Created
March 27, 2021 16:07
-
-
Save oysters76/69070c8b7eea5b7c53e34e4bf856dc3b to your computer and use it in GitHub Desktop.
Trival Bag of Words implementation without the Hashing Trick
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#Trivial Word Bag implementation using Python | |
import string | |
doc1 = "John likes to watch movies. Mary likes movies too."; | |
doc2 = "Mary also likes to watch football games."; | |
documents = [doc1, doc2] | |
def transform(s): | |
return s.translate(str.maketrans('','',string.punctuation)).lower() | |
def createWordBag(documents): | |
result = [transform(document) for document in documents] | |
result = " ".join(result) | |
result = result.split(" ") | |
result = set(result) | |
wordBag = {} | |
for index, word in enumerate(result): | |
wordBag[word] = index; | |
return wordBag; | |
def getFeature(document, wordBag): | |
newDocument = transform(document).split(" ") | |
n = len(newDocument) | |
feature = [0] * len(wordBag.keys()) | |
for word in newDocument: | |
index = wordBag[word] | |
feature[index] += 1 | |
return feature | |
wordBag = createWordBag(documents) | |
feature1 = getFeature(doc1, wordBag) | |
feature2 = getFeature(doc2, wordBag) | |
print(feature1) # [0, 1, 1, 0, 2, 2, 1, 1, 0, 1] | |
print(feature2) # [1, 1, 1, 1, 1, 0, 1, 0, 1, 0] |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment