def process(database, inputMetaPath, resultBaseDir, cutoff=50, verbose=3, parallel=1,
preDispatch='2*n_jobs', randomize=False, limit=1, debug=False,
dummy=False, rerun=None, hideFinished=False, slurm=False):
meta = result.getMeta(inputMetaPath)
connection = batch.getConnection(slurm, debug)
makeDir(resultBaseDir)
cacheDir = makeDir(os.path.join(resultBaseDir, "cache"))
resultDir = makeDir(os.path.join(resultBaseDir, "results"))
jobDir = makeDir(os.path.join(resultBaseDir, "jobs"))
#cachedMetaPath = os.path.join(cacheDir, "base.json")
baseXPath, baseYPath, baseMetaPath = cache.getExperiment(
experiment=meta["experiment"]["name"], experimentOptions=meta["experiment"]["options"],
database=database, writer="writeNumpyText", useCached=True, cacheDir=cacheDir)
features = meta["features"]
count = 0
featureSet = []
cls = meta["results"]["best"]
paramSets = [x["params"] for x in meta["results"]["all"]]
classifierArgs = {}
for paramSet in paramSets:
for key in paramSet:
if not key in classifierArgs:
classifierArgs[key] = []
classifierArgs[key].append(paramSet[key])
classifierNameMap = {
"LinearSVC":"svm.LinearSVC",
"svm.LinearSVC":"svm.LinearSVC",
"ExtraTreesClassifier":"ensemble.ExtraTreesClassifier",
"ensemble.ExtraTreesClassifier":"ensemble.ExtraTreesClassifier",
"RLScore":"RLScore",
"RFEWrapper":"svm.LinearSVC"
}
classifierName = classifierNameMap[cls["classifier"]]
#classifier, classifierArgs = learn.getClassifier(classifierName, params)
submitCount = 0
sleepTime = 15
for featureName in features:
feature = features[featureName]
batch.waitForJobs(limit, submitCount, connection, sleepTime)
print "Processing feature", featureName
print feature
featureSet.append(feature["id"])
jobName = "_".join([meta["experiment"]["name"], meta["template"]["project"], classifierName, "feature-" + str(feature["rank"])])
pointResultPath = os.path.join(resultDir, jobName + ".json")
print "Feature set", featureSet
if len(featureSet) > 1:
# hiddenResults = curvePoint(baseXPath, baseYPath, baseMetaPath, featureSet, pointResultPath,
# classifier=classifier, classifierArgs=params, getCV=eval(cls["cv"]),
# numFolds=cls["folds"], verbose=verbose, parallel=parallel,
# preDispatch=preDispatch, randomize=randomize, metric=cls["metric"])[3]
#results.append(hiddenResults)
command = "python curvePoint.py"
command += " -X " + baseXPath
command += " -y " + baseYPath
command += " -m " + inputMetaPath
command += " -o " + pointResultPath
command += " --cutoff " + str(count)
command += " --classifier " + classifierName
command += " --classifierArgs \"" + str(classifierArgs) + "\""
command += " --iteratorCV " + cls["cv"]
command += " --numFolds " + str(cls["folds"])
command += " --verbose " + str(verbose)
command += " --parallel " + str(parallel)
command += " --preDispatch \"" + str(preDispatch) + "\""
if randomize:
command += " --randomize "
command += " --metric " + cls["metric"]
if batch.submitJob(command, connection, jobDir, jobName, dummy, rerun, hideFinished):
submitCount += 1
count += 1
if count > cutoff:
break
parser = argparse.ArgumentParser(parents=[exampleOptions], description='Feature selection with Greedy RLS')
parser.add_argument('-x','--features', help='Input file for feature vectors (X)', default=None)
parser.add_argument('-y','--labels', help='Input file for class labels (Y)', default=None)
parser.add_argument('-m','--meta', help='Metadata input file name (optional)', default=None)
parser.add_argument('--noCache', help='Do not use cache', default=False, action="store_true")
parser.add_argument('--cacheDir', help='Cache directory, used if x, y or m are undefined (optional)', default=os.path.join(tempfile.gettempdir(), "CAMDA2014"))
parser.add_argument('-n','--numFolds', help='Number of folds in cross-validation', type=int, default=5)
parser.add_argument('-s','--subsetsize', help='Number of features to be selected', type=int, default=50)
parser.add_argument('--useOrigOut', help='', default=True, action="store_true")
parser.add_argument('--outfile', help='Output file for results', type=str, default="selected.txt")
#parser.add_argument('--outaccuracies', help='Output file for accuracies on each CV round', type=str, default="accuracies.txt")
parser.add_argument('-r', '--result', help='Output file for detailed results (optional)', default=None)
options = parser.parse_args()
featureFilePath, labelFilePath, metaFilePath = getExperiment(experiment=options.experiment, experimentOptions=options.options,
database=options.database, writer=options.writer,
useCached=not options.noCache, featureFilePath=options.features,
labelFilePath=options.labels, metaFilePath=options.meta)
#X = np.loadtxt(options.features)
#Y = np.loadtxt(options.labels)
#f = open('X')
#X = cPickle.load(f)
#f.close()
model, perfs, selected, best_logrp, best_scount = greedyRLS(featureFilePath, labelFilePath, metaFilePath, options.numFolds, options.subsetsize, resultPath=options.result)
if (options.useOrigOut):
f = open(options.outfile, 'w')
f.write(str(best_logrp)+" " +str(best_scount)+"\n")
f.write("".join(str(x)+" " for x in perfs)+"\n")
f.write("".join(str(x)+" " for x in selected)+"\n")
f.close()
#np.savetxt(options.outfeatures, selected, fmt="%d")
