def typoIt(judgmentInFile, judgmentOutFile, rounds=100):
with open(judgmentInFile) as f:
currJudgments = [judg for judg in judgments_from_file(f)]
lastQid = currJudgments[-1].qid
judgDict = judgments_by_qid(currJudgments)
existingTypos = set()
for i in range(0, rounds):
for qid, judglist in judgDict.items():
keywords = judglist[0].keywords
keywordsWTypo = butterfingers(keywords)
if keywordsWTypo != keywords and keywordsWTypo not in existingTypos:
newQid = lastQid+1
print("%s => %s" % (keywords, keywordsWTypo))
lastQid += 1
for judg in judglist:
typoJudg = Judgment(grade=judg.grade,
qid=newQid,
keywords=keywordsWTypo,
doc_id=judg.doc_id)
currJudgments.append(typoJudg)
existingTypos.add(keywordsWTypo)
with open(judgmentOutFile, 'w') as f:
judgments_to_file(f, judgmentsList=currJudgments)
def train():
from judgments import judgments_from_file, judgments_by_qid
es = elastic_connection(timeout=1000)
# Load features into Elasticsearch
init_default_store()
load_features(FEATURE_SET_NAME)
# Parse a judgments
movieJudgments = judgments_by_qid(
judgments_from_file(filename=JUDGMENTS_FILE))
# Use proposed Elasticsearch queries (1.json.jinja ... N.json.jinja) to generate a training set
# output as "sample_judgments_wfeatures.txt"
log_features(es, judgments_dict=movieJudgments, search_index=INDEX_NAME)
build_features_judgments_file(movieJudgments,
filename=JUDGMENTS_FILE_FEATURES)
# 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
# 7, ListNET
# 8, Random Forests
# 9, Linear Regression
Logger.logger.info("*** Training %s " % modelType)
train_model(judgments_with_features_file=JUDGMENTS_FILE_FEATURES,
model_output='model.txt',
which_model=modelType)
save_model(script_name="gsearch_model_%s" % modelType,
feature_set=FEATURE_SET_NAME,
model_fname='model.txt')
verify=False)
Logger.logger.info(resp.status_code)
if resp.status_code >= 300:
Logger.logger.error(resp.text)
if __name__ == "__main__":
from judgments import judgments_from_file, judgments_by_qid
es = elastic_connection(timeout=1000)
# Load features into Elasticsearch
init_default_store()
load_features(FEATURE_SET_NAME)
# Parse a judgments
movieJudgments = judgments_by_qid(
judgments_from_file(filename=JUDGMENTS_FILE))
# Use proposed Elasticsearch queries (1.json.jinja ... N.json.jinja) to generate a training set
# output as "sample_judgments_wfeatures.txt"
log_features(es, judgments_dict=movieJudgments, search_index=INDEX_NAME)
build_features_judgments_file(movieJudgments,
filename=JUDGMENTS_FILE_FEATURES)
# Train each ranklib model type
#for modelType in [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]:
for modelType in [6]:
# 0, MART
# 1, RankNet
# 2, RankBoost
# 3, AdaRank
# 4, coord Ascent
# 6, LambdaMART
# 7, ListNET
# Add feature back to each judgment
features_per_doc = {}
for doc in res['hits']['hits']:
docId = doc['_id']
features = doc['fields']['_ltrlog'][0]['main']
features_per_doc[docId] = feature_dict_to_list(features)
# Append features from ES back to ranklib judgment list
for judgment in judgments:
try:
features = features_per_doc[
judgment.docId] # If KeyError, then we have a judgment but no file in index
judgment.features = features
except Exception as e:
print(e)
Logger.logger.info("Missing id %s" % judgment.docId)
def build_features_judgments_file(judgments_with_features, filename):
with open(filename, 'w') as judgmentFile:
for qid, judgmentList in judgments_with_features.items():
for judgment in judgmentList:
judgmentFile.write(judgment.to_ranklib_format() + "\n")
if __name__ == "__main__":
es_connection = elastic_connection()
judgmentsByQid = judgments_by_qid(judgments_from_file(JUDGMENTS_FILE))
log_features(es_connection, judgmentsByQid, INDEX_NAME)
build_features_judgments_file(judgmentsByQid, JUDGMENTS_FILE_FEATURES)