Project Paraphrases Embedding

project_we.py

from sklearn.decomposition import PCA

def project(words, phrases, model):
    embeddings = []
    associated_words = []
    pca = PCA(n_components=2)
    for word in words:
        associated_words.append(word)
        embeddings.append(model[word])
        for pphrase in phrases[word]:
            associated_words.append(phrase)
            embeddings.append(model[phrase])
    return pca.fit_transform(embeddings), associated_words