countvectorizer.py

def create_heatmap(similarity, cmap = "YlGnBu"):
    df = pd.DataFrame(similarity)
    df.columns = ['john', 'luke','mark', 'matt'] #ohn 0 mark 2 matt 3 luke 1
    df.index = ['john', 'luke','mark', 'matt']
    fig, ax = plt.subplots(figsize=(5,5))
    sns.heatmap(df, cmap=cmap)

from sklearn.metrics.pairwise import cosine_similarity
from sklearn.feature_extraction.text import TfidfVectorizer
import seaborn as sns 

vectorizer = TfidfVectorizer()
X = vectorizer.fit_transform(data)
arr = X.toarray()

create_heatmap(cosine_similarity(arr))