def choose_best(self, clustering_info):
"""
Normalizes the values of the evaluation scores, then calculates the scores for all clusterings and criteria
and finally chooses the best clustering.
@param clustering_info: Is the clustering_info structure with clusterings, evaluation info... etc
@return: The id of the best clustering with the criteria_id with higher score and the score itself.
"""
if len(clustering_info) == 0:
print "[WARNING BestClusteringSelector::choose_best] clustering_info is empty."
return None
evaluation_types = AnalysisPopulator.get_evaluation_analysis_types(self.parameters)
# If there were no criteria defined, then the clustering is randomly selected
if evaluation_types == []:
return clustering_info[clustering_info.keys()[random.randint(0,len(clustering_info.keys())-1)]]
for evaluation_type in evaluation_types:
BestClusteringSelector.normalize_one_evaluation_type(evaluation_type, clustering_info)
scores = BestClusteringSelector.get_scores_for_all_clusters_and_criterias(self.criteria, clustering_info)
best_clustering_id, criteria_id, scores = self.get_best_clustering(scores)
return best_clustering_id, scores
def test_get_query_and_evaluation_analysis_types(self):
parameters = {
"clustering":{
"evaluation": {
"evaluation_criteria": {
"criteria_0": {
"CythonMirrorCohesion":{
"action": ">",
"weight": 0.05
},
"CythonMinimumMeanSeparation":{
"action": ">",
"weight": 0.1
},
"CythonSilhouette":{
"action": ">",
"weight": 0.15
}
}
},
"query_types": [
"NumClusters",
"CythonMinimumMeanSeparation",
"NoiseLevel"
]
}
}
}
self.assertItemsEqual( AnalysisPopulator.get_evaluation_analysis_types(parameters),
['CythonMinimumMeanSeparation', 'CythonMirrorCohesion', 'CythonSilhouette'])
self.assertItemsEqual( AnalysisPopulator.get_query_and_evaluation_analysis_types(parameters),
['CythonMinimumMeanSeparation', 'NumClusters', 'CythonMirrorCohesion', 'NoiseLevel', 'CythonSilhouette'])
def choose_best(self, clustering_info):
"""
Normalizes the values of the evaluation scores, then calculates the scores for all clusterings and criteria
and finally chooses the best clustering.
@param clustering_info: Is the clustering_info structure with clusterings, evaluation info... etc
@return: The id of the best clustering with the criteria_id with higher score and the score itself.
"""
if len(clustering_info) == 0:
print "[WARNING BestClusteringSelector::choose_best] clustering_info is empty."
return None
evaluation_types = AnalysisPopulator.get_evaluation_analysis_types(
self.parameters)
# If there were no criteria defined, then the clustering is randomly selected
if evaluation_types == []:
return clustering_info[clustering_info.keys()[random.randint(
0,
len(clustering_info.keys()) - 1)]]
for evaluation_type in evaluation_types:
BestClusteringSelector.normalize_one_evaluation_type(
evaluation_type, clustering_info)
scores = BestClusteringSelector.get_scores_for_all_clusters_and_criterias(
self.criteria, clustering_info)
best_clustering_id, criteria_id, scores = self.get_best_clustering(
scores)
return best_clustering_id, scores
