Using PCA to represent word vectors in 2D

Using PCA to represent word vectors in 2D.py

from sentence_transformers import SentenceTransformer
from sklearn.cluster import KMeans
embedder = SentenceTransformer('paraphrase-multilingual-mpnet-base-v2')
#embedder = SentenceTransformer('all-MiniLM-L6-v2')
corpus = tfidf_sum.index.to_list()
corpus_embeddings = embedder.encode(corpus)

# Perform kmean clustering
num_clusters = 8
clustering_model = KMeans(n_clusters=num_clusters, random_state=42, init='k-means++')
clustering_model.fit(corpus_embeddings)
cluster_assignment = clustering_model.labels_
clustered_sentences = [[] for i in range(num_clusters)]
for sentence_id, cluster_id in enumerate(cluster_assignment):
    clustered_sentences[cluster_id].append(corpus[sentence_id])

print("Development Areas Clusters")
for i, cluster in enumerate(clustered_sentences):
    print("-- Cluster ", i+1)
    print(cluster)
    print("")


import seaborn as sns
import matplotlib.pyplot as plt
from sklearn.decomposition import PCA

pca = PCA(n_components=2)
scatter_plot_points = pca.fit_transform(corpus_embeddings)
colors = ["r", "b", "c", "y", "m", "g", "k", "w"]

x_axis = [o[0] for o in scatter_plot_points]
y_axis = [o[1] for o in scatter_plot_points]
fig, ax = plt.subplots(figsize=(20,20))
ax.scatter(x_axis, y_axis, c=[colors[d] for d in cluster_assignment])

for i, txt in enumerate(corpus):
    ax.annotate(txt, (x_axis[i], y_axis[i]))