import gensim.downloader as api
import numpy as np
import matplotlib.pyplot as plt
from sklearn.decomposition import PCA


print("Loading model... (This may take a while)")
model = api.load("word2vec-google-news-300")
print("Model Loaded")


tech_words = [
    "computer",
    "algorithm",
    "software",
    "hardware",
    "AI",
    "cloud",
    "database",
    "network",
    "programming",
    "internet"
]


word_vectors = np.array([model[word] for word in tech_words])

pca = PCA(n_components=2)
reduced_vectors = pca.fit_transform(word_vectors)


plt.figure(figsize=(8, 6))

for word, (x, y) in zip(tech_words, reduced_vectors):
    plt.scatter(x, y)
    plt.text(x + 0.02, y + 0.02, word, fontsize=12)

plt.title("2D Visualization of Technology Word Embeddings")
plt.xlabel("PCA Component 1")
plt.ylabel("PCA Component 2")
plt.grid()

plt.show()


def find_similar_words(word):
    try:
        similar_words = model.most_similar(word, topn=5)

        print(f"\n5 words similar to '{word}':")

        for w, score in similar_words:
            print(f"{w}: {score:.4f}")

    except KeyError:
        print(f"'{word}' not found in the vocabulary.")


find_similar_words("AI")