MOVIE RECOMMENDATION SYSTEM.pptx

It's a powerpoint presentation on movie recommendation system using cosine similarity.

1. MOVIE RECOMMENDATION SYSTEM PROJECT PRESENTATION Under the guidance of : Mrs. Jheelam Mondal (Asst. Professor CSE) Presented By : Abhishek Kuila : 00119007 Debabrata Makhal : 00119041 Jayoti Podder : 00119055 Ankit Kumar : 10300120202

2. Table Of Content Problem Statement Introduction Objective Project Requirements Design & Diagram Coding part Results Conclusion References

3. Problem Statement Aim: To build a movie recommendation system based on ‘Kaggle’ dataset using machine learning. We wish to integrate the aspects of personalization of user with the overallfeatures of movie such as genre, popularity etc. The goal of the project is to recommend a movie to the user on the basis of rating, genre using cosine similarity Providing related content out of relevant and irrelevant collection of items to users of online service providers.

4. Introduction A recommendation system or recommendation engine is a model used for information filtering where it tries to predict the preferences of a user and provide suggests based on these preferences. Movie Recommendation Systems helps us to search our preferred movies among all of these different types of movies and hence reduce the trouble of spending a lot of time searching our favourable movies. Recommendation systems have several benefits, the most important being customer satisfaction and revenue .

5. Objective The goal of our project is to develop a movie recommendation system for binge watchers to help and recommend them good quality of movies. The Objectives Are : Improving the Accuracy of the recommendation system Improve the Quality of the movie Recommendation system Improving the Scalability. Enhancing the user experience.

6. Project Requirements Hardware Requirements A PC with Windows/Linux OS Processor with 1.7-2.4gHz speed Minimum of 8gb RAM 2gb Graphic card Software Requirements Text Editor (VS-code) Streamlit Dataset Jupyter (Editor) Python libraries

7. Design & Diagram USER ID Content Based Filter Movies Cosine Similarity Algorithm Optimal Result

8. Approach Used To build recommendation system there are many approach that can be used to build good recommendation system Content based recommendation system and collaborative filtering. Youtube also used content based recommended system, we also used content based recommendation system in our project and cosine similarity algorithm. Cosine Similarity Cosine similarity is used as a metric in different machine learning algorithms like the KNN for determining the distance between the neighbors, in recommendation systems, it is used to recommend movies with the same similarities and for textual data, it is used to find the similarity of texts in the document. For webhosting we use Streamlit Streamlit is  a promising open-source Python library, which enables developers to build attractive user interfaces in no time . Streamlit is the easiest way especially for people with no front-end knowledge to put their code into a web application: No front-end (html, js , css ) experience or knowledge is required

9. CODING PART ( Main.ipynb ) import pandas as pd movies = pd.read_csv ('dataset.csv’) #to read csv file movies.head (10) #to print all details of 10 movies movies.describe () #to calculate statiscal data like count, mean,std , movies.info() #to print all columns and nonull and data types movies.isnull ().sum() # returns the number of missing values in the dataset movies.columns movies=movies[['id', 'title', 'overview', 'genre']] movies movies['tags'] = movies['overview']+movies['genre’] # it will combine the genre and overview column m ovies new_data  = movies.drop (columns=['overview', 'genre']) new_data

10. from sklearn.feature_extraction.text import CountVectorizer # method to convert text to numerical data .  cv= CountVectorizer ( max_features =10000, stop_words =' english ') cv vector= cv.fit_transform ( new_data ['tags']. values.astype ('U')). toarray () vector.shape from sklearn.metrics.pairwise import cosine_similarity similarity= cosine_similarity (vector) similarity new_data [ new_data ['title']=="The Godfather"].index[0] distance = sorted(list(enumerate(similarity[2])), reverse=True, key=lambda vector:vector [1]) for i in distance[0:5]:     print( new_data.iloc [ i [0]].title)

11. def recommend(movies):     index= new_data [ new_data ['title']==movies].index[0]     distance = sorted(list(enumerate(similarity[index])), reverse=True, key=lambda vector:vector [1])     for i in distance[0:5]: #to print only top 5 movies         print( new_data.iloc [ i [0]].title) import pickle pickle.dump ( new_data , open(' movies_list.pkl ', ' wb ')) pickle.dump (similarity, open(' similarity.pkl ', ' wb ')) pickle.load (open(' movies_list.pkl ', ' rb '))

12. Code For webhosting import streamlit as st import pickle import requests def fetch_poster ( movie_id ):       url = "https://api.themoviedb.org/3/movie/{}? api_key =43c2c7148a22f65595a5dcc10a9d6c8b".format( movie_id )      data= requests.get ( url )      data= data.json ()       poster_path = data[' poster_path ']       full_path = "https://image.tmdb.org/t/p/w500/"+ poster_path      return full_path movies = pickle.load (open(" movies_list.pkl ", ' rb ')) similarity = pickle.load (open(" similarity.pkl ", ' rb ')) movies_list =movies['title'].values st.header ("Movie Recommender System")

13. import streamlit.components.v1 as components imageCarouselComponent = components.declare_component ("image-carousel-component", path="frontend/public") #imageCarouselComponent(imageUrls=imageUrls, height=200) selectvalue = st.selectbox ("Select movie from dropdown", movies_list ) def recommend(movie):     index=movies[movies['title']==movie].index[0]     distance = sorted(list(enumerate(similarity[index])), reverse=True, key=lambda vector:vector [1])     recommend_movie =[]     recommend_poster =[]     for i in distance[1:6]:         movies_id = movies.iloc [ i [0]].id         recommend_movie.append ( movies.iloc [ i [0]].title)         recommend_poster.append ( fetch_poster ( movies_id ))     return recommend_movie , recommend_poster     if st.button ("Show Recommend"):     movie_name , movie_poster = recommend( selectvalue )     col1,col2,col3,col4,col5= st.columns (5)     with col1:         st.text ( movie_name [0])         st.image ( movie_poster [0]) with col2:         st.text ( movie_name [1])         st.image ( movie_poster [1])     with col3:         st.text ( movie_name [2])         st.image ( movie_poster [2])     with col4:         st.text ( movie_name [3])         st.image ( movie_poster [3])     with col5:         st.text ( movie_name [4])         st.image ( movie_poster [4])

14. Snapshots

15. Sample Video Of Project

16. Key Benefits Provides relevant content to user. It saves time and money. It increases customer engagement. Specially designed for binge watchers

17. Conclusion In this project, to improve the accuracy, quality and scalability of movie recommendation system. A Hybrid approach by unifying content based filtering and collaborative filtering; using Singular Value Decomposition (SVD) as a classifier. The Proposed system will recommends good movies according to user’s choice. Bring interests and make users happy.

18. References 1. Hirdesh Shivhare , Anshul Gupta and Shalki Sharma (2015) , IEEE International Conference on Computer, Communication and Control. 2. Manoj Kumar, D.K. Yadav, Ankur Singh and Vijay Kr. Gupta (2015), “A Movie Recommender System: MOVREC”, International Journal of Computer Applications (0975 – 8887) Volume 124 – No.3. 3. Debadrita Roy, Arnab Kundu, (2013), International Journal of Emerging Technology and Advanced Engineering, Volume 3, Issue 4.