diff --git a/multiview_platform/mono_multi_view_classifiers/exec_classif.py b/multiview_platform/mono_multi_view_classifiers/exec_classif.py
index b81a93048436ee5f12509c954236c832d5089c0a..aaf8743c0ae2668fca593f94bc35e04b36fca949 100644
--- a/multiview_platform/mono_multi_view_classifiers/exec_classif.py
+++ b/multiview_platform/mono_multi_view_classifiers/exec_classif.py
@@ -14,7 +14,6 @@ from . import monoview_classifiers
from . import multiview_classifiers
from .monoview.exec_classif_mono_view import exec_monoview
from .multiview.exec_multiview import exec_multiview
-from .result_analysis.noise_analysis import plot_results_noise
from .result_analysis.execution import analyze_iterations, analyze
from .utils import execution, dataset, configuration
from .utils.organization import secure_file_path
diff --git a/multiview_platform/mono_multi_view_classifiers/metrics/roc_auc_score.py b/multiview_platform/mono_multi_view_classifiers/metrics/roc_auc_score.py
index 4ab88b73e7e3bbece56f333003f91ef807ac0cb8..ae21428b347caef47dc3bcc596404ea6d85c5dd5 100644
--- a/multiview_platform/mono_multi_view_classifiers/metrics/roc_auc_score.py
+++ b/multiview_platform/mono_multi_view_classifiers/metrics/roc_auc_score.py
@@ -12,11 +12,6 @@ __status__ = "Prototype" # Production, Development, Prototype
def score(y_true, y_pred, multiclass=False, **kwargs):
- if multiclass:
- mlb = MultiLabelBinarizer()
- y_true = mlb.fit_transform([(label) for label in y_true])
- y_pred = mlb.fit_transform([(label) for label in y_pred])
-
score = metric(y_true, y_pred, **kwargs)
return score
diff --git a/multiview_platform/mono_multi_view_classifiers/result_analysis/noise_analysis.py b/multiview_platform/mono_multi_view_classifiers/result_analysis/noise_analysis.py
index 96973ba36f3858fc16eaa54179f7b6effcb90db2..b4fc81215d5b50564d98108262a332adf617932c 100644
--- a/multiview_platform/mono_multi_view_classifiers/result_analysis/noise_analysis.py
+++ b/multiview_platform/mono_multi_view_classifiers/result_analysis/noise_analysis.py
@@ -1,56 +1,56 @@
-
-import numpy as np
-import pandas as pd
-import matplotlib.pyplot as plt
-import os
-from matplotlib.patches import Patch
-
-
-def plot_results_noise(directory, noise_results, metric_to_plot, name,
- width=0.1):
- avail_colors = ["tab:blue", "tab:orange", "tab:brown", "tab:gray",
- "tab:olive", "tab:red", ]
- colors = {}
- lengend_patches = []
- noise_levels = np.array([noise_level for noise_level, _ in noise_results])
- df = pd.DataFrame(
- columns=['noise_level', 'classifier_name', 'mean_score', 'score_std'], )
- if len(noise_results) > 1:
- width = np.min(np.diff(noise_levels))
- for noise_level, noise_result in noise_results:
- classifiers_names, meaned_metrics, metric_stds = [], [], []
- for noise_result in noise_result:
- classifier_name = noise_result[0].split("-")[0]
- if noise_result[1] is metric_to_plot:
- classifiers_names.append(classifier_name)
- meaned_metrics.append(noise_result[2])
- metric_stds.append(noise_result[3])
- if classifier_name not in colors:
- try:
- colors[classifier_name] = avail_colors.pop(0)
- except IndexError:
- colors[classifier_name] = "k"
- classifiers_names, meaned_metrics, metric_stds = np.array(
- classifiers_names), np.array(meaned_metrics), np.array(metric_stds)
- sorted_indices = np.argsort(-meaned_metrics)
- for index in sorted_indices:
- row = pd.DataFrame(
- {'noise_level': noise_level,
- 'classifier_name': classifiers_names[index],
- 'mean_score': meaned_metrics[index],
- 'score_std': metric_stds[index]}, index=[0])
- df = pd.concat([df, row])
- plt.bar(noise_level, meaned_metrics[index], yerr=metric_stds[index],
- width=0.5 * width, label=classifiers_names[index],
- color=colors[classifiers_names[index]])
- for classifier_name, color in colors.items():
- lengend_patches.append(Patch(facecolor=color, label=classifier_name))
- plt.legend(handles=lengend_patches, loc='lower center',
- bbox_to_anchor=(0.5, 1.05), ncol=2)
- plt.ylabel(metric_to_plot)
- plt.title(name)
- plt.xticks(noise_levels)
- plt.xlabel("Noise level")
- plt.savefig(os.path.join(directory, name + "_noise_analysis.png"))
- plt.close()
- df.to_csv(os.path.join(directory, name + "_noise_analysis.csv"))
+#
+# import numpy as np
+# import pandas as pd
+# import matplotlib.pyplot as plt
+# import os
+# from matplotlib.patches import Patch
+#
+#
+# def plot_results_noise(directory, noise_results, metric_to_plot, name,
+# width=0.1):
+# avail_colors = ["tab:blue", "tab:orange", "tab:brown", "tab:gray",
+# "tab:olive", "tab:red", ]
+# colors = {}
+# lengend_patches = []
+# noise_levels = np.array([noise_level for noise_level, _ in noise_results])
+# df = pd.DataFrame(
+# columns=['noise_level', 'classifier_name', 'mean_score', 'score_std'], )
+# if len(noise_results) > 1:
+# width = np.min(np.diff(noise_levels))
+# for noise_level, noise_result in noise_results:
+# classifiers_names, meaned_metrics, metric_stds = [], [], []
+# for noise_result in noise_result:
+# classifier_name = noise_result[0].split("-")[0]
+# if noise_result[1] is metric_to_plot:
+# classifiers_names.append(classifier_name)
+# meaned_metrics.append(noise_result[2])
+# metric_stds.append(noise_result[3])
+# if classifier_name not in colors:
+# try:
+# colors[classifier_name] = avail_colors.pop(0)
+# except IndexError:
+# colors[classifier_name] = "k"
+# classifiers_names, meaned_metrics, metric_stds = np.array(
+# classifiers_names), np.array(meaned_metrics), np.array(metric_stds)
+# sorted_indices = np.argsort(-meaned_metrics)
+# for index in sorted_indices:
+# row = pd.DataFrame(
+# {'noise_level': noise_level,
+# 'classifier_name': classifiers_names[index],
+# 'mean_score': meaned_metrics[index],
+# 'score_std': metric_stds[index]}, index=[0])
+# df = pd.concat([df, row])
+# plt.bar(noise_level, meaned_metrics[index], yerr=metric_stds[index],
+# width=0.5 * width, label=classifiers_names[index],
+# color=colors[classifiers_names[index]])
+# for classifier_name, color in colors.items():
+# lengend_patches.append(Patch(facecolor=color, label=classifier_name))
+# plt.legend(handles=lengend_patches, loc='lower center',
+# bbox_to_anchor=(0.5, 1.05), ncol=2)
+# plt.ylabel(metric_to_plot)
+# plt.title(name)
+# plt.xticks(noise_levels)
+# plt.xlabel("Noise level")
+# plt.savefig(os.path.join(directory, name + "_noise_analysis.png"))
+# plt.close()
+# df.to_csv(os.path.join(directory, name + "_noise_analysis.csv"))
diff --git a/multiview_platform/mono_multi_view_classifiers/utils/execution.py b/multiview_platform/mono_multi_view_classifiers/utils/execution.py
index fab4079b6c8a17b48dfdcc28dc0795d3d888c7ad..3570bb2b685a9fe0e2cdded10f367177ad046a85 100644
--- a/multiview_platform/mono_multi_view_classifiers/utils/execution.py
+++ b/multiview_platform/mono_multi_view_classifiers/utils/execution.py
@@ -166,7 +166,7 @@ def init_log_file(name, views, cl_type, log, debug, label,
"%Y_%m_%d-%H_%M") + "_" + label)
log_file_name = time.strftime("%Y_%m_%d-%H_%M") + "-" + ''.join(
cl_type) + "-" + "_".join(views) + "-" + name + "-LOG.log"
- if os.path.exists(result_directory):
+ if os.path.exists(result_directory): # pragma: no cover
raise NameError("The result dir already exists, wait 1 min and retry")
log_file_path = os.path.join(result_directory, log_file_name)
os.makedirs(os.path.dirname(log_file_path))
@@ -348,8 +348,10 @@ def find_dataset_names(path, type, names):
available_file_names))
return path, [used_name for used_name in available_file_names if
used_name in names]
- else:
+ elif names[0] in available_file_names:
return path, names
+ else:
+ raise ValueError("The asked dataset ({}) is not available in {}. \n The available ones are {}".format(names[0], path, available_file_names))
def gen_argument_dictionaries(labels_dictionary, directories,
diff --git a/multiview_platform/tests/test_exec_classif.py b/multiview_platform/tests/test_exec_classif.py
index ef3ed1172e0077e823baa9e87aa846aa34218cbc..71cdc9e8948cbd1a129091c08e8c6fdedde0f486 100644
--- a/multiview_platform/tests/test_exec_classif.py
+++ b/multiview_platform/tests/test_exec_classif.py
@@ -28,6 +28,21 @@ class Test_execute(unittest.TestCase):
def tearDown(self):
rm_tmp()
+class Test_gen_single_monoview_arg_dictionary(unittest.TestCase):
+
+ def test_no_config(self):
+ conf = exec_classif.gen_single_monoview_arg_dictionary("classifier_name1",
+ {}, "nb_class",
+ "view_index",
+ "view_name",
+ "hps_kwargs")
+ self.assertEqual(conf, {"classifier_name1": {},
+ "view_name": "view_name",
+ "view_index": "view_index",
+ "classifier_name": "classifier_name1",
+ "nb_class": "nb_class",
+ "hps_kwargs":"hps_kwargs" } )
+
class Test_initBenchmark(unittest.TestCase):
def test_benchmark_wanted(self):
diff --git a/multiview_platform/tests/test_mono_view/test_exec_classif_mono_view.py b/multiview_platform/tests/test_mono_view/test_exec_classif_mono_view.py
index c4059803861fa02c605072bbb1431e93330cd283..784bac2a394c614d1693a343a9e039ca20ef4e06 100644
--- a/multiview_platform/tests/test_mono_view/test_exec_classif_mono_view.py
+++ b/multiview_platform/tests/test_mono_view/test_exec_classif_mono_view.py
@@ -143,6 +143,21 @@ class Test_getHPs(unittest.TestCase):
self.metrics,
self.kwargs,
**self.hps_kwargs)
+ def test_simple_config(self):
+ kwargs = exec_classif_mono_view.get_hyper_params(self.classifierModule,
+ "None",
+ self.classifier_name,
+ self.classifier_class_name,
+ self.X,
+ self.y,
+ self.random_state,
+ self.output_file_name,
+ self.cv,
+ self.nb_cores,
+ self.metrics,
+ self.kwargs,
+ **self.hps_kwargs)
+
class Test_exec_monoview(unittest.TestCase):
diff --git a/multiview_platform/tests/test_mono_view/test_monoview_utils.py b/multiview_platform/tests/test_mono_view/test_monoview_utils.py
index 7488e4778f79f9dadb7a0435f996d9daf32d7b72..b0f414ba102a1e55e8882d26052c1af695518695 100644
--- a/multiview_platform/tests/test_mono_view/test_monoview_utils.py
+++ b/multiview_platform/tests/test_mono_view/test_monoview_utils.py
@@ -36,4 +36,16 @@ class TestFunctions(unittest.TestCase):
def test_compute_possible_combinations(self):
n_possib = monoview_utils.compute_possible_combinations({"a":[1, 2], "b":{"c":[2,3]}, "d":CustomRandint(0,10)})
- np.testing.assert_array_equal(n_possib, np.array([2, np.inf, 10]))
\ No newline at end of file
+ np.testing.assert_array_equal(n_possib, np.array([2, np.inf, 10]))
+
+class FakeClf(monoview_utils.BaseMonoviewClassifier):
+
+ def __init__(self):
+ pass
+
+
+class TestBaseMonoviewClassifier(unittest.TestCase):
+
+ def test_simple(self):
+ name = FakeClf().get_name_for_fusion()
+ self.assertEqual(name, 'Fake')
diff --git a/multiview_platform/tests/test_multi_view/test_multiview_utils.py b/multiview_platform/tests/test_multi_view/test_multiview_utils.py
index f68daf67eaec79e8e42f5368f219d1cc5d8d3a29..6cb880637e3d415844199fb103c6122184c3a143 100644
--- a/multiview_platform/tests/test_multi_view/test_multiview_utils.py
+++ b/multiview_platform/tests/test_multi_view/test_multiview_utils.py
@@ -40,3 +40,50 @@ class TestBaseMultiviewClassifier(unittest.TestCase):
self.assertEqual(accepts, True)
accepts = FakeMVClassif(mc=False).accepts_multi_class(rs)
self.assertEqual(accepts, False)
+ self.assertRaises(ValueError, FakeMVClassif(mc=False).accepts_multi_class, rs,**{"n_samples":2, "n_classes":3})
+
+class TestConfigGenerator(unittest.TestCase):
+
+ @classmethod
+ def setUpClass(cls):
+ cls.rs = np.random.RandomState(42)
+
+ def test_simple(self):
+ cfg_gen = multiview_utils.ConfigGenerator(["decision_tree", "decision_tree"])
+ sample = cfg_gen.rvs(self.rs)
+ self.assertEqual(sample, {'decision_tree': {'criterion': 'entropy',
+ 'max_depth': 103,
+ 'splitter': 'best'}})
+
+class TestFunctions(unittest.TestCase):
+
+ @classmethod
+ def setUpClass(cls):
+ os.mkdir(tmp_path)
+ cls.rs = np.random.RandomState(42)
+
+ @classmethod
+ def tearDownClass(cls):
+ rm_tmp()
+
+ def test_get_available_monoview_classifiers(self):
+ avail = multiview_utils.get_available_monoview_classifiers()
+ self.assertEqual(avail, ['adaboost',
+ 'decision_tree',
+ 'gradient_boosting',
+ 'knn',
+ 'lasso',
+ 'random_forest',
+ 'sgd',
+ 'svm_linear',
+ 'svm_poly',
+ 'svm_rbf'])
+ avail = multiview_utils.get_available_monoview_classifiers(need_probas=True)
+ self.assertEqual(avail, ['adaboost',
+ 'decision_tree',
+ 'gradient_boosting',
+ 'knn',
+ 'random_forest',
+ 'svm_linear',
+ 'svm_poly',
+ 'svm_rbf'])
diff --git a/multiview_platform/tests/test_utils/test_execution.py b/multiview_platform/tests/test_utils/test_execution.py
index cffb6de632950fa3c794beb40a61bb0cf1fadaa1..2bd7e8608e6a92140a9125ba1a27c6c76002cdc0 100644
--- a/multiview_platform/tests/test_utils/test_execution.py
+++ b/multiview_platform/tests/test_utils/test_execution.py
@@ -3,7 +3,7 @@ import unittest
import numpy as np
-from multiview_platform.tests.utils import rm_tmp, tmp_path
+from multiview_platform.tests.utils import rm_tmp, tmp_path, test_dataset
from multiview_platform.mono_multi_view_classifiers.utils import execution
@@ -15,7 +15,138 @@ class Test_parseTheArgs(unittest.TestCase):
def test_empty_args(self):
args = execution.parse_the_args([])
- # print args
+
+class Test_init_log_file(unittest.TestCase):
+
+ @classmethod
+ def setUpClass(cls):
+ os.mkdir(tmp_path)
+
+ @classmethod
+ def tearDownClass(cls):
+ rm_tmp()
+
+ def test_simple(self):
+ res_dir = execution.init_log_file(name="test_dataset",
+ views=["V1", "V2", "V3"],
+ cl_type="",
+ log=True,
+ debug=False,
+ label="No",
+ result_directory=tmp_path,
+ args={})
+ self.assertTrue(res_dir.startswith(os.path.join(os.path.dirname(os.path.dirname(os.path.realpath(__file__))),"tmp_tests", "test_dataset", "started" )))
+
+ def test_no_log(self):
+ res_dir = execution.init_log_file(name="test_dataset",
+ views=["V1", "V2", "V3"],
+ cl_type="",
+ log=False,
+ debug=False,
+ label="No1",
+ result_directory=tmp_path,
+ args={})
+ self.assertTrue(res_dir.startswith(os.path.join(
+ os.path.dirname(os.path.dirname(os.path.realpath(__file__))),
+ "tmp_tests", "test_dataset", "started")))
+
+ def test_debug(self):
+ res_dir = execution.init_log_file(name="test_dataset",
+ views=["V1", "V2", "V3"],
+ cl_type="",
+ log=True,
+ debug=True,
+ label="No",
+ result_directory=tmp_path,
+ args={})
+ self.assertTrue(res_dir.startswith(os.path.join(
+ os.path.dirname(os.path.dirname(os.path.realpath(__file__))),
+ "tmp_tests", "test_dataset", "debug_started")))
+
+class Test_gen_k_folds(unittest.TestCase):
+
+ @classmethod
+ def setUpClass(cls):
+ cls.random_state = np.random.RandomState(42)
+ cls.statsIter = 1
+
+ @classmethod
+ def tearDownClass(cls):
+ pass
+
+ def test_simple(self):
+ folds_list = execution.gen_k_folds(stats_iter=1,
+ nb_folds=4,
+ stats_iter_random_states=np.random.RandomState(42))
+ self.assertEqual(folds_list[0].n_splits, 4)
+ self.assertEqual(len(folds_list), 1)
+
+ def test_multple_iters(self):
+ folds_list = execution.gen_k_folds(stats_iter=2,
+ nb_folds=4,
+ stats_iter_random_states=[np.random.RandomState(42), np.random.RandomState(43)])
+ self.assertEqual(folds_list[0].n_splits, 4)
+ self.assertEqual(len(folds_list), 2)
+
+ def test_list_rs(self):
+ folds_list = execution.gen_k_folds(stats_iter=1,
+ nb_folds=4,
+ stats_iter_random_states=[np.random.RandomState(42)])
+ self.assertEqual(folds_list[0].n_splits, 4)
+ self.assertEqual(len(folds_list), 1)
+
+
+class Test_init_views(unittest.TestCase):
+
+ @classmethod
+ def setUpClass(cls):
+ cls.random_state = np.random.RandomState(42)
+ cls.statsIter = 1
+
+ @classmethod
+ def tearDownClass(cls):
+ pass
+
+ def test_simple(self):
+ views, views_indices, all_views = execution.init_views(test_dataset, ["ViewN1", "ViewN2"])
+ self.assertEqual(views, ["ViewN1", "ViewN2"])
+ self.assertEqual(views_indices, [1,2])
+ self.assertEqual(all_views, ["ViewN0", "ViewN1", "ViewN2"])
+
+ views, views_indices, all_views = execution.init_views(test_dataset,None)
+ self.assertEqual(views, ["ViewN0", "ViewN1", "ViewN2"])
+ self.assertEqual(views_indices, range(3))
+ self.assertEqual(all_views, ["ViewN0", "ViewN1", "ViewN2"])
+
+
+class Test_find_dataset_names(unittest.TestCase):
+
+ @classmethod
+ def setUpClass(cls):
+ os.mkdir(tmp_path)
+ with open(os.path.join(tmp_path, "test.txt"), "w") as file_stream:
+ file_stream.write("test")
+ with open(os.path.join(tmp_path, "test1.txt"), "w") as file_stream:
+ file_stream.write("test")
+
+
+
+ @classmethod
+ def tearDownClass(cls):
+ rm_tmp()
+
+ def test_simple(self):
+ path, names = execution.find_dataset_names(tmp_path, ".txt", ["test"])
+ self.assertEqual(path, tmp_path)
+ self.assertEqual(names, ["test"])
+ path, names = execution.find_dataset_names(tmp_path, ".txt", ["test", 'test1'])
+ self.assertEqual(path, tmp_path)
+ self.assertEqual(names, ["test1", 'test'])
+ path, names = execution.find_dataset_names("examples/data", ".hdf5", ["all"])
+ self.assertEqual(names, ["doc_summit", "digits_doc"])
+ self.assertRaises(ValueError, execution.find_dataset_names, tmp_path+"test", ".txt",
+ ["test"])
+ self.assertRaises(ValueError, execution.find_dataset_names, tmp_path, ".txt", ["ah"])
class Test_initStatsIterRandomStates(unittest.TestCase):
diff --git a/setup.cfg b/setup.cfg
index ebf39f6bbf5995493862c14b54398767cd66de3a..43c4b4ed043e81147260b3d5e1bdec505d7f19c9 100644
--- a/setup.cfg
+++ b/setup.cfg
@@ -17,6 +17,8 @@ omit = */tests/*
*/datasets/*
*declare_classifier.py
*make_file_config.py
+ *execute*
+ *versions*
[coverage:report]