config = configparser.ConfigParser()
config.read('settings.cfg')
esUrl = config['DEFAULT']['ESHost']
if len(argv) > 1:
esUrl = argv[1]
es = Elasticsearch(esUrl, timeout=1000)
# Load features into Elasticsearch
initDefaultStore(esUrl)
loadFeatures(esUrl)
# Parse a judgments
movieJudgments = judgmentsByQid(
judgmentsFromFile(filename=HUMAN_JUDGMENTS))
movieJudgments = duplicateJudgmentsByWeight(movieJudgments)
trainJudgments, testJudgments = partitionJudgments(movieJudgments,
testProportion=0.0)
# Use proposed Elasticsearch queries (1.json.jinja ... N.json.jinja) to generate a training set
# output as "sample_judgments_wfeatures.txt"
logFeatures(es, judgmentsByQid=movieJudgments)
buildFeaturesJudgmentsFile(trainJudgments, filename=TRAIN_JUDGMENTS)
buildFeaturesJudgmentsFile(testJudgments, filename=TEST_JUDGMENTS)
# Train each ranklib model type
for modelType in [8, 9, 6]:
# 0, MART
# 1, RankNet
# 2, RankBoost
if draw <= testProportion:
testJudgments[qid] = judgment
else:
trainJudgments[qid] = judgment
return (trainJudgments, testJudgments)
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