Created
June 11, 2020 13:12
-
-
Save Krishna829/56f5dde6430ff7a1b7b1d2b3409b7c53 to your computer and use it in GitHub Desktop.
Recommender System #RecommenderSystem
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.feature_extraction.text import TfidfVectorizer | |
tf = TfidfVectorizer(analyzer='word',ngram_range=(1, 2),min_df=0, stop_words='english') | |
tfidf_matrix = tf.fit_transform(movies['genres']) | |
from sklearn.metrics.pairwise import linear_kernel | |
cosine_sim = linear_kernel(tfidf_matrix, tfidf_matrix) | |
# Build a 1-dimensional array with movie titles | |
titles = movies['title'] | |
indices = pd.Series(movies.index, index=movies['title']) | |
# Function that get movie recommendations based on the cosine similarity score of movie genres | |
def genre_recommendations(title): | |
idx = indices[title] | |
sim_scores = list(enumerate(cosine_sim[idx])) | |
sim_scores = sorted(sim_scores, key=lambda x: x[1], reverse=True) | |
sim_scores = sim_scores[1:21] | |
movie_indices = [i[0] for i in sim_scores] | |
return titles.iloc[movie_indices] |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment