Replaced hand-chosen regressors with completely arbitrary ones

Instead of having the `--regressor` option take one of a few hand-chosen
values, it now takes the name of _any arbitrary regressor object_, such
as the default, `--regressor sklearn.linear_model.LassoLarsIC`. This
requires a little more user-knowledge, but opens a world of
possibilities.

This is accomplished through the new `plotypus.utils.import_name`
function, which imports an object from its full name and returns it,
without affecting the enclosing namespace.

src/plotypus/cli.py

@@ -5,8 +5,7 @@
 import dill
 from argparse import ArgumentError, ArgumentParser, SUPPRESS
 from pandas import read_table
-from sklearn.linear_model import (LassoCV, LassoLarsCV, LassoLarsIC,
-                                  LinearRegression, RidgeCV, ElasticNetCV)
+import sklearn.linear_model
 from sklearn.grid_search import GridSearchCV
 from matplotlib import rc_params_from_file
 from collections import ChainMap
@@ -20,8 +19,9 @@
                                   plot_periodogram)
 import plotypus
 from plotypus.preprocessing import Fourier
-from plotypus.utils import (colvec, mad, make_sure_path_exists, pmap,
-                            strlist_to_dict, valid_basename, verbose_print)
+from plotypus.utils import (colvec, import_name, mad, make_sure_path_exists,
+                            pmap, strlist_to_dict, valid_basename,
+                            verbose_print)
 from plotypus.resources import matplotlibrc
 
 import pkg_resources # part of setuptools
@@ -277,12 +277,12 @@ def get_args():
         default=(2, 20), metavar=('MIN', 'MAX'),
         help='range of degrees of fourier fits to use '
              '(default = 2 20)')
-    fourier_group.add_argument('-r', '--regressor',
-        choices=['LassoCV', 'LassoLarsCV', 'LassoLarsIC', 'OLS', 'RidgeCV',
-                 'ElasticNetCV'],
-        default='LassoLarsIC',
-        help='type of regressor to use '
-             '(default = "Lasso")')
+    fourier_group.add_argument('-r', '--regressor', type=import_name,
+        default=sklearn.linear_model.LassoLarsIC,
+        help='type of regressor to use, loads any Python object named like '
+             '*module.submodule.etc.object_name*, though it must behave like a '
+             'scikit-learn regressor '
+             '(default = "sklearn.linear_model.LassoLarsIC")')
     fourier_group.add_argument('--selector',
         choices=['Baart', 'GridSearch'],
         default='GridSearch',
@@ -333,16 +333,6 @@ def get_args():
     # parse regressor (TODO: and selector) options into a dict
     regressor_options = strlist_to_dict(args.regressor_options)
 
-    regressor_choices = {
-        "LassoCV"             : LassoCV,
-        "LassoLarsCV"         : LassoLarsCV,
-        "LassoLarsIC"         : LassoLarsIC,
-        "OLS"                 : LinearRegression,
-        "RidgeCV"             : RidgeCV,
-        "ElasticNetCV"        : ElasticNetCV
-    }
-
-
     selector_choices = {
         "Baart"               : None,
         "GridSearch"          : GridSearchCV
@@ -363,7 +353,7 @@ def get_args():
         }
         args.scoring = scoring_choices[args.scoring]
 
-    args.regressor = regressor_choices[args.regressor](**regressor_options)
+    args.regressor = args.regressor(**regressor_options)
     Selector = selector_choices[args.selector] or GridSearchCV
     args.periodogram = periodogram_choices[args.periodogram]
     args.sigma_clipping = sigma_clipping_choices[args.sigma_clipping]

src/plotypus/utils.py

@@ -8,6 +8,7 @@
 
 __all__ = [
     'verbose_print',
+    'import_name',
     'literal_eval_str',
     'strlist_to_dict',
     'pmap',
@@ -47,6 +48,51 @@ def verbose_print(message, *, operation, verbosity):
         print(message, file=stderr)
 
 
+def import_name(dotted_name):
+    """import_name(dotted_name)
+
+    Import an object from a module, and return the object. Does not affect the
+    encapsulating namespace.
+
+    **Parameters**
+
+    dotted_name : str
+        The fully-qualified name of the object to import, in the form
+        *module.submodule.etc.object_name*. Will error if *dotted_name* is
+        a top-level module (e.g. *module* and not *module.something*) or if
+        the object does not exist.
+
+    **Returns**
+
+    obj : object
+        The object specified by *dotted_name*.
+    """
+    # Separate `module.submodule.object` into `[module, submodule]` and `object`
+    *module_path_components, object_name = dotted_name.split(".")
+
+    # Ensure `object_name` is contained within a module, and is not a
+    # standalone module.
+    # In other words, make sure `dotted_name` is a module containing an object
+    # like `foo.bar.baz` and not just a module like `baz`
+    if len(module_path_components) == 0:
+        raise ValueError("must name object within a module, not just a module")
+
+    # Reinsert the dots into the module name, e.g. turn
+    # `[module, submodule]` back into `module.submodule`
+    module_name = ".".join(module_path_components)
+
+    # import the module
+    from importlib import import_module
+    module = import_module(module_name)
+
+    # return the desired object
+    try:
+        return getattr(module, object_name)
+    except AttributeError:
+        raise ImportError("module '{module}' has no object '{object_name}'"
+                          .format(module=module_name, object_name=object_name))
+
+
 def literal_eval_str(string):
     """literal_eval_str(string)