def train(self):
# Load features into Elasticsearch
initDefaultStore()
loadFeatures(ES_FEATURE_SET_NAME)
# Parse a judgments
label_file = self.find_label_file()
print(self.find_label_file(),file=sys.stderr)
movieJudgments = judgmentsByQid(
judgmentsFromFile(filename=label_file))
# Use proposed Elasticsearch queries (1.json.jinja ... N.json.jinja) to generate a training set
# output as "sample_judgments_wfeatures.txt"
logFeatures(self.__es, judgmentsByQid=movieJudgments)
buildFeaturesJudgmentsFile(
movieJudgments, filename='sample_judgments_wfeatures.txt')
# Train each ranklib model type
# for modelType in [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]:
modelType = int(ES_MODEL_TYPE)
# 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)
self.trainModel(judgmentsWithFeaturesFile='sample_judgments_wfeatures.txt',
modelOutput='model.txt', whichModel=modelType)
self.saveModel(scriptName=ES_MODEL_NAME,
featureSet='movie_features', modelFname='model.txt')
with open('/opt/services/flaskapp/src/training_log.txt') as flog:
log_lines = flog.readlines()
print(label_file)
return '{}{}\n{}'.format('Model trained and deployed to Elasticsearch: \n', ''.join(log_lines[-5:-3]), 'Now test the model')
import configparser
from elasticsearch5 import Elasticsearch
from sys import argv
from judgments import judgmentsFromFile, judgmentsByQid, duplicateJudgmentsByWeight
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)
resp = requests.post(fullPath,
data=json.dumps(modelPayload),
headers=head,
auth=ES_AUTH)
print(resp.status_code)
if (resp.status_code >= 300):
print(resp.text)
if __name__ == "__main__":
import configparser
from judgments import judgmentsFromFile, judgmentsByQid
es = Elasticsearch(timeout=1000)
# Load features into Elasticsearch
initDefaultStore()
loadFeatures()
# Parse a judgments
movieJudgments = judgmentsByQid(
judgmentsFromFile(filename='search_sample_judgments.txt'))
# 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(
movieJudgments, filename='search_sample_judgments_wfeatures.txt')
# Train each ranklib model type
for modelType in [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]:
# 0, MART
# 1, RankNet
# 2, RankBoost
# 3, AdaRank
resp = requests.post(fullPath, data=json.dumps(modelPayload), headers=head, auth=ES_AUTH)
print(resp.status_code)
if (resp.status_code >= 300):
print(resp.text)
if __name__ == "__main__":
import configparser
from judgments import judgmentsFromFile, judgmentsByQid
es = Elasticsearch(timeout=1000)
# Load features into Elasticsearch
initDefaultStore()
loadFeatures()
# Parse a judgments
movieJudgments = judgmentsByQid(judgmentsFromFile(filename='sample_judgments.txt'))
# 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(movieJudgments, filename='sample_judgments_wfeatures.txt')
# Train each ranklib model type
for modelType in [0,1,2,3,4,5,6,7,8,9]:
# 0, MART
# 1, RankNet
# 2, RankBoost
# 3, AdaRank
# 4, coord Ascent
# 6, LambdaMART