:
     parameters, network, datahandler, trainer = initial_setup()
     printout("Starting original training.")
 
 trainer.train_network()
-

examples/advanced/ex02_shuffle_data.py

@@ -19,9 +19,12 @@
 parameters.data.shuffling_seed = 1234
 
 data_shuffler = mala.DataShuffler(parameters)
-data_shuffler.add_snapshot("Be_snapshot0.in.npy", data_path,
-                           "Be_snapshot0.out.npy", data_path)
-data_shuffler.add_snapshot("Be_snapshot1.in.npy", data_path,
-                           "Be_snapshot1.out.npy", data_path)
-data_shuffler.shuffle_snapshots(complete_save_path=".",
-                                save_name="Be_shuffled*")
+data_shuffler.add_snapshot(
+    "Be_snapshot0.in.npy", data_path, "Be_snapshot0.out.npy", data_path
+)
+data_shuffler.add_snapshot(
+    "Be_snapshot1.in.npy", data_path, "Be_snapshot1.out.npy", data_path
+)
+data_shuffler.shuffle_snapshots(
+    complete_save_path=".", save_name="Be_shuffled*"
+)

examples/advanced/ex03_tensor_board.py

@@ -4,6 +4,7 @@
 from mala import printout
 
 from mala.datahandling.data_repo import data_repo_path
+
 data_path = os.path.join(data_repo_path, "Be2")
 
 
@@ -29,17 +30,24 @@
 
 
 data_handler = mala.DataHandler(parameters)
-data_handler.add_snapshot("Be_snapshot0.in.npy", data_path,
-                          "Be_snapshot0.out.npy", data_path, "tr")
-data_handler.add_snapshot("Be_snapshot1.in.npy", data_path,
-                          "Be_snapshot1.out.npy", data_path, "va")
+data_handler.add_snapshot(
+    "Be_snapshot0.in.npy", data_path, "Be_snapshot0.out.npy", data_path, "tr"
+)
+data_handler.add_snapshot(
+    "Be_snapshot1.in.npy", data_path, "Be_snapshot1.out.npy", data_path, "va"
+)
 data_handler.prepare_data()
-parameters.network.layer_sizes = [data_handler.input_dimension,
-                                  100,
-                                  data_handler.output_dimension]
+parameters.network.layer_sizes = [
+    data_handler.input_dimension,
+    100,
+    data_handler.output_dimension,
+]
 
 network = mala.Network(parameters)
 trainer = mala.Trainer(parameters, network, data_handler)
 trainer.train_network()
-printout("Run finished, launch tensorboard with \"tensorboard --logdir " +
-         trainer.full_visualization_path + "\"")
+printout(
+    'Run finished, launch tensorboard with "tensorboard --logdir '
+    + trainer.full_visualization_path
+    + '"'
+)

examples/advanced/ex04_acsd.py

@@ -1,8 +1,8 @@
 import os
 
 import mala
-import numpy as np
 from mala.datahandling.data_repo import data_repo_path
+
 data_path = os.path.join(data_repo_path, "Be2")
 
 """
@@ -29,12 +29,20 @@
 # When adding data for the ACSD analysis, add preprocessed LDOS data for
 # and a calculation output for the descriptor calculation.
 ####################
-hyperoptimizer.add_snapshot("espresso-out", os.path.join(data_path, "Be_snapshot1.out"),
-                            "numpy", os.path.join(data_path, "Be_snapshot1.out.npy"),
-                            target_units="1/(Ry*Bohr^3)")
-hyperoptimizer.add_snapshot("espresso-out", os.path.join(data_path, "Be_snapshot2.out"),
-                            "numpy", os.path.join(data_path, "Be_snapshot2.out.npy"),
-                            target_units="1/(Ry*Bohr^3)")
+hyperoptimizer.add_snapshot(
+    "espresso-out",
+    os.path.join(data_path, "Be_snapshot1.out"),
+    "numpy",
+    os.path.join(data_path, "Be_snapshot1.out.npy"),
+    target_units="1/(Ry*Bohr^3)",
+)
+hyperoptimizer.add_snapshot(
+    "espresso-out",
+    os.path.join(data_path, "Be_snapshot2.out"),
+    "numpy",
+    os.path.join(data_path, "Be_snapshot2.out.npy"),
+    target_units="1/(Ry*Bohr^3)",
+)
 
 # If you plan to plot the results (recommended for exploratory searches),
 # the optimizer can return the necessary quantities to plot.

examples/advanced/ex05_checkpoint_hyperparameter_optimization.py

@@ -1,9 +1,9 @@
 import os
 
 import mala
-from mala import printout
 
 from mala.datahandling.data_repo import data_repo_path
+
 data_path = os.path.join(data_repo_path, "Be2")
 
 """
@@ -29,34 +29,47 @@ def initial_setup():
     parameters.hyperparameters.checkpoint_name = "ex05_checkpoint"
 
     data_handler = mala.DataHandler(parameters)
-    data_handler.add_snapshot("Be_snapshot0.in.npy", data_path,
-                              "Be_snapshot0.out.npy", data_path, "tr")
-    data_handler.add_snapshot("Be_snapshot1.in.npy", data_path,
-                              "Be_snapshot1.out.npy", data_path, "va")
+    data_handler.add_snapshot(
+        "Be_snapshot0.in.npy",
+        data_path,
+        "Be_snapshot0.out.npy",
+        data_path,
+        "tr",
+    )
+    data_handler.add_snapshot(
+        "Be_snapshot1.in.npy",
+        data_path,
+        "Be_snapshot1.out.npy",
+        data_path,
+        "va",
+    )
     data_handler.prepare_data()
 
     hyperoptimizer = mala.HyperOpt(parameters, data_handler)
-    hyperoptimizer.add_hyperparameter("float", "learning_rate",
-                                      0.0000001, 0.01)
+    hyperoptimizer.add_hyperparameter(
+        "float", "learning_rate", 0.0000001, 0.01
+    )
     hyperoptimizer.add_hyperparameter("int", "ff_neurons_layer_00", 10, 100)
     hyperoptimizer.add_hyperparameter("int", "ff_neurons_layer_01", 10, 100)
-    hyperoptimizer.add_hyperparameter("categorical", "layer_activation_00",
-                                      choices=["ReLU", "Sigmoid"])
-    hyperoptimizer.add_hyperparameter("categorical", "layer_activation_01",
-                                      choices=["ReLU", "Sigmoid"])
-    hyperoptimizer.add_hyperparameter("categorical", "layer_activation_02",
-                                      choices=["ReLU", "Sigmoid"])
+    hyperoptimizer.add_hyperparameter(
+        "categorical", "layer_activation_00", choices=["ReLU", "Sigmoid"]
+    )
+    hyperoptimizer.add_hyperparameter(
+        "categorical", "layer_activation_01", choices=["ReLU", "Sigmoid"]
+    )
+    hyperoptimizer.add_hyperparameter(
+        "categorical", "layer_activation_02", choices=["ReLU", "Sigmoid"]
+    )
 
     return parameters, data_handler, hyperoptimizer
 
 
 if mala.HyperOptOptuna.checkpoint_exists("ex05_checkpoint"):
-    parameters, datahandler, hyperoptimizer = \
-        mala.HyperOptOptuna.resume_checkpoint(
-            "ex05_checkpoint")
+    parameters, datahandler, hyperoptimizer = (
+        mala.HyperOptOptuna.resume_checkpoint("ex05_checkpoint")
+    )
 else:
     parameters, datahandler, hyperoptimizer = initial_setup()
 
 # Perform hyperparameter optimization.
 hyperoptimizer.perform_study()
-

examples/advanced/ex06_distributed_hyperparameter_optimization.py

@@ -1,9 +1,9 @@
 import os
 
 import mala
-from mala import printout
 
 from mala.datahandling.data_repo import data_repo_path
+
 data_path = os.path.join(data_repo_path, "Be2")
 
 """
@@ -36,7 +36,7 @@
 parameters.hyperparameters.checkpoint_name = "ex06"
 parameters.hyperparameters.hyper_opt_method = "optuna"
 parameters.hyperparameters.study_name = "ex06"
-parameters.hyperparameters.rdb_storage = 'sqlite:///ex06.db'
+parameters.hyperparameters.rdb_storage = "sqlite:///ex06.db"
 
 # Hyperparameter optimization can be further refined by using ensemble training
 # at each step and by using a different metric then the validation loss
@@ -50,27 +50,37 @@
 
 data_handler = mala.DataHandler(parameters)
 
-data_handler.add_snapshot("Be_snapshot1.in.npy", data_path,
-                          "Be_snapshot1.out.npy", data_path, "tr",
-                          calculation_output_file=
-                          os.path.join(data_path, "Be_snapshot1.out"))
-data_handler.add_snapshot("Be_snapshot2.in.npy", data_path,
-                          "Be_snapshot2.out.npy", data_path, "va",
-                          calculation_output_file=
-                          os.path.join(data_path, "Be_snapshot2.out"))
+data_handler.add_snapshot(
+    "Be_snapshot1.in.npy",
+    data_path,
+    "Be_snapshot1.out.npy",
+    data_path,
+    "tr",
+    calculation_output_file=os.path.join(data_path, "Be_snapshot1.out"),
+)
+data_handler.add_snapshot(
+    "Be_snapshot2.in.npy",
+    data_path,
+    "Be_snapshot2.out.npy",
+    data_path,
+    "va",
+    calculation_output_file=os.path.join(data_path, "Be_snapshot2.out"),
+)
 data_handler.prepare_data()
 
 
 hyperoptimizer = mala.HyperOpt(parameters, data_handler)
-hyperoptimizer.add_hyperparameter("float", "learning_rate",
-                                  0.0000001, 0.01)
+hyperoptimizer.add_hyperparameter("float", "learning_rate", 0.0000001, 0.01)
 hyperoptimizer.add_hyperparameter("int", "ff_neurons_layer_00", 10, 100)
 hyperoptimizer.add_hyperparameter("int", "ff_neurons_layer_01", 10, 100)
-hyperoptimizer.add_hyperparameter("categorical", "layer_activation_00",
-                                  choices=["ReLU", "Sigmoid"])
-hyperoptimizer.add_hyperparameter("categorical", "layer_activation_01",
-                                  choices=["ReLU", "Sigmoid"])
-hyperoptimizer.add_hyperparameter("categorical", "layer_activation_02",
-                                  choices=["ReLU", "Sigmoid"])
+hyperoptimizer.add_hyperparameter(
+    "categorical", "layer_activation_00", choices=["ReLU", "Sigmoid"]
+)
+hyperoptimizer.add_hyperparameter(
+    "categorical", "layer_activation_01", choices=["ReLU", "Sigmoid"]
+)
+hyperoptimizer.add_hyperparameter(
+    "categorical", "layer_activation_02", choices=["ReLU", "Sigmoid"]
+)
 hyperoptimizer.perform_study()
 hyperoptimizer.set_optimal_parameters()