iNocturnis/Search_Engine
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Added way to save doc score

Browse Source
This commit is contained in:
unknown 2022-05-25 19:59:31 -07:00
parent a567424a54
commit d80a977450
1 changed files with 28 additions and 25 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

53
indexer.py
View File

@ -43,21 +43,8 @@ class Indexer():
self.trimming = trimming self.trimming = trimming
self.stemmer = PorterStemmer() self.stemmer = PorterStemmer()
self.id = list() self.id = list()
# list that contains the denominator for normalization before taking the square root of it. square root will be taken during query time
self.normalize = list()
# Creates a pickle file that is a list of urls where the index of the url is the id that the posting refers to.
p = os.path.dirname(os.path.abspath(__file__))
my_filename = os.path.join(p, "urlID.pkl")
if os.path.exists(my_filename):
os.remove(my_filename)
# Creates file and closes it
self.f = open(my_filename, "wb")
pickle.dump(id, self.f)
self.f.close()
# Opens for reading for the entire duration of indexer for worker to use
self.f = open(my_filename, "rb+")
#Shelves for index #Shelves for index
#https://www3.nd.edu/~busiforc/handouts/cryptography/letterfrequencies.html #https://www3.nd.edu/~busiforc/handouts/cryptography/letterfrequencies.html
@ -192,10 +179,13 @@ class Indexer():
tokens[split[i]].positions.append(i) tokens[split[i]].positions.append(i)
return tokens return tokens
# Does the idf part of the tfidf
def tfidf(self, current_save): def tfidf(self, current_save):
for token, postings in current_save.items(): for token, postings in current_save.items():
for p in postings: for p in postings:
p.tfidf = p.tf * math.log(len(self.id)/len(postings)) p.tfidf = p.tf * math.log(len(self.id)/len(postings))
self.normalize[p.url] += p.tfidf
def get_data(self): def get_data(self):
@ -236,14 +226,35 @@ class Indexer():
if(index >= num_threads): if(index >= num_threads):
index = 0 index = 0
time.sleep(.1) time.sleep(.1)
# Make a list the size of the corpus to keep track of document scores
self.normalize = [0] * len(self.id)
# These last few function calls calculates idf and finalizes tf-idf weighting for each index # These last few function calls calculates idf and finalizes tf-idf weighting for each index
self.tfidf(self.save_1) self.tfidf(self.save_1)
self.tfidf(self.save_2) self.tfidf(self.save_2)
self.tfidf(self.save_3) self.tfidf(self.save_3)
self.tfidf(self.save_4) self.tfidf(self.save_4)
self.tfidf(self.save_5) self.tfidf(self.save_5)
pickle.dump(self.id, self.f)
# should I self.f.close() here? # Creates a pickle file that is a list of urls where the index of the url is the id that the posting refers to.
p = os.path.dirname(os.path.abspath(__file__))
my_filename = os.path.join(p, "urlID.pkl")
if os.path.exists(my_filename):
os.remove(my_filename)
# Creates file and closes it
f = open(my_filename, "wb")
pickle.dump(self.id, f)
f.close()
# Creates a pickle file that will contain the denominator (before the square root) for normalizing wt
p = os.path.dirname(os.path.abspath(__file__))
my_filename = os.path.join(p, "normalize.pkl")
if os.path.exists(my_filename):
os.remove(my_filename)
# Creates file and closes it
f = open(my_filename, "wb")
pickle.dump(self.normalize, f)
f.close()
#Found 55770 documents #Found 55770 documents
# #
@ -251,14 +262,6 @@ class Indexer():
def main(): def main():
indexer = Indexer(True,0) indexer = Indexer(True,0)