matrix

# Loop over each synopsis and append its content to a list of string named 'corpus'
corpus = []
for i in range(0, frame["Synopsis"].size):
    corpus.append(frame["Synopsis"][i])
# Create tf–idf matrix
from sklearn.feature_extraction.text import TfidfVectorizer
vectorizer = TfidfVectorizer(stop_words = 'english', min_df = 0.2)
# min_df = 0.2 means that the term must be in at least 20% of the documents
X = vectorizer.fit_transform(corpus)

k = 2 # Define the number of clusters in which we want to partion our data
# Define the proper notion of distance to deal with documents
from sklearn.metrics.pairwise import cosine_similarity
dist = 1 - cosine_similarity(X)
# Run the algorithm kmeans
model = KMeans(n_clusters = k)
model.fit(X);

no_words = 4 # Number of words to print per cluster
order_centroids = model.cluster_centers_.argsort()[:, ::-1] # Sort cluster centers by proximity to centroid
terms = vectorizer.get_feature_names()
labels = model.labels_ # Get labels assigned to each data

print("Top terms per cluster:\n")
for i in range(k):

    print("Cluster %d movies:" % i, end='')
    for title in frame["Title"][labels == i]:
        print(' %s,' % title, end='')
    print() #add a whitespace

    print("Cluster %d words:" % i, end='')
    for ind in order_centroids[i, :no_words]:
        print (' %s' % terms[ind], end=','),
    print()
    print()
Top terms per cluster:

Cluster 0 movies: Mad Max: Fury Road, The Matrix, No Country for Old Men, A Beautiful Mind, Inception, Frozen, Finding Nemo, Toy Story,
Cluster 0 words: room, tank, says, joe,

Cluster 1 movies: The King's Speech, The Lion King, Aladdin, Cinderella, Robin Hood,
Cluster 1 words: king, prince, john, palace,