merge

.gitlab-ci.yml

@@ -4,7 +4,9 @@ tests:
     tags:
         - docker
     script:
-        - pip3 install -e . --no-deps
+        - export LC_ALL=$(locale -a | grep en_US)
+        - export LANG=$(locale -a | grep en_US)
+        - pip3 install -e .
         - pytest-3
     coverage: '/^TOTAL.+?(\d+\%)$/'
     artifacts:

README.rst

@@ -57,6 +57,7 @@ And the following python modules will be automatically installed  :
 * `pyyaml <https://pypi.org/project/PyYAML/>`_ - Used to read the config files,
 * `plotly <https://plot.ly/>`_ - Used to generate interactive HTML visuals,
 * `tabulate <https://pypi.org/project/tabulate/>`_ - Used to generated the confusion matrix.
+* `pyscm-ml <https://pypi.org/project/pyscm-ml/>`_ - 
 
 
 Installing

docker/Dockerfile_ubuntu_18.04

@@ -29,6 +29,7 @@ RUN apt-get install -y --no-install-recommends locales && \
     update-locale en_US.UTF-8 && \
     echo "export LC_ALL=$(locale -a | grep en_US)" >> /root/.bashrc && \
     echo "export LANG=$(locale -a | grep en_US)" >>  /root/.bashrc
+ENV LANGUAGE'en_US:en'
 COPY requirements.txt .
 RUN pip3 install -r requirements.txt
 

requirements.txt

@@ -11,3 +11,4 @@ pyyaml>=3.12
 plotly>=4.2.1
 matplotlib>=3.1.1
 tabulate>=0.8.6
+pyscm-ml>=1.0.0
\ No newline at end of file

summit/multiview_platform/result_analysis/execution.py

@@ -129,7 +129,8 @@ def analyze_all(iter_results, stats_iter, directory, data_base_name,
     publish_all_sample_errors(error_analysis, directory, stats_iter,
                               sample_ids, labels, data_base_name, label_names)
     publish_feature_importances(feature_importances, directory,
-                                data_base_name, feature_importances_stds)
+                                data_base_name, feature_importances_stds,
+                                metric_scores=metrics_analysis)
     plot_durations(duration_means, directory, data_base_name, duration_stds)
     return results
 

summit/multiview_platform/result_analysis/feature_importances.py

@@ -102,6 +102,7 @@ def publish_feature_importances(feature_importances, directory, database_name,
 def plot_feature_importances(file_name, feature_importance,
                              feature_std):  # pragma: no cover
     s = feature_importance.sum(axis=1)
+    s = s[s!=0]
     feature_importance = feature_importance.loc[s.sort_values(ascending=False).index]
     feature_importance.to_csv(file_name + "_dataframe.csv")
     hover_text = [["-Feature :" + str(feature_name) +
@@ -134,6 +135,8 @@ def plot_feature_relevance(file_name, feature_importance,
                              feature_std, metric_scores): # pragma: no cover
     for metric, score_df in metric_scores.items():
         if metric.endswith("*"):
+            if isinstance(score_df, dict):
+                score_df = score_df["mean"]
             for score in score_df.columns:
                 if len(score.split("-"))>1:
                     algo, view = score.split("-")

summit/tests/test_multi_view/test_multiview_utils.py

@@ -79,6 +79,7 @@ class TestFunctions(unittest.TestCase):
                                  'knn',
                                  'lasso',
                                  'random_forest',
+                                 'scm',
                                  'sgd',
                                  'svm_linear',
                                  'svm_poly',
@@ -90,6 +91,7 @@ class TestFunctions(unittest.TestCase):
                                  'gradient_boosting',
                                  'knn',
                                  'random_forest',
+                                 'scm',
                                  'svm_linear',
                                  'svm_poly',
                                  'svm_rbf'])