Created
March 15, 2020 16:26
-
-
Save ikatsov/c380cd6baa37bb170e6fc2eb229ba4a4 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from sklearn.manifold import TSNE | |
from sklearn.metrics import pairwise_distances | |
# prepare inputs for t-SNE | |
word_vectors = model.wv | |
vocab = list(model.wv.vocab.keys()) | |
item2vector_dict = {arg:model.wv[arg] for arg in vocab} | |
X = pd.DataFrame(item2vector_dict).T.values | |
# perform t-SNE | |
distance_matrix = pairwise_distances(X, X, metric='cosine', n_jobs=-1) | |
tsne = TSNE(metric="precomputed", n_components=2, | |
verbose=1, perplexity=30, n_iter=500) | |
tsne_results = tsne.fit_transform(distance_matrix) | |
# prepare t-SNE outputs for visualization | |
df_semantic_item = pd.DataFrame({'product_id': vocab}) | |
df_semantic_item['tsne-2d-one'] = tsne_results[:,0] | |
df_semantic_item['tsne-2d-two'] = tsne_results[:,1] | |
df_semantic_item['product_id'] = df_semantic_item['product_id'].astype(int) | |
# join the embeddings with department and aisle names | |
df_semantic_item = df_semantic_item.merge(data_dict['products'], | |
on='product_id', how='left') | |
df_semantic_item = df_semantic_item.merge(data_dict['aisles'], | |
on='aisle_id', how='left') | |
df_semantic_item = df_semantic_item.merge(data_dict['departments'], | |
on='department_id', how='left') | |
# visualize the semantic space and its mapping to the departments | |
sns.scatterplot( | |
x="tsne-2d-one", y="tsne-2d-two", | |
hue='department', | |
palette=sns.color_palette("hls", n_department), | |
data=df_semantic_item, | |
legend="full", | |
alpha=0.3 | |
) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment