# java -jar RankLib-2.6.jar -ranker 6 -train sample_judgements_wfeatures.txt -save model.txt
cmd = "java -jar RankLib-2.6.jar -ranker 6 -train %s -save %s" % (
judgmentsWithFeaturesFile, modelOutput)
print("Running %s" % cmd)
os.system(cmd)
pass
def saveModel(es, scriptName, modelFname):
""" Save the ranklib model in Elasticsearch """
with open(modelFname) as modelFile:
modelContent = modelFile.read()
es.put_script(lang='ranklib',
id=scriptName,
body={"script": modelContent})
if __name__ == "__main__":
from elasticsearch import Elasticsearch
from judgments import judgmentsFromFile, judgmentsByQid
esUrl = "http://localhost:9200"
es = Elasticsearch(timeout=1000)
judgements = judgmentsByQid(
judgmentsFromFile(filename='sample_judgements.txt'))
kwDocFeatures(es, index='tmdb', searchType='movie', judgements=judgements)
buildFeaturesJudgmentsFile(judgements,
filename='sample_judgements_wfeatures.txt')
trainModel(judgmentsWithFeaturesFile='sample_judgements_wfeatures.txt',
modelOutput='model.txt')
saveModel(es, scriptName='test', modelFname='model.txt')
if __name__ == "__main__":
from elasticsearch import Elasticsearch
from judgments import judgmentsFromFile, judgmentsByQid, duplicateJudgmentsByWeight
esUrl = "http://ec2-54-234-184-186.compute-1.amazonaws.com:9616/supersecretsquirrel/"
es = Elasticsearch(esUrl, timeout=1000)
# Parse a judgments
judgments = judgmentsByQid(judgmentsFromFile(filename='osc_judgments.txt'))
judgments = duplicateJudgmentsByWeight(judgments)
trainJudgments, testJudgments = partitionJudgments(judgments,
testProportion=0.00)
# Use proposed Elasticsearch queries (1.json.jinja ... N.json.jinja) to generate a training set
# output as "osc_judgments_wfeatures.txt"
kwDocFeatures(es, index='o19s', searchType='post', judgements=judgments)
numFeatures = len(judgments[1][0].features)
print("Training on %s features" % numFeatures)
buildFeaturesJudgmentsFile(trainJudgments,
filename='osc_judgments_wfeatures_train.txt')
buildFeaturesJudgmentsFile(testJudgments,
filename='osc_judgments_wfeatures_test.txt')
# Train each ranklib model type
for modelType in [0, 6, 9]:
# 0, MART
# 1, RankNet
# 2, RankBoost
# 3, AdaRank
# 4, coord Ascent
# 6, LambdaMART
# 7, ListNET
# 8, Random Forests
# 9, Linear Regression
print("*** Training %s " % modelType)
trainModel(trainingData='osc_judgments_wfeatures_train.txt',