Rico

import gensim
from sklearn.decomposition import PCA
import matplotlib
import matplotlib.pyplot as plt

model = gensim.models.Word2Vec.load('white_moves.model')
dict_moves = model.wv.vocab
dict_moves_appr = {}
for k in dict_moves:
    if not k.startswith('->'):
        continue
    dict_moves_appr[k] = dict_moves[k]
X = model[model.wv.vocab]
pca = PCA(n_components=2)
result = pca.fit_transform(X)
fig, ax = plt.subplots()
ax.plot(Y[:, 0], Y[:, 1], 'o')
ax.set_title('White moves')
lab = list(dict_moves_appr)
for i, lb in enumerate(lab):
    plt.annotate(lb, xy=(Y[i, 0], Y[i, 1]))
plt.show()

git lfs install

git clone https://huggingface.co/datasets/{dataset/id}

from datasets import load_dataset

dataset = load_dataset("id")