def get_ranked_queries(self, text=''):
"""
loads the background document model and generates the ranked queries
:return: the queries in a list
"""
if not text:
text = self.page_html
backgroundfile = 'background.txt'
filename = raw_input("enter the filename of the background file, background.txt is default")
if filename:
backgroundfile = filename
print "background file is ", backgroundfile
doc_extractor = SingleQueryGeneration(minlen=3,stopwordfile=self.stopwordfile)
query_generator = BiTermQueryGeneration(minlen=3, stopwordfile=self.stopwordfile)
print "Loading background distribution"
colLM = LanguageModel(file=backgroundfile)
print "Background loaded, number of terms: ", colLM.get_num_terms()
#doc_extractor.extract_queries_from_html(self.page_html)
doc_extractor.extract_queries_from_html(text)
doc_term_counts = doc_extractor.query_count
print "Number of terms in document: %d" % (len(doc_term_counts))
docLM = LanguageModel(term_dict=doc_term_counts)
slm = BayesLanguageModel(docLM=docLM, colLM=colLM, beta=500)
#query_list = query_generator.extract_queries_from_html(self.page_html)
query_list = query_generator.extract_queries_from_html(text)
print "Queries generated: ", len(query_list)
qr = OddsRatioQueryRanker(smoothed_language_model=slm)
scored_queries = qr.calculate_query_list_probabilities(query_list)
queries = qr.get_top_queries(self.mq)
query_list = []
for query in queries:
query_list.append(query[0])
return query_list
def generate_query_list(self, search_context):
"""
Given a Topic object, produces a list of query terms that could be issued by the simulated agent.
"""
topic_text = search_context.topic.get_topic_text()
if self.topic_lang_model is None:
self.topic_lang_model = self._generate_topic_language_model(
search_context)
snip_text = self._get_snip_text(search_context)
all_text = topic_text + ' ' + snip_text
all_text = self._check_terms(all_text)
bi_query_generator = BiTermQueryGeneration(
minlen=3, stopwordfile=self._stopword_file)
tri_query_generator = TriTermQueryGeneration(
minlen=3, stopwordfile=self._stopword_file)
tri_query_list = tri_query_generator.extract_queries_from_text(
all_text)
bi_query_list = bi_query_generator.extract_queries_from_text(all_text)
query_list = tri_query_list + bi_query_list
query_ranker = QueryRanker(
smoothed_language_model=self.topic_lang_model)
query_ranker.calculate_query_list_probabilities(query_list)
gen_query_list = query_ranker.get_top_queries(100)
return gen_query_list
def generate_query_list(self, search_context):
"""
Given a Topic object, produces a list of query terms that could be issued by the simulated agent.
"""
topic_text = search_context.topic.get_topic_text()
if self.topic_lang_model is None:
self.topic_lang_model = self._generate_topic_language_model(search_context)
snip_text = self._get_snip_text(search_context)
all_text = topic_text + ' ' + snip_text
all_text = self._check_terms(all_text)
bi_query_generator = BiTermQueryGeneration(minlen=3, stopwordfile=self._stopword_file)
tri_query_generator = TriTermQueryGeneration(minlen=3, stopwordfile=self._stopword_file)
tri_query_list = tri_query_generator.extract_queries_from_text(all_text)
bi_query_list = bi_query_generator.extract_queries_from_text(all_text)
query_list = tri_query_list + bi_query_list
query_ranker = QueryRanker(smoothed_language_model=self.topic_lang_model)
query_ranker.calculate_query_list_probabilities(query_list)
gen_query_list = query_ranker.get_top_queries(100)
return gen_query_list
def get_position_queries(self, text):
#print "text is ", text
query_gen = None
query_list = []
if self.stopwordfile:
query_gen = BiTermQueryGeneration(minlen=3, stopwordfile=self.stopwordfile)
else:
query_gen = BiTermQueryGeneration(minlen=3)
query_list = query_gen.extract_queries_from_text(text)
print query_list
return query_list
def get_position_queries(self, text):
# print "text is ", text
query_gen = None
query_list = []
if self.stopwordfile:
query_gen = BiTermQueryGeneration(minlen=3, stopwordfile=self.stopwordfile)
else:
query_gen = BiTermQueryGeneration(minlen=3)
query_list = query_gen.extract_queries_from_text(text)
print query_list
return query_list
def produce_query_list(self, topic):
topic_text = topic.content
topicLM = self.make_topic_lm(topic)
bi_query_generator = BiTermQueryGeneration(minlen=3, stopwordfile=self.stopword_file)
tri_query_generator = TriTermQueryGeneration(minlen=3, stopwordfile=self.stopword_file)
tri_query_list = tri_query_generator.extract_queries_from_text(topic_text)
bi_query_list = bi_query_generator.extract_queries_from_text(topic_text)
query_list = tri_query_list + bi_query_list
qr = QueryRanker(smoothed_language_model=topicLM)
qr.calculate_query_list_probabilities(query_list)
queries = qr.get_top_queries(100)
return queries
def generate_query_list(self, topic):
"""
Given a Topic object, produces a list of query terms that could be issued by the simulated agent.
"""
topic_text = topic.content
topic_lang_model = self._generate_topic_language_model(topic)
bi_query_generator = BiTermQueryGeneration(minlen=3, stopwordfile=self._stopword_file)
tri_query_generator = TriTermQueryGeneration(minlen=3, stopwordfile=self._stopword_file)
tri_query_list = tri_query_generator.extract_queries_from_text(topic_text)
bi_query_list = bi_query_generator.extract_queries_from_text(topic_text)
query_list = tri_query_list + bi_query_list
query_ranker = QueryRanker(smoothed_language_model=topic_lang_model)
query_ranker.calculate_query_list_probabilities(query_list)
return query_ranker.get_top_queries(100)
def produce_query_list(self, topic):
topic_text = topic.content
topicLM = self.make_topic_lm(topic)
bi_query_generator = BiTermQueryGeneration(
minlen=3, stopwordfile=self.stopword_file)
tri_query_generator = TriTermQueryGeneration(
minlen=3, stopwordfile=self.stopword_file)
tri_query_list = tri_query_generator.extract_queries_from_text(
topic_text)
bi_query_list = bi_query_generator.extract_queries_from_text(
topic_text)
query_list = tri_query_list + bi_query_list
qr = QueryRanker(smoothed_language_model=topicLM)
qr.calculate_query_list_probabilities(query_list)
queries = qr.get_top_queries(100)
return queries
def generate_query_list(self, search_context):
"""
Given a Topic object, produces a list of query terms that could be issued by the simulated agent.
"""
topic = search_context.topic
topic_text = "{0} {1}".format(topic.title, topic.content)
topic_lang_model = self._generate_topic_language_model(search_context)
bi_query_generator = BiTermQueryGeneration(minlen=3, stopwordfile=self._stopword_file)
bi_query_list = bi_query_generator.extract_queries_from_text(topic_text)
query_list = bi_query_list
query_ranker = QueryRanker(smoothed_language_model=topic_lang_model)
query_ranker.calculate_query_list_probabilities(query_list)
gen_query_list = query_ranker.get_top_queries(100)
return gen_query_list
def generate_query_list(self, search_context):
"""
Given a Topic object, produces a list of query terms that could be issued by the simulated agent.
"""
topic = search_context.topic
topic_text = "{0} {1}".format(topic.title, topic.content)
topic_lang_model = self._generate_topic_language_model(search_context)
bi_query_generator = BiTermQueryGeneration(
minlen=3, stopwordfile=self._stopword_file)
bi_query_list = bi_query_generator.extract_queries_from_text(
topic_text)
query_list = bi_query_list
query_ranker = QueryRanker(smoothed_language_model=topic_lang_model)
query_ranker.calculate_query_list_probabilities(query_list)
gen_query_list = query_ranker.get_top_queries(100)
return gen_query_list
def main():
"""
:return:
"""
parser = argparse.ArgumentParser(
description="Page Calculator for pages")
parser.add_argument("-u", "--url", type=str,
help="url address")
parser.add_argument("-e","--engine",type=str,
help="Name of search engine: " + ENGINE_LIST.__str__())
parser.add_argument("-k","--key",type=str,
help="API Key for search engine (if applicable)")
parser.add_argument("-c","--cutoff", type=int,
help ="The cutoff value for queries")
parser.add_argument("-m","--maxqueries", type=int,
help ="The maximum number of queries per page")
parser.add_argument("-s","--stopwordfile", type=str,
help ="The filename name containing stopwords")
parser.add_argument("-b","--backgroundfile", type=str,
help ="The filename name containing background term counts")
parser.add_argument("-ca", "--cache",
action="store_true", default=False,
help="use cache")
args = parser.parse_args()
if not args.url:
print "Check your URL argument"
parser.print_help()
return 2
cache = None
if args.cache:
cache = 'engine'
if args.key:
engine = EngineFactory(engine=args.engine, api_key=args.key, throttle=0.1, cache=cache)
else:
print "cache is ", cache
engine = EngineFactory(engine=args.engine, cache=cache, throttle=0.1)
stopwordfile = None
if args.stopwordfile:
stopwordfile = args.stopwordfile
mq = 50
if args.maxqueries:
mq = args.maxqueries
backgroundfile = 'background.txt'
if args.backgroundfile:
backgroundfile = args.backgroundfile
doc_extractor = SingleQueryGeneration(minlen=3,stopwordfile=stopwordfile)
query_generator = BiTermQueryGeneration(minlen=3, stopwordfile=stopwordfile)
print "Loading background distribution"
colLM = LanguageModel(file=backgroundfile)
print "Background loaded, number of terms: ", colLM.get_num_terms()
print "Fetching page: %s" % (args.url)
pc = PageCapture(args.url)
page_html = pc.get_page_sourcecode()
print "Page loaded"
doc_extractor.extract_queries_from_html(page_html)
doc_term_counts = doc_extractor.query_count
print "Number of terms in document: %d" % (len(doc_term_counts))
docLM = LanguageModel(term_dict=doc_term_counts)
slm = BayesLanguageModel(docLM=docLM, colLM=colLM, beta=500)
query_list = query_generator.extract_queries_from_html(page_html)
print "Queries generated: ", len(query_list)
qr = OddsRatioQueryRanker(smoothed_language_model=slm)
scored_queries = qr.calculate_query_list_probabilities(query_list)
queries = qr.get_top_queries(mq)
query_list = []
for query in queries:
query_list.append(query[0])
prc = PageRetrievabilityCalculator(engine=engine)
prc.score_page(args.url, query_list)
print "\nRetrievability Scores for cumulative c=20"
prc.calculate_page_retrievability(c=20)
prc.report()
print "\nRetrievability Scores for gravity beta=1.0"
prc.calculate_page_retrievability(c=20, beta=1.0)
prc.report()
print "Done!"
return 0
def setup(self):
"""
:return:
"""
parser = argparse.ArgumentParser(
description="Page Calculator for pages")
parser.add_argument("-u", "--url", type=str,
help="url address")
parser.add_argument("-e","--engine",type=str,
help="Name of search engine: " + ENGINE_LIST.__str__())
parser.add_argument("-k","--key",type=str,
help="API Key for search engine (if applicable)")
parser.add_argument("-d","--domain",type=str,
help="domain for search engine (if applicable, i.e. engine is sitebing, default is gla.ac.uk)")
parser.add_argument("-c","--cutoff", type=int,
help ="The cutoff value for queries")
parser.add_argument("-m","--maxqueries", type=int,
help ="The maximum number of queries per page")
parser.add_argument("-s","--stopwordfile", type=str,
help ="The filename name containing stopwords")
parser.add_argument("-ca", "--cache",
action="store_true", default=False,
help="use cache")
#parser.add_argument("-ex","--experiment", type=int, help=" experiment number 1 - x")
args = parser.parse_args()
if not args.url:
print "Check your URL argument"
parser.print_help()
return 2
else:
self.url = args.url
# cache = None
# if args.cache:
# cache = 'engine'
# if args.key:
# engine = EngineFactory(engine=args.engine, api_key=args.key, throttle=0.1, cache=cache)
# else:
# print "cache is ", cache
# engine = EngineFactory(engine=args.engine, cache=cache, throttle=0.1)
cache = None
if args.cache:
self.cache = 'engine'
else:
self.cache = cache
if args.key:
self.engine = EngineFactory(engine=args.engine, api_key=args.key, throttle=0.1, cache=self.cache)
else:
self.engine = EngineFactory(engine=args.engine, cache=self.cache, throttle=0.1)
if args.domain:
self.engine.site = args.domain
stopwordfile = None
if args.stopwordfile:
self.stopwordfile = args.stopwordfile
else:
self.stopwordfile = None
self.mq = 250
if args.maxqueries:
self.mq = args.maxqueries
print "Fetching page: %s" % (args.url)
pc = PageCapture(args.url)
self.page_html = pc.get_page_sourcecode()
print "Page loaded"
self.page_text = ''
# answer = raw_input("Do you want to use a percentage of this page? Enter y or n \n")
# if answer == 'y':
# percent = raw_input("What percentage do you want to use? \n")
# if self.is_integer(percent):
# self.page_text = self.reduce_page(percentage=percent)
# else:
# print "input error, will exit"
# sys.exit(2)
# #todo update so asks again, not exit
# else:
self.page_text = self.page_html
query_list = []
answer = raw_input("Do you want to use only a position based extractor? Enter y or n \n")
if answer == 'y' or answer != 'n': #if enter is hit then assume y
text = self.get_position_text()
#todo at this stage this could be single, bi or tri terms
query_gen = None
if self.stopwordfile:
query_gen = BiTermQueryGeneration(minlen=3, stopwordfile=self.stopwordfile)
else:
query_gen = BiTermQueryGeneration(minlen=3)
query_list = query_gen.extract_queries_from_text(text)
elif answer == 'n':
answer = raw_input("Do you want to use only a rank based extractor? Enter y or n \n")
if answer == 'y' or answer != 'n': #if enter is hit then assume y:
query_list = self.get_ranked_queries()
elif answer == 'n':
answer = raw_input("Do you want to use a rank based extractor combined with a position extractor? Enter y or n \n")
if answer == 'y' or answer != 'n': #if enter is hit then assume y:
text = self.get_position_text()
query_list = self.get_ranked_queries(text)
elif answer == 'n':
print "sorry, that's all the options, system will exit"
sys.exit(0)
print "Queries generated: ", len(query_list)
prc = None
if args.cutoff:
prc = PageRetrievabilityCalculator(engine=self.engine, max_queries=self.mq)
else:
prc = PageRetrievabilityCalculator(engine=self.engine, max_queries=self.mq)
prc.score_page(self.url, query_list)
print "\nRetrievability Scores for cumulative pce=20"
prc.calculate_page_retrievability(c=20)
prc.report()
print "\nRetrievability Scores for gravity beta=1.0"
prc.calculate_page_retrievability(c=20, beta=1.0)
prc.report()
print "Done!"
return 0
