Release 1.1.0

.bumpversion.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 0.0.5
+current_version = 1.0.0
 commit = True
 tag = True
 files = setup.py campa/__init__.py

.pre-commit-config.yaml

@@ -7,28 +7,30 @@ default_stages:
 minimum_pre_commit_version: 2.9.3
 repos:
 -   repo: https://github.com/pre-commit/mirrors-mypy
-    rev: v0.910
+    rev: v0.982
     hooks:
     -   id: mypy
         additional_dependencies: [numpy==1.20.0, scipy, pandas, types-requests]
 -   repo: https://github.com/psf/black
-    rev: 21.6b0
+    rev: 22.10.0
     hooks:
     -   id: black
         additional_dependencies: [toml]
 -   repo: https://github.com/timothycrosley/isort
-    rev: 5.9.1
+    rev: 5.10.1
     hooks:
     -   id: isort
         additional_dependencies: [toml]
         args: [--order-by-type]
--   repo: https://github.com/asottile/yesqa
-    rev: v1.2.3
-    hooks:
-    -   id: yesqa
-        additional_dependencies: [flake8-tidy-imports, flake8-docstrings, flake8-rst-docstrings, flake8-comprehensions, flake8-bugbear, flake8-logging-format, flake8-blind-except, flake8-builtins, flake8-pytest-style, flake8-mock, flake8-string-format]
+# temporarily disable yesqa, because of: ValueError: not enough values to unpack (expected 2, got 1).
+# Possibly related to https://github.com/asottile/yesqa/issues/132
+#-   repo: https://github.com/asottile/yesqa
+#    rev: v1.4.0
+#    hooks:
+#    -   id: yesqa
+#        additional_dependencies: [flake8-tidy-imports, flake8-docstrings, flake8-rst-docstrings, flake8-comprehensions, flake8-bugbear, flake8-logging-format, flake8-blind-except, flake8-builtins, flake8-pytest-style, flake8-mock, flake8-string-format]
 -   repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.0.1
+    rev: v4.3.0
     hooks:
     -   id: detect-private-key
     -   id: check-merge-conflict
@@ -49,7 +51,7 @@ repos:
     -   id: check-toml
     -   id: requirements-txt-fixer
 -   repo: https://github.com/myint/autoflake
-    rev: v1.4
+    rev: v1.7.7
     hooks:
     -   id: autoflake
         args: [--in-place, --remove-all-unused-imports, --remove-unused-variable, --ignore-init-module-imports]
@@ -59,29 +61,29 @@ repos:
     -   id: flake8
         additional_dependencies: [flake8-tidy-imports, flake8-docstrings, flake8-rst-docstrings, flake8-comprehensions, flake8-bugbear, flake8-logging-format, flake8-blind-except, flake8-builtins, flake8-pytest-style, flake8-mock, flake8-string-format]
 -   repo: https://github.com/jumanjihouse/pre-commit-hooks
-    rev: 2.1.5
+    rev: 3.0.0
     hooks:
     -   id: script-must-have-extension
         name: Check executable files use .sh extension
         types: [shell, executable]
 # YAML files
 -   repo: https://github.com/macisamuele/language-formatters-pre-commit-hooks
-    rev: v2.1.0
+    rev: v2.4.0
     hooks:
     -   id: pretty-format-yaml
         args: [--autofix, --indent, '4']
 # docs (md/rst files)
--   repo: https://github.com/myint/rstcheck
-    rev: 3f92957478422df87bd730abde66f089cc1ee19b
-    hooks:
-    -   id: rstcheck
+#-   repo: https://github.com/myint/rstcheck
+#    rev: v6.1.0
+#    hooks:
+#    -   id: rstcheck
 -   repo: https://github.com/asottile/blacken-docs
-    rev: v1.10.0
+    rev: v1.12.1
     hooks:
     -   id: blacken-docs
-        additional_dependencies: [black==20.8b1]
+        additional_dependencies: [black==22.10.0]
 -   repo: https://github.com/asottile/pyupgrade
-    rev: v2.19.4
+    rev: v3.1.0
     hooks:
     -   id: pyupgrade
         args: [--py3-plus, --py37-plus]
@@ -95,26 +97,26 @@ repos:
     -   id: rst-directive-colons
     -   id: rst-inline-touching-normal
 -   repo: https://github.com/PyCQA/doc8
-    rev: 0.9.0a1
+    rev: v1.0.0
     hooks:
     -   id: doc8
 # jupyter notebooks
 -   repo: https://github.com/nbQA-dev/nbQA
-    rev: 1.3.1
+    rev: 1.5.3
     hooks:
     -   id: nbqa-black
-        additional_dependencies: [black==21.6b0]
+        additional_dependencies: [black==22.10.0]
     -   id: nbqa-isort
         additional_dependencies: [isort==5.9.1]
         args: [--order-by-type]
     -   id: nbqa
         entry: nbqa autoflake
         name: nbqa-autoflake
         alias: nbqa-autoflake
-        additional_dependencies: [autoflake==v1.4]
+        additional_dependencies: [autoflake==v1.7.7]
         args: [--in-place, --remove-all-unused-imports, --remove-unused-variable, --ignore-init-module-imports]
     -   id: nbqa-flake8
         additional_dependencies: [flake8==3.9.2, flake8-tidy-imports, flake8-docstrings, flake8-rst-docstrings, flake8-comprehensions, flake8-bugbear, flake8-logging-format, flake8-blind-except, flake8-builtins, flake8-pytest-style, flake8-mock, flake8-string-format]
     -   id: nbqa-pyupgrade
         args: [--py3-plus, --py37-plus]
-        additional_dependencies: [pyupgrade==v2.19.4]
+        additional_dependencies: [pyupgrade==v3.1.0]

.rstcheck.cfg

@@ -1,3 +1,3 @@
 [rstcheck]
-ignore_messages=(Unknown target name:.*|No (directive|role) entry for "(auto)?(bibliography|nbgallery|class|method|property|function|func|mod|module|attribute|argparse)" in module "docutils\.parsers\.rst\.languages\.en"\.|Hyperlink target "campatutorials" is not referenced.)
+ignore_messages=(Unknown target name:.*|No (directive|role) entry for "(auto)?(bibliography|nbgallery|class|method|property|function|func|mod|module|attribute|argparse|currentmodule|autosummary)" in module "docutils\.parsers\.rst\.languages\.en"\.|Hyperlink target "campatutorials" is not referenced.)
 report=info

README.rst

@@ -30,14 +30,10 @@ Please see our preprint
 Installation
 ------------
 
-Install CAMPA by running::
+CAMPA was developed for Python 3.9 and can be installed by running::
 
     pip install campa
 
-Setup `data and experiment paths`_ with::
-
-    campa setup
-
 
 Contributing
 ------------

README_pypi.rst

@@ -27,14 +27,10 @@ Please see our preprint
 Installation
 ------------
 
-Install CAMPA by running::
+CAMPA was developed for Python 3.9 and can be installed by running::
 
     pip install campa
 
-Setup `data and experiment paths`_ with::
-
-    campa setup
-
 
 Contributing
 ------------

campa/__init__.py

@@ -2,7 +2,7 @@
 
 __author__ = __maintainer__ = "Hannah Spitzer, Scott Berry"
 __email__ = ", ".join(["hannah.spitzer@helmholtz-muenchen.de", "scott.berry@unsw.edu.au"])
-__version__ = "0.0.5"
+__version__ = "1.0.0"
 
 
 from importlib.metadata import version

campa/cli/main.py

@@ -13,7 +13,7 @@ def _get_base_parser():
         usage="""campa <command> [<args>]
 
 Available subcommands are:
-setup               Create configuration file campa.ini
+setup               Create configuration file ``campa.ini``
 create_dataset      Create NNDataset using parameter file
 train               Train and evaluate models defined by experiment config
 cluster             Cluster data and project clustering
@@ -25,18 +25,18 @@ def _get_base_parser():
 
 
 def _get_setup_parser():
-    parser = argparse.ArgumentParser(description="Create configuration file campa.ini.")
+    parser = argparse.ArgumentParser(description="Create configuration file ``campa.ini``.")
     parser.add_argument(
-        "--force",
+        "--quiet",
         action="store_true",
-        help="force recreation of campa.ini even if exists",
+        help="create default configuration file without asking for user input.",
     )
     return parser
 
 
 def _get_create_dataset_parser():
     parser = argparse.ArgumentParser(description=("Create NNDataset using parameter file"))
-    parser.add_argument("params", help="path to data_params.py")
+    parser.add_argument("params", help="path to ``data_params.py``")
     return parser
 
 
@@ -48,10 +48,10 @@ def _get_train_parser():
         choices=["all", "train", "evaluate", "trainval", "compare"],
     )
     group = parser.add_mutually_exclusive_group(required=True)
-    group.add_argument("--config", help="path_to_experiment_config.py")
+    group.add_argument("--config", help="path to ``experiment_config.py``")
     group.add_argument(
         "--experiment-dir",
-        help="experiment_dir containing experiment folders. Relative to EXPERIMENT_DIR",
+        help="``experiment_dir`` containing experiment folders. Relative to EXPERIMENT_DIR",
     )
     parser.add_argument(
         "--exp-name",
@@ -80,37 +80,47 @@ def _get_cluster_parser():
     )
     create.add_argument(
         "--save-dir",
-        help="directory to save subsampled cluster data, relative to experiment dir. Default is aggregated/sub-FRAC",  # noqa: E501
+        help="directory to save subsampled cluster data, relative to ``experiment-dir``. Default is ``aggregated/sub-FRAC``",  # noqa: E501
     )
     create.add_argument(
         "--cluster",
-        help="use cluster params in Experiment config to cluster the subsetted data.",
+        help="use cluster parameters in Experiment config to cluster the subsetted data.",
         action="store_true",
     )
     create.set_defaults(func=campa.tl.create_cluster_data)
     # prepare-full
     prepare = subparsers.add_parser("prepare-full", help="Prepare full data for clustering. Predicts cluster-rep.")
     prepare.add_argument(
         "--save-dir",
-        help="directory to save prepared full data to, relative to experiment dir.",
+        help="directory to save prepared full data to, relative to ``experiment-dir``.",
         default="aggregated/full_data",
     )
+    prepare.add_argument(
+        "--data-dirs",
+        help="Data directories to prepare. Defaults to experiment data directories",
+        nargs="+",
+        type=str,
+        default=None,
+    ),
     prepare.set_defaults(func=campa.tl.prepare_full_dataset)
     # project
     project = subparsers.add_parser("project", help="Project existing clustering.")
     project.add_argument(
         "cluster_data_dir",
         metavar="cluster-data-dir",
-        help="directory in which clustering is stored relative to experiment dir. Usually in aggregated/sub-FRAC",
+        help="""
+        directory in which clustering is stored relative to ``experiment-dir``.
+        Usually in ``aggregated/sub-FRAC``
+        """,
     )
     project.add_argument(
         "--save-dir",
-        help="directory in which data to be projected is stored, relative to experiment dir.",
+        help="directory in which data to be projected is stored, relative to ``experiment-dir``.",
         default="aggregated/full_data",
     )
     project.add_argument(
         "--data-dir",
-        help="data to project. If not specified, project all data_dirs in save_dir",
+        help="data to project. If not specified, project all ``data_dirs`` in ``save_dir``",
     )
     project.add_argument("--cluster-name", default="clustering", help="name of clustering to project")
     project.set_defaults(func=campa.tl.project_cluster_data)
@@ -119,7 +129,7 @@ def _get_cluster_parser():
 
 def _get_extract_features_parser():
     parser = argparse.ArgumentParser(description=("Extract features from clustered dataset."))
-    parser.add_argument("params", help="path to feature_params.py")
+    parser.add_argument("params", help="path to ``feature_params.py``")
     return parser
 
 
@@ -141,7 +151,7 @@ def setup(self):
         parser = _get_setup_parser()
         args = parser.parse_args(sys.argv[2:])
         # create and populate campa.ini
-        prepare_config(args)
+        prepare_config(**vars(args))
 
     def create_dataset(self):
         parser = _get_create_dataset_parser()
@@ -165,11 +175,12 @@ def cluster(self):
         parser = _get_cluster_parser()
         args = parser.parse_args(sys.argv[2:])
         init_logging()
+        vars_args = vars(args)
         try:
-            func = args.func
+            func = vars_args.pop("func")
         except AttributeError:
             parser.error("too few arguments")
-        func(**vars(args))
+        func(**vars_args)
 
     def extract_features(self):
         parser = _get_extract_features_parser()

campa/cli/prepare_config.py

@@ -5,7 +5,7 @@
 from campa.constants import campa_config
 
 
-def prepare_config(args):
+def prepare_config(quiet=False):
     def get_yn_input():
         r = input()
         while r.lower() not in ("y", "n"):
@@ -49,14 +49,15 @@ def get_path_input(name, current_value=None):
         )
         campa_config.write()
 
-    print("Would you like to configure your campa.ini config now? (y/n)")
-    if get_yn_input():
-        # read config file
-        campa_config.EXPERIMENT_DIR = get_path_input("EXPERIMENT_DIR", campa_config.EXPERIMENT_DIR)
-        campa_config.BASE_DATA_DIR = get_path_input("BASE_DATA_DIR", campa_config.BASE_DATA_DIR)
-        campa_config.write()
-    else:
-        print("Exiting without setting up campa.ini")
+    if not quiet:
+        print("Would you like to configure your campa.ini config now? (y/n)")
+        if get_yn_input():
+            # read config file
+            campa_config.EXPERIMENT_DIR = get_path_input("EXPERIMENT_DIR", campa_config.EXPERIMENT_DIR)
+            campa_config.BASE_DATA_DIR = get_path_input("BASE_DATA_DIR", campa_config.BASE_DATA_DIR)
+            campa_config.write()
+        else:
+            print("Exiting without setting up campa.ini")
 
     # print currently registered data config files
     print(f"Currently registered data configs in {campa_config.config_fname}:")