retrofitting_blog_2.py

# Method to plot the top no_similar_words in 2D using TSNE
def display_closestwords_tsnescatterplot(model, word, word_vector_dimension, no_similar_words, plot_title):
    
    arr = np.empty((0,word_vector_dimension), dtype='f')
    word_labels = [word]

    # get close words
    close_words = model.similar_by_word(word, topn=no_similar_words)
    
    # add the vector for each of the closest words to the array
    arr = np.append(arr, np.array([model[word]]), axis=0)
    for wrd_score in close_words:
        wrd_vector = model[wrd_score[0]]
        word_labels.append(wrd_score[0])
        arr = np.append(arr, np.array([wrd_vector]), axis=0)
        
    # find tsne coords for 2 dimensions
    tsne = TSNE(n_components=2, random_state=0)
    np.set_printoptions(suppress=True)
    Y = tsne.fit_transform(arr)

    x_coords = Y[:, 0]
    y_coords = Y[:, 1]
    # display scatter plot
    plt.scatter(x_coords, y_coords)

    for label, x, y in zip(word_labels, x_coords, y_coords):
        plt.annotate(label, xy=(x, y), xytext=(0, 0), textcoords='offset points')
    plt.xlim(x_coords.min()+0.00005, x_coords.max()+0.00005)
    plt.ylim(y_coords.min()+0.00005, y_coords.max()+0.00005)
    plt.xticks(rotation=35)
    plt.title(plot_title)
    plt.show()