Merge pull request #42 from gmrukwa/develop

Release v2.3.19

.github/workflows/deploy.yml

@@ -12,7 +12,7 @@ on:
 env:
   MAJOR: ${{ 2 }}
   MINOR: ${{ 3 }}
-  FIXUP: ${{ 18 }}
+  FIXUP: ${{ 19 }}
   PACKAGE_INIT_FILE: ${{ 'divik/__init__.py' }}
   DOCKER_REPO: ${{ 'gmrukwa/divik' }}
   IS_ALPHA: ${{ github.event_name == 'pull_request' }}

README.md

@@ -40,7 +40,7 @@ docker pull gmrukwa/divik
 To install specific version, you can specify it in the command, e.g.:
 
 ```bash
-docker pull gmrukwa/divik:2.3.18
+docker pull gmrukwa/divik:2.3.19
 ```
 
 ## Python package
@@ -60,7 +60,7 @@ pip install divik
 or any stable tagged version, e.g.:
 
 ```bash
-pip install divik==2.3.18
+pip install divik==2.3.19
 ```
 
 If you want to have compatibility with

divik/__init__.py

@@ -1,4 +1,4 @@
-__version__ = '2.3.18'
+__version__ = '2.3.19'
 
 from divik import core
 from divik import feature_selection

divik/_cli/_data_io.py

@@ -35,7 +35,8 @@ def _load_mat(path: str) -> np.ndarray:
         return _load_mat_with(path, backend=scio.loadmat, ignore='__')
     except NotImplementedError:  # v7.3 MATLAB HDF5 MAT-File
         logging.debug('Legacy MAT-file loader failed, restarting with HDF5 loader.')
-        return _load_mat_with(path, backend=h5py.File, ignore='#').T
+        hdf5 = partial(h5py.File, mode='r')
+        return _load_mat_with(path, backend=hdf5, ignore='#').T
 
 
 def _load_disk_file(path: str) -> u.Data:

divik/_cli/_utils.py

@@ -48,22 +48,39 @@ def prepare_destination(destination: str, omit_datetime: bool = False) -> str:
     return destination
 
 
-def setup_logger(destination: str, verbose: bool = False):
+_PRECISE_FORMAT = '%(asctime)s [%(levelname)s] %(filename)40s:%(lineno)3s' \
+    + ' - %(funcName)40s\t%(message)s'
+_INFO_FORMAT = '%(asctime)s [%(levelname)s]\t%(message)s'
+
+
+def _file_handler(destination: str):
     log_destination = os.path.join(destination, 'logs.txt')
+    handler = logging.FileHandler(filename=log_destination, mode='a')
+    handler.setLevel(logging.DEBUG)
+    handler.setFormatter(logging.Formatter(_PRECISE_FORMAT))
+    return handler
+
+
+def _stream_handler(verbose: bool):
+    handler = logging.StreamHandler(tqdm.tqdm)
     if verbose:
-        log_format = '%(asctime)s [%(levelname)s] %(filename)40s:%(lineno)3s' \
-                     + ' - %(funcName)40s\t%(message)s'
-        log_level = logging.DEBUG
+        handler.setLevel(logging.INFO)
+        handler.setFormatter(logging.Formatter(_INFO_FORMAT))
     else:
-        log_format = '%(asctime)s [%(levelname)s]\t%(message)s'
-        log_level = logging.INFO
+        handler.setLevel(logging.CRITICAL)
+        handler.setFormatter(logging.Formatter(_INFO_FORMAT))
+    return handler
+
+
+def setup_logger(destination: str, verbose: bool = False):
+    stream_handler = _stream_handler(verbose)
+    file_handler = _file_handler(destination)
     handlers = [
-        logging.StreamHandler(tqdm.tqdm),
-        logging.FileHandler(filename=log_destination,
-                            mode='a')
+        stream_handler,
+        file_handler,
     ]
     del logging.root.handlers[:]
-    logging.basicConfig(format=log_format, level=log_level, handlers=handlers)
+    logging.basicConfig(level=logging.DEBUG, handlers=handlers)
     version_notice = "Using " + sys.argv[0] + \
                      " (divik, version " + __version__ + ")"
     logging.info(version_notice)

divik/cluster/_divik/_dunn.py

@@ -23,7 +23,7 @@ def _recursive_selection(current_selection: np.ndarray, partition: np.ndarray,
 
 # @gmrukwa: I could not find more readable solution than recursion for now.
 def dunn_divik(data: Data, selection: np.ndarray,
-               fast_kmeans: DunnSearch, full_kmeans: GAPSearch,
+               fast_kmeans: GAPSearch, full_kmeans: DunnSearch,
                feature_selector: StatSelector,
                minimal_size: int, rejection_size: int, report: DivikReporter) \
         -> Optional[DivikResult]:

divik/feature_selection/_stat_selector_mixin.py

@@ -2,7 +2,10 @@
 
 import numpy as np
 from sklearn.base import BaseEstimator
-from sklearn.feature_selection._base import SelectorMixin
+try:
+    from sklearn.feature_selection._base import SelectorMixin
+except ImportError:
+    from sklearn.feature_selection.base import SelectorMixin
 
 
 class StatSelectorMixin(SelectorMixin, metaclass=ABCMeta):

docs/instructions/installation.rst

@@ -14,7 +14,7 @@ To install latest stable version use::
 
 To install specific version, you can specify it in the command, e.g.::
 
-    docker pull gmrukwa/divik:2.3.18
+    docker pull gmrukwa/divik:2.3.19
 
 Python package
 --------------
@@ -31,7 +31,7 @@ package::
 
 or any stable tagged version, e.g.::
 
-    pip install divik==2.3.18
+    pip install divik==2.3.19
 
 If you want to have compatibility with
 `gin-config <https://github.com/google/gin-config>`_, you can install