Word2Vec Explained

[UKVeteran]

TL;DR

Article Link

https://towardsdatascience.com/word2vec-explained-49c52b4ccb71

Author

Vatsal

Key Takeaways

Implementation

• Data
• Requirements
• Import Data
• Preprocess Data
• Embed
• PCA on Embeddings

Useful Code Snippets

w = w2v(
    filtered_lines,
    min_count=3,  
    sg = 1,       
    window=7      
)       

print(w.wv.most_similar('thou'))

emb_df = (
    pd.DataFrame(
        [w.wv.get_vector(str(n)) for n in w.wv.key_to_index],
        index = w.wv.key_to_index
    )
)
print(emb_df.shape)
emb_df.head()

pca = PCA(n_components=2, random_state=7)
pca_mdl = pca.fit_transform(emb_df)

emb_df_PCA = (
    pd.DataFrame(
        pca_mdl,
        columns=['x','y'],
        index = emb_df.index
    )
)

plt.clf()
fig = plt.figure(figsize=(6,4))

plt.scatter(
    x = emb_df_PCA['x'],
    y = emb_df_PCA['y'],
    s = 0.4,
    color = 'maroon',
    alpha = 0.5
)

plt.xlabel('PCA-1')
plt.ylabel('PCA-2')
plt.title('PCA Visualization')
plt.plot()

Useful Tools

Comments/ Questions