Merged in development (pull request #24)

* Feat: Allow setting list-type parameters with single values * Refac: Move logging from wrapper/ -> utils/ * Add single-value type hints in ConstavaParameters help * Hotfix: Special treatment of None in set_single_as_list-decorator. * Add parameter table to README. Minor fix in help texts. * Hotfix: Fix typos, clarify README.
Bio2Byte · Sep 26, 2023 · 6a3a292 · 6a3a292
1 parent 7938b44
commit 6a3a292
Show file tree

Hide file tree

Showing 7 changed files with 80 additions and 42 deletions.
diff --git a/README.md b/README.md
@@ -3,7 +3,7 @@
 <div align="center">
   <a href="bio2byte.be/b2btools" target="_blank" ref="noreferrer noopener">
   <img src="https://pbs.twimg.com/profile_images/1247824923546079232/B9b_Yg7n_400x400.jpg" width="80px"/>
-   </a>
+  </a>
 
   # Constava
 </div>
@@ -25,6 +25,7 @@
     * [Extracting backbone dihedrals as a DataFrame](#extracting-backbone-dihedrals-as-a-dataframe)
     * [Setting parameters and analyzing a conformational ensemble](#setting-parameters-and-analyzing-a-conformational-ensemble)
     * [Generating and loading conformational state models](#generating-and-loading-conformational-state-models)
+    * [Constava-class parameters vs. command line arguments](#constava-class-parameters-vs-command-line-arguments)
 * [License](#license)
 * [Authors](#authors)
 * [Acknowledgements](#acknowledgments)
@@ -393,8 +394,8 @@ output_file = f"./{PDBID}_constava.csv"
 c = Constava(
     input_files = input_files,
     output_file = output_file,
-    window = None,
     bootstrap = [3,5,10,25],
+    input_degrees = True,
     verbose = 2)
 
 # Alter parameters after initialization
@@ -451,6 +452,39 @@ c.run()
 
 [<Go to top>](#constava)
 
+#### Constava-class parameters vs. command line arguments
+
+In the following table, all available parameters of the Python interface (`Constava` 
+class) and their corresponding command line arguments are listed. The defaults for 
+parameters in Python and command line are the same.
+
+| Python parameter | Command line argument | Description |
+|---|---|---|
+| `input_files : List[str] or str` | `constava analyze --input <file> [<file> ...]`  | Input file(s) that contain the dihedral angles. |
+| `input_format : str` | `constava analyze --input-format <enum>` | Format of the input file: `{'auto', 'csv', 'xvg'}` |
+| `output_file : str` | `constava analyze --output <file>` | The file to write the output to. |
+| `output_format : str` | `constava analyze --output-format <enum>` | Format of output file: `{'auto', 'csv', 'json', 'tsv'}` |
+| | | |
+| `model_type : str` | `constava fit-model --model-type <enum>` | The probabilistic conformational state model used. Default is `kde`. The alternative `grid` runs significantly faster while slightly sacrificing accuracy: `{'kde', 'grid'}` |
+| `model_load : str` | `constava analyze --load-model <file>` | Load a conformational state model from the given pickled file. |
+| `model_data : str` | `constava fit-model --input <file>` | Fit conformational state models to data provided in the given file. |
+| `model_dump : str` | `constava fit-model --output <file>` | Write the generated model to a pickled file, that can be loaded again using `model_load`. |
+| | | |
+| `window : List[int] or int` | `constava analyze --window <Int>  [<Int> ...]` | Do inference using a moving reading-frame of <int> consecutive samples. Multiple values can be given as a list. |
+| `window_series : List[int] or int` | `constava analyze --window-series <Int>  [<Int> ...]` | Do inference using a moving reading-frame of <int> consecutive samples. Return the results for every window rather than the average. Multiple values can be given as a list. |
+| `bootstrap : List[int] or int` | `constava analyze --bootstrap <Int> [<Int>  ...]` | Do inference using <Int> samples obtained through bootstrapping. Multiple values can be given as a list. |
+| `bootstrap_samples : int` | `constava analyze --bootstrap-samples <Int> ` | When bootstrapping, sample <Int> times from the input data. |
+| | | |
+| `input_degrees : bool` | `constava analyze --degrees` | Set `True` if input files are in degrees. |
+| `model_data_degrees : bool` | `constava fit-model --degrees` | Set `True` if the data given under `model_data` to is given in degrees. |
+| `precision : int` | `constava analyze --precision <int> ` | Sets the number of decimals in the output files. By default, 4 decimals. |
+| `kde_bandwidth : float` | `constava fit-model --kde-bandwidth <float>` | This controls the bandwidth of the Gaussian kernel density estimator. |
+| `grid_points : int` | `constava analyze --grid-points <int>` | When `model_type` equals 'grid', this controls how many grid points are used to describe the probability density function. |
+| `seed : int` | `constava analyze --seed <int>` | Set the random seed especially for bootstrapping. |
+| `verbose : int` | `constava <...> -v [-v] ` | Set verbosity level of screen output. |
+
+[<Go to top>](#constava)
+
 ## License
 
 Distributed under the GNU General Public License v3 (GPLv3) License.

diff --git a/constava/__main__.py b/constava/__main__.py
@@ -191,7 +191,7 @@ def parse_parameters(cmdline_arguments):
         """\
         Set this flag, if dihedrals in the input files are in 
         degrees."""))
-    anaMisc.add_argument("--precision", type=int, default=4, 
+    anaMisc.add_argument("--precision", metavar="<int>", type=int, default=4, 
         help="Sets the number of decimals in the output files.")
     anaMisc.add_argument("--seed", metavar="<int>", type=int, default=None, 
         required=False, help="Set random seed for bootstrap sampling")

diff --git a/constava/tests/tests.py b/constava/tests/tests.py
@@ -6,7 +6,7 @@
 from constava import Constava
 from constava.utils.constants import CONSTAVA_DATA_DIR
 from constava.calc.csmodels import ConfStateModelLoadingError, ConfStateModelKDE, ConfStateModelGrid
-from constava.wrapper.logging import logging
+from constava.utils.logging import logging
 
 logger = logging.getLogger("Constava")
 
@@ -55,10 +55,6 @@ def get_test_count(cls):
     def test_csmodel_loading_kde(self):
         logger.warning(f"TEST #{self.get_test_count()}: Testing loading procedures for 'kde' models...")
         cva = Constava(verbose=1)
-        # It should fail to load a 'grid' model as kde
-        # with self.assertRaises(ConfStateModelLoadingError):
-        #     c.initialize_calculator(model_type = "kde",
-        #                             load_model = self.grid_model)
         # Load the KDE model
         csmodel0 = cva.load_csmodel(pickled_csmodel = self.kde_model)
         self.assertIsInstance(csmodel0, ConfStateModelKDE, "Failed to load conformational state model.")
@@ -78,10 +74,6 @@ def test_csmodel_loading_kde(self):
     def test_csmodel_loading_grid(self):
         logger.warning(f"TEST #{self.get_test_count()}: Testing loading procedures for 'grid' models...")
         cva = Constava(verbose=1)
-        # # It should fail to load a 'grid' model as kde
-        # with self.assertRaises(ConfStateModelLoadingError):
-        #     c.initialize_calculator(model_type = "grid",
-        #                             load_model = self.kde_model)
         # Load the KDE model
         cva.load_csmodel(pickled_csmodel = self.grid_model)
         csmodel0, cshash0 = cva._csmodel, cva._cshash
@@ -111,7 +103,7 @@ def test_inference_kde(self):
 
     def test_inference_grid(self):
         logger.warning(f"TEST #{self.get_test_count()}: Testing inference for 'grid' models...")
-        input_files = [f"{self.tmpdir}/csv/dihedrals.csv"]
+        input_files = f"{self.tmpdir}/csv/dihedrals.csv"
         expected_result = f"{self.tmpdir}/csv/result_grid.csv"
         output_file  = tempfile.NamedTemporaryFile(prefix="grid.", suffix=".csv", dir=self.tmpdir)
         c = Constava(

diff --git a/constava/wrapper/logging.py → constava/utils/logging.py b/constava/wrapper/logging.py → constava/utils/logging.py
diff --git a/constava/wrapper/params.py b/constava/wrapper/params.py
@@ -1,17 +1,43 @@
 from dataclasses import dataclass, field
-from typing import List, ClassVar
-from .logging import logging
+import typing
+from ..utils.logging import logging
 
 logger = logging.getLogger("Constava")
 
+def set_logger_level(func):
+    """Set logger.level while modifying verbose-attribute"""
+    def _inner_(self, __attr, __value):
+        rvalue = func(self, __attr, __value)
+        if __attr == "verbose":
+            if __value == 0:
+                logger.setLevel(logging.WARNING)
+            elif __value == 1:
+                logger.setLevel(logging.INFO)
+            else:
+                logger.setLevel(logging.DEBUG)
+        return rvalue
+    return _inner_
+
+def set_single_as_list(func):
+    """Allows list-attributes (e.g., window) to be set with a single value"""
+    def _inner_(self, __attr, __value):
+        dtype = typing.get_type_hints(self).get(__attr, None)
+        if typing.get_origin(dtype) is list:
+            if __value is None:
+                __value = []
+            elif not isinstance(__value, typing.Iterable) or isinstance(__value, str):
+                __value = [__value]
+        return func(self, __attr, __value)
+    return _inner_
+
 
 @dataclass
 class ConstavaParameters:
     """The parameters that govern the function of Constava
     
     Parameters:
     -----------
-        input_files : List[str]
+        input_files : List[str] or str
             Input file(s) that contain the dihedral angles.
         input_format : str
             Format of the input file: {'auto', 'csv', 'xvg'}
@@ -32,14 +58,14 @@ class ConstavaParameters:
             Write the generated model to a pickled file, that can be loaded 
             again using `model_load`.
 
-        window : List[int]
+        window : List[int] or int
             Do inference using a moving reading-frame of <int> consecutive samples.
             Multiple values can be given as a list.
-        window_series : List[int]
+        window_series : List[int] or int
             Do inference using a moving reading-frame of <int> consecutive samples.
             Return the results for every window rather than the average. Multiple 
             values can be given as a list.
-        bootstrap : List[int]
+        bootstrap : List[int] or int
             Do inference using <Int> samples obtained through bootstrapping.
             Multiple values can be given as a list.
         bootstrap_samples : int
@@ -60,7 +86,7 @@ class ConstavaParameters:
             Set the random seed especially for bootstrapping.
     """
     # Input/Output Options
-    input_files : List[str] = None
+    input_files : typing.List[str] = field(default_factory=list)
     input_format : str = "auto"
     output_file : str = None
     output_format : str = "auto"
@@ -72,9 +98,9 @@ class ConstavaParameters:
     model_dump : str = None
 
     # Subsampling Options
-    window : List[int] = field(default_factory=list)
-    bootstrap : List[int] = field(default_factory=list)
-    window_series : List[int] = field(default_factory=list)
+    window : typing.List[int] = field(default_factory=list)
+    bootstrap : typing.List[int] = field(default_factory=list)
+    window_series : typing.List[int] = field(default_factory=list)
     bootstrap_samples : int = 500
 
     # Miscellaneous Options
@@ -89,22 +115,8 @@ class ConstavaParameters:
     # References to the owning Constava object, not to be set by user
     _constava = None
 
+    @set_logger_level
+    @set_single_as_list
     def __setattr__(self, __attr, __value) -> None:
         """Custom function to set attributes, to catch certain special behaviours"""
-        # Set the actual value
-        super(ConstavaParameters, self).__setattr__(__attr, __value)
-        # Some special behaviours for selected cases
-        # ... "model_load" and "model_data" are mutually exclusive
-        if __attr == "model_load" and __value is not None and self.model_data is not None:
-            logger.warning("`model_load` takes precedence over `model_data`. The latter will be ignored.")
-        # ... "model_load" and "model_data" are mutually exclusive
-        elif __attr == "model_data" and __value is not None and __value and self.model_load is not None:
-            logger.warning("`model_load` is not None. While `model_load` is set `model_data` will be ignored")
-        # ... if verbosity is changed, apply to logger
-        elif __attr == "verbose":
-            if __value == 0:
-                logger.setLevel(logging.WARNING)
-            elif __value == 1:
-                logger.setLevel(logging.INFO)
-            else:
-                logger.setLevel(logging.DEBUG)
+        super().__setattr__(__attr, __value)
diff --git a/constava/wrapper/wrapper.py b/constava/wrapper/wrapper.py
@@ -2,7 +2,7 @@
 from typing import List
 
 from ..utils.constants import DEFAULT_TRAINING_DATA_PATH
-from .logging import logging
+from ..utils.logging import logging
 from .params import ConstavaParameters
 from ..io import ResultsWriter, EnsembleReader
 from ..calc.calculator import ConfStateCalculator

diff --git a/setup.py b/setup.py
@@ -5,7 +5,7 @@
 
 setup(
     name="constava",
-    version="1.0.0b3",
+    version="1.0.0b4",
     author="Wim Vranken",
     author_email="[email protected]",
     description="This software is used to calculate conformational states probability & conformational state "