Merge branch 'sort' into 'master'

Adds a sort command and small fixes

See merge request !174

bob/bio/base/annotator/FailSafe.py

@@ -48,6 +48,8 @@ class FailSafe(Annotator):
             if not annotations:
                 logger.debug(
                     "Annotator `%s' returned empty annotations.", annotator)
+            else:
+                logger.debug("Annotator `%s' succeeded!", annotator)
             kwargs['annotations'].update(annotations or {})
             # check if we have all the required annotations
             if all(key in kwargs['annotations'] for key in self.required_keys):

bob/bio/base/grid.py

@@ -8,13 +8,14 @@ PREDEFINED_QUEUES = {
   'default'     : {},
   '2G'          : {'queue' : 'all.q',  'memfree' : '2G'},
   '4G'          : {'queue' : 'all.q',  'memfree' : '4G'},
+  '4G-q1d'      : {'queue' : 'q1d',  'memfree' : '4G'},
   '4G-io-big'   : {'queue' : 'q1d',  'memfree' : '4G', 'io_big' : True},
   '8G'          : {'queue' : 'q1d',  'memfree' : '8G'},
   '8G-io-big'   : {'queue' : 'q1d',  'memfree' : '8G', 'io_big' : True},
   '16G'         : {'queue' : 'q1dm', 'memfree' : '16G', 'pe_opt' : 'pe_mth 2', 'hvmem' : '8G'},
   '16G-io-big'  : {'queue' : 'q1dm', 'memfree' : '16G', 'pe_opt' : 'pe_mth 2', 'hvmem' : '8G', 'io_big' : True},
   '32G'         : {'queue' : 'q1dm', 'memfree' : '32G', 'pe_opt' : 'pe_mth 4', 'hvmem' : '8G', 'io_big' : True},
-  '64G'         : {'queue' : 'q1dm', 'memfree' : '64G', 'pe_opt' : 'pe_mth 8', 'hvmem' : '8G', 'io_big' : True},
+  '64G'         : {'queue' : 'q1dm', 'memfree' : '56G', 'pe_opt' : 'pe_mth 8', 'hvmem' : '7G', 'io_big' : True},
   'Week'        : {'queue' : 'q1wm', 'memfree' : '32G', 'pe_opt' : 'pe_mth 4', 'hvmem' : '8G'},
   'GPU'         : {'queue' : 'gpu'}
 }

bob/bio/base/script/sort.py

+"""Sorts score files based on their score value
+"""
+import click
+import logging
+import numpy
+from bob.bio.base.score.load import load_score, dump_score
+from bob.extension.scripts.click_helper import verbosity_option, log_parameters
+
+logger = logging.getLogger(__name__)
+
+
+@click.command(
+    epilog="""\b
+Examples:
+
+  $ bob bio sort -vvv /path/to/scores
+"""
+)
+@click.argument(
+    "score_paths",
+    type=click.Path(exists=True, file_okay=True, dir_okay=False, writable=True),
+    nargs=-1,
+)
+@verbosity_option()
+def sort(score_paths, **kwargs):
+    """Sorts score files based on their score values
+
+    The conversion happens in-place; backup your scores before using this script
+    """
+    log_parameters(logger)
+
+    for path in score_paths:
+        logger.info("Sorting: %s", path)
+        scores = load_score(path)
+        scores = scores[numpy.argsort(scores["score"])]
+        dump_score(path, scores)

bob/bio/base/test/test_commands.py

 '''Tests for bob.measure scripts'''
 
-import sys
-import filecmp
 import click
 from click.testing import CliRunner
+import shutil
 import pkg_resources
-from ..script import commands
+import numpy
+import nose
 from bob.extension.scripts.click_helper import assert_click_runner_result
+from ..script import commands, sort
+from ..score import scores
 
 def test_metrics():
     dev1 = pkg_resources.resource_filename('bob.bio.base.test',
@@ -87,7 +89,6 @@ def test_metrics():
         assert_click_runner_result(result)
 
 
-
 def test_roc():
     dev1 = pkg_resources.resource_filename('bob.bio.base.test',
                                            'data/dev-4col.txt')
@@ -138,7 +139,6 @@ def test_roc():
         assert_click_runner_result(result)
 
 
-
 def test_det():
     dev1 = pkg_resources.resource_filename('bob.bio.base.test',
                                            'data/dev-4col.txt')
@@ -170,7 +170,6 @@ def test_det():
             click.echo(result.output)
         assert_click_runner_result(result)
 
-
     dev_nonorm = pkg_resources.resource_filename('bob.bio.base.test',
                                                  'data/scores-nonorm-dev')
     dev_ztnorm = pkg_resources.resource_filename('bob.bio.base.test',
@@ -225,7 +224,6 @@ def test_epc():
         assert_click_runner_result(result)
 
 
-
 def test_hist():
     dev1 = pkg_resources.resource_filename('bob.bio.base.test',
                                            'data/dev-4col.txt')
@@ -260,7 +258,6 @@ def test_hist():
         assert_click_runner_result(result)
 
 
-
 def test_cmc():
     dev1 = pkg_resources.resource_filename('bob.bio.base.test',
                                            'data/scores-cmc-5col.txt')
@@ -296,8 +293,6 @@ def test_cmc():
         assert_click_runner_result(result)
 
 
-
-
 def test_dir():
     dev1 = pkg_resources.resource_filename('bob.bio.base.test',
                                            'data/scores-nonorm-openset-dev')
@@ -317,3 +312,34 @@ def test_dir():
         if result.output:
             click.echo(result.output)
         assert_click_runner_result(result)
+
+
+def test_sort():
+
+    def sorted_scores(score_lines):
+        lines = []
+        floats = []
+        for line in score_lines:
+            lines.append(line)
+            floats.append(line[-1])
+        sort_idx = numpy.argsort(floats)
+        lines = [lines[i] for i in sort_idx]
+        return lines
+
+    dev1 = pkg_resources.resource_filename('bob.bio.base.test',
+                                           'data/scores-nonorm-dev')
+    runner = CliRunner()
+    with runner.isolated_filesystem():
+        # create a temporary sort file and sort it and check if it is sorted!
+
+        path = "scores.txt"
+        shutil.copy(dev1, path)
+
+        result = runner.invoke(sort.sort, [path])
+        assert_click_runner_result(result, exit_code=0)
+
+        # load dev1 and sort it and compare to path
+        dev1_sorted = sorted_scores(scores(dev1))
+        path_scores = list(scores(path))
+
+        nose.tools.assert_list_equal(dev1_sorted, path_scores)

bob/bio/base/utils/io.py

@@ -306,7 +306,10 @@ def vstack_features(reader, paths, same_size=False, allow_missing_files=False):
     raise ValueError("Both same_size and allow_missing_files cannot be True at"
                      " the same time.")
   iterable = _generate_features(reader, paths, same_size, allow_missing_files)
-  dtype, shape = next(iterable)
+  try:
+    dtype, shape = next(iterable)
+  except StopIteration:
+    return numpy.array([])
   if same_size:
     total_size = int(len(paths) * numpy.prod(shape))
     all_features = numpy.fromiter(iterable, dtype, total_size)

conda/meta.yaml

@@ -75,6 +75,7 @@ test:
     - bob bio dir --help
     - bob bio gen --help
     - bob bio evaluate --help
+    - bob bio sort --help
     - nosetests --with-coverage --cover-package={{ name }} -sv {{ name }}
     - sphinx-build -aEW {{ project_dir }}/doc {{ project_dir }}/sphinx
     - sphinx-build -aEb doctest {{ project_dir }}/doc sphinx

setup.py

@@ -149,6 +149,7 @@ setup(
         'gen               = bob.bio.base.script.gen:gen',
         'evaluate          = bob.bio.base.script.commands:evaluate',
         'baseline          = bob.bio.base.script.baseline:baseline',
+        'sort              = bob.bio.base.script.sort:sort',
       ],
 
       # annotators