def saveDetails(meta, predictions, importances, fold, featureByIndex=None, reclassify=False):
if featureByIndex == None:
featureByIndex = result.getFeaturesByIndex(meta)
if predictions != None:
for index in predictions:
if fold == "hidden":
example = result.getExampleFromSet(meta, index, "hidden")
else:
example = result.getExampleFromSet(meta, index, "train")
if reclassify and ("classification" in example):
del example["classification"]
if "classification" in example:
raise Exception("Example " + str(index) + " has already been classified " + str([fold, str(example)]))
result.setValue(example, "prediction", predictions[index], "classification")
result.setValue(example, "fold", fold, "classification")
if importances != None:
for i in range(len(importances)):
if importances[i] != 0:
feature = result.getFeature(meta, i, featureByIndex)
if fold != "hidden":
result.setValue(feature, fold, importances[i], "importances")
#if "sort" not in feature:
# result.setValue(feature, "sort", 0)
else:
result.setValue(feature, "hidden-importance", importances[i])
result.setValue(feature, "sort", importances[i])
def saveResults(meta, resultPath, perfs, selected):
if not os.path.exists(os.path.dirname(resultPath)):
os.makedirs(os.path.dirname(resultPath))
meta = result.getMeta(meta)
featureByIndex = result.getFeaturesByIndex(meta)
for foldIndex in range(len(selected)):
ranks = selected[foldIndex]
for featureRank in range(len(ranks)):
featureIndex = ranks[featureRank]
feature = result.getFeature(meta, featureIndex, featureByIndex)
result.setValue(feature, foldIndex, featureRank, "ranks")
result.setValue(feature, "sort", -sum(feature["ranks"].values()) / len(feature["ranks"]))
result.saveMeta(meta, resultPath)
def analyze(meta, dbPath=None, resultPath=None, verbose=False):
meta = result.getMeta(meta)
if dbPath == None:
dbPath = settings.CGI_DB_PATH
print "Analyzing", dbPath
con = DB.connect(dbPath)
result.sortFeatures(meta)
features = meta["features"]
count = 1
numFeatures = len(features)
nonSelected = []
for featureName in features:
if not isinstance(features[featureName], int):
if verbose:
print "Processing feature", featureName, str(count) + "/" + str(numFeatures)
geneName = getGeneName(featureName)
if geneName != None:
mappings = getTermAnalysis(con, geneName, "disease")
result.setValue(features[featureName], "CancerGeneIndex", mappings)
mappings = getTermAnalysis(con, geneName, "drug")
result.setValue(features[featureName], "CancerGeneDrug", mappings)
else:
geneName = getGeneName(featureName)
if geneName != None:
nonSelected.append(geneName)
count += 1
result.setValue(meta, "CancerGeneIndex", analyzeTermCoverage(features), "analysis")
result.setValue(meta["analysis"], "non-selected", getCancerGeneCoverage(con, nonSelected), "CancerGeneIndex")
if resultPath != None:
result.saveMeta(meta, resultPath)
return meta
