Created
September 30, 2023 15:55
-
-
Save jonas-kell/7f95a9535d14881dfe1a6582386ea383 to your computer and use it in GitHub Desktop.
Code of the Mathezirkel "Clustering und Wort-Einbettungen"
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
""" | |
INSTALLATION REQUIREMENTS: | |
- Download the datase from https://www.kaggle.com/datasets/leadbest/googlenewsvectorsnegative300 (you need to make an account) | |
- Copy the code into a file named words.py | |
- Install Python: https://www.python.org/ | |
- Install gensim (pip install gensim) | |
- Make a folder called bin inside the folder where words.py is saved and place GoogleNews-vectors-negative300.bin inside | |
""" | |
from gensim.models import KeyedVectors | |
# Load the pre-trained Word2Vec model | |
model_path = "./bin/GoogleNews-vectors-negative300.bin" | |
model = KeyedVectors.load_word2vec_format(model_path, binary=True) | |
def similar(word): | |
print(f"Most similar to {word}: {model.similar_by_word(word)}") | |
def distance(word1, word2): | |
print(f"{word1} <-> {word2}: {model.distance(word1, word2)}") | |
def transfer_relation(start, minus, plus): | |
answers = model.most_similar_cosmul( | |
positive=[start, plus], negative=[minus], topn=5 | |
) | |
print(f"{start} - {minus} + {plus} = {answers[0][0]}") | |
print(answers) | |
print("") | |
# You can check out what is most similar to... | |
similar("car") | |
# You can check out the distance of words (cat and dog are more closely related than cat and car) | |
distance("cat", "car") | |
distance("cat", "dog") | |
# You can check out combinations of words-meaning-directions | |
transfer_relation("ocean", "water", "sand") # dunes | |
transfer_relation("dog", "bark", "miaow") # chihuahua, but kitten actually really close | |
transfer_relation("Italy", "pizza", "sushi") # Japan | |
transfer_relation("butcher", "meat", "bread") # baker | |
transfer_relation("car", "road", "river") # boat | |
transfer_relation("Germany", "Berlin", "Paris") # France | |
transfer_relation("Germany", "Berlin", "Tokyo") # Japan | |
transfer_relation("Germany", "Berlin", "Beijing") # China | |
transfer_relation("Germany", "Berlin", "Paris") # France | |
transfer_relation("Germany", "Berlin", "Lisbon") # Portugal | |
transfer_relation("Germany", "Berlin", "Sofia") # Bulgaria | |
transfer_relation("Germany", "Berlin", "London") # UK | |
# But it can also not work really well sometimes | |
# sadly not ice, here "good" comes up, because "solid" is a synonym for good | |
transfer_relation("water", "liquid", "solid") | |
# no idea what happens here, but apparently things that burn ... | |
transfer_relation("fire", "heat", "cold") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment