Update indexer.py

had incorrect implementation

indexer.py

@@ -116,6 +116,7 @@ class Indexer():
 			print(word)
 			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):
@@ -130,10 +131,13 @@ class Indexer():
 			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
@@ -143,6 +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())
@@ -162,11 +167,23 @@ 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 = 8
+		num_threads = 1
 		threads = list()
 
 		for directory in os.listdir(self.path):

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

@@ -52,49 +52,54 @@ class Worker(Thread):
 		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.indexer.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 !")
 
-		counts = Counter(stemmed_words)
-		size = len(stemmed_words)
-		for word in counts:
-			#posting = Posting(data["url"],self.get_tf_idf(list(' '.join(stemmed_words)),word))
-			tic = perf_counter()
-			weight = 1.0
-			index = 0
 			"""
-			for group in important:
-				for word_important in group:
-					if word_important.lower() == word.lower():
-						if index == 0:
-							weight = 1.2
-						elif index == 1:
-							weight = 1.8
-						elif index == 2:
-							weight = 1.5
-						elif index == 3:
-							weight = 1.3
-						elif index == 4:
-							weight = 2.0
-				index = index + 1
+		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)
 		"""
 
-			posting = Posting(data["url"],counts[word]/size*weight)
+		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 !")