Convert modules into sub-packages

.travis.yml

@@ -6,10 +6,10 @@ notifications:
   slack:
     secure: d+NSaR+cfRkcJfX/uEVwdyQDlayZO6c8QV96grl1stmWxG3XOXvXg1tM6v7EBeb9VRw5T4VglnnJGNJA62j1ReEJ0XyWr5XtaNWiF6Lc4UOty/TTG36IQdkWS1vQA8v2Hre73YbvOhtBb6biNneVAk+rrfRSgomEa+ec22cjgUo=
 env:
-  - TESTFILES="tests/test_featureset.py tests/test_utilities.py"
+  - TESTFILES="tests/test_featureset.py tests/test_commandline_utils.py"
   - TESTFILES="tests/test_output.py"
   - TESTFILES="tests/test_regression.py"
-  - TESTFILES="tests/test_input.py tests/test_preprocessing.py tests/test_metrics.py tests/test_custom_learner.py tests/test_logutils.py tests/test_examples.py"
+  - TESTFILES="tests/test_input.py tests/test_preprocessing.py tests/test_metrics.py tests/test_custom_learner.py tests/test_logging_utils.py tests/test_examples.py"
   - TESTFILES="tests/test_classification.py tests/test_cv.py tests/test_ablation.py"
 
 # run on the new Travis infrastructure

DistributeTests.ps1

@@ -30,7 +30,7 @@ $testsToRun= @()
 
 if ($agentNumber -eq 1) {
     $testsToRun = $testsToRun + "tests/test_featureset.py"
-    $testsToRun = $testsToRun + "tests/test_utilities.py"
+    $testsToRun = $testsToRun + "tests/test_commandline_utils.py"
 }
 elseif ($agentNumber -eq 2) {
     $testsToRun = $testsToRun + "tests/test_output.py"
@@ -43,7 +43,7 @@ elseif ($agentNumber -eq 4) {
     $testsToRun = $testsToRun + "tests/test_preprocessing.py"
     $testsToRun = $testsToRun + "tests/test_metrics.py"
     $testsToRun = $testsToRun + "tests/test_custom_learner.py"
-    $testsToRun = $testsToRun + "tests/test_logutils.py"
+    $testsToRun = $testsToRun + "tests/test_logging_utils.py"
     $testsToRun = $testsToRun + "tests/test_examples.py"
 }
 elseif ($agentNumber -eq 5) {

doc/api.rst

@@ -8,7 +8,9 @@ API Documentation
 
    api/quickstart
    api/skll
+   api/config
    api/data
    api/experiments
    api/learner
    api/metrics
+   api/utils

doc/api/config.rst

@@ -0,0 +1,6 @@
+:mod:`config` Package
+=====================
+
+.. autofunction:: skll.config.fix_json
+.. autofunction:: skll.config.load_cv_folds
+.. autofunction:: skll.config.locate_file

doc/api/experiments.rst

@@ -1,5 +1,5 @@
-:mod:`experiments` Module
-=========================
+:mod:`experiments` Package
+==========================
 
 .. automodule:: skll.experiments
     :members:

doc/api/learner.rst

@@ -1,5 +1,5 @@
-:mod:`learner` Module
-=====================
+:mod:`learner` Package
+======================
 
 .. automodule:: skll.learner
     :members:

doc/api/quickstart.rst

@@ -5,7 +5,7 @@ Here is a quick run-down of how you accomplish common tasks.
 
 Load a ``FeatureSet`` from a file::
 
-    from skll import Reader
+    from skll.data import Reader
 
     example_reader = Reader.for_path('myexamples.megam')
     train_examples = example_reader.read()

doc/api/skll.rst

@@ -1,33 +1,22 @@
 :mod:`skll` Package
 ===================
 
-The most useful parts of our API are available at the package level in addition
-to the module level. They are documented in both places for convenience.
+We have made the most useful parts of our API available in the top-level
+``skll`` namespace even though some of them actually live in subpackages.
+They are documented in both places for convenience.
 
 From :py:mod:`~skll.data` Package
 ---------------------------------
 .. autoclass:: skll.FeatureSet
     :members:
     :show-inheritance:
-.. autoclass:: skll.Reader
-    :members:
-    :show-inheritance:
-.. autoclass:: skll.Writer
-    :members:
-    :show-inheritance:
 
-From :py:mod:`~skll.experiments` Module
----------------------------------------
+From :py:mod:`~skll.experiments` Package
+----------------------------------------
 .. autofunction:: skll.run_configuration
 
-From :py:mod:`~skll.learner` Module
------------------------------------
+From :py:mod:`~skll.learner` Package
+------------------------------------
 .. autoclass:: skll.Learner
     :members:
     :show-inheritance:
-
-From :py:mod:`~skll.metrics` Module
------------------------------------
-.. autofunction:: skll.f1_score_least_frequent
-.. autofunction:: skll.kappa
-.. autofunction:: skll.correlation

doc/api/utils.rst

@@ -0,0 +1,15 @@
+:mod:`utils` Package
+====================
+
+Various useful constants defining groups of evaluation metrics.
+
+.. autodata:: skll.utils.constants.CLASSIFICATION_ONLY_METRICS
+.. autodata:: skll.utils.constants.CORRELATION_METRICS
+.. autodata:: skll.utils.constants.PROBABILISTIC_METRICS
+.. autodata:: skll.utils.constants.REGRESSION_ONLY_METRICS
+.. autodata:: skll.utils.constants.UNWEIGHTED_KAPPA_METRICS
+.. autodata:: skll.utils.constants.WEIGHTED_KAPPA_METRICS
+
+A useful logging function for SKLL developers
+
+.. autofunction:: skll.utils.logging.get_skll_logger

examples/make_titanic_example_data.py

@@ -10,10 +10,9 @@
 
 import logging
 import os
-import sys
 from itertools import chain
 
-from skll import Writer, Reader
+from skll.data import Reader, Writer
 
 
 def main():

setup.py

@@ -31,15 +31,15 @@ def requirements():
       license='BSD 3 clause',
       packages=find_packages(exclude=['tests', 'examples']),
       entry_points={'console_scripts':
-                    ['filter_features = skll.utilities.filter_features:main',
-                     'generate_predictions = skll.utilities.generate_predictions:main',
-                     'join_features = skll.utilities.join_features:main',
-                     'print_model_weights = skll.utilities.print_model_weights:main',
-                     'run_experiment = skll.utilities.run_experiment:main',
-                     'skll_convert = skll.utilities.skll_convert:main',
-                     'summarize_results = skll.utilities.summarize_results:main',
-                     'compute_eval_from_predictions = skll.utilities.compute_eval_from_predictions:main',
-                     'plot_learning_curves = skll.utilities.plot_learning_curves:main']},
+                    ['filter_features = skll.utils.commandline.filter_features:main',
+                     'generate_predictions = skll.utils.commandline.generate_predictions:main',
+                     'join_features = skll.utils.commandline.join_features:main',
+                     'print_model_weights = skll.utils.commandline.print_model_weights:main',
+                     'run_experiment = skll.utils.commandline.run_experiment:main',
+                     'skll_convert = skll.utils.commandline.skll_convert:main',
+                     'summarize_results = skll.utils.commandline.summarize_results:main',
+                     'compute_eval_from_predictions = skll.utils.commandline.compute_eval_from_predictions:main',
+                     'plot_learning_curves = skll.utils.commandline.plot_learning_curves:main']},
       install_requires=requirements(),
       classifiers=['Intended Audience :: Science/Research',
                    'Intended Audience :: Developers',

skll/__init__.py

@@ -3,43 +3,37 @@
 This package provides a number of utilities to make it simpler to run
 common scikit-learn experiments with pre-generated features.
 
+:author: Nitin Madnani (nmadnani@ets.org)
 :author: Dan Blanchard (dblanchard@ets.org)
 :author: Michael Heilman (mheilman@ets.org)
-:author: Nitin Madnani (nmadnani@ets.org)
 :organization: ETS
 """
 
 from sklearn.metrics import f1_score, make_scorer, SCORERS
-from .logutils import (close_and_remove_logger_handlers,
-                       get_skll_logger, orig_showwarning)
-from .data import FeatureSet, Reader, Writer
+from .data import FeatureSet
 from .experiments import run_configuration
 from .learner import Learner
 from .metrics import correlation, f1_score_least_frequent, kappa
 
-__all__ = ['FeatureSet', 'Learner', 'Reader', 'get_skll_logger',
-           'orig_showwarning', 'close_and_remove_logger_handlers',
-           'run_configuration', 'Writer']
+__all__ = ['FeatureSet', 'Learner', 'run_configuration']
 
 # Add our scorers to the sklearn dictionary here so that they will always be
 # available if you import anything from skll
-_scorers = {'f1_score_micro': make_scorer(f1_score,
-                                          average='micro'),
-            'f1_score_macro': make_scorer(f1_score,
-                                          average='macro'),
-            'f1_score_weighted': make_scorer(f1_score,
-                                             average='weighted'),
+_scorers = {'f1_score_micro': make_scorer(f1_score, average='micro'),
+            'f1_score_macro': make_scorer(f1_score, average='macro'),
+            'f1_score_weighted': make_scorer(f1_score, average='weighted'),
             'f1_score_least_frequent': make_scorer(f1_score_least_frequent),
             'pearson': make_scorer(correlation, corr_type='pearson'),
             'spearman': make_scorer(correlation, corr_type='spearman'),
             'kendall_tau': make_scorer(correlation, corr_type='kendall_tau'),
             'unweighted_kappa': make_scorer(kappa),
-            'quadratic_weighted_kappa': make_scorer(kappa,
-                                                    weights='quadratic'),
+            'quadratic_weighted_kappa': make_scorer(kappa, weights='quadratic'),
             'linear_weighted_kappa': make_scorer(kappa, weights='linear'),
-            'qwk_off_by_one': make_scorer(kappa, weights='quadratic',
+            'qwk_off_by_one': make_scorer(kappa,
+                                          weights='quadratic',
                                           allow_off_by_one=True),
-            'lwk_off_by_one': make_scorer(kappa, weights='linear',
+            'lwk_off_by_one': make_scorer(kappa,
+                                          weights='linear',
                                           allow_off_by_one=True),
             'uwk_off_by_one': make_scorer(kappa, allow_off_by_one=True)}