Update indexer.py

had incorrect implementation

indexer.py

@@ -15,7 +15,8 @@ import os
 import shelve
 from bs4 import BeautifulSoup
 from time import perf_counter
-
+import time
+import threading
 
 
 #Data process
@@ -29,6 +30,7 @@ import re
 
 #Logging postings
 from posting import Posting
+from worker import Worker
 
 
 class Indexer():
@@ -61,16 +63,27 @@ class Indexer():
 
 
 		self.save_1 = shelve.open("save_1.shelve")
+		self.save_1_lock = threading.Lock()
 		self.save_2 = shelve.open("save_2.shelve")
+		self.save_2_lock = threading.Lock()
 		self.save_3 = shelve.open("save_3.shelve")
+		self.save_3_lock = threading.Lock()
 		self.save_4 = shelve.open("save_4.shelve")
+		self.save_4_lock = threading.Lock()
 		self.save_5 = shelve.open("save_5.shelve")
+		self.save_5_lock = threading.Lock()
 
+		print(len(list(self.save_1.keys())))
+		print(len(list(self.save_2.keys())))
+		print(len(list(self.save_3.keys())))
+		print(len(list(self.save_4.keys())))
+		print(len(list(self.save_5.keys())))
 
 	def save_index(self,word,posting):
 		cur_save = self.get_save_file(word)
+		lock = self.get_save_lock(word)
+		lock.acquire()
 		shelve_list = list()
-
 		try:
 			shelve_list = cur_save[word]
 			shelve_list.append(posting)
@@ -80,10 +93,12 @@ class Indexer():
 			if toc - tic > 1 :
 				print("Took " + str(toc - tic) + "seconds to sort shelve list !")
 			cur_save.sync()
+			lock.release()
 		except:
 			shelve_list.append(posting)
 			cur_save[word] = shelve_list
 			cur_save.sync()
+			lock.release()
 
 	def get_save_file(self,word):
 		#return the correct save depending on the starting letter of word
@@ -102,10 +117,27 @@ class Indexer():
 			print("You have somehow went beyond the magic")
 			return self.save_5
 
+	def get_save_lock(self,word):
+		word_lower = word.lower()
+		if re.match(r"^[a-d0-1].*",word_lower):
+			return self.save_1_lock
+		elif re.match(r"^[e-k2-3].*",word_lower):
+			return self.save_2_lock
+		elif re.match(r"^[l-q4-7].*",word_lower):
+			return self.save_3_lock
+		elif re.match(r"^[r-z8-9].*",word_lower):
+			return self.save_4_lock
+		else:
+			print(word)
+			print("You have somehow went beyond the magic")
+			return self.save_5_lock.acquire()
+
 	# I have a test file (mytest.py) with pandas but couldn't figure out how to grab just a single cell.
 	# so I came up with this, if anyone knows how to get a single cell and can explain it to
 	# me I would love to know, as I think that method might be quicker, maybe, idk it like
 	# 4am
+
+	# retuns a dict of words/n-grams with their assosiated tf-idf score *can also return just a single score or a pandas dataframe
 	# https://stackoverflow.com/questions/34449127/sklearn-tfidf-transformer-how-to-get-tf-idf-values-of-given-words-in-documen
 
 	# Andy: added paramenter imporant_words in order to do multiplication of score
@@ -115,6 +147,7 @@ class Indexer():
 		#word the word we finding the score for
 		#return the score
 		try:
+			'''
 			tfidf = TfidfVectorizer()
 			tfidf_matrix = tfidf.fit_transform(words)
 			df = pd.DataFrame(tfidf_matrix.toarray(), columns = tfidf.get_feature_names_out())
@@ -134,82 +167,56 @@ class Indexer():
 			#print(df)
 		except KeyError: 
 			return -1
+			'''
+		try:	
+			tfidf = TfidfVectorizer(ngram_range=(1,3)) # ngram_range is range of n-values for different n-grams to be extracted (1,3) gets unigrams, bigrams, trigrams
+			tfidf_matrix = tfidf.fit_transform(words)  # fit trains the model, transform creates matrix
+			df = pd.DataFrame(tfidf_matrix.toarray(), columns = tfidf.get_feature_names_out()) # store value of matrix to associated word/n-gram
+			#return(df.iloc[0][''.join(word)]) #used for finding single word in dataset
+			tfidf_dict = df.to_dict() # transform dataframe to dict *could be expensive the larger the data gets, tested on ~1000 word doc and took 0.002 secs to run
+			return tfidf_dict			# returns the dict of words/n-grams with tf-idf as value
+			#print(df)			# debugging 
+		except: 		
+			print("Error in tf_idf!")
+			return
 
 
 	def get_data(self):
+
+		num_threads = 1
+		threads = list()
+
 		for directory in os.listdir(self.path):
 			for file in os.listdir(self.path + "/" + directory + "/"):
 				#Actual files here
 				#JSON["url"] = url of crawled page, ignore fragments
 				#JSON["content"] = actual HTML
 				#JSON["encoding"] = ENCODING
-				ticker = perf_counter()
-				tic = perf_counter()
-				file_load = open(self.path + "/" + directory + "/"+file)
-				data = json.load(file_load)
-				soup = BeautifulSoup(data["content"],from_encoding=data["encoding"])
-				words = word_tokenize(soup.get_text())
+				index = 0
+				while True:
+					file_path = self.path + "" + directory + "/"+file
+					if len(threads) < num_threads:
+						thread = Worker(self,file_path)
+						threads.append(thread)
+						thread.start()
+						break
+					else:
+						if not threads[index].is_alive():
+							threads[index] = Worker(self,file_path)
+							threads[index].start()
+							break
+						else:
+							index = index + 1
+							if(index >= num_threads):
+								index = 0
+							time.sleep(.1)
+	
+	#Found 55770 documents
+	#
 
 				#getting important tokens
-				important = {'b' : [], 'h1' : [], 'h2' : [], 'h3' : [], 'title' : []}
-				for type in important.keys():
-					for i in soup.findAll(type):
-						for word in word_tokenize(i.text):
-							important[type].append(self.stemmer.stem(word))
 				
 						
-				toc = perf_counter()
-				if toc - tic > 1 :
-					print("Took " + str(toc - tic) + "seconds to tokenize text !")
-
-				tokenized_words = list()
-				stemmed_words = list()
-
-				tic = perf_counter()
-				for word in words:
-					if word != "" and re.fullmatch('[A-Za-z0-9]+',word):
-						#So all the tokenized words are here,
-						tokenized_words.append(word)
-				toc = perf_counter()
-				if toc - tic > 1 :
-					print("Took " + str(toc - tic) + "seconds to isalnum text !")
-				#YOUR CODE HERE
-
-				tic = perf_counter()
-				for word in tokenized_words:
-					stemmed_words.append(self.stemmer.stem(word))
-					#stemming,
-					#tf_idf
-					#get_tf_idf(stemmed_words,word)
-					#post = Posting()
-				toc = perf_counter()
-				if toc - tic > 1 :
-					print("Took " + str(toc - tic) + "seconds to stemmed text !")
-
-				for word in stemmed_words:
-					#posting = Posting(data["url"],self.get_tf_idf(list(' '.join(stemmed_words)),word))
-					tic = perf_counter()
-					#added argument important
-					posting = Posting(data["url"],self.tf_idf_raw(stemmed_words,word, important))
-					toc = perf_counter()
-					if toc - tic > 1 :
-						print("Took " + str(toc - tic) + "seconds to tf_idf text !")
-
-					tic = perf_counter()
-					self.save_index(word,posting)
-					toc = perf_counter()
-					if toc - tic > 1 :
-						print("Took " + str(toc - tic) + "seconds to save text !")
-
-				tocker = perf_counter()
-				print("Finished " + data['url'] + " in \t " + str(tocker-ticker))
-
-	def tf_idf_raw(self,words,word):
-		tf_times = words.count(word)
-
-		tf = tf_times/len(words)
-
-		return tf
 
 		
 

mytest.py

@@ -4,6 +4,7 @@ from sklearn.feature_extraction.text import TfidfVectorizer
 import pandas as pd
 import numpy as np
 
+
 #tf_idf
 #words = whole text
 #word the word we finding the score for
@@ -19,13 +20,12 @@ words = ['this is the first document '
 doc1 = ["I can't fucking take it any more. Among Us has singlehandedly ruined my life. The other day my teacher was teaching us Greek Mythology and he mentioned a pegasus and I immediately thought 'Pegasus? more like Mega Sus!!!!' and I've never wanted to kms more. I can't look at a vent without breaking down and fucking crying. I can't eat pasta without thinking 'IMPASTA??? THATS PRETTY SUS!!!!' Skit 4 by Kanye West. The lyrics ruined me. A Mongoose, or the 25th island of greece. The scientific name for pig. I can't fucking take it anymore. Please fucking end my suffering."]
 doc2 = ["Anyways, um... I bought a whole bunch of shungite rocks, do you know what shungite is? Anybody know what shungite is? No, not Suge Knight, I think he's locked up in prison. I'm talkin' shungite. Anyways, it's a two billion year-old like, rock stone that protects against frequencies and unwanted frequencies that may be traveling in the air. That's my story, I bought a whole bunch of stuff. Put 'em around the la casa. Little pyramids, stuff like that."]
 word = 'life'
-
 try:
-    tfidf = TfidfVectorizer()
-    tfidf_matrix = tfidf.fit_transform(doc1)
+    tfidf = TfidfVectorizer(ngram_range=(3,3)) # ngram_range is range of n-values for different n-grams to be extracted (1,3) gets unigrams, bigrams, trigrams
+    tfidf_matrix = tfidf.fit_transform(words)
     df = pd.DataFrame(tfidf_matrix.toarray(), columns = tfidf.get_feature_names_out())
-    print(df.iloc[0][''.join(word)])
-    #print(df)
+    #print(df.iloc[0][''.join(word)])
+    data = df.to_dict()
 except KeyError: # word does not exist 
     print(-1)
 

worker.py

@@ -0,0 +1,114 @@
+from threading import Thread
+import json
+import os
+import shelve
+from bs4 import BeautifulSoup
+from time import perf_counter
+import time
+
+import re
+
+
+#Data process
+from nltk.tokenize import word_tokenize
+from nltk.stem import PorterStemmer
+from sklearn.feature_extraction.text import TfidfVectorizer
+import pandas as pd
+import numpy as np
+from collections import Counter
+
+from posting import Posting
+
+
+import sys
+
+class Worker(Thread):
+	def __init__(self,indexer,target):
+		self.file = target
+		self.indexer = indexer
+		super().__init__(daemon=True)
+
+	def run(self):
+		print("Target: " + str(self.file))
+		ticker = perf_counter()
+		tic = perf_counter()
+		file_load = open(self.file)
+		data = json.load(file_load)
+		soup = BeautifulSoup(data["content"],features="lxml")
+		words = word_tokenize(soup.get_text())
+		toc = perf_counter()
+		if toc - tic > 1 :
+			print("Took " + str(toc - tic) + "seconds to tokenize text !")
+
+		tokenized_words = list()
+		stemmed_words = list()
+
+		important = {'b' : [], 'h1' : [], 'h2' : [], 'h3' : [], 'title' : []}
+		for key_words in important.keys():
+			for i in soup.findAll(key_words):
+				for word in word_tokenize(i.text):
+					important[key_words].append(self.indexer.stemmer.stem(word))
+
+		tic = perf_counter()
+		for word in words:
+			if word != "" and re.fullmatch('[A-Za-z0-9]+',word):
+				tokenized_words.append(word)
+		toc = perf_counter()
+		if toc - tic > 1 :
+			print("Took " + str(toc - tic) + "seconds to isalnum text !")
+
+		tic = perf_counter()
+		for word in tokenized_words:
+			stemmed_words.append(self.indexer.stemmer.stem(word))
+
+		toc = perf_counter()
+		if toc - tic > 1 :
+			print("Took " + str(toc - tic) + "seconds to stemmed text !")
+
+			"""
+		tfidf = TfidfVectorizer(ngram_range=(1,3)) # ngram_range is range of n-values for different n-grams to be extracted (1,3) gets unigrams, bigrams, trigrams
+		tfidf_matrix = tfidf.fit_transform(stemmed_words)  # fit trains the model, transform creates matrix
+		#df = pd.DataFrame(tfidf_matrix.toarray(), columns = tfidf.get_feature_names_out()) # store value of matrix to associated word/n-gram
+		tfidf.sget_feature_names_out()
+		#tf_idf_dict = df.to_dict() # transform dataframe to dict *could be expensive the larger the data gets, tested on ~1000 word doc and took 0.002 secs to run
+		
+		print(tfidf_matrix)
+		"""
+
+		tfIdfVectorizer=TfidfVectorizer(use_idf=True)
+		tfIdf = tfIdfVectorizer.fit_transform(stemmed_words)
+		df = pd.DataFrame(tfIdf[0].T.todense(), index=tfIdfVectorizer.get_feature_names_out(), columns=["TF-IDF"])
+		df = df.sort_values('TF-IDF', ascending=False)
+
+		print(df.head(25))
+
+		for word in tf_idf_dict.keys():
+			tic = perf_counter()
+			print(tf_idf_dict)
+			weight = 1.0
+			for k,v in important.items():
+				if k == 'b' and word in v:
+					weight = 1.2
+				elif k == 'h1' and word in v:
+					weight = 1.75
+				elif k == 'h2' and word in v:
+					weight = 1.5
+				elif k == 'h3' and word in v:
+					weight = 1.2
+				elif k == 'title' and word in v:
+					weight = 2
+			
+			posting = Posting(data["url"],tf_idf_dict[word]*weight)
+			
+			toc = perf_counter()
+			if toc - tic > 1 :
+				print("Took " + str(toc - tic) + "seconds to tf_idf text !")
+
+			tic = perf_counter()
+			self.indexer.save_index(word,posting)
+			toc = perf_counter()
+			if toc - tic > 1 :
+				print("Took " + str(toc - tic) + "seconds to save text !")
+
+		tocker = perf_counter()
+		print("Finished " + data['url'] + "\n" + str(tocker-ticker))