text_sim_tfidf

text_sim_tfidf_eng2.py

labels = posts.url.str.split('/').str[3:].str[1] # we extract the titles of the articles from the url
similarity_df = pd.DataFrame(M, columns=labels, index=labels) # let's create the dataframe
mask = np.triu(np.ones_like(similarity_df)) # we apply a mask to remove the top of the heatmap

# let's create the viz
plt.figure(figsize=(12, 12))
sns.heatmap(
			similarity_df,
			square=True, 
			annot=True, 
			robust=True,
			fmt='.2f',
			annot_kws={'size': 7, 'fontweight': 'bold'},
			yticklabels=similarity_df.columns
			xticklabels=similarity_df.columns,
			cmap="YlGnBu",
			mask=mask
)

plt.title('Similarity heatmap', fontdict={'fontsize': 24})
plt.show()